public final class CL
extends java.lang.Object
| Modifier and Type | Class and Description |
|---|---|
static class |
CL.LogLevel
The log levels which may be used to control the internal
logging of the native JOCL library
|
| Modifier and Type | Method and Description |
|---|---|
static java.nio.ByteBuffer |
allocateAligned(int size,
int alignment)
Deprecated.
This method is not intended (and should not be required)
for public use, and will be removed in future releases.
|
static int |
clBuildProgram(cl_program program,
int num_devices,
cl_device_id[] device_list,
java.lang.String options,
BuildProgramFunction pfn_notify,
java.lang.Object user_data)
Builds (compiles and links) a program executable from the program source or binary.
|
static int |
clCompileProgram(cl_program program,
int num_devices,
cl_device_id[] device_list,
java.lang.String options,
int num_input_headers,
cl_program[] input_headers,
java.lang.String[] header_include_names,
BuildProgramFunction pfn_notify,
java.lang.Object user_data)
Compiles a programs source for all the devices or a specific device(s) in the OpenCL context
associated with
program. |
static cl_mem |
clCreateBuffer(cl_context context,
long flags,
long size,
Pointer host_ptr,
int[] errcode_ret)
Creates a buffer object.
|
static cl_command_queue |
clCreateCommandQueue(cl_context context,
cl_device_id device,
long properties,
int[] errcode_ret)
Deprecated.
As of OpenCL 2.0. Use
clCreateCommandQueueWithProperties(org.jocl.cl_context, org.jocl.cl_device_id, org.jocl.cl_queue_properties, int[]) instead |
static cl_command_queue |
clCreateCommandQueueWithProperties(cl_context context,
cl_device_id device,
cl_queue_properties properties,
int[] errcode_ret)
Create a host or device command-queue on a specific device.
|
static cl_context |
clCreateContext(cl_context_properties properties,
int num_devices,
cl_device_id[] devices,
CreateContextFunction pfn_notify,
java.lang.Object user_data,
int[] errcode_ret)
Creates an OpenCL context.
|
static cl_context |
clCreateContextFromType(cl_context_properties properties,
long device_type,
CreateContextFunction pfn_notify,
java.lang.Object user_data,
int[] errcode_ret)
Create an OpenCL context from a device type that identifies the specific device(s) to use.
|
static cl_mem |
clCreateFromGLBuffer(cl_context context,
long flags,
int bufobj,
int[] errcode_ret)
Creates an OpenCL buffer object from an OpenGL buffer object.
|
static cl_mem |
clCreateFromGLRenderbuffer(cl_context context,
long flags,
int renderbuffer,
int[] errcode_ret)
Creates an OpenCL 2D image object from an OpenGL renderbuffer object.
|
static cl_mem |
clCreateFromGLTexture(cl_context context,
long flags,
int target,
int miplevel,
int texture,
int[] errcode_ret)
Creates an OpenCL image object, image array object, or image buffer object from an OpenGL texture object,
texture array object, texture buffer object, or a single face of an OpenGL cubemap texture object.
|
static cl_mem |
clCreateFromGLTexture2D(cl_context context,
long flags,
int target,
int miplevel,
int texture,
int[] errcode_ret)
Deprecated.
As of OpenCL 1.2 and replaced by
clCreateFromGLTexture(cl_context, long, int, int, int, int[]) |
static cl_mem |
clCreateFromGLTexture3D(cl_context context,
long flags,
int target,
int miplevel,
int texture,
int[] errcode_ret)
Deprecated.
As of OpenCL 1.2 and replaced by
clCreateFromGLTexture(cl_context, long, int, int, int, int[]) |
static cl_mem |
clCreateImage(cl_context context,
long flags,
cl_image_format image_format,
cl_image_desc image_desc,
Pointer host_ptr,
int[] errcode_ret)
Creates a 1D image, 1D image buffer, 1D image array, 2D image, 2D image array or 3D image object.
|
static cl_mem |
clCreateImage2D(cl_context context,
long flags,
cl_image_format[] image_format,
long image_width,
long image_height,
long image_row_pitch,
Pointer host_ptr,
int[] errcode_ret)
Deprecated.
As of OpenCL 1.2 and replaced by
clCreateImage(cl_context, long, cl_image_format, cl_image_desc, Pointer, int[]) |
static cl_mem |
clCreateImage3D(cl_context context,
long flags,
cl_image_format[] image_format,
long image_width,
long image_height,
long image_depth,
long image_row_pitch,
long image_slice_pitch,
Pointer host_ptr,
int[] errcode_ret)
Deprecated.
As of OpenCL 1.2 and replaced by
clCreateImage(cl_context, long, cl_image_format, cl_image_desc, Pointer, int[]) |
static cl_kernel |
clCreateKernel(cl_program program,
java.lang.String kernel_name,
int[] errcode_ret)
Creates a kernal object.
|
static int |
clCreateKernelsInProgram(cl_program program,
int num_kernels,
cl_kernel[] kernels,
int[] num_kernels_ret)
Creates kernel objects for all kernel functions in a program object.
|
static cl_mem |
clCreatePipe(cl_context context,
long flags,
int pipe_packet_size,
int pipe_max_packets,
cl_pipe_properties properties,
int[] errcode_ret)
Creates a pipe object.
|
static cl_program |
clCreateProgramWithBinary(cl_context context,
int num_devices,
cl_device_id[] device_list,
long[] lengths,
byte[][] binaries,
int[] binary_status,
int[] errcode_ret)
Creates a program object for a context, and loads the binary bits specified by
binary into the program object.
|
static cl_program |
clCreateProgramWithBuiltInKernels(cl_context context,
int num_devices,
cl_device_id[] device_list,
java.lang.String kernel_names,
int[] errcode_ret)
Creates a program object for a context, and loads the information related to the built-in kernels
into a program object.
|
static cl_program |
clCreateProgramWithSource(cl_context context,
int count,
java.lang.String[] strings,
long[] lengths,
int[] errcode_ret)
Creates a program object for a context, and loads the source code specified by the text strings in
the
strings array into the program object. |
static cl_sampler |
clCreateSampler(cl_context context,
boolean normalized_coords,
int addressing_mode,
int filter_mode,
int[] errcode_ret)
Deprecated.
As of OpenCL 2.0. Use
clCreateSamplerWithProperties(org.jocl.cl_context, org.jocl.cl_sampler_properties, int[]) instead. |
static cl_sampler |
clCreateSamplerWithProperties(cl_context context,
cl_sampler_properties properties,
int[] errcode_ret)
Creates a sampler object.
|
static cl_mem |
clCreateSubBuffer(cl_mem buffer,
long flags,
int buffer_create_type,
cl_buffer_region buffer_create_info,
int[] errcode_ret)
Creates a buffer object (referred to as a sub-buffer object) from an existing buffer object.
|
static cl_mem |
clCreateSubBuffer(cl_mem buffer,
long flags,
int buffer_create_type,
Pointer buffer_create_info,
int[] errcode_ret)
Deprecated.
The buffer_create_info that has to be passed to this function
is specific for the underlying architecture (32/64 bit). The preferred
way of creating a sub-buffer is now via
clCreateSubBuffer(cl_mem, long, int, cl_buffer_region, int[]) |
static int |
clCreateSubDevices(cl_device_id in_device,
cl_device_partition_property properties,
int num_devices,
cl_device_id[] out_devices,
int[] num_devices_ret)
Creates an array of sub-devices that each reference a non-intersecting set of compute units within
in_device. |
static cl_event |
clCreateUserEvent(cl_context context,
int[] errcode_ret)
Creates a user event object.
|
static int |
clEnqueueAcquireGLObjects(cl_command_queue command_queue,
int num_objects,
cl_mem[] mem_objects,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Acquire OpenCL memory objects that have been created from OpenGL objects.
|
static int |
clEnqueueBarrier(cl_command_queue command_queue)
Deprecated.
As of OpenCL 1.2
|
static int |
clEnqueueBarrierWithWaitList(cl_command_queue command_queue,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
A synchronization point that enqueues a barrier operation.
|
static int |
clEnqueueCopyBuffer(cl_command_queue command_queue,
cl_mem src_buffer,
cl_mem dst_buffer,
long src_offset,
long dst_offset,
long cb,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a command to copy from one buffer object to another.
|
static int |
clEnqueueCopyBufferRect(cl_command_queue command_queue,
cl_mem src_buffer,
cl_mem dst_buffer,
long[] src_origin,
long[] dst_origin,
long[] region,
long src_row_pitch,
long src_slice_pitch,
long dst_row_pitch,
long dst_slice_pitch,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a command to copy a rectangular region from the buffer object to another buffer object.
|
static int |
clEnqueueCopyBufferToImage(cl_command_queue command_queue,
cl_mem src_buffer,
cl_mem dst_image,
long src_offset,
long[] dst_origin,
long[] region,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a command to copy a buffer object to an image object.
|
static int |
clEnqueueCopyImage(cl_command_queue command_queue,
cl_mem src_image,
cl_mem dst_image,
long[] src_origin,
long[] dst_origin,
long[] region,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a command to copy image objects.
|
static int |
clEnqueueCopyImageToBuffer(cl_command_queue command_queue,
cl_mem src_image,
cl_mem dst_buffer,
long[] src_origin,
long[] region,
long dst_offset,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a command to copy an image object to a buffer object.
|
static int |
clEnqueueFillBuffer(cl_command_queue command_queue,
cl_mem buffer,
Pointer pattern,
long pattern_size,
long offset,
long size,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a command to fill a buffer object with a pattern of a given pattern size.
|
static int |
clEnqueueFillImage(cl_command_queue command_queue,
cl_mem image,
Pointer fill_color,
long[] origin,
long[] region,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a command to fill an image object with a specified color.
|
static java.nio.ByteBuffer |
clEnqueueMapBuffer(cl_command_queue command_queue,
cl_mem buffer,
boolean blocking_map,
long map_flags,
long offset,
long cb,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event,
int[] errcode_ret)
Enqueues a command to map a region of the buffer object given by
buffer into the host address space and returns a pointer to this mapped region. |
static java.nio.ByteBuffer |
clEnqueueMapImage(cl_command_queue command_queue,
cl_mem image,
boolean blocking_map,
long map_flags,
long[] origin,
long[] region,
long[] image_row_pitch,
long[] image_slice_pitch,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event,
int[] errcode_ret)
Enqueues a command to map a region of an image object into the host address
space and returns a pointer to this mapped region.
|
static int |
clEnqueueMarker(cl_command_queue command_queue,
cl_event event)
Deprecated.
As of OpenCL 1.2
|
static int |
clEnqueueMarkerWithWaitList(cl_command_queue command_queue,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a marker command which waits for either a list of events to complete,
or all previously enqueued commands to complete.
|
static int |
clEnqueueMigrateMemObjects(cl_command_queue command_queue,
int num_mem_objects,
cl_mem[] mem_objects,
long flags,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a command to indicate which device a set of memory objects should be associated with.
|
static int |
clEnqueueNativeKernel(cl_command_queue command_queue,
EnqueueNativeKernelFunction user_func,
java.lang.Object args,
long cb_args,
int num_mem_objects,
cl_mem[] mem_list,
Pointer[] args_mem_loc,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a command to execute a native C/C++ function not compiled using the OpenCL compiler.
|
static int |
clEnqueueNDRangeKernel(cl_command_queue command_queue,
cl_kernel kernel,
int work_dim,
long[] global_work_offset,
long[] global_work_size,
long[] local_work_size,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a command to execute a kernel on a device.
|
static int |
clEnqueueReadBuffer(cl_command_queue command_queue,
cl_mem buffer,
boolean blocking_read,
long offset,
long cb,
Pointer ptr,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueue commands to read from a buffer object to host memory.
|
static int |
clEnqueueReadBufferRect(cl_command_queue command_queue,
cl_mem buffer,
boolean blocking_read,
long[] buffer_offset,
long[] host_offset,
long[] region,
long buffer_row_pitch,
long buffer_slice_pitch,
long host_row_pitch,
long host_slice_pitch,
Pointer ptr,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueue commands to read from a rectangular region from a buffer object to host memory.
|
static int |
clEnqueueReadImage(cl_command_queue command_queue,
cl_mem image,
boolean blocking_read,
long[] origin,
long[] region,
long row_pitch,
long slice_pitch,
Pointer ptr,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a command to read from a 2D or 3D image object to host memory.
|
static int |
clEnqueueReleaseGLObjects(cl_command_queue command_queue,
int num_objects,
cl_mem[] mem_objects,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Release OpenCL memory objects that have been created from OpenGL objects.
|
static int |
clEnqueueSVMFree(cl_command_queue command_queue,
int num_svm_pointers,
Pointer[] svm_pointers,
SVMFreeFunction pfn_free_func,
java.lang.Object user_data,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a command to free the shared virtual memory allocated using clSVMAlloc or a shared system memory pointer.
|
static int |
clEnqueueSVMMap(cl_command_queue command_queue,
boolean blocking_map,
long flags,
Pointer svm_ptr,
long size,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a command that will allow the host to update a region of a SVM buffer.
|
static int |
clEnqueueSVMMemcpy(cl_command_queue command_queue,
boolean blocking_copy,
Pointer dst_ptr,
Pointer src_ptr,
long size,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a command to do a memcpy operation.
|
static int |
clEnqueueSVMMemFill(cl_command_queue command_queue,
Pointer svm_ptr,
Pointer pattern,
long pattern_size,
long size,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a command to fill a region in memory with a pattern of a given pattern size.
|
static int |
clEnqueueSVMUnmap(cl_command_queue command_queue,
Pointer svm_ptr,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a command to indicate that the host has completed
updating the region given by
svm_ptr and which was specified in a
previous call to clEnqueueSVMMap. |
static int |
clEnqueueTask(cl_command_queue command_queue,
cl_kernel kernel,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Deprecated.
As of OpenCL 2.0
|
static int |
clEnqueueUnmapMemObject(cl_command_queue command_queue,
cl_mem memobj,
java.nio.ByteBuffer mapped_ptr,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a command to unmap a previously mapped region of a memory object.
|
static int |
clEnqueueWaitForEvents(cl_command_queue command_queue,
int num_events,
cl_event[] event_list)
Deprecated.
As of OpenCL 1.2
|
static int |
clEnqueueWriteBuffer(cl_command_queue command_queue,
cl_mem buffer,
boolean blocking_write,
long offset,
long cb,
Pointer ptr,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueue commands to write to a buffer object from host memory.
|
static int |
clEnqueueWriteBufferRect(cl_command_queue command_queue,
cl_mem buffer,
boolean blocking_write,
long[] buffer_offset,
long[] host_offset,
long[] region,
long buffer_row_pitch,
long buffer_slice_pitch,
long host_row_pitch,
long host_slice_pitch,
Pointer ptr,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueue commands to write a rectangular region to a buffer object from host memory.
|
static int |
clEnqueueWriteImage(cl_command_queue command_queue,
cl_mem image,
boolean blocking_write,
long[] origin,
long[] region,
long input_row_pitch,
long input_slice_pitch,
Pointer ptr,
int num_events_in_wait_list,
cl_event[] event_wait_list,
cl_event event)
Enqueues a command to write to a 2D or 3D image object from host memory.
|
static int |
clFinish(cl_command_queue command_queue)
Blocks until all previously queued OpenCL commands in a command-queue are issued to the associated device and have completed.
|
static int |
clFlush(cl_command_queue command_queue)
Issues all previously queued OpenCL commands in a command-queue to the device associated with the command-queue.
|
static int |
clGetCommandQueueInfo(cl_command_queue command_queue,
int param_name,
long param_value_size,
Pointer param_value,
long[] param_value_size_ret)
Query information about a command-queue.
|
static int |
clGetContextInfo(cl_context context,
int param_name,
long param_value_size,
Pointer param_value,
long[] param_value_size_ret)
Query information about a context.
|
static int |
clGetDeviceIDs(cl_platform_id platform,
long device_type,
int num_entries,
cl_device_id[] devices,
int[] num_devices)
Obtain the list of devices available on a platform.
|
static int |
clGetDeviceInfo(cl_device_id device,
int param_name,
long param_value_size,
Pointer param_value,
long[] param_value_size_ret)
Get information about an OpenCL device.
|
static int |
clGetEventInfo(cl_event event,
int param_name,
long param_value_size,
Pointer param_value,
long[] param_value_size_ret)
Returns information about the event object.
|
static int |
clGetEventProfilingInfo(cl_event event,
int param_name,
long param_value_size,
Pointer param_value,
long[] param_value_size_ret)
Returns profiling information for the command associated with event if profiling is enabled.
|
static int |
clGetGLObjectInfo(cl_mem memobj,
int[] gl_object_type,
int[] gl_object_name)
Query an OpenGL memory object used to create an OpenCL memory object.
|
static int |
clGetGLTextureInfo(cl_mem memobj,
int param_name,
long param_value_size,
Pointer param_value,
long[] param_value_size_ret)
Returns additional information about the GL texture object associated with a memory object.
|
static int |
clGetImageInfo(cl_mem image,
int param_name,
long param_value_size,
Pointer param_value,
long[] param_value_size_ret)
Get information specific to an image object.
|
static int |
clGetKernelArgInfo(cl_kernel kernel,
int arg_indx,
int param_name,
long param_value_size,
Pointer param_value,
long[] param_value_size_ret)
Returns information about the arguments of a kernel.
|
static int |
clGetKernelInfo(cl_kernel kernel,
int param_name,
long param_value_size,
Pointer param_value,
long[] param_value_size_ret)
Returns information about the kernel object.
|
static int |
clGetKernelWorkGroupInfo(cl_kernel kernel,
cl_device_id device,
int param_name,
long param_value_size,
Pointer param_value,
long[] param_value_size_ret)
Returns information about the kernel object that may be specific to a device.
|
static int |
clGetMemObjectInfo(cl_mem memobj,
int param_name,
long param_value_size,
Pointer param_value,
long[] param_value_size_ret)
Used to get information that is common to all memory objects (buffer and image objects).
|
static int |
clGetPipeInfo(cl_mem pipe,
int param_name,
long param_value_size,
Pointer param_value,
long[] param_value_size_ret)
Get information specific to a pipe object created with clCreatePipe.
|
static int |
clGetPlatformIDs(int num_entries,
cl_platform_id[] platforms,
int[] num_platforms)
Obtain the list of platforms available.
|
static int |
clGetPlatformInfo(cl_platform_id platform,
int param_name,
long param_value_size,
Pointer param_value,
long[] param_value_size_ret)
Get specific information about the OpenCL platform.
|
static int |
clGetProgramBuildInfo(cl_program program,
cl_device_id device,
int param_name,
long param_value_size,
Pointer param_value,
long[] param_value_size_ret)
Returns build information for each device in the program object.
|
static int |
clGetProgramInfo(cl_program program,
int param_name,
long param_value_size,
Pointer param_value,
long[] param_value_size_ret)
Returns information about the program object.
|
static int |
clGetSamplerInfo(cl_sampler sampler,
int param_name,
long param_value_size,
Pointer param_value,
long[] param_value_size_ret)
Returns information about the sampler object.
|
static int |
clGetSupportedImageFormats(cl_context context,
long flags,
int image_type,
int num_entries,
cl_image_format[] image_formats,
int[] num_image_formats)
Get the list of image formats supported by an OpenCL implementation.
|
static cl_program |
clLinkProgram(cl_context context,
int num_devices,
cl_device_id[] device_list,
java.lang.String options,
int num_input_programs,
cl_program[] input_programs,
BuildProgramFunction pfn_notify,
java.lang.Object user_data,
int[] errcode_ret)
Links a set of compiled program objects and libraries for all the devices or a specific device(s) in
the OpenCL context and creates an executable.
|
static int |
clReleaseCommandQueue(cl_command_queue command_queue)
Decrements the
command_queue reference count. |
static int |
clReleaseContext(cl_context context)
Decrement the context reference count.
|
static int |
clReleaseDevice(cl_device_id device)
Decrements the
device reference count. |
static int |
clReleaseEvent(cl_event event)
Decrements the
event reference count. |
static int |
clReleaseKernel(cl_kernel kernel)
Decrements the kernel reference count.
|
static int |
clReleaseMemObject(cl_mem memobj)
Decrements the memory object reference count.
|
static int |
clReleaseProgram(cl_program program)
Decrements the
program reference count. |
static int |
clReleaseSampler(cl_sampler sampler)
Decrements the sampler reference count.
|
static int |
clRetainCommandQueue(cl_command_queue command_queue)
Increments the
command_queue reference count. |
static int |
clRetainContext(cl_context context)
Increment the context reference count.
|
static int |
clRetainDevice(cl_device_id device)
Increments the
devices reference count. |
static int |
clRetainEvent(cl_event event)
Increments the
event reference count. |
static int |
clRetainKernel(cl_kernel kernel)
Increments the kernel object reference count.
|
static int |
clRetainMemObject(cl_mem memobj)
Increments the memory object reference count.
|
static int |
clRetainProgram(cl_program program)
Increments the
program reference count. |
static int |
clRetainSampler(cl_sampler sampler)
Increments the sampler reference count.
|
static int |
clSetCommandQueueProperty(cl_command_queue command_queue,
long properties,
boolean enable,
long[] old_properties)
Deprecated.
This API introduces mutable state into the OpenCL implementation.
It has been REMOVED to better facilitate thread safety. The 1.0 API is not
thread safe. It is not tested by the OpenCL 1.1 conformance test, and consequently
may not work or may not work dependably.
It is likely to be non-performant. Use of this API is not advised. Use at your own risk. Software developers previously relying on this API are instructed to set the command queue properties when creating the queue, instead. |
static int |
clSetEventCallback(cl_event event,
int command_exec_callback_type,
EventCallbackFunction pfn_notify,
java.lang.Object user_data)
Registers a user callback function for a specific command execution status.
|
static int |
clSetKernelArg(cl_kernel kernel,
int arg_index,
long arg_size,
Pointer arg_value)
Used to set the argument value for a specific argument of a kernel.
|
static int |
clSetKernelArgSVMPointer(cl_kernel kernel,
int arg_index,
Pointer arg_value)
Used to set a SVM pointer as the argument value for a specific argument of a kernel.
|
static int |
clSetKernelExecInfo(cl_kernel kernel,
int param_name,
long param_value_size,
Pointer param_value)
Used to pass additional information other than argument values to a kernel.
|
static int |
clSetMemObjectDestructorCallback(cl_mem memobj,
MemObjectDestructorCallbackFunction pfn_notify,
java.lang.Object user_data)
Registers a user callback function that will be called when the memory object is
deleted and its resources freed.
|
static int |
clSetPrintfCallback(cl_context context,
PrintfCallbackFunction pfn_notify,
java.lang.Object user_data)
Deprecated.
As of OpenCL 2.0
|
static int |
clSetUserEventStatus(cl_event event,
int execution_status)
Sets the execution status of a user event object.
|
static Pointer |
clSVMAlloc(cl_context context,
long flags,
long size,
int alignment)
Allocates a shared virtual memory (SVM) buffer that can be shared by the host and all devices in an OpenCL context that support shared virtual memory.
|
static void |
clSVMFree(cl_context context,
Pointer svm_pointer)
Frees a shared virtual memory buffer allocated using clSVMAlloc.
|
static int |
clUnloadCompiler()
Deprecated.
As of OpenCL 1.2
|
static int |
clUnloadPlatformCompiler(cl_platform_id platform)
Allows the implementation to release the resources allocated by the OpenCL compiler for <>platform.
|
static int |
clWaitForEvents(int num_events,
cl_event[] event_list)
Waits on the host thread for commands identified by event objects to complete.
|
static void |
setExceptionsEnabled(boolean enabled)
Enables or disables exceptions.
|
static void |
setLogLevel(CL.LogLevel logLevel)
Set the specified log level for the library.
|
static java.lang.String |
stringFor_cl_addressing_mode(int n)
Returns the String identifying the given cl_addressing_mode
|
static java.lang.String |
stringFor_cl_build_status(int n)
Returns the String identifying the given cl_build_status
|
static java.lang.String |
stringFor_cl_channel_order(int n)
Returns the String identifying the given cl_channel_order
|
static java.lang.String |
stringFor_cl_channel_type(int n)
Returns the String identifying the given cl_channel_type
|
static java.lang.String |
stringFor_cl_command_queue_info(int n)
Returns the String identifying the given cl_command_queue_info
|
static java.lang.String |
stringFor_cl_command_queue_properties(long n)
Returns the string describing the given cl_command_queue_properties - bitfield
|
static java.lang.String |
stringFor_cl_command_type(int n)
Returns the String identifying the given cl_command_type
|
static java.lang.String |
stringFor_cl_context_info(int n)
Returns the String identifying the given cl_context_info
|
static java.lang.String |
stringFor_cl_context_properties(int n)
Returns the String identifying the given cl_context_properties
|
static java.lang.String |
stringFor_cl_device_address_info(long n)
Returns the string describing the given cl_device_address_info - bitfield
|
static java.lang.String |
stringFor_cl_device_affinity_domain(long n)
Returns the string describing the given cl_device_affinity_domain - bitfield
|
static java.lang.String |
stringFor_cl_device_exec_capabilities(long n)
Returns the string describing the given cl_device_exec_capabilities - bitfield
|
static java.lang.String |
stringFor_cl_device_fp_config(long n)
Returns the string describing the given cl_device_fp_config - bitfield
|
static java.lang.String |
stringFor_cl_device_info(int n)
Returns the String identifying the given cl_device_info
|
static java.lang.String |
stringFor_cl_device_local_mem_type(int n)
Returns the String identifying the given cl_device_local_mem_type
|
static java.lang.String |
stringFor_cl_device_mem_cache_type(int n)
Returns the String identifying the given cl_device_mem_cache_type
|
static java.lang.String |
stringFor_cl_device_partition_property(int n)
Returns the String identifying the given cl_device_partition_property
|
static java.lang.String |
stringFor_cl_device_svm_capabilities(long n)
Returns the string describing the given cl_device_svm_capabilities - bitfield
|
static java.lang.String |
stringFor_cl_device_type(long n)
Returns the string describing the given cl_device_type - bitfield
|
static java.lang.String |
stringFor_cl_event_info(int n)
Returns the String identifying the given cl_event_info
|
static java.lang.String |
stringFor_cl_filter_mode(int n)
Returns the String identifying the given cl_filter_mode
|
static java.lang.String |
stringFor_cl_gl_object_type(int n)
Returns the String identifying the given cl_gl_object_type
|
static java.lang.String |
stringFor_cl_gl_texture_info(int n)
Returns the String identifying the given cl_gl_texture_info
|
static java.lang.String |
stringFor_cl_image_info(int n)
Returns the String identifying the given cl_image_info
|
static java.lang.String |
stringFor_cl_kernel_arg_access_qualifier(int n)
Returns the String identifying the given cl_kernel_arg_access_qualifier
|
static java.lang.String |
stringFor_cl_kernel_arg_address_qualifier(int n)
Returns the String identifying the given cl_kernel_arg_address_qualifier
|
static java.lang.String |
stringFor_cl_kernel_arg_info(int n)
Returns the String identifying the given cl_kernel_arg_info
|
static java.lang.String |
stringFor_cl_kernel_arg_type_qualifer(long n)
Returns the string describing the given cl_kernel_arg_type_qualifer - bitfield
|
static java.lang.String |
stringFor_cl_kernel_exec_info(int n)
Returns the String identifying the given cl_kernel_exec_info
|
static java.lang.String |
stringFor_cl_kernel_info(int n)
Returns the String identifying the given cl_kernel_info
|
static java.lang.String |
stringFor_cl_kernel_work_group_info(int n)
Returns the String identifying the given cl_kernel_work_group_info
|
static java.lang.String |
stringFor_cl_khr_gl_sharing(int n)
Returns the String identifying the given cl_khr_gl_sharing
|
static java.lang.String |
stringFor_cl_map_flags(long n)
Returns the string describing the given cl_map_flags - bitfield
|
static java.lang.String |
stringFor_cl_mem_flags(long n)
Returns the string describing the given cl_mem_flags - bitfield
|
static java.lang.String |
stringFor_cl_mem_info(int n)
Returns the String identifying the given cl_mem_info
|
static java.lang.String |
stringFor_cl_mem_migration_flags(long n)
Returns the string describing the given cl_mem_migration_flags - bitfield
|
static java.lang.String |
stringFor_cl_mem_object_type(int n)
Returns the String identifying the given cl_mem_object_type
|
static java.lang.String |
stringFor_cl_pipe_info(int n)
Returns the String identifying the given cl_pipe_info
|
static java.lang.String |
stringFor_cl_platform_info(int n)
Returns the String identifying the given cl_platform_info
|
static java.lang.String |
stringFor_cl_profiling_info(int n)
Returns the String identifying the given cl_profiling_info
|
static java.lang.String |
stringFor_cl_program_binary_type(int n)
Returns the String identifying the given cl_program_binary_type
|
static java.lang.String |
stringFor_cl_program_build_info(int n)
Returns the String identifying the given cl_program_build_info
|
static java.lang.String |
stringFor_cl_program_info(int n)
Returns the String identifying the given cl_program_info
|
static java.lang.String |
stringFor_cl_sampler_info(int n)
Returns the String identifying the given cl_sampler_info
|
static java.lang.String |
stringFor_command_execution_status(int n)
Returns the command execution String identifying the given command_execution_status
|
static java.lang.String |
stringFor_errorCode(int n)
Returns the String identifying the given error code
|
public static final int CL_CHAR_BIT
public static final int CL_SCHAR_MAX
public static final int CL_SCHAR_MIN
public static final int CL_CHAR_MAX
public static final int CL_CHAR_MIN
public static final int CL_UCHAR_MAX
public static final int CL_SHRT_MAX
public static final int CL_SHRT_MIN
public static final int CL_USHRT_MAX
public static final int CL_INT_MAX
public static final int CL_INT_MIN
public static final long CL_UINT_MAX
public static final long CL_LONG_MAX
public static final long CL_LONG_MIN
public static final long CL_ULONG_MAX
public static final int CL_FLT_DIG
public static final int CL_FLT_MANT_DIG
public static final int CL_FLT_MAX_10_EXP
public static final int CL_FLT_MAX_EXP
public static final int CL_FLT_MIN_10_EXP
public static final int CL_FLT_MIN_EXP
public static final int CL_FLT_RADIX
public static final float CL_FLT_MAX
public static final float CL_FLT_MIN
public static final float CL_FLT_EPSILON
public static final int CL_DBL_DIG
public static final int CL_DBL_MANT_DIG
public static final int CL_DBL_MAX_10_EXP
public static final int CL_DBL_MAX_EXP
public static final int CL_DBL_MIN_10_EXP
public static final int CL_DBL_MIN_EXP
public static final int CL_DBL_RADIX
public static final double CL_DBL_MAX
public static final double CL_DBL_MIN
public static final double CL_DBL_EPSILON
public static final int CL_SUCCESS
public static final int CL_DEVICE_NOT_FOUND
public static final int CL_DEVICE_NOT_AVAILABLE
public static final int CL_COMPILER_NOT_AVAILABLE
public static final int CL_MEM_OBJECT_ALLOCATION_FAILURE
public static final int CL_OUT_OF_RESOURCES
public static final int CL_OUT_OF_HOST_MEMORY
public static final int CL_PROFILING_INFO_NOT_AVAILABLE
public static final int CL_MEM_COPY_OVERLAP
public static final int CL_IMAGE_FORMAT_MISMATCH
public static final int CL_IMAGE_FORMAT_NOT_SUPPORTED
public static final int CL_BUILD_PROGRAM_FAILURE
public static final int CL_MAP_FAILURE
public static final int CL_MISALIGNED_SUB_BUFFER_OFFSET
public static final int CL_EXEC_STATUS_ERROR_FOR_EVENTS_IN_WAIT_LIST
public static final int CL_COMPILE_PROGRAM_FAILURE
public static final int CL_LINKER_NOT_AVAILABLE
public static final int CL_LINK_PROGRAM_FAILURE
public static final int CL_DEVICE_PARTITION_FAILED
public static final int CL_KERNEL_ARG_INFO_NOT_AVAILABLE
public static final int CL_INVALID_VALUE
public static final int CL_INVALID_DEVICE_TYPE
public static final int CL_INVALID_PLATFORM
public static final int CL_INVALID_DEVICE
public static final int CL_INVALID_CONTEXT
public static final int CL_INVALID_QUEUE_PROPERTIES
public static final int CL_INVALID_COMMAND_QUEUE
public static final int CL_INVALID_HOST_PTR
public static final int CL_INVALID_MEM_OBJECT
public static final int CL_INVALID_IMAGE_FORMAT_DESCRIPTOR
public static final int CL_INVALID_IMAGE_SIZE
public static final int CL_INVALID_SAMPLER
public static final int CL_INVALID_BINARY
public static final int CL_INVALID_BUILD_OPTIONS
public static final int CL_INVALID_PROGRAM
public static final int CL_INVALID_PROGRAM_EXECUTABLE
public static final int CL_INVALID_KERNEL_NAME
public static final int CL_INVALID_KERNEL_DEFINITION
public static final int CL_INVALID_KERNEL
public static final int CL_INVALID_ARG_INDEX
public static final int CL_INVALID_ARG_VALUE
public static final int CL_INVALID_ARG_SIZE
public static final int CL_INVALID_KERNEL_ARGS
public static final int CL_INVALID_WORK_DIMENSION
public static final int CL_INVALID_WORK_GROUP_SIZE
public static final int CL_INVALID_WORK_ITEM_SIZE
public static final int CL_INVALID_GLOBAL_OFFSET
public static final int CL_INVALID_EVENT_WAIT_LIST
public static final int CL_INVALID_EVENT
public static final int CL_INVALID_OPERATION
public static final int CL_INVALID_GL_OBJECT
public static final int CL_INVALID_BUFFER_SIZE
public static final int CL_INVALID_MIP_LEVEL
public static final int CL_INVALID_GLOBAL_WORK_SIZE
public static final int CL_INVALID_PROPERTY
public static final int CL_INVALID_IMAGE_DESCRIPTOR
public static final int CL_INVALID_COMPILER_OPTIONS
public static final int CL_INVALID_LINKER_OPTIONS
public static final int CL_INVALID_DEVICE_PARTITION_COUNT
public static final int CL_INVALID_PIPE_SIZE
public static final int CL_INVALID_DEVICE_QUEUE
public static final int CL_JOCL_INTERNAL_ERROR
public static final int CL_INVALID_GL_SHAREGROUP_REFERENCE_KHR
public static final int CL_PLATFORM_NOT_FOUND_KHR
public static final boolean CL_TRUE
public static final boolean CL_FALSE
public static final boolean CL_BLOCKING
public static final boolean CL_NON_BLOCKING
public static final int CL_PLATFORM_PROFILE
public static final int CL_PLATFORM_VERSION
public static final int CL_PLATFORM_NAME
public static final int CL_PLATFORM_VENDOR
public static final int CL_PLATFORM_EXTENSIONS
public static final int CL_PLATFORM_ICD_SUFFIX_KHR
public static final long CL_DEVICE_TYPE_DEFAULT
public static final long CL_DEVICE_TYPE_CPU
public static final long CL_DEVICE_TYPE_GPU
public static final long CL_DEVICE_TYPE_ACCELERATOR
public static final long CL_DEVICE_TYPE_ALL
public static final long CL_DEVICE_TYPE_CUSTOM
public static final int CL_DEVICE_TYPE
public static final int CL_DEVICE_VENDOR_ID
public static final int CL_DEVICE_MAX_COMPUTE_UNITS
public static final int CL_DEVICE_MAX_WORK_ITEM_DIMENSIONS
public static final int CL_DEVICE_MAX_WORK_GROUP_SIZE
public static final int CL_DEVICE_MAX_WORK_ITEM_SIZES
public static final int CL_DEVICE_PREFERRED_VECTOR_WIDTH_CHAR
public static final int CL_DEVICE_PREFERRED_VECTOR_WIDTH_SHORT
public static final int CL_DEVICE_PREFERRED_VECTOR_WIDTH_INT
public static final int CL_DEVICE_PREFERRED_VECTOR_WIDTH_LONG
public static final int CL_DEVICE_PREFERRED_VECTOR_WIDTH_FLOAT
public static final int CL_DEVICE_PREFERRED_VECTOR_WIDTH_DOUBLE
public static final int CL_DEVICE_MAX_CLOCK_FREQUENCY
public static final int CL_DEVICE_ADDRESS_BITS
public static final int CL_DEVICE_MAX_READ_IMAGE_ARGS
public static final int CL_DEVICE_MAX_WRITE_IMAGE_ARGS
public static final int CL_DEVICE_MAX_MEM_ALLOC_SIZE
public static final int CL_DEVICE_IMAGE2D_MAX_WIDTH
public static final int CL_DEVICE_IMAGE2D_MAX_HEIGHT
public static final int CL_DEVICE_IMAGE3D_MAX_WIDTH
public static final int CL_DEVICE_IMAGE3D_MAX_HEIGHT
public static final int CL_DEVICE_IMAGE3D_MAX_DEPTH
public static final int CL_DEVICE_IMAGE_SUPPORT
public static final int CL_DEVICE_MAX_PARAMETER_SIZE
public static final int CL_DEVICE_MAX_SAMPLERS
public static final int CL_DEVICE_MEM_BASE_ADDR_ALIGN
public static final int CL_DEVICE_MIN_DATA_TYPE_ALIGN_SIZE
public static final int CL_DEVICE_SINGLE_FP_CONFIG
public static final int CL_DEVICE_GLOBAL_MEM_CACHE_TYPE
public static final int CL_DEVICE_GLOBAL_MEM_CACHELINE_SIZE
public static final int CL_DEVICE_GLOBAL_MEM_CACHE_SIZE
public static final int CL_DEVICE_GLOBAL_MEM_SIZE
public static final int CL_DEVICE_MAX_CONSTANT_BUFFER_SIZE
public static final int CL_DEVICE_MAX_CONSTANT_ARGS
public static final int CL_DEVICE_LOCAL_MEM_TYPE
public static final int CL_DEVICE_LOCAL_MEM_SIZE
public static final int CL_DEVICE_ERROR_CORRECTION_SUPPORT
public static final int CL_DEVICE_PROFILING_TIMER_RESOLUTION
public static final int CL_DEVICE_ENDIAN_LITTLE
public static final int CL_DEVICE_AVAILABLE
public static final int CL_DEVICE_COMPILER_AVAILABLE
public static final int CL_DEVICE_EXECUTION_CAPABILITIES
public static final int CL_DEVICE_QUEUE_PROPERTIES
CL_DEVICE_QUEUE_ON_HOST_PROPERTIESpublic static final int CL_DEVICE_NAME
public static final int CL_DEVICE_VENDOR
public static final int CL_DRIVER_VERSION
public static final int CL_DEVICE_PROFILE
public static final int CL_DEVICE_VERSION
public static final int CL_DEVICE_EXTENSIONS
public static final int CL_DEVICE_PLATFORM
public static final int CL_DEVICE_PREFERRED_VECTOR_WIDTH_HALF
public static final int CL_DEVICE_HOST_UNIFIED_MEMORY
public static final int CL_DEVICE_NATIVE_VECTOR_WIDTH_CHAR
public static final int CL_DEVICE_NATIVE_VECTOR_WIDTH_SHORT
public static final int CL_DEVICE_NATIVE_VECTOR_WIDTH_INT
public static final int CL_DEVICE_NATIVE_VECTOR_WIDTH_LONG
public static final int CL_DEVICE_NATIVE_VECTOR_WIDTH_FLOAT
public static final int CL_DEVICE_NATIVE_VECTOR_WIDTH_DOUBLE
public static final int CL_DEVICE_NATIVE_VECTOR_WIDTH_HALF
public static final int CL_DEVICE_OPENCL_C_VERSION
public static final int CL_DEVICE_LINKER_AVAILABLE
public static final int CL_DEVICE_BUILT_IN_KERNELS
public static final int CL_DEVICE_IMAGE_MAX_BUFFER_SIZE
public static final int CL_DEVICE_IMAGE_MAX_ARRAY_SIZE
public static final int CL_DEVICE_PARENT_DEVICE
public static final int CL_DEVICE_PARTITION_MAX_SUB_DEVICES
public static final int CL_DEVICE_PARTITION_PROPERTIES
public static final int CL_DEVICE_PARTITION_AFFINITY_DOMAIN
public static final int CL_DEVICE_PARTITION_TYPE
public static final int CL_DEVICE_REFERENCE_COUNT
public static final int CL_DEVICE_PREFERRED_INTEROP_USER_SYNC
public static final int CL_DEVICE_PRINTF_BUFFER_SIZE
public static final int CL_DEVICE_QUEUE_ON_HOST_PROPERTIES
public static final int CL_DEVICE_IMAGE_PITCH_ALIGNMENT
public static final int CL_DEVICE_IMAGE_BASE_ADDRESS_ALIGNMENT
public static final int CL_DEVICE_MAX_READ_WRITE_IMAGE_ARGS
public static final int CL_DEVICE_MAX_GLOBAL_VARIABLE_SIZE
public static final int CL_DEVICE_QUEUE_ON_DEVICE_PROPERTIES
public static final int CL_DEVICE_QUEUE_ON_DEVICE_PREFERRED_SIZE
public static final int CL_DEVICE_QUEUE_ON_DEVICE_MAX_SIZE
public static final int CL_DEVICE_MAX_ON_DEVICE_QUEUES
public static final int CL_DEVICE_MAX_ON_DEVICE_EVENTS
public static final int CL_DEVICE_SVM_CAPABILITIES
public static final int CL_DEVICE_GLOBAL_VARIABLE_PREFERRED_TOTAL_SIZE
public static final int CL_DEVICE_MAX_PIPE_ARGS
public static final int CL_DEVICE_PIPE_MAX_ACTIVE_RESERVATIONS
public static final int CL_DEVICE_PIPE_MAX_PACKET_SIZE
public static final int CL_DEVICE_PREFERRED_PLATFORM_ATOMIC_ALIGNMENT
public static final int CL_DEVICE_PREFERRED_GLOBAL_ATOMIC_ALIGNMENT
public static final int CL_DEVICE_PREFERRED_LOCAL_ATOMIC_ALIGNMENT
public static final int CL_DEVICE_DOUBLE_FP_CONFIG
public static final int CL_DEVICE_HALF_FP_CONFIG
public static final long CL_DEVICE_ADDRESS_32_BITS
public static final long CL_DEVICE_ADDRESS_64_BITS
public static final long CL_FP_DENORM
public static final long CL_FP_INF_NAN
public static final long CL_FP_ROUND_TO_NEAREST
public static final long CL_FP_ROUND_TO_ZERO
public static final long CL_FP_ROUND_TO_INF
public static final long CL_FP_FMA
public static final long CL_FP_SOFT_FLOAT
public static final long CL_FP_CORRECTLY_ROUNDED_DIVIDE_SQRT
public static final int CL_NONE
public static final int CL_READ_ONLY_CACHE
public static final int CL_READ_WRITE_CACHE
public static final int CL_LOCAL
public static final int CL_GLOBAL
public static final long CL_EXEC_KERNEL
public static final long CL_EXEC_NATIVE_KERNEL
public static final long CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE
public static final long CL_QUEUE_PROFILING_ENABLE
public static final long CL_QUEUE_ON_DEVICE
public static final long CL_QUEUE_ON_DEVICE_DEFAULT
public static final int CL_CONTEXT_REFERENCE_COUNT
public static final int CL_CONTEXT_DEVICES
public static final int CL_CONTEXT_PROPERTIES
public static final int CL_CONTEXT_NUM_DEVICES
public static final int CL_CONTEXT_PLATFORM
public static final int CL_CONTEXT_INTEROP_USER_SYNC
public static final int CL_DEVICE_PARTITION_EQUALLY
public static final int CL_DEVICE_PARTITION_BY_COUNTS
public static final int CL_DEVICE_PARTITION_BY_COUNTS_LIST_END
public static final int CL_DEVICE_PARTITION_BY_AFFINITY_DOMAIN
public static final long CL_DEVICE_AFFINITY_DOMAIN_NUMA
public static final long CL_DEVICE_AFFINITY_DOMAIN_L4_CACHE
public static final long CL_DEVICE_AFFINITY_DOMAIN_L3_CACHE
public static final long CL_DEVICE_AFFINITY_DOMAIN_L2_CACHE
public static final long CL_DEVICE_AFFINITY_DOMAIN_L1_CACHE
public static final long CL_DEVICE_AFFINITY_DOMAIN_NEXT_PARTITIONABLE
public static final long CL_DEVICE_SVM_COARSE_GRAIN_BUFFER
public static final long CL_DEVICE_SVM_FINE_GRAIN_BUFFER
public static final long CL_DEVICE_SVM_FINE_GRAIN_SYSTEM
public static final long CL_DEVICE_SVM_ATOMICS
public static final int CL_QUEUE_CONTEXT
public static final int CL_QUEUE_DEVICE
public static final int CL_QUEUE_REFERENCE_COUNT
public static final int CL_QUEUE_PROPERTIES
public static final int CL_QUEUE_SIZE
public static final long CL_MEM_READ_WRITE
public static final long CL_MEM_WRITE_ONLY
public static final long CL_MEM_READ_ONLY
public static final long CL_MEM_USE_HOST_PTR
public static final long CL_MEM_ALLOC_HOST_PTR
public static final long CL_MEM_COPY_HOST_PTR
public static final long CL_MEM_HOST_WRITE_ONLY
public static final long CL_MEM_HOST_READ_ONLY
public static final long CL_MEM_HOST_NO_ACCESS
public static final long CL_MEM_SVM_FINE_GRAIN_BUFFER
public static final long CL_MEM_SVM_ATOMICS
public static final long CL_MIGRATE_MEM_OBJECT_HOST
public static final long CL_MIGRATE_MEM_OBJECT_CONTENT_UNDEFINED
public static final int CL_R
public static final int CL_A
public static final int CL_RG
public static final int CL_RA
public static final int CL_RGB
public static final int CL_RGBA
public static final int CL_BGRA
public static final int CL_ARGB
public static final int CL_INTENSITY
public static final int CL_LUMINANCE
public static final int CL_Rx
public static final int CL_RGx
public static final int CL_RGBx
public static final int CL_DEPTH
public static final int CL_DEPTH_STENCIL
public static final int CL_sRGB
public static final int CL_sRGBx
public static final int CL_sRGBA
public static final int CL_sBGRA
public static final int CL_ABGR
public static final int CL_SNORM_INT8
public static final int CL_SNORM_INT16
public static final int CL_UNORM_INT8
public static final int CL_UNORM_INT16
public static final int CL_UNORM_SHORT_565
public static final int CL_UNORM_SHORT_555
public static final int CL_UNORM_INT_101010
public static final int CL_SIGNED_INT8
public static final int CL_SIGNED_INT16
public static final int CL_SIGNED_INT32
public static final int CL_UNSIGNED_INT8
public static final int CL_UNSIGNED_INT16
public static final int CL_UNSIGNED_INT32
public static final int CL_HALF_FLOAT
public static final int CL_FLOAT
public static final int CL_UNORM_INT24
public static final int CL_MEM_OBJECT_BUFFER
public static final int CL_MEM_OBJECT_IMAGE2D
public static final int CL_MEM_OBJECT_IMAGE3D
public static final int CL_MEM_OBJECT_IMAGE2D_ARRAY
public static final int CL_MEM_OBJECT_IMAGE1D
public static final int CL_MEM_OBJECT_IMAGE1D_ARRAY
public static final int CL_MEM_OBJECT_IMAGE1D_BUFFER
public static final int CL_MEM_OBJECT_PIPE
public static final int CL_MEM_TYPE
public static final int CL_MEM_FLAGS
public static final int CL_MEM_SIZE
public static final int CL_MEM_HOST_PTR
public static final int CL_MEM_MAP_COUNT
public static final int CL_MEM_REFERENCE_COUNT
public static final int CL_MEM_CONTEXT
public static final int CL_MEM_ASSOCIATED_MEMOBJECT
public static final int CL_MEM_OFFSET
public static final int CL_MEM_USES_SVM_POINTER
public static final int CL_IMAGE_FORMAT
public static final int CL_IMAGE_ELEMENT_SIZE
public static final int CL_IMAGE_ROW_PITCH
public static final int CL_IMAGE_SLICE_PITCH
public static final int CL_IMAGE_WIDTH
public static final int CL_IMAGE_HEIGHT
public static final int CL_IMAGE_DEPTH
public static final int CL_IMAGE_ARRAY_SIZE
public static final int CL_IMAGE_BUFFER
public static final int CL_IMAGE_NUM_MIP_LEVELS
public static final int CL_IMAGE_NUM_SAMPLES
public static final int CL_PIPE_PACKET_SIZE
public static final int CL_PIPE_MAX_PACKETS
public static final int CL_ADDRESS_NONE
public static final int CL_ADDRESS_CLAMP_TO_EDGE
public static final int CL_ADDRESS_CLAMP
public static final int CL_ADDRESS_REPEAT
public static final int CL_ADDRESS_MIRRORED_REPEAT
public static final int CL_FILTER_NEAREST
public static final int CL_FILTER_LINEAR
public static final int CL_SAMPLER_REFERENCE_COUNT
public static final int CL_SAMPLER_CONTEXT
public static final int CL_SAMPLER_NORMALIZED_COORDS
public static final int CL_SAMPLER_ADDRESSING_MODE
public static final int CL_SAMPLER_FILTER_MODE
public static final int CL_SAMPLER_MIP_FILTER_MODE
public static final int CL_SAMPLER_LOD_MIN
public static final int CL_SAMPLER_LOD_MAX
public static final long CL_MAP_READ
public static final long CL_MAP_WRITE
public static final long CL_MAP_WRITE_INVALIDATE_REGION
public static final int CL_PROGRAM_REFERENCE_COUNT
public static final int CL_PROGRAM_CONTEXT
public static final int CL_PROGRAM_NUM_DEVICES
public static final int CL_PROGRAM_DEVICES
public static final int CL_PROGRAM_SOURCE
public static final int CL_PROGRAM_BINARY_SIZES
public static final int CL_PROGRAM_BINARIES
public static final int CL_PROGRAM_NUM_KERNELS
public static final int CL_PROGRAM_KERNEL_NAMES
public static final int CL_PROGRAM_BUILD_STATUS
public static final int CL_PROGRAM_BUILD_OPTIONS
public static final int CL_PROGRAM_BUILD_LOG
public static final int CL_PROGRAM_BINARY_TYPE
public static final int CL_PROGRAM_BUILD_GLOBAL_VARIABLE_TOTAL_SIZE
public static final int CL_PROGRAM_BINARY_TYPE_NONE
public static final int CL_PROGRAM_BINARY_TYPE_COMPILED_OBJECT
public static final int CL_PROGRAM_BINARY_TYPE_LIBRARY
public static final int CL_PROGRAM_BINARY_TYPE_EXECUTABLE
public static final int CL_BUILD_SUCCESS
public static final int CL_BUILD_NONE
public static final int CL_BUILD_ERROR
public static final int CL_BUILD_IN_PROGRESS
public static final int CL_KERNEL_FUNCTION_NAME
public static final int CL_KERNEL_NUM_ARGS
public static final int CL_KERNEL_REFERENCE_COUNT
public static final int CL_KERNEL_CONTEXT
public static final int CL_KERNEL_PROGRAM
public static final int CL_KERNEL_ATTRIBUTES
public static final int CL_KERNEL_ARG_ADDRESS_QUALIFIER
public static final int CL_KERNEL_ARG_ACCESS_QUALIFIER
public static final int CL_KERNEL_ARG_TYPE_NAME
public static final int CL_KERNEL_ARG_TYPE_QUALIFIER
public static final int CL_KERNEL_ARG_NAME
public static final int CL_KERNEL_ARG_ADDRESS_GLOBAL
public static final int CL_KERNEL_ARG_ADDRESS_LOCAL
public static final int CL_KERNEL_ARG_ADDRESS_CONSTANT
public static final int CL_KERNEL_ARG_ADDRESS_PRIVATE
public static final int CL_KERNEL_ARG_ACCESS_READ_ONLY
public static final int CL_KERNEL_ARG_ACCESS_WRITE_ONLY
public static final int CL_KERNEL_ARG_ACCESS_READ_WRITE
public static final int CL_KERNEL_ARG_ACCESS_NONE
public static final long CL_KERNEL_ARG_TYPE_NONE
public static final long CL_KERNEL_ARG_TYPE_CONST
public static final long CL_KERNEL_ARG_TYPE_RESTRICT
public static final long CL_KERNEL_ARG_TYPE_VOLATILE
public static final long CL_KERNEL_ARG_TYPE_PIPE
public static final int CL_KERNEL_WORK_GROUP_SIZE
public static final int CL_KERNEL_COMPILE_WORK_GROUP_SIZE
public static final int CL_KERNEL_LOCAL_MEM_SIZE
public static final int CL_KERNEL_PREFERRED_WORK_GROUP_SIZE_MULTIPLE
public static final int CL_KERNEL_PRIVATE_MEM_SIZE
public static final int CL_KERNEL_GLOBAL_WORK_SIZE
public static final int CL_KERNEL_EXEC_INFO_SVM_PTRS
public static final int CL_KERNEL_EXEC_INFO_SVM_FINE_GRAIN_SYSTEM
public static final int CL_EVENT_COMMAND_QUEUE
public static final int CL_EVENT_COMMAND_TYPE
public static final int CL_EVENT_REFERENCE_COUNT
public static final int CL_EVENT_COMMAND_EXECUTION_STATUS
public static final int CL_EVENT_CONTEXT
public static final int CL_COMMAND_NDRANGE_KERNEL
public static final int CL_COMMAND_TASK
public static final int CL_COMMAND_NATIVE_KERNEL
public static final int CL_COMMAND_READ_BUFFER
public static final int CL_COMMAND_WRITE_BUFFER
public static final int CL_COMMAND_COPY_BUFFER
public static final int CL_COMMAND_READ_IMAGE
public static final int CL_COMMAND_WRITE_IMAGE
public static final int CL_COMMAND_COPY_IMAGE
public static final int CL_COMMAND_COPY_IMAGE_TO_BUFFER
public static final int CL_COMMAND_COPY_BUFFER_TO_IMAGE
public static final int CL_COMMAND_MAP_BUFFER
public static final int CL_COMMAND_MAP_IMAGE
public static final int CL_COMMAND_UNMAP_MEM_OBJECT
public static final int CL_COMMAND_MARKER
public static final int CL_COMMAND_ACQUIRE_GL_OBJECTS
public static final int CL_COMMAND_RELEASE_GL_OBJECTS
public static final int CL_COMMAND_READ_BUFFER_RECT
public static final int CL_COMMAND_WRITE_BUFFER_RECT
public static final int CL_COMMAND_COPY_BUFFER_RECT
public static final int CL_COMMAND_USER
public static final int CL_COMMAND_BARRIER
public static final int CL_COMMAND_MIGRATE_MEM_OBJECTS
public static final int CL_COMMAND_FILL_BUFFER
public static final int CL_COMMAND_FILL_IMAGE
public static final int CL_COMMAND_SVM_FREE
public static final int CL_COMMAND_SVM_MEMCPY
public static final int CL_COMMAND_SVM_MEMFILL
public static final int CL_COMMAND_SVM_MAP
public static final int CL_COMMAND_SVM_UNMAP
public static final int CL_COMPLETE
public static final int CL_RUNNING
public static final int CL_SUBMITTED
public static final int CL_QUEUED
public static final int CL_BUFFER_CREATE_TYPE_REGION
public static final int CL_PROFILING_COMMAND_QUEUED
public static final int CL_PROFILING_COMMAND_SUBMIT
public static final int CL_PROFILING_COMMAND_START
public static final int CL_PROFILING_COMMAND_END
public static final int CL_PROFILING_COMMAND_COMPLETE
public static final int CL_GL_OBJECT_BUFFER
public static final int CL_GL_OBJECT_TEXTURE2D
public static final int CL_GL_OBJECT_TEXTURE3D
public static final int CL_GL_OBJECT_RENDERBUFFER
public static final int CL_GL_OBJECT_TEXTURE2D_ARRAY
public static final int CL_GL_OBJECT_TEXTURE1D
public static final int CL_GL_OBJECT_TEXTURE1D_ARRAY
public static final int CL_GL_OBJECT_TEXTURE_BUFFER
public static final int CL_GL_TEXTURE_TARGET
public static final int CL_GL_MIPMAP_LEVEL
public static final int CL_GL_NUM_SAMPLES
public static final int CL_CURRENT_DEVICE_FOR_GL_CONTEXT_KHR
public static final int CL_DEVICES_FOR_GL_CONTEXT_KHR
public static final int CL_GL_CONTEXT_KHR
public static final int CL_EGL_DISPLAY_KHR
public static final int CL_GLX_DISPLAY_KHR
public static final int CL_WGL_HDC_KHR
public static final int CL_CGL_SHAREGROUP_KHR
public static void setExceptionsEnabled(boolean enabled)
enabled - Whether exceptions are enabledpublic static java.lang.String stringFor_errorCode(int n)
n - The error codepublic static java.lang.String stringFor_cl_platform_info(int n)
n - A cl_platform_info valuepublic static java.lang.String stringFor_cl_device_info(int n)
n - A cl_device_info valuepublic static java.lang.String stringFor_cl_device_mem_cache_type(int n)
n - A cl_device_mem_cache_type valuepublic static java.lang.String stringFor_cl_device_local_mem_type(int n)
n - A cl_device_local_mem_type valuepublic static java.lang.String stringFor_cl_context_info(int n)
n - A cl_context_info valuepublic static java.lang.String stringFor_cl_context_properties(int n)
n - A cl_context_properties valuepublic static java.lang.String stringFor_cl_device_partition_property(int n)
n - A cl_device_partition_property valuepublic static java.lang.String stringFor_cl_command_queue_info(int n)
n - A cl_command_queue_info valuepublic static java.lang.String stringFor_cl_channel_order(int n)
n - A cl_channel_order valuepublic static java.lang.String stringFor_cl_channel_type(int n)
n - A cl_channel_type valuepublic static java.lang.String stringFor_cl_mem_object_type(int n)
n - A cl_mem_object_type valuepublic static java.lang.String stringFor_cl_mem_info(int n)
n - A cl_mem_info valuepublic static java.lang.String stringFor_cl_image_info(int n)
n - A cl_image_info valuepublic static java.lang.String stringFor_cl_pipe_info(int n)
n - A cl_pipe_info valuepublic static java.lang.String stringFor_cl_addressing_mode(int n)
n - A cl_addressing_mode valuepublic static java.lang.String stringFor_cl_filter_mode(int n)
n - A cl_filter_mode valuepublic static java.lang.String stringFor_cl_sampler_info(int n)
n - A cl_sampler_info valuepublic static java.lang.String stringFor_cl_program_info(int n)
n - A cl_program_info valuepublic static java.lang.String stringFor_cl_program_build_info(int n)
n - A cl_program_build_info valuepublic static java.lang.String stringFor_cl_program_binary_type(int n)
n - A cl_program_binary_type valuepublic static java.lang.String stringFor_cl_build_status(int n)
n - A cl_build_status valuepublic static java.lang.String stringFor_cl_kernel_info(int n)
n - A cl_kernel_info valuepublic static java.lang.String stringFor_cl_kernel_arg_info(int n)
n - A cl_kernel_arg_info valuepublic static java.lang.String stringFor_cl_kernel_arg_address_qualifier(int n)
n - A cl_kernel_arg_address_qualifier valuepublic static java.lang.String stringFor_cl_kernel_arg_access_qualifier(int n)
n - A cl_kernel_arg_access_qualifier valuepublic static java.lang.String stringFor_cl_kernel_work_group_info(int n)
n - A cl_kernel_work_group_info valuepublic static java.lang.String stringFor_cl_kernel_exec_info(int n)
n - A cl_kernel_exec_info valuepublic static java.lang.String stringFor_cl_event_info(int n)
n - A cl_event_info valuepublic static java.lang.String stringFor_cl_command_type(int n)
n - A cl_command_type valuepublic static java.lang.String stringFor_command_execution_status(int n)
n - A command_execution_status valuepublic static java.lang.String stringFor_cl_profiling_info(int n)
n - A cl_profiling_info valuepublic static java.lang.String stringFor_cl_gl_object_type(int n)
n - A cl_gl_object_type valuepublic static java.lang.String stringFor_cl_gl_texture_info(int n)
n - A cl_gl_texture_info valuepublic static java.lang.String stringFor_cl_khr_gl_sharing(int n)
n - A cl_khr_gl_sharing valuepublic static java.lang.String stringFor_cl_device_type(long n)
n - The cl_device_type - bitfieldpublic static java.lang.String stringFor_cl_device_address_info(long n)
n - The cl_device_address_info - bitfieldpublic static java.lang.String stringFor_cl_device_fp_config(long n)
n - The cl_device_fp_config - bitfieldpublic static java.lang.String stringFor_cl_device_exec_capabilities(long n)
n - The cl_device_exec_capabilities - bitfieldpublic static java.lang.String stringFor_cl_command_queue_properties(long n)
n - The cl_command_queue_properties - bitfieldpublic static java.lang.String stringFor_cl_device_affinity_domain(long n)
n - The cl_device_affinity_domain - bitfieldpublic static java.lang.String stringFor_cl_device_svm_capabilities(long n)
n - The cl_device_svm_capabilities - bitfieldpublic static java.lang.String stringFor_cl_mem_flags(long n)
n - The cl_mem_flags - bitfieldpublic static java.lang.String stringFor_cl_mem_migration_flags(long n)
n - The cl_mem_migration_flags - bitfieldpublic static java.lang.String stringFor_cl_map_flags(long n)
n - The cl_map_flags - bitfieldpublic static java.lang.String stringFor_cl_kernel_arg_type_qualifer(long n)
n - The cl_kernel_arg_type_qualifer - bitfieldpublic static void setLogLevel(CL.LogLevel logLevel)
Currently supported log levels:
LOG_QUIET: Never print anything
LOG_ERROR: Print error messages
LOG_TRACE: Print a trace of all native function calls
logLevel - The log level to use.public static int clGetPlatformIDs(int num_entries,
cl_platform_id[] platforms,
int[] num_platforms)
Obtain the list of platforms available.
cl_int clGetPlatformIDs(
|
cl_uint num_entries, |
| cl_platform_id *platforms, | |
cl_uint *num_platforms) |
num_entries
The number of cl_platform_id
entries that can be added to platforms. If
platforms is not NULL, the num_entries
must be greater than zero.
platforms
Returns a list of OpenCL platforms found. The cl_platform_id values returned
in platforms can be used to identify a specific OpenCL
platform. If platforms argument is NULL, this argument
is ignored. The number of OpenCL platforms returned is the mininum of the
value specified by num_entries or the number of OpenCL
platforms available.
num_platforms
Returns the number of OpenCL platforms available. If
num_platforms is NULL, this argument is ignored.
Returns CL_SUCCESS if the function is executed
successfully. If the
cl_khr_icd
extension is enabled, clGetPlatformIDs returns
CL_SUCCESS if the function is executed successfully
and there are a non zero number of platforms available.
Otherwise it returns one of the following errors:
num_entries
is equal to zero and platforms is not NULL or if
both num_platforms and
platforms are NULL.
clGetPlatformInfo, clGetDeviceInfo, Cardinality Diagram
public static int clGetPlatformInfo(cl_platform_id platform, int param_name, long param_value_size, Pointer param_value, long[] param_value_size_ret)
Get specific information about the OpenCL platform.
cl_int clGetPlatformInfo(
|
cl_platform_idplatform, |
| cl_platform_infoparam_name, | |
| size_tparam_value_size, | |
| void*param_value, | |
size_t*param_value_size_ret) |
platform
The platform ID returned by clGetPlatformIDs or can be NULL. If platform is NULL, the behavior is implementation-defined.
param_name
An enumeration constant that identifies the platform information being queried. It can be one of the following values as specified in the table below.
param_value_size
Specifies the size in bytes of memory pointed to by param_value. This size in bytes must be greater than or equal to size of return type specified in the table below.
param_value
A pointer to memory location where appropriate values for a given param_value will be returned. Possible param_value values returned are listed in the table below. If param_value is NULL, it is ignored.
param_value_size_ret
Returns the actual size in bytes of data being queried by param_value. If param_value_size_ret is NULL, it is ignored
OpenCL Platform Queries
| cl_platform_info | Return Type | Description |
|---|---|---|
CL_PLATFORM_PROFILE
|
char[] |
OpenCL profile string. Returns the profile name supported by the implementation. The profile name returned can be one of the following strings: FULL_PROFILE - if the implementation supports the OpenCL specification (functionality defined as part of the core specification and does not require any extensions to be supported). EMBEDDED_PROFILE - if the implementation supports the OpenCL embedded profile. The embedded profile is defined to be a subset for each version of OpenCL. |
CL_PLATFORM_VERSION
|
char[] |
OpenCL version string. Returns the OpenCL version supported by the implementation. This version string has the following format:
The |
CL_PLATFORM_NAME
|
char[] | Platform name string. |
CL_PLATFORM_VENDOR
|
char[] | Platform vendor string. |
CL_PLATFORM_EXTENSIONS
|
char[] | Returns a space-separated list of extension names (the extension names themselves do not contain any spaces) supported by the platform. Extensions defined here must be supported by all devices associated with this platform. |
A null terminated string is returned by OpenCL query function calls if the return type of the information being queried is a char[].
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns the following:
platform is not a valid platform.
param_name is not one of the supported values or if size in bytes specified by param_value_size is less than size of return type and param_value is not a NULL value.
The OpenCL specification does not describe the order of precedence for error codes returned by API calls.
public static int clGetDeviceIDs(cl_platform_id platform, long device_type, int num_entries, cl_device_id[] devices, int[] num_devices)
Obtain the list of devices available on a platform.
cl_int clGetDeviceIDs(
|
cl_platform_idplatform, |
| cl_device_typedevice_type, | |
| cl_uintnum_entries, | |
| cl_device_id*devices, | |
cl_uint*num_devices) |
platform
Refers to the platform ID returned by clGetPlatformIDs or can be NULL. If platform is NULL, the behavior is implementation-defined.
device_type
A bitfield that identifies the type of OpenCL device. The device_type can be used to query specific OpenCL devices or all OpenCL devices available. The valid values for device_type are specified in the following table.
| cl_device_type | Description |
|---|---|
CL_DEVICE_TYPE_CPU
|
An OpenCL device that is the host processor. The host processor runs the OpenCL implementations and is a single or multi-core CPU. |
CL_DEVICE_TYPE_GPU
|
An OpenCL device that is a GPU. By this we mean that the device can also be used to accelerate a 3D API such as OpenGL or DirectX. |
CL_DEVICE_TYPE_ACCELERATOR
|
Dedicated OpenCL accelerators (for example the IBM CELL Blade). These devices communicate with the host processor using a peripheral interconnect such as PCIe. |
CL_DEVICE_TYPE_DEFAULT
|
The default OpenCL device in the system. |
CL_DEVICE_TYPE_ALL
|
All OpenCL devices available in the system. |
num_entries
The number of cl_device entries that can be added to devices. If devices is not NULL, the num_entries must be greater than zero.
devices
A list of OpenCL devices found. The cl_device_id values returned in devices can be used to identify a specific OpenCL device. If devices argument is NULL, this argument is ignored. The number of OpenCL devices returned is the mininum of the value specified by num_entries or the number of OpenCL devices whose type matches device_type.
num_devices
The number of OpenCL devices available that match device_type. If num_devices is NULL, this argument is ignored.
clGetDeviceIDs may return all or a subset of the actual physical devices present in the platform and that match device_type.
The application can query specific capabilities of the OpenCL device(s) returned by clGetDeviceIDs. This can be used by the application to determine which device(s) to use.
clGetDeviceIDs returns CL_SUCCESS if the function is executed successfully. Otherwise it returns one of the following:
platform is not a valid platform.
device_type is not a valid value.
num_entries is equal to zero and devices is not NULL or if both num_devices and devices are NULL.
device_type were found.
public static int clGetDeviceInfo(cl_device_id device, int param_name, long param_value_size, Pointer param_value, long[] param_value_size_ret)
Get information about an OpenCL device.
cl_int clGetDeviceInfo(
|
cl_device_iddevice, |
| cl_device_infoparam_name, | |
| size_tparam_value_size, | |
| void*param_value, | |
size_t*param_value_size_ret) |
device
Refers to the device returned by clGetDeviceIDs.
param_name
An enumeration constant that identifies the device information being queried. It can be one of the values as specified in the table below.
param_value
A pointer to memory location where appropriate values for a given param_name as specified in the table below will be returned. If param_value is NULL, it is ignored.
param_value_size
Specifies the size in bytes of memory pointed to by param_value. This size in bytes must be greater than or equal to size of return type specified in the table below.
param_value_size_ret
Returns the actual size in bytes of data being queried by param_value. If param_value_size_ret is NULL, it is ignored
| cl_device_info | Description |
|---|---|
CL_DEVICE_ADDRESS_BITS
|
Return type: cl_uint The default compute device address space size specified as an unsigned integer value in bits. Currently supported values are 32 or 64 bits. |
CL_DEVICE_AVAILABLE
|
Return type: cl_bool Is CL_TRUE if the device is available and CL_FALSE if the device is not available. |
CL_DEVICE_COMPILER_AVAILABLE
|
Return type: cl_bool Is CL_FALSE if the implementation does not have a compiler available to compile the program source. Is CL_TRUE if the compiler is available. This can be CL_FALSE for the embedded platform profile only. |
CL_DEVICE_DOUBLE_FP_CONFIG
|
Return type: cl_device_fp_config Describes the OPTIONAL double precision floating-point capability of the OpenCL device. This is a bit-field that describes one or more of the following values:
The mandated minimum double precision floating-point capability is CL_FP_FMA | CL_FP_ROUND_TO_NEAREST | CL_FP_ROUND_TO_ZERO | CL_FP_ROUND_TO_INF | CL_FP_INF_NAN | CL_FP_DENORM. |
CL_DEVICE_ENDIAN_LITTLE
|
Return type: cl_bool Is CL_TRUE if the OpenCL device is a little endian device and CL_FALSE otherwise. |
CL_DEVICE_ERROR_CORRECTION_SUPPORT
|
Return type: cl_bool Is CL_TRUE if the device implements error correction for all accesses to compute device memory (global and constant). Is CL_FALSE if the device does not implement such error correction. |
CL_DEVICE_EXECUTION_CAPABILITIES
|
Return type: cl_device_exec_capabilities Describes the execution capabilities of the device. This is a bit-field that describes one or more of the following values: CL_EXEC_KERNEL - The OpenCL device can execute OpenCL kernels. CL_EXEC_NATIVE_KERNEL - The OpenCL device can execute native kernels. The mandated minimum capability is CL_EXEC_KERNEL. |
CL_DEVICE_EXTENSIONS
|
Return type: char[] Returns a space-separated list of extension names (the extension names themselves do not contain any spaces). The list of extension names returned currently can include one or more of the following approved extension names: cl_khr_fp64 |
CL_DEVICE_GLOBAL_MEM_CACHE_SIZE
|
Return type: cl_ulong Size of global memory cache in bytes. |
CL_DEVICE_GLOBAL_MEM_CACHE_TYPE
|
Return type: cl_device_mem_cache_type Type of global memory cache supported. Valid values are: CL_NONE, CL_READ_ONLY_CACHE, and CL_READ_WRITE_CACHE. |
CL_DEVICE_GLOBAL_MEM_CACHELINE_SIZE
|
Return type: cl_uint Size of global memory cache line in bytes. |
CL_DEVICE_GLOBAL_MEM_SIZE
|
Return type: cl_ulong Size of global device memory in bytes. |
CL_DEVICE_HALF_FP_CONFIG
|
Return type: cl_device_fp_config Describes the OPTIONAL half precision floating-point capability of the OpenCL device. This is a bit-field that describes one or more of the following values:
The required minimum half precision floating-point capability as implemented by this extension is CL_FP_ROUND_TO_ZERO or CL_FP_ROUND_TO_INF | CL_FP_INF_NAN. |
CL_DEVICE_HOST_UNIFIED_MEMORY
|
Return type: cl_bool Is CL_TRUE if the device and the host have a unified memory subsystem and is CL_FALSE otherwise. |
CL_DEVICE_IMAGE_SUPPORT
|
Return type: cl_bool Is CL_TRUE if images are supported by the OpenCL device and CL_FALSE otherwise. |
CL_DEVICE_IMAGE2D_MAX_HEIGHT
|
Return type: size_t Max height of 2D image in pixels. The minimum value is 8192 if CL_DEVICE_IMAGE_SUPPORT is CL_TRUE. |
CL_DEVICE_IMAGE2D_MAX_WIDTH
|
Return type: size_t Max width of 2D image in pixels. The minimum value is 8192 if CL_DEVICE_IMAGE_SUPPORT is CL_TRUE. |
CL_DEVICE_IMAGE3D_MAX_DEPTH
|
Return type: size_t Max depth of 3D image in pixels. The minimum value is 2048 if CL_DEVICE_IMAGE_SUPPORT is CL_TRUE. |
CL_DEVICE_IMAGE3D_MAX_HEIGHT
|
Return type: size_t Max height of 3D image in pixels. The minimum value is 2048 if CL_DEVICE_IMAGE_SUPPORT is CL_TRUE. |
CL_DEVICE_IMAGE3D_MAX_WIDTH
|
Return type: size_t Max width of 3D image in pixels. The minimum value is 2048 if CL_DEVICE_IMAGE_SUPPORT is CL_TRUE. |
CL_DEVICE_LOCAL_MEM_SIZE
|
Return type: cl_ulong Size of local memory arena in bytes. The minimum value is 32 KB. |
CL_DEVICE_LOCAL_MEM_TYPE
|
Return type: cl_device_local_mem_type Type of local memory supported. This can be set to CL_LOCAL implying dedicated local memory storage such as SRAM, or CL_GLOBAL. |
CL_DEVICE_MAX_CLOCK_FREQUENCY
|
Return type: cl_uint Maximum configured clock frequency of the device in MHz. |
CL_DEVICE_MAX_COMPUTE_UNITS
|
Return type: cl_uint The number of parallel compute cores on the OpenCL device. The minimum value is 1. |
CL_DEVICE_MAX_CONSTANT_ARGS
|
Return type: cl_uint Max number of arguments declared with the __constant qualifier in a kernel. The minimum value is 8. |
CL_DEVICE_MAX_CONSTANT_BUFFER_SIZE
|
Return type: cl_ulong Max size in bytes of a constant buffer allocation. The minimum value is 64 KB. |
CL_DEVICE_MAX_MEM_ALLOC_SIZE
|
Return type: cl_ulong Max size of memory object allocation in bytes. The minimum value is max (1/4th of CL_DEVICE_GLOBAL_MEM_SIZE, 128*1024*1024) |
CL_DEVICE_MAX_PARAMETER_SIZE
|
Return type: size_t Max size in bytes of the arguments that can be passed to a kernel. The minimum value is 1024. For this minimum value, only a maximum of 128 arguments can be passed to a kernel. |
CL_DEVICE_MAX_READ_IMAGE_ARGS
|
Return type: cl_uint Max number of simultaneous image objects that can be read by a kernel. The minimum value is 128 if CL_DEVICE_IMAGE_SUPPORT is CL_TRUE. |
CL_DEVICE_MAX_SAMPLERS
|
Return type: cl_uint Maximum number of samplers that can be used in a kernel. The minimum value is 16 if CL_DEVICE_IMAGE_SUPPORT is CL_TRUE. (Also see sampler_t.) |
CL_DEVICE_MAX_WORK_GROUP_SIZE
|
Return type: size_t Maximum number of work-items in a work-group executing a kernel using the data parallel execution model. (Refer to clEnqueueNDRangeKernel). The minimum value is 1. |
CL_DEVICE_MAX_WORK_ITEM_DIMENSIONS
|
Return type: cl_uint Maximum dimensions that specify the global and local work-item IDs used by the data parallel execution model. (Refer to clEnqueueNDRangeKernel). The minimum value is 3. |
CL_DEVICE_MAX_WORK_ITEM_SIZES
|
Return type: size_t[] Maximum number of work-items that can be specified in each dimension of the work-group to clEnqueueNDRangeKernel. Returns |
CL_DEVICE_MAX_WRITE_IMAGE_ARGS
|
Return type: cl_uint Max number of simultaneous image objects that can be written to by a kernel. The minimum value is 8 if CL_DEVICE_IMAGE_SUPPORT is CL_TRUE. |
CL_DEVICE_MEM_BASE_ADDR_ALIGN
|
Return type: cl_uint Describes the alignment in bits of the base address of any allocated memory object. |
CL_DEVICE_MIN_DATA_TYPE_ALIGN_SIZE
|
Return type: cl_uint The smallest alignment in bytes which can be used for any data type. |
CL_DEVICE_NAME
|
Return type: char[] Device name string. |
CL_DEVICE_NATIVE_VECTOR_WIDTH_CHAR
|
Return type: cl_uint Returns the native ISA vector width. The vector width is defined as the number of scalar elements that can be stored in the vector. If the cl_khr_fp64 extension is not supported, CL_DEVICE_NATIVE_VECTOR_WIDTH_DOUBLE must return 0. If the cl_khr_fp16 extension is not supported, CL_DEVICE_NATIVE_VECTOR_WIDTH_HALF must return 0. |
CL_DEVICE_OPENCL_C_VERSION
|
Return type: char[] OpenCL C version string. Returns the highest OpenCL C version supported by the compiler for this device. This version string has the following format:
The The |
CL_DEVICE_PLATFORM
|
Return type: cl_platform_id The platform associated with this device. |
CL_DEVICE_PREFERRED_VECTOR_WIDTH_CHAR
|
Return type: cl_uint Preferred native vector width size for built-in scalar types that can be put into vectors. The vector width is defined as the number of scalar elements that can be stored in the vector. If the cl_khr_fp64 extension is not supported, CL_DEVICE_PREFERRED_VECTOR_WIDTH_DOUBLE must return 0. If the cl_khr_fp16 extension is not supported, CL_DEVICE_PREFERRED_VECTOR_WIDTH_HALF must return 0. |
CL_DEVICE_PROFILE
|
Return type: char[] OpenCL profile string. Returns the profile name supported by the device (see note). The profile name returned can be one of the following strings: FULL_PROFILE - if the device supports the OpenCL specification (functionality defined as part of the core specification and does not require any extensions to be supported). EMBEDDED_PROFILE - if the device supports the OpenCL embedded profile. |
CL_DEVICE_PROFILING_TIMER_RESOLUTION
|
Return type: size_t Describes the resolution of device timer. This is measured in nanoseconds. |
CL_DEVICE_QUEUE_PROPERTIES
|
Return type: cl_command_queue_properties Describes the command-queue properties supported by the device. This is a bit-field that describes one or more of the following values: CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE CL_QUEUE_PROFILING_ENABLE These properties are described in the table for clCreateCommandQueue. The mandated minimum capability is CL_QUEUE_PROFILING_ENABLE. |
CL_DEVICE_SINGLE_FP_CONFIG
|
Return type: cl_device_fp_config Describes single precision floating-point capability of the device. This is a bit-field that describes one or more of the following values: CL_FP_DENORM - denorms are supported CL_FP_INF_NAN - INF and quiet NaNs are supported CL_FP_ROUND_TO_NEAREST - round to nearest even rounding mode supported CL_FP_ROUND_TO_ZERO - round to zero rounding mode supported CL_FP_ROUND_TO_INF - round to +ve and -ve infinity rounding modes supported CL_FP_FMA - IEEE754-2008 fused multiply-add is supported CL_FP_SOFT_FLOAT - Basic floating-point operations (such as addition, subtraction, multiplication) are implemented in software. The mandated minimum floating-point capability is CL_FP_ROUND_TO_NEAREST | CL_FP_INF_NAN. |
CL_DEVICE_TYPE
|
Return type: cl_device_type The OpenCL device type. Currently supported values are one of or a combination of: CL_DEVICE_TYPE_CPU, CL_DEVICE_TYPE_GPU, CL_DEVICE_TYPE_ACCELERATOR, or CL_DEVICE_TYPE_DEFAULT. |
CL_DEVICE_VENDOR
|
Return type: char[] Vendor name string. |
CL_DEVICE_VENDOR_ID
|
Return type: cl_uint A unique device vendor identifier. An example of a unique device identifier could be the PCIe ID. |
CL_DEVICE_VERSION
|
Return type: char[] OpenCL version string. Returns the OpenCL version supported by the device. This version string has the following format:
The |
CL_DRIVER_VERSION
|
Return type: char[] OpenCL software driver version string in the form |
CL_DEVICE_PROFILE: The platform profile returns the profile that is implemented by the OpenCL framework. If the platform profile returned is FULL_PROFILE, the OpenCL framework will support devices that are FULL_PROFILE and may also support devices that are EMBEDDED_PROFILE. The compiler must be available for all devices i.e. CL_DEVICE_COMPILER_AVAILABLE is CL_TRUE. If the platform profile returned is EMBEDDED_PROFILE, then devices that are only EMBEDDED_PROFILE are supported.
clGetDeviceInfo returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns the following:
device is not valid.
param_name is not one of the supported values or if size in
bytes specified by param_value_size is less than size of return type as shown in the table above and
param_value is not a NULL value.
public static int clCreateSubDevices(cl_device_id in_device, cl_device_partition_property properties, int num_devices, cl_device_id[] out_devices, int[] num_devices_ret)
Creates an array of sub-devices that each reference a non-intersecting set of compute units within in_device.
cl_int clCreateSubDevices
(
|
cl_device_id in_device , |
| const cl_device_partition_property *properties , | |
| cl_uint num_devices , | |
| cl_device_id *out_devices , | |
cl_uint
*num_devices_ret
)
|
in_device
The device to be partitioned.
properties
Specifies how in_device is to be partition described
by a partition name and its corresponding value. Each partition name
is immediately followed by the corresponding desired value. The list is
terminated with 0. The list of supported partitioning schemes is described
in the table below. Only one of the listed partitioning schemes can be
specified in properties.
| cl_device_partition_ property enum (Partition value) | Description |
|---|---|
| CL_DEVICE_PARTITION_EQUALLY (unsigned int) |
Split the aggregate device into as many smaller
aggregate devices as can be created, each
containing n compute
units. The value n is
passed as the value accompanying this property. If
n does not divide evenly into
CL_DEVICE_PARTITION_MAX_COMPUTE_UNITS,
then the remaining compute units are not used.
|
| CL_DEVICE_PARTITION_BY_COUNTS (unsigned int) |
This property is followed by a
CL_DEVICE_PARTITION_BY_COUNTS_LIST_END
terminated list of compute unit counts. For
each nonzero count m
in the list, a sub-device is created with
m compute units in it.
CL_DEVICE_PARTITION_BY_COUNTS_LIST_END
is defined to be 0.
The number of non-zero count
entries in the list may not exceed
The total number of compute
units specified may not exceed
|
| CL_DEVICE_PARTITION_BY_- AFFINITY_DOMAIN (cl_device_affinity_domain) |
Split the device into smaller aggregate devices
containing one or more compute units that all share
part of a cache hierarchy. The value accompanying
this property may be drawn from the following list:
The user may determine what happened by calling
clGetDeviceInfo
( |
num_devices
Size of memory pointed to by out_devices specified as
the number of cl_device_id entries.
out_devices
The buffer where the OpenCL sub-devices will be returned. If
out_devices is NULL, this argument is ignored. If
out_devices is not NULL, num_devices
must be greater than or equal to the number of sub-devices that
device may be partitioned into according to the
partitioning scheme specified in properties.
num_devices_ret
Returns the number of sub-devices that device may be
partitioned into according to the partitioning scheme specified in
properties. If num_devices_ret
is NULL, it is ignored.
Creates an array of sub-devices that each reference a non-intersecting set of compute
units within in_device, according to a partition scheme given
by properties. The output sub-devices may be used in every way
that the root (or parent) device can be used, including creating contexts, building
programs, further calls to clCreateSubDevices and creating
command-queues. When a command-queue is created against a sub-device, the commands
enqueued on the queue are executed only on the sub-device.
Returns CL_SUCCESS if the partition is created successfully.
Otherwise, it returns a null value with the following error values returned in
errcode_ret:
in_device is not valid.
properties are not valid or if values specified in
properties are valid but not supported by the device.
out_devices is not
NULL and num_devices is less than the number of sub-devices
created by the partition scheme.
in_device could not be
further partitioned.
properties is
CL_DEVICE_PARTITION_BY_COUNTS and the number of sub-devices
requested exceeds CL_DEVICE_PARTITION_MAX_SUB_DEVICES
or the total number of compute units requested exceeds
CL_DEVICE_PARTITION_MAX_COMPUTE_UNITS for
in_device, or the number of compute units requested
for one or more sub-devices is less than zero or the number of sub-devices
requested exceeds CL_DEVICE_PARTITION_MAX_COMPUTE_UNITS
for in_device.
A few examples that describe how to specify partition properties in
properties argument to clCreateSubDevices
are given below.
To partition a device containing 16 compute units into two sub-devices, each containing
8 compute units, pass the following in properties:
| { CL_DEVICE_PARTITION_EQUALLY, 8, 0 } |
To partition a device with four compute units into two sub-devices with one sub-device
containing 3 compute units and the other sub-device 1 compute unit, pass the following
in properties argument:
| { CL_DEVICE_PARTITION_BY_COUNTS, 3, 1, CL_DEVICE_PARTITION_BY_COUNTS_LIST_END, 0 } |
To split a device along the outermost cache line (if any), pass the following in
properties argument:
| { CL_DEVICE_PARTITION_BY_AFFINITY_DOMAIN, CL_DEVICE_AFFINITY_DOMAIN_NEXT_PARTITIONABLE, 0 } |
public static int clRetainDevice(cl_device_id device)
Increments the devices reference count.
cl_int
clRetainDevice
(
|
cl_device_id
device
)
|
Increments the device reference count if
device is a valid sub-device created by a call to
clCreateSubDevices.
If device is a root level device i.e. a cl_device_id
returned by clGetDeviceIDs,
the device reference count remains unchanged.
Returns CL_SUCCESS if the function is executed successfully or the device is a root-level device. Otherwise, it returns one of the following errors:
device is not a valid
sub-device created by a call to
clCreateSubDevices.
public static int clReleaseDevice(cl_device_id device)
Decrements the device reference count.
cl_int clReleaseDevice
(
|
cl_device_iddevice) |
Decrements the device reference
count if device is a valid sub-device created by a call to
clCreateSubDevices.
If device is a root level device i.e. a cl_device_id
returned by clGetDeviceIDs,
the device reference count remains unchanged.
After the device reference count becomes zero and all the objects
attached to device (such as command-queues) are released, the
device object is deleted.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
device
is not a valid sub-device created by a call to
clCreateSubDevices.
public static cl_context clCreateContext(cl_context_properties properties, int num_devices, cl_device_id[] devices, CreateContextFunction pfn_notify, java.lang.Object user_data, int[] errcode_ret)
Creates an OpenCL context.
cl_context clCreateContext(
|
const cl_context_properties*properties, |
| cl_uintnum_devices, | |
| const cl_device_id*devices, | |
(voidCL_CALLBACK *pfn_notify)
(
constchar*errinfo, ),
|
|
| void*user_data, | |
cl_int*errcode_ret) |
An OpenCL context is created with one or more devices. Contexts are used by the OpenCL runtime for managing objects such as command-queues, memory, program and kernel objects and for executing kernels on one or more devices specified in the context.
Specifies a list of context property names and their corresponding values. Each property name is
immediately followed by the corresponding desired value. The list is terminated with 0.
properties can be NULL in which case the platform that is selected is
implementation-defined. The list of supported properties is described in the table below.
If the extension cl_khr_d3d10_sharing
is enabled, then if a property is not specified in properties, then its default value is used
(it is said to be specified implicitly). If properties is NULL or empty (points to a list
whose first value is zero), all attributes take on their default value.
If the extension cl_khr_gl_sharing
is enabled, then properties points to an attribute list, which is a array of ordered <attribute name, value> pairs terminated with zero. If an attribute is not specified in properties, then its default value is used (it is said to be specified implicitly). If properties is NULL or empty (points to a list whose first value is zero), all attributes take on their default values..
| cl_context_properties enum | Property value | Description |
|---|---|---|
CL_CONTEXT_PLATFORM
|
cl_platform_id | Specifies the platform to use. |
CL_CONTEXT_D3D10_DEVICE_KHR
|
ID3D10Device* | If the cl_khr_d3d10_sharing extension is enabled, specifies the ID3D10Device* to use for Direct3D 10 interoperability. The default value is NULL. |
|
|
Available if the cl_khr_gl_sharing extension is enabled. |
num_devices
The number of devices specified in the devices argument.
devices
A pointer to a list of unique devices returned by clGetDeviceIDs
for a platform. Duplicate devices specified in devices are ignored.
pfn_notify
A callback function that can be registered by the application. This callback function will be used by the OpenCL implementation to report information on errors that occur in this context. This callback function may be called asynchronously by the OpenCL implementation.
It is the application's responsibility to ensure that the callback function is thread-safe. If pfn_notify is NULL, no callback function is registered. The parameters to this callback function are:
errinfo is a pointer to an error string.
private_info and cb represent a pointer to binary data that is returned by the OpenCL implementation that can be used to log additional information helpful in debugging the error.
user_data is a pointer to user supplied data.
NOTE: There are a number of cases where error notifications need to be delivered due to an error that occurs outside a context. Such notifications may not be delivered through the pfn_notify callback. Where these notifications go is implementation-defined.
user_data
Passed as the user_data argument when pfn_notify is called. user_data can be NULL.
errcode_ret
Returns an appropriate error code. If errcode_ret is NULL, no error code is returned.
clCreateContext and clCreateContextFromType perform an implicit retain. This is very helpful for 3rd party libraries, which typically get a context passed to them by the application.
However, it is possible that the application may delete the context without informing the library.
Allowing functions to attach to (i.e. retain) and release a context solves the problem of a context
being used by a library no longer being valid.
clCreateContext returns a valid non-zero context and errcode_ret is set to CL_SUCCESS if the context is created successfully. Otherwise, it returns NULL value with the following error
values returned in errcode_ret:
properties is NULL and no platform could be selected or if platform value specified in properties is not a valid platform. (If the extension cl_khr_gl_sharing is enabled, then see error "CL_INVALID_GL_SHAREGROUP_REFERENCE_KHR" below.)
properties is not a supported
property name, if the value specified for a supported property name is not valid, or if the
same property name is specified more than once. However if the extension cl_khr_gl_sharing is enabled, then CL_INVALID_PROPERTY is returned if an attribute name other than those listed in the table for properties above is specified in properties.
devices is NULL; if num_devices is equal to zero; or
if pfn_notify is NULL but user_data is not NULL.
devices contains an invalid device.
devices is currently not available
even though the device was returned by clGetDeviceIDs.
cl_device_ids against which this context
is to be created may interoperate (if the
cl_khr_d3d10_sharing extension is enabled).
properties (only if the
cl_khr_gl_sharing extension is enabled).
public static cl_context clCreateContextFromType(cl_context_properties properties, long device_type, CreateContextFunction pfn_notify, java.lang.Object user_data, int[] errcode_ret)
Create an OpenCL context from a device type that identifies the specific device(s) to use.
cl_context
clCreateContextFromType
(
|
const cl_context_properties *properties, |
| cl_device_type device_type, | |
| void (CL_CALLBACK *pfn_notify) (const char *errinfo, | |
| const void *private_info, | |
| size_t cb, | |
| void *user_data), | |
| void *user_data, | |
cl_int
*errcode_ret)
|
Specifies a list of context property names and their corresponding values. Each property name is immediately followed by the corresponding desired value. The list is terminated with 0. properties can be NULL in which case the platform that is selected is implementation-defined. The list of supported properties is described in the table below.
| cl_context_properties enum | Property value | Description |
|---|---|---|
CL_CONTEXT_PLATFORM
|
cl_platform_id | Specifies the platform to use. |
CL_CONTEXT_D3D10_DEVICE_KHR
|
ID3D10Device* | If the cl_khr_d3d10_sharing extension is enabled, specifies the ID3D10Device* to use for Direct3D 10 interoperability. The default value is NULL. |
|
|
Available if the cl_khr_gl_sharing extension is enabled. |
A bit-field that identifies the type of device and is described in the table below.
| cl_device_type | Description |
|---|---|
CL_DEVICE_TYPE_CPU
|
An OpenCL device that is the host processor. The host processor runs the OpenCL implementations and is a single or multi-core CPU. |
CL_DEVICE_TYPE_GPU
|
An OpenCL device that is a GPU. By this we mean that the device can also be used to accelerate a 3D API such as OpenGL or DirectX. |
CL_DEVICE_TYPE_ACCELERATOR
|
Dedicated OpenCL accelerators (for example the IBM CELL Blade). These devices communicate with the host processor using a peripheral interconnect such as PCIe. |
CL_DEVICE_TYPE_DEFAULT
|
The default OpenCL device in the system. |
CL_DEVICE_TYPE_ALL
|
All OpenCL devices available in the system. |
pfn_notify
A callback function that can be registered by the application. This callback function will be used by the OpenCL implementation to report information on errors that occur in this context. This callback function may be called asynchronously by the OpenCL implementation.
It is the application's responsibility to ensure that the callback function is thread-safe. If pfn_notify is NULL, no callback function is registered. The parameters to this callback function are:
errinfo is a pointer to an error string.
private_info and cb represent a pointer to binary data that is returned by the OpenCL implementation that can be used to log additional information helpful in debugging the error.
user_data is a pointer to user supplied data.
There are a number of cases where error notifications need to be delivered due to an error that occurs outside a context. Such notifications may not be delivered through the pfn_notify callback. Where these notifications go is implementation-defined.
user_data
Passed as the user_data argument when pfn_notify is called. user_data can be NULL.
errcode_ret
Return an appropriate error code. If errcode_ret is NULL, no error code is returned.
clCreateContextFromType may return all or a subset of the actual physical devices present in the platform and that match device_type.
clCreateContextFromType and clCreateContext perform an implicit retain. This is very helpful for 3rd party libraries, which typically get a context passed to them by the application.
However, it is possible that the application may delete the context without informing the library.
Allowing functions to attach to (i.e. retain) and release a context solves the problem of a context
being used by a library no longer being valid.
clCreateContextFromType returns a valid non-zero context and errcode_ret is set
to CL_SUCCESS if the context is created successfully. Otherwise, it returns a NULL value with the following
error vlaues returned in errcode_ret:
properties is NULL and no platform could be selected or
if platform value specified in properties is not a valid platform. (If the extension cl_khr_gl_sharing is enabled, then see error "CL_INVALID_GL_SHAREGROUP_REFERENCE_KHR" below.)
properties is not a supported property
name, or if the value specified for a supported property name is not valid, or if the same property name is specified more than once.
pfn_notify is NULL but user_data is not NULL.
device_type is not a valid value.
device_type and property values
specified in properties are currently available.
device_type and property values
specified in properties were found.
cl_device_ids against which this context
is to be created may interoperate (if the
cl_khr_d3d10_sharing extension is enabled).
properties if the cl_khr_gl_sharing extension is enabled.
| Example goes here - it will be set in "code" type with white space preserved. |
public static int clRetainContext(cl_context context)
Increment the context reference count.
cl_int
clRetainContext
(
|
cl_contextcontext) |
context
The context to retain.
clCreateContext and clCreateContextFromType perform an implicit retain. This is very helpful for 3rd party libraries, which typically get a context passed to them by the application. However, it is possible that the application may delete the context without informing the library. Allowing functions to attach to (i.e. retain) and release a context solves the problem of a context being used by a library no longer being valid.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following values:
context is not a valid OpenCL context.
public static int clReleaseContext(cl_context context)
Decrement the context reference count.
cl_int
clReleaseContext
(
|
cl_contextcontext) |
context
The context to release.
After the context reference count becomes zero and all the objects attached to context (such as
memory objects, command-queues) are released, the context is deleted.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following values:
context is not a valid OpenCL context.
public static int clGetContextInfo(cl_context context, int param_name, long param_value_size, Pointer param_value, long[] param_value_size_ret)
Query information about a context.
cl_int
clGetContextInfo
(
|
cl_contextcontext, |
| cl_context_infoparam_name, | |
| size_tparam_value_size, | |
| void*param_value, | |
size_t *param_value_size_ret) |
context
Specifies the OpenCL context being queried.
param_name
An enumeration constant that specifies the information to query.
The valid values for param_name are:
| cl_context_info | Return Type | Information returned in param_value |
|---|---|---|
CL_CONTEXT_REFERENCE_COUNT
|
cl_uint |
Return the context reference count. The reference count returned should be
considered immediately stale. It is unsuitable for general use in applications. This feature is provided
for identifying memory leaks.
|
CL_CONTEXT_NUM_DEVICES
|
cl_uint |
Return the number of devices in context.
|
CL_CONTEXT_DEVICES
|
cl_device_id[] |
Return the list of devices in context.
|
CL_CONTEXT_PROPERTIES
|
cl_context_properties[] |
Return the properties argument specified
in clCreateContext or
clCreateContextFromType.
If the
If the |
CL_CONTEXT_D3D10_PREFER_SHARED_RESOURCES_KHR
|
cl_bool |
If the
cl_khr_d3d10_sharing
extension is enabled, returns CL_TRUE if Direct3D 10 resources created as
shared by setting MiscFlags to include D3D10_RESOURCE_MISC_SHARED will perform if
aster when shared with OpenCL, compared with resources which have not set this flag. Otherwise
returns CL_FALSE.
|
param_value
A pointer to memory where the appropriate result being queried is returned. If param_value is NULL, it is ignored.
param_value_size
Specifies the size in bytes of memory pointed to by param_value. This size must be greater than or equal to the size of return type as described in the table above.
param_value_size_ret
Returns the actual size in bytes of data being queried by param_value. If
param_value_size_ret is NULL, it is ignored.
Returns CL_SUCCESS if the function executed successfully, or one of the errors below:
context
is not a valid context.
param_name is not one of the supported values or if size in
bytes specified by param_value_size is less than size of return type as specified in the table above
and param_value is not a NULL value.
public static cl_command_queue clCreateCommandQueue(cl_context context, cl_device_id device, long properties, int[] errcode_ret)
clCreateCommandQueueWithProperties(org.jocl.cl_context, org.jocl.cl_device_id, org.jocl.cl_queue_properties, int[]) insteadCreate a command-queue on a specific device.
cl_command_queue clCreateCommandQueue(
|
cl_contextcontext, |
| cl_device_iddevice, | |
| cl_command_queue_propertiesproperties, | |
cl_int*errcode_ret) |
context
Must be a valid OpenCL context.
device
Must be a device associated with context. It can either be in the list of devices specified when context is created using clCreateContext or have the same device type as the device type specified when the context is created using clCreateContextFromType.
properties
Specifies a list of properties for the command-queue. This is a bit-field. Only command-queue properties specified in the table below can be set in
properties; otherwise the value specified in properties is considered to be not valid.
| Command-Queue Properties | Description |
|---|---|
CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE
|
Determines whether the commands queued in the command-queue are executed in-order or out-of-order. If set, the commands in the command-queue are executed out-of-order. Otherwise, commands are executed in-order. |
CL_QUEUE_PROFILING_ENABLE
|
Enable or disable profiling of commands in the command-queue. If set, the profiling of commands is enabled. Otherwise profiling of commands is disabled. See clGetEventProfilingInfo for more information. |
errcode_ret
Returns an appropriate error code. If errcode_ret is NULL, no error code is returned.
The OpenCL functions that are submitted to a command-queue are enqueued in the order the
calls are made but can be configured to execute in-order or out-of-order. The properties
argument in clCreateCommandQueue can be used to specify the execution order.
If the CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE property of a command-queue is not set, the commands enqueued to a command-queue execute in order. For example, if an application calls clEnqueueNDRangeKernel to execute kernel A followed by a clEnqueueNDRangeKernel to execute kernel B, the application can assume that kernel A finishes first and then kernel B is executed. If the memory objects output by kernel A are inputs to kernel B then kernel B will see the correct data in memory objects produced by execution of kernel A. If the CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE property of a commandqueue is set, then there is no guarantee that kernel A will finish before kernel B starts execution.
Applications can configure the commands enqueued to a command-queue to execute out-of-order by setting the CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE property of the command-queue. This can be specified when the command-queue is created. In out-of-order execution mode there is no guarantee that the enqueued commands will finish execution in the order they were queued. As there is no guarantee that kernels will be executed in order, that is based on when the clEnqueueNDRangeKernel calls are made within a command-queue, it is therefore possible that an earlier clEnqueueNDRangeKernel call to execute kernel A identified by event A may execute and/or finish later than a clEnqueueNDRangeKernel call to execute kernel B which was called by the application at a later point in time. To guarantee a specific order of execution of kernels, a wait on a particular event (in this case event A) can be used. The wait for event A can be specified in the event_wait_list argument to clEnqueueNDRangeKernel for kernel B.
In addition, a wait for events or a barrier command can be enqueued to the command-queue. The wait for events command ensures that previously enqueued commands identified by the list of events to wait for have finished before the next batch of commands is executed. The barrier command ensures that all previously enqueued commands in a command-queue have finished execution before the next batch of commands is executed.
Similarly, commands to read, write, copy or map memory objects that are enqueued after clEnqueueNDRangeKernel, clEnqueueTask or clEnqueueNativeKernel commands are not guaranteed to wait for kernels scheduled for execution to have completed (if the CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE property is set). To ensure correct ordering of commands, the event object returned by clEnqueueNDRangeKernel, clEnqueueTask or clEnqueueNativeKernel can be used to enqueue a wait for event or a barrier command can be enqueued that must complete before reads or writes to the memory object(s) occur.
clCreateCommandQueue returns a valid non-zero command-queue and errcode_ret is set to CL_SUCCESS if the command-queue is created successfully. Otherwise, it returns a NULL value with one of the following error values returned in errcode_ret:
context is not a valid context.
device is not a valid device or is
not associated with context.
properties
are not valid.
properties
are valid but are not supported by the device.
public static cl_command_queue clCreateCommandQueueWithProperties(cl_context context, cl_device_id device, cl_queue_properties properties, int[] errcode_ret)
Create a host or device command-queue on a specific device.
cl_command_queue clCreateCommandQueueWithProperties(
|
cl_context context, |
| cl_device_id device, | |
| const cl_queue_properties *properties, | |
cl_int *errcode_ret) |
context
Must be a valid OpenCL context.
device
Must be a device associated with context.
It can either be in the list of devices specified when
context is created using
clCreateContext
or have the same device type as the device type specified
when the context is created using
clCreateContextFromType.
properties
Specifies a list of properties for the
command-queue and their corresponding values.
Each property name is immediately followed
by the corresponding desired value. The list is
terminated with 0. The list of supported properties
is described in the table below. If a
supported property and its value is not specified in
properties, its default value will be used.
properties can be NULL in which case
the default values for supported command-queue properties
will be used.
| Queue Properties | Property Value | Description |
|---|---|---|
CL_QUEUE_PROPERTIES
|
cl_command_queue_- properties |
This is a bitfield and can be set to a combination of the following values:
If |
CL_QUEUE_SIZE
|
cl_uint |
Specifies the size of the device queue in bytes. This can only be specified if
For best performance, this should be ≤
If |
errcode_ret
Returns an appropriate error code. If errcode_ret
is NULL, no error code is returned.
OpenCL objects such as memory, program and kernel objects are created using a context. Operations on these objects are performed using a command-queue. The command-queue can be used to queue a set of operations (referred to as commands) in order. Having multiple command-queues allows applications to queue multiple independent commands without requiring synchronization. Note that this should work as long as these objects are not being shared. Sharing of objects across multiple command-queues will require the application to perform appropriate synchronization. This is described in Appendix A of the specification.
The OpenCL functions that are submitted to a command-queue are enqueued in the order
the calls are made but can be configured to execute in-order or out-of-order. The
properties argument in clCreateCommandQueueWithProperties
can be used to specify the execution order.
If the CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE
property of a command-queue is not set, the commands enqueued to a
command-queue execute in order. For example, if an application calls
clEnqueueNDRangeKernel
to execute kernel A followed by a
clEnqueueNDRangeKernel
to execute kernel B, the application can assume that kernel A finishes first and then
kernel B is executed. If the memory objects output by kernel A are inputs to kernel
B then kernel B will see the correct data in memory objects produced by execution of
kernel A. If the CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE property
of a command-queue is set, then there is no guarantee that kernel A will finish before
kernel B starts execution.
Applications can configure the commands enqueued to a command-queue to execute
out-of-order by setting the CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE
property of the command-queue. This can be specified when the command-queue is
created. In out-of-order execution mode there is no guarantee that the enqueued
commands will finish execution in the order they were queued. As there is no
guarantee that kernels will be executed in order, i.e. based on when the
clEnqueueNDRangeKernel
calls are made within a command-queue, it is therefore possible that an earlier
clEnqueueNDRangeKernel
call to execute kernel A identified by event A may execute and/or finish later than a
clEnqueueNDRangeKernel
call to execute kernel B which was called by the application at a later
point in time. To guarantee a specific order of execution of kernels, a
wait on a particular event (in this case event A) can be used. The wait for
event A can be specified in the event_wait_list argument to
clEnqueueNDRangeKernel
for kernel B.
In addition, a wait for events (clEnqueueMarkerWithWaitList) or a barrier (clEnqueueBarrierWithWaitList) command can be enqueued to the command-queue. The wait for events command ensures that previously enqueued commands identified by the list of events to wait for have finished before the next batch of commands is executed. The barrier command ensures that all previously enqueued commands in a command-queue have finished execution before the next batch of commands is executed.
Similarly, commands to read, write, copy or map memory objects that are enqueued after
clEnqueueNDRangeKernel or
clEnqueueNativeKernel
commands are not guaranteed to wait for kernels scheduled for execution to have
completed (if the CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE
property is set). To ensure correct ordering of commands, the event object returned by
clEnqueueNDRangeKernel or
clEnqueueNativeKernel
can be used to enqueue a wait for event or a barrier command can be enqueued that
must complete before reads or writes to the memory object(s) occur.
clCreateCommandQueueWithProperties
returns a valid non-zero command-queue and
errcode_ret is set to CL_SUCCESS if the
command-queue is created successfully. Otherwise, it returns a NULL value with one
of the following error values returned in errcode_ret:
context is not a valid
context.
device is not a valid
device or is not associated with context.
properties are not valid.
properties are valid but are not supported by the device.
clGetCommandQueueInfo, clReleaseCommandQueue, clRetainCommandQueue, clCreateContext, clCreateContextFromType, clEnqueueNDRangeKernel
public static int clRetainCommandQueue(cl_command_queue command_queue)
Increments the command_queue reference count.
cl_int clRetainCommandQueue(
|
cl_command_queuecommand_queue) |
command_queue
Specifies the command-queue to retain.
clCreateCommandQueue performs an implicit retain. This is very helpful for 3rd party libraries, which typically get a command-queue passed to them by the application. However, it is possible that the application may delete the command-queue without informing the library. Allowing functions to attach to (i.e. retain) and release a command-queue solves the problem of a command-queue being used by a library no longer being valid.
Returns CL_SUCCESS if the function executed successfully, or one of the errors below:
command_queue is not a valid command-queue.
public static int clReleaseCommandQueue(cl_command_queue command_queue)
Decrements the command_queue reference count.
cl_int clReleaseCommandQueue(
|
cl_command_queuecommand_queue) |
command_queue
Specifies the command-queue to release.
After the command_queue reference count becomes zero and all commands queued to
command_queue have finished (e.g., kernel executions, memory object updates, etc.), the command-queue is deleted.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following:
command_queue is not a valid command queue.
Returns CL_SUCCESS if the function is executed successfully. It returns CL_INVALID_COMMAND_QUEUE if command_queue is not a valid command-queue.
public static int clGetCommandQueueInfo(cl_command_queue command_queue, int param_name, long param_value_size, Pointer param_value, long[] param_value_size_ret)
Query information about a command-queue.
cl_int clGetCommandQueueInfo(
|
cl_command_queuecommand_queue, |
| cl_command_queue_infoparam_name, | |
| size_tparam_value_size, | |
| void*param_value, | |
size_t*param_value_size_ret) |
command_queue
Specifies the command-queue being queried.
param_name
Specifies the information to query.
param_value_size
Specifies the size in bytes of memory pointed to by param_value. This size must be greater than or equal to the size of return type as described in the table below. If param_value is NULL, it is ignored.
param_value
A pointer to memory where the appropriate result being queried is returned. If param_value is NULL, it is ignored.
param_value_size_ret
Returns the actual size in bytes of data being queried by param_value. If param_value_size_ret is NULL, it is ignored
The list of supported param_name values and the information returned in param_value by clGetCommandQueueInfo is described in the table below.
| cl_command_queue_info | Return Type and Information returned in param_value |
|---|---|
CL_QUEUE_CONTEXT
|
Return type: cl_context
Return the context specified when the command-queue is created. |
CL_QUEUE_DEVICE
|
Return type: cl_device_id
Return the device specified when the command-queue is created. |
CL_QUEUE_REFERENCE_COUNT
|
Return type: cl_uint
Return the command-queue reference count.
The reference count returned with |
CL_QUEUE_PROPERTIES
|
Return type: cl_command_queue_properties
Return the currently specified properties for the command-queue. These properties are specified by the properties argument in clCreateCommandQueue. |
It is possible that a device(s) becomes unavailable after a context and command-queues that use
this device(s) have been created and commands have been queued to command-queues. In this
case the behavior of OpenCL API calls that use this context (and command-queues) are
considered to be implementation-defined. The user callback function, if specified, when the
context is created can be used to record appropriate information in the errinfo, private_info arguments passed to the callback function when the device becomes unavailable.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns the following:
command_queue is not a valid command-queue.
param_name is not one of the supported values or if size
in bytes specified by param_value_size is less than size of return type and param_value is not a NULL value.
public static int clSetCommandQueueProperty(cl_command_queue command_queue, long properties, boolean enable, long[] old_properties)
Enable or disable the properties of a command-queue.
cl_int clSetCommandQueueProperty(
|
cl_command_queuecommand_queue, |
| cl_command_queue_propertiesproperties, | |
| cl_boolenable, | |
cl_command_queue_properties*old_properties) |
THIS FUNCITON IS DEPRECATED.
command_queue
Specifies the command-queue being queried.
properties
Specifies the new command-queue properties to be applied to command_queue. Only command-queue properties specified for clCreateCommandQueue can be set in properties; otherwise the value specified in properties is considered to be not valid.
enable
Determines whether the values specified by properties are enabled (if enable is CL_TRUE) or disabled (if enable is CL_FALSE) for the command-queue. The allowed property values are the same as those specified for clCreateCommandQueue.
old_properties
Returns the command-queue properties before they were changed by
clSetCommandQueueProperty. If old_properties is NULL, it is ignored.
As specified for clCreateCommandQueue, the CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE command-queue property determines whether the commands in a command-queue are executed in-order or out-of-order. Changing this command-queue property will cause the OpenCL implementation to block until all previously queued commands in command_queue have completed. This can be an expensive operation and therefore changes to the CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE property should be only done when absolutely necessary.
It is possible that a device(s) becomes unavailable after a context and command-queues that use this device(s) have been created and commands have been queued to command-queues. In this
case the behavior of OpenCL API calls that use this context (and command-queues) are
considered to be implementation-defined. The user callback function, if specified when the
context is created, can be used to record appropriate information in the errinfo, private_info arguments passed to the callback function when the device becomes unavailable.
Returns CL_SUCCESS if the command-queue properties are successfully updated. Otherwise, it returns the following:
command_queue is not a valid command-queue.
properties are not valid.
properties are not supported by the device.
public static cl_mem clCreateBuffer(cl_context context, long flags, long size, Pointer host_ptr, int[] errcode_ret)
Creates a buffer object.
cl_mem clCreateBuffer
(
|
cl_contextcontext, |
| cl_mem_flagsflags, | |
| size_tsize, | |
| void*host_ptr, | |
cl_int*errcode_ret) |
context
A valid OpenCL context used to create the buffer object.
flags
A bit-field that is used to specify allocation and usage information such as the memory
arena that should be used to allocate the buffer object and how it will be used. The
following table describes the possible values for flags:
| cl_mem_flags | Description |
|---|---|
CL_MEM_READ_WRITE
|
This flag specifies that the memory object will be read and written by a kernel. This is the default. |
CL_MEM_WRITE_ONLY
|
This flags specifies that the memory object will be written but not read by a kernel. Reading from a buffer or image object created with
|
CL_MEM_READ_ONLY
|
This flag specifies that the memory object is a read-only memory object when used inside a kernel. Writing to a buffer or image object created with
|
CL_MEM_USE_HOST_PTR
|
This flag is valid only if OpenCL implementations are allowed to cache the buffer
contents pointed to by The result of OpenCL commands that operate on multiple
buffer objects created with the same |
CL_MEM_ALLOC_HOST_PTR
|
This flag specifies that the application wants the OpenCL implementation to allocate memory from host accessible memory.
|
CL_MEM_COPY_HOST_PTR
|
This flag is valid only if
|
size
The size in bytes of the buffer memory object to be allocated.
host_ptr
A pointer to the buffer data that may already be allocated by the application. The size
of the buffer that host_ptr points to must be greater than or equal to the size bytes.
errcode_ret
Returns an appropriate error code. If errcode_ret is NULL, no error code is returned.
Returns a valid non-zero buffer object and errcode_ret is set to CL_SUCCESS if
the buffer object is created successfully. Otherwise, it returns a NULL value with one of the
following error values returned in errcode_ret:
context is not a valid context..
flags are not valid.
size is 0 or is greater than
CL_DEVICE_MAX_MEM_ALLOC_SIZE value specified in table of OpenCL Device Queries
for clGetDeviceInfo for all devices in context.
host_ptr is NULL and CL_MEM_USE_HOST_PTR or
CL_MEM_COPY_HOST_PTR are set in flags or if host_ptr is not NULL but
CL_MEM_COPY_HOST_PTR or CL_MEM_USE_HOST_PTR are not set in flags.
public static cl_mem clCreateSubBuffer(cl_mem buffer, long flags, int buffer_create_type, Pointer buffer_create_info, int[] errcode_ret)
clCreateSubBuffer(cl_mem, long, int, cl_buffer_region, int[])public static cl_mem clCreateSubBuffer(cl_mem buffer, long flags, int buffer_create_type, cl_buffer_region buffer_create_info, int[] errcode_ret)
Creates a buffer object (referred to as a sub-buffer object) from an existing buffer object.
cl_mem clCreateSubBuffer
(
|
cl_membuffer, |
| cl_mem_flagsflags, | |
| cl_buffer_create_typebuffer_create_type, | |
| const void*buffer_create_info, | |
cl_int*errcode_ret) |
buffer
A valid object. Cannot be a sub-buffer object.
flags
A bit-field that is used to specify allocation and usage information about the image memory
object being created. The
following table describes the possible values for flags:
| cl_mem_flags | Description |
|---|---|
CL_MEM_READ_WRITE
|
This flag specifies that the memory object will be read and written by a kernel. This is the default. |
CL_MEM_WRITE_ONLY
|
This flags specifies that the memory object will be written but not read by a kernel. Reading from a buffer or image object created with
|
CL_MEM_READ_ONLY
|
This flag specifies that the memory object is a read-only memory object when used inside a kernel. Writing to a buffer or image object created with
|
CL_MEM_USE_HOST_PTR
|
This flag is valid only if OpenCL implementations are allowed to cache the buffer
contents pointed to by The result of OpenCL commands that operate on multiple
buffer objects created with the same |
CL_MEM_ALLOC_HOST_PTR
|
This flag specifies that the application wants the OpenCL implementation to allocate memory from host accessible memory.
|
CL_MEM_COPY_HOST_PTR
|
This flag is valid only if
|
buffer_create_type and buffer_create_info
The type of buffer object to be created. The supported value for buffer_create_type is CL_BUFFER_CREATE_TYPE_REGION, which create a buffer object that represents a specific region in buffer. buffer_create_info is a pointer to the following structure:
typedefstruct_cl_buffer_region{
size_torigin;
size_tsize;
}cl_buffer_region;
(origin, size) defines the offset and size in bytes in buffer.
If buffer is created with CL_MEM_USE_HOST_PTR, the host_ptr associated with the buffer object returned is host_ptr + origin.
The buffer object returned references the data store allocated for buffer and points to a specific region given by (origin, size) in this data store.
CL_INVALID_VALUE is returned in errcode_ret if the region specified by (origin, size) is out of bounds in buffer.
CL_MISALIGNED_SUB_BUFFER_OFFSET is returned in errcode_ret if there are no devices in context associated with buffer for which the origin value is aligned to the CL_DEVICE_MEM_BASE_ADDR_ALIGN value.
errcode_ret
Returns an appropriate error code. If errcode_ret is NULL, no error code is returned.
The implementation may return the same cl_mem object with the reference count incremented
appropriately for multiple calls to clCreateSubBuffer that use the same values for buffer, flags, buffer_create_type and buffer_create_info points to the same descriptor or descriptors that
describe values that are exactly the same.
The result of OpenCL commands that read from and write to multiple sub-buffer objects created
using clCreateSubBuffer with the same buffer object but represent overlapping regions in the
buffer object is undefined. The result of OpenCL commands that read from and write to a buffer
object and its sub-buffer object(s) created using clCreateSubBuffer with the same buffer object
is undefined. OpenCL commands that only read from multiple sub-buffer objects created using
clCreateSubBuffer with the same buffer object but represent overlapping regions in the buffer
object or read from a buffer object and its sub-buffer objects should work as defined.
Returns a valid non-zero buffer object and errcode_ret is set to CL_SUCCESS if
the buffer object is created successfully. Otherwise, it returns one of the following error in errcode_ret:
buffer is not a valid buffer object or is a sub-buffer object.
flags are not valid; or if value specified in buffer_create_type is not valid; or if value(s) specified in buffer_create_info (for a given buffer_create_type) is not valid or if buffer_create_info is NULL.
public static cl_mem clCreateImage(cl_context context, long flags, cl_image_format image_format, cl_image_desc image_desc, Pointer host_ptr, int[] errcode_ret)
Creates a 1D image, 1D image buffer, 1D image array, 2D image, 2D image array or 3D image object.
cl_mem clCreateImage
(
|
cl_contextcontext, |
| cl_mem_flagsflags, | |
| const cl_image_format*image_format, | |
| const cl_image_desc*image_desc, | |
| void*host_ptr, | |
cl_int*errcode_ret) |
context
A valid OpenCL context on which the image object is to be created.
flags
A bit-field that is used to specify allocation and usage information about the image memory object being created and is described in the table below.
For all image types except CL_MEM_OBJECT_IMAGE1D_BUFFER,
if value specified for flags is 0, the default is used
which is CL_MEM_READ_WRITE.
For CL_MEM_OBJECT_IMAGE1D_BUFFER image type, if the
CL_MEM_READ_WRITE, CL_MEM_READ_ONLY
or CL_MEM_WRITE_ONLY values are not specified in
flags, they are inherited from the corresponding
memory access qualifers associated with buffer.
The CL_MEM_USE_HOST_PTR,
CL_MEM_ALLOC_HOST_PTR and
CL_MEM_COPY_HOST_PTR values cannot
be specified in flags but are inherited
from the corresponding memory access qualifiers associated with
buffer. If CL_MEM_COPY_HOST_PTR
is specified in the memory access qualifier values associated with
buffer it does not imply any additional copies
when the sub-buffer is created from buffer.
If the CL_MEM_HOST_WRITE_ONLY,
CL_MEM_HOST_READ_ONLY or
CL_MEM_HOST_NO_ACCESS values are not specified in
flags, they are inherited from the corresponding memory
access qualifiers associated with buffer.
| cl_mem_flags | Description |
|---|---|
CL_MEM_READ_WRITE
|
This flag specifies that the memory object will be read and written by a kernel. This is the default. |
CL_MEM_WRITE_ONLY
|
This flags specifies that the memory object will be written but not read by a kernel.
Reading from a buffer or image object created with
|
CL_MEM_READ_ONLY
|
This flag specifies that the memory object is a read-only memory object when used inside a kernel.
Writing to a buffer or image object created with
|
CL_MEM_USE_HOST_PTR
|
This flag is valid only if
OpenCL implementations are allowed to cache the buffer contents pointed to by
The result of OpenCL commands that operate on multiple buffer objects created with
the same
Refer to the description
of the alignment rules for
|
CL_MEM_ALLOC_HOST_PTR
|
This flag specifies that the application wants the OpenCL implementation to allocate memory from host accessible memory.
|
CL_MEM_COPY_HOST_PTR
|
This flag is valid only if
|
CL_MEM_COPY_HOST_WRITE_ONLY
|
This flag specifies that the host will only write to the memory object (using OpenCL APIs that enqueue a write or a map for write). This can be used to optimize write access from the host (e.g. enable write combined allocations for memory objects for devices that communicate with the host over a system bus such as PCIe). |
CL_MEM_COPY_HOST_READ_ONLY
|
This flag specifies that the host will only read the memory object (using OpenCL APIs that enqueue a read or a map for read).
|
CL_MEM_COPY_HOST_NO_ACCESS
|
This flag specifies that the host will not read or write the memory object.
|
image_format
A pointer to a structure that describes format properties of the image to be allocated. See cl_image_format for a detailed description of the image format descriptor.
image_desc
A pointer to a structure that describes type and dimensions of the image to be allocated. See imageDescriptor for more information.
host_ptr
A pointer to the image data that may already be allocated by the application.
Refer to table below for a description of how large the buffer that
host_ptr points to must be.
| Image Type | Size of buffer that host_ptr points to |
|---|---|
CL_MEM_OBJECT_IMAGE1D
|
≥ image_row_pitch
|
CL_MEM_OBJECT_IMAGE1D_BUFFER
|
≥ image_row_pitch
|
CL_MEM_OBJECT_IMAGE2D
|
≥ image_row_pitch * image_height
|
CL_MEM_OBJECT_IMAGE3D
|
≥ image_slice_pitch * image_depth
|
CL_MEM_OBJECT_IMAGE1D_ARRAY
|
≥ image_slice_pitch * image_array_size
|
CL_MEM_OBJECT_IMAGE2D_ARRAY
|
≥ image_slice_pitch * image_array_size
|
For a 3D image or 2D image array, the image data specified by
host_ptr is stored as a linear sequence of adjacent 2D
image slices or 2D images respectively. Each 2D image is a linear sequence
of adjacent scanlines. Each scanline is a linear sequence of image elements.
For a 2D image, the image data specified by host_ptr
is stored as a linear sequence of adjacent scanlines. Each scanline is
a linear sequence of image elements.
For a 1D image array, the image data specified by host_ptr
is stored as a linear sequence of adjacent 1D images respectively. Each 1D
image or 1D image buffer is a single scanline which is a linear sequence
of adjacent elements.
errcode_ret
Will return an appropriate error code. If errcode_ret
is NULL, no error code is returned.
clCreateImage returns a valid non-zero image object and
errcode_ret is set to CL_SUCCESS if the
image object is created successfully. Otherwise, it returns a NULL value with one of
the following error values returned in errcode_ret:
context is not a valid context.
flags are not valid.
image_format are not valid or if image_format
is NULL.
image_desc are not valid or if image_desc
is NULL.
image_desc exceed the minimum maximum image dimensions
described in the table of allowed values for param_name
for clGetDeviceInfo
for all devices in context.
host_ptr in
image_desc is NULL and CL_MEM_USE_HOST_PTR or
CL_MEM_COPY_HOST_PTR are set in flags or if
host_ptr is not NULL but CL_MEM_COPY_HOST_PTR
or CL_MEM_USE_HOST_PTR are not set in flags.
CL_MEM_WRITE_ONLY
and flags specifies CL_MEM_READ_WRITE
or CL_MEM_READ_ONLY, or if the buffer object was
created with CL_MEM_READ_ONLY and flags specifies
CL_MEM_READ_WRITE or CL_MEM_WRITE_ONLY, or
if flags specifies CL_MEM_USE_HOST_PTR
or CL_MEM_ALLOC_HOST_PTR or
CL_MEM_COPY_HOST_PTR.
CL_MEM_HOST_WRITE_ONLY
and flags specifies CL_MEM_HOST_READ_ONLY,
or if the buffer object was created with CL_MEM_HOST_READ_ONLY
and flags specifies CL_MEM_HOST_WRITE_ONLY,
or if the buffer object was created with CL_MEM_HOST_NO_ACCESS
and flags specifies CL_MEM_HOST_READ_ONLY
or CL_MEM_HOST_WRITE_ONLY.
image_format is not supported.
context that support
images (i.e. CL_DEVICE_IMAGE_SUPPORT
(specified in the table of OpenCL Device Queries for
clGetDeviceInfo)
is CL_FALSE).
public static cl_mem clCreatePipe(cl_context context, long flags, int pipe_packet_size, int pipe_max_packets, cl_pipe_properties properties, int[] errcode_ret)
Creates a pipe object.
cl_mem clCreatePipe
(
|
cl_context context, |
| cl_mem_flags flags, | |
| cl_uint pipe_packet_size, | |
| cl_uint pipe_max_packets, | |
| const cl_pipe_properties * properties, | |
cl_int *errcode_ret) |
context
A valid OpenCL context used to create the pipe object.
flags
A bit-field that is used to specify
allocation and usage information such as the memory
arena that should be used to allocate the pipe object and how it
will be used. The table below describes
the possible values for flags.
Only CL_MEM_READ_ONLY,
CL_MEM_WRITE_ONLY, CL_MEM_READ_WRITE,
and CL_MEM_HOST_NO_ACCESS
can be specified when creating a pipe object.
If value specified for flags is 0,
the default is used which is
CL_MEM_READ_WRITE.
| cl_mem_flags | Description |
|---|---|
CL_MEM_READ_WRITE
|
This flag specifies that the memory object will be read and written by a kernel. This is the default. |
CL_MEM_WRITE_ONLY
|
This flag specifies that the memory object will be written but not read by a kernel.
Reading from a buffer or image object created with
|
CL_MEM_READ_ONLY
|
This flag specifies that the memory object is a read-only memory object when used inside a kernel.
Writing to a buffer or image object created with
|
CL_MEM_USE_HOST_PTR
|
This flag is valid only if
OpenCL implementations are allowed to cache the buffer contents pointed to by
The result of OpenCL commands that operate on multiple buffer objects created with
the same
Refer to the description
of the alignment rules for
|
CL_MEM_ALLOC_HOST_PTR
|
This flag specifies that the application wants the OpenCL implementation to allocate memory from host accessible memory.
|
CL_MEM_COPY_HOST_PTR
|
This flag is valid only if
|
CL_MEM_HOST_WRITE_ONLY
|
This flag specifies that the host will only write to the memory object (using OpenCL APIs that enqueue a write or a map for write). This can be used to optimize write access from the host (e.g. enable write-combined allocations for memory objects for devices that communicate with the host over a system bus such as PCIe). |
CL_MEM_HOST_READ_ONLY
|
This flag specifies that the host will only read the memory object (using OpenCL APIs that enqueue a read or a map for read).
|
CL_MEM_HOST_NO_ACCESS
|
This flag specifies that the host will not read or write the memory object.
|
pipe_packet_size
Size in bytes of a pipe packet.
pipe_max_packets
Specifies the pipe capacity by specifying the maximum number of packets the pipe can hold.
properties
A list of properties for the pipe and their corresponding values. Each property
name is immediately followed by the corresponding desired value.
The list is terminated with 0.
In OpenCL 2.0, properties must be NULL.
errcode_ret
Will return an appropriate error code. If errcode_ret
is NULL, no error code is returned.
Pipes follow the same memory consistency model as defined for buffer and image objects. The pipe state i.e. contents of the pipe across kernel executions (on the same or different devices) is enforced at a synchronization point.
clCreatePipe returns a valid non-zero pipe object and
errcode_ret is set to CL_SUCCESS if the
pipe object is created successfully. Otherwise, it returns a NULL value with one of
the following error values returned in errcode_ret:
context is not a valid context.
flags are not as defined above.
properties is not NULL.
pipe_packet_size
is 0 or the pipe_packet_size exceeds
CL_DEVICE_PIPE_MAX_PACKET_SIZE value specified in table 4.3
(see clGetDeviceInfo)
for all devices in context or if
pipe_max_packets is 0.
clCreateBuffer, clCreateImage
public static cl_mem clCreateImage2D(cl_context context, long flags, cl_image_format[] image_format, long image_width, long image_height, long image_row_pitch, Pointer host_ptr, int[] errcode_ret)
clCreateImage(cl_context, long, cl_image_format, cl_image_desc, Pointer, int[])Creates a 2D image object.
cl_mem clCreateImage2D
(
|
cl_contextcontext, |
| cl_mem_flagsflags, | |
| const cl_image_format*image_format, | |
| size_timage_width, | |
| size_timage_height, | |
| size_timage_row_pitch, | |
| void*host_ptr, | |
cl_int*errcode_ret) |
context
A valid OpenCL context on which the image object is to be created.
flags
A bit-field that is used to specify allocation and usage information about the image memory object being created and is described in the table List of supported cl_mem_flags values for clCreateBuffer.
image_format
A pointer to a structure that describes format properties of the image to be allocated. See cl_image_format for a detailed description of the image format descriptor.
image_width
,
image_height
The width and height of the image in pixels. These must be values greater than or equal to 1.
image_row_pitch
The scan-line pitch in bytes. This must be 0 if host_ptr is NULL and can be
either 0 or greater than or equal to image_width * size of element in bytes
if host_ptr is not NULL. If host_ptr is not
NULL and image_row_pitch is equal to 0, image_row_pitch is calculated as image_width * size of
element in bytes. If image_row_pitch is not 0, it must be a multiple of the image element size in
bytes.
host_ptr
A pointer to the image data that may already be allocated by the application. The size
of the buffer that host_ptr points to must be greater than or equal to image_row_pitch * image_height. The size of
each element in bytes must be a power of 2. The image data specified by host_ptr is stored as a
linear sequence of adjacent scanlines. Each scanline is stored as a linear sequence of image elements.
errcode_ret
Will return an appropriate error code. If errcode_ret is NULL, no error code is returned.
clCreateImage2D returns a valid non-zero image object
and errcode_ret is set to CL_SUCCESS
if the image object is created successfully. Otherwise, it returns a NULL value
with one of the following error values returned in errcode_ret:
context is not a valid context.
flags are not valid.
image_format are not valid or if image_format is NULL.
image_width or
image_height are 0 or if they exceed values specified in
CL_DEVICE_IMAGE2D_MAX_WIDTH or CL_DEVICE_IMAGE2D_MAX_HEIGHT
respectively for all devices in context or if values specified by
image_row_pitch do not follow rules
described in the argument description above.
host_ptr is NULL and
CL_MEM_USE_HOST_PTR or CL_MEM_COPY_HOST_PTR
are set in flags or if host_ptr is not NULL but
CL_MEM_COPY_HOST_PTR or CL_MEM_USE_HOST_PTR
are not set in flags.
image_format is not supported.
context that support images
(i.e. CL_DEVICE_IMAGE_SUPPORT (specified in the table of OpenCL Device Queries for
clGetDeviceInfo) is CL_FALSE).
public static cl_mem clCreateImage3D(cl_context context, long flags, cl_image_format[] image_format, long image_width, long image_height, long image_depth, long image_row_pitch, long image_slice_pitch, Pointer host_ptr, int[] errcode_ret)
clCreateImage(cl_context, long, cl_image_format, cl_image_desc, Pointer, int[])Creates a 3D image object.
cl_mem clCreateImage3D
(
|
cl_contextcontext, |
| cl_mem_flagsflags, | |
| const cl_image_format*image_format, | |
| size_timage_width, | |
| size_timage_height, | |
| size_timage_depth, | |
| size_timage_row_pitch, | |
| size_timage_slice_pitch, | |
| void*host_ptr, | |
cl_int*errcode_ret) |
context
A valid OpenCL context on which the image object is to be created.
flags
A bit-field that is used to specify allocation and usage information about the image memory object being created and is described in the table List of supported cl_mem_flags values for clCreateBuffer.
image_format
A pointer to a structure that describes format properties of the image to be allocated. See cl_image_format for a detailed description of the image format descriptor.
image_width
,
image_height
The width and height of the image in pixels. These must be values greater than or equal to 1.
image depth
The depth of the image in pixels. This must be a value greater than 1.
image_row_pitch
The scan-line pitch in bytes. This must be 0 if host_ptr is NULL and can be
either 0 or greater than or equal to image_width * size of element in bytes
if host_ptr is not NULL. If host_ptr is not
NULL and image_row_pitch is equal to 0, image_row_pitch is calculated as image_width * size of
element in bytes. If image_row_pitch is not 0, it must be a multiple of the image element size in
bytes.
image_slice_pitch
The size in bytes of each 2D slice in the 3D image. This must be 0 if
host_ptr is NULL and can be either 0 or greater than or equal to image_row_pitch * image_height if host_ptr is not
NULL. If host_ptr is not NULL and image_slice_pitch equal to 0, image_slice_pitch is calculated as
image_row_pitch * image_height. If image_slice_pitch is not 0, it must be a multiple of the
image_row_pitch.
host_ptr
A pointer to the image data that may already be allocated by the application. The size
of the buffer that host_ptr points to must be greater than or equal to image_slice_pitch * image_depth. The size of
each element in bytes must be a power of 2. The image data specified by host_ptr is stored as a
linear sequence of adjacent 2D slices. Each 2D slice is a linear sequence of adjacent scanlines.
Each scanline is a linear sequence of image elements.
errcode_ret
Will return an appropriate error code. If errcode_ret is NULL, no error code is returned.
Returns a valid non-zero image object created and the errcode_ret is set to
CL_SUCCESS if the image object is created successfully. Otherwise, it
returns a NULL value with one of the following error values returned in errcode_ret:
context is not a valid context.
flags are not valid.
image_format are
not valid or if image_format is NULL.
image_width, image_height are 0 or if image_depth less than or equal to 1
or if they exceed values specified in CL_DEVICE_IMAGE3D_MAX_WIDTH,
CL_DEVICE_IMAGE3D_MAX_HEIGHT or CL_DEVICE_IMAGE3D_MAX_DEPTH
respectively for all devices in context or if values specified by image_row_pitch and
image_slice_pitch do not follow rules described in the argument description above.
host_ptr is NULL and CL_MEM_USE_HOST_PTR or CL_MEM_COPY_HOST_PTR are set in flags or if host_ptr is not NULL but
CL_MEM_COPY_HOST_PTR or CL_MEM_USE_HOST_PTR are not set in flags.
image_format is not supported.
context that support images (i.e.
CL_DEVICE_IMAGE_SUPPORT (specified in the table of OpenCL Device Queries for clGetDeviceInfo) is CL_FALSE).
public static int clRetainMemObject(cl_mem memobj)
Increments the memory object reference count.
cl_int
clRetainMemObject
(
|
cl_memmemobj) |
After the memobj reference count becomes zero and
commands queued for execution on a command-queue(s) that use memobj have finished, the
memory object is deleted.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
memobj is a not a valid memory object (buffer or image object).
clCreateBuffer, clCreateSubBuffer, clCreateImage2D, and clCreateImage3D perform an implicit retain. clCreateSubBuffer also performs an implicit retain on the memory object used to create the sub-buffer or image object.
public static int clReleaseMemObject(cl_mem memobj)
Decrements the memory object reference count.
cl_int
clReleaseMemObject
(
|
cl_memmemobj) |
After the memobj reference count becomes zero and
commands queued for execution on a command-queue(s) that use memobj have finished, the
memory object is deleted.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
memobj is a not a valid memory object.
After the memobj reference count becomes zero and commands queued for execution on a
command-queue(s) that use memobj have finished, the memory object is deleted.
public static int clGetSupportedImageFormats(cl_context context, long flags, int image_type, int num_entries, cl_image_format[] image_formats, int[] num_image_formats)
Get the list of image formats supported by an OpenCL implementation.
cl_int
clGetSupportedImageFormats
(
|
cl_contextcontext, |
| cl_mem_flagsflags, | |
| cl_mem_object_typeimage_type, | |
| cl_uintnum_entries, | |
| cl_image_format*image_formats, | |
cl_uint*num_image_formats) |
context
A valid OpenCL context on which the image object(s) will be created.
flags
A bit-field that is used to specify allocation and usage information about the image memory object being created and is described in the List of supported cl_mem_flags values for clCreateBuffer
image_type
Describes the image type and must be either CL_MEM_OBJECT_IMAGE2D or
CL_MEM_OBJECT_IMAGE3D.
num_entries
Specifies the number of entries that can be returned in the memory location given by
image_formats.
image_formats
A pointer to a memory location where the list of supported image formats are
returned. Each entry describes a cl_image_format structure supported
by the OpenCL implementation. If image_formats is NULL, it is ignored.
num_image_formats
The actual number of supported image formats for a specific context and
values specified by flags. If num_image_formats is NULL, it is ignored.
clGetSupportedImageFormats can be used to get the list of image formats supported by an OpenCL
implementation when the following information about an image memory object is specified:
The minimum list of supported image formats is given by the table below:
|
image_num_channels |
image_channel_order |
image_channel_data_type |
|---|---|---|
|
4 |
CL_RGBA |
CL_UNORM_INT8 |
|
4 |
CL_BGRA |
CL_UNORM_INT8 |
If CL_DEVICE_IMAGE_SUPPORT specified in the table of OpenCL Device Queries for clGetDeviceInfo is CL_TRUE, the values assigned to the following constants by the implementation must be greater than or equal to the minimum values specified in the table of OpenCL Device Queries for clGetDeviceInfo: CL_DEVICE_MAX_READ_IMAGE_ARGS, CL_DEVICE_MAX_WRITE_IMAGE_ARGS, CL_DEVICE_IMAGE2D_MAX_WIDTH, CL_DEVICE_IMAGE2D_MAX_HEIGHT, CL_DEVICE_IMAGE3D_MAX_WIDTH, CL_DEVICE_IMAGE3D_MAX_HEIGHT, CL_DEVICE_IMAGE3D_MAX_DEPTH, CL_DEVICE_MAX_SAMPLERS.
Returns CL_SUCCESS if the function is executed successfully.
Otherwise, it returns a NULL value
with one of the following error values returned in errcode_ret:
context is not a valid context.
flags or image_type are not valid, or
if num_entries is 0 and image_formats is not NULL.
public static int clGetMemObjectInfo(cl_mem memobj, int param_name, long param_value_size, Pointer param_value, long[] param_value_size_ret)
Used to get information that is common to all memory objects (buffer and image objects).
cl_int
clGetMemObjectInfo
(
|
cl_memmemobj, |
| cl_mem_infoparam_name, | |
| size_tparam_value_size, | |
| void*param_value, | |
size_t*param_value_size_ret) |
memobj
Specifies the memory object being queried.
param_name
Specifies the information to query. The list of supported param_name types and the
information returned in param_value by clGetMemObjectInfo is described
in the table below.
| cl_mem_info | Return Type | Info. returned in param_value |
|---|---|---|
CL_MEM_TYPE
|
cl_mem_object_type |
Returns one of the following values:
|
CL_MEM_FLAGS
|
cl_mem_flags |
Returns the flags argument value
specified when memobj is created with clCreateBuffer,
clCreateSubBuffer, clCreateImage2D, or clCreateImage3D.
|
CL_MEM_SIZE
|
size_t |
Return actual size of the data store associated with memobj in bytes.
|
CL_MEM_HOST_PTR
|
void * |
Return the host_ptr argument value specified when memobj is created.
|
CL_MEM_MAP_COUNT
|
cl_uint | Map count. The map count returned should be considered immediately stale. It is unsuitable for general use in applications. This feature is provided for debugging. |
CL_MEM_REFERENCE_COUNT
|
cl_uint |
Return memobj reference count. The reference count returned should be considered immediately stale. It is unsuitable for general use in
applications. This feature is provided for identifying memory leaks.
|
CL_MEM_CONTEXT
|
cl_context | Return context specified when memory object is created. |
CL_MEM_ASSOCIATED_MEMOBJECT
|
cl_mem |
Return memory object from which memobj is created.
This returns the memory object specified as Otherwise a NULL value is returned. |
CL_MEM_OFFSET
|
size_t |
Return offset if memobj is a sub-buffer object created using
clCreateSubBuffer.
This return 0 if |
CL_MEM_D3D10_RESOURCE_KHR
|
ID3D10Resource * |
The propery being queried (if the
cl_khr_d3d10_sharing
extension is enabled). If memobj was created using
clCreateFromD3D10BufferKHR,
clCreateFromD3D10Texture2DKHR,
or clCreateFromD3D10Texture3DKHR,
returns the resource argument specified
when memobj was created.
|
param_value
A pointer to memory where the appropriate result being queried is returned. If param_value is NULL, it is ignored.
param_value_size
Used to specify the size in bytes of memory pointed to by param_value.
This size must be greater than or equal to size of return type as described in the table above.
param_value_size_ret
Returns the actual size in bytes of data being queried by param_value. If param_value_size_ret is NULL, it is ignored.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
param_name is not valid, or if size
in bytes specified by param_value_size is less than the size of return type as
described in the table above and param_value is not NULL.
param_name is
CL_MEM_D3D10_RESOURCE_KHR and memobj was not created by the function
clCreateFromD3D10BufferKHR,
clCreateFromD3D10Texture2DKHR, or
clCreateFromD3D10Texture3DKHR.
memobj is a not a valid memory object.
public static int clGetImageInfo(cl_mem image, int param_name, long param_value_size, Pointer param_value, long[] param_value_size_ret)
Get information specific to an image object.
cl_int * clGetImageInfo
(
|
cl_memimage, |
| cl_image_infoparam_name, | |
| size_tparam_value_size, | |
| void*param_value, | |
size_t*param_value_size_ret) |
image
Specifies the image object being queried.
param_name
Specifies the information to query. The list of supported param_name types and the
information returned in param_value by clGetImageInfo is described in the table below.
param_value
A pointer to memory where the appropriate result being queried is returned. If param_value is NULL, it is ignored.
param_value_size
Used to specify the size in bytes of memory pointed to by param_value.
This size must be greater than or equal to size of return type as described in the table below.
| cl_image_info | Return Type | Info. returned in param_value |
|---|---|---|
CL_IMAGE_FORMAT
|
cl_image_format |
Return image format descriptor specified when
image is created with clCreateImage2D or clCreateImage3D.
|
CL_IMAGE_ELEMENT_SIZE
|
size_t |
Return size of each element of the image
memory object given by image. An element is
made up of n channels. The value of n is given
in cl_image_format descriptor.
|
CL_IMAGE_ROW_PITCH
|
size_t |
Return size in bytes of a row of elements of the
image object given by image.
|
CL_IMAGE_SLICE_PITCH
|
size_t |
Return size in bytes of a 2D slice for the 3D
image object given by image. For a 2D image
object this value will be 0.
|
CL_IMAGE_WIDTH
|
size_t | Return width of image in pixels. |
CL_IMAGE_HEIGHT
|
size_t | Return height of image in pixels. |
CL_IMAGE_DEPTH
|
size_t | Return depth of the image in pixels. For a 2D image, depth equals 0. |
CL_IMAGE_D3D10_SUBRESOURCE_KHR
|
ID3D10Resource * |
The propery being queried (if the
cl_khr_d3d10_sharing
extension is enabled). If image was created using
clCreateFromD3D10Texture2DKHR or
clCreateFromD3D10Texture3DKHR,
returns the subresource argument
specified when image was created.
|
param_value_size_ret
the actual size in bytes of data being queried by param_value. If param_value_size_ret is NULL, it is ignored.
To get information that is common to all memory objects (buffer and image objects), use the clGetMemObjectInfo function.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
image is a not a valid image object.
param_name is not valid, or if
size in bytes specified by param_value_size is less than the size of return
type as described in the table above and param_value is not NULL.
param_name is
CL_MEM_D3D10_SUBRESOURCE_KHR and image was not created by the function
clCreateFromD3D10Texture2DKHR or
clCreateFromD3D10Texture3DKHR.
public static int clGetPipeInfo(cl_mem pipe, int param_name, long param_value_size, Pointer param_value, long[] param_value_size_ret)
Get information specific to a pipe object created with clCreatePipe.
cl_int
clGetPipeInfo
(
|
cl_mem pipe , |
| cl_pipe_info param_name , | |
| size_t param_value_size , | |
| void *param_value , | |
size_t
*param_value_size_ret
)
|
pipe
Specifies the pipe object being queried.
param_name
Specifies the information to query. The list of supported
param_name types and the
information returned in param_value by
clGetPipeInfo is described
in the table below.
| cl_pipe_info | Return Type | Info. returned in param_value |
|---|---|---|
CL_PIPE_PACKET_SIZE
|
cl_uint |
Return pipe packet size specified when
pipe is created with
clCreatePipe.
|
CL_PIPE_MAX_PACKETS
|
cl_uint |
Return max. number of packets specified
when pipe is created with
clCreatePipe.
|
param_value
A pointer to memory where the appropriate result being queried is returned.
If param_value is NULL, it is ignored.
param_value_size
Used to specify the size in bytes of memory pointed to by param_value.
This size must be ≥ size of return type as described in the table above.
param_value_size_ret
Returns the actual size in bytes of data being queried by param_value.
If param_value_size_ret is NULL, it is ignored.
To get information that is common to all memory objects, use the clGetMemObjectInfo function.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
param_name is not valid, or if size
in bytes specified by param_value_size
is < the size of return type as
described in the table above and param_value is not NULL.
pipe
is a not a valid memory object.
clGetImageInfo
public static int clSetMemObjectDestructorCallback(cl_mem memobj, MemObjectDestructorCallbackFunction pfn_notify, java.lang.Object user_data)
Registers a user callback function that will be called when the memory object is deleted and its resources freed.
cl_int
clSetMemObjectDestructorCallback
(
|
cl_memmemobj, |
| void (CL_CALLBACK *pfn_notify) (cl_mem memobj, | |
| void*user_data), | |
void*user_data) |
memobj
A valid memory object.
pfn_notify
The callback function that can be registered by the application. This callback function may be called asynchronously by the OpenCL implementation. It is the application's responsibility to ensure that the callback function is thread-safe. The parameters to this callback function are:
memobj: the memory object being deleted.
user_data: a pointer to user supplied data.
user_data
Data which will be passed as the user_data argument when
pfn_notify is called. user_data can be NULL.
Each call to clSetMemObjectDestructorCallback registers the specified user
callback function on a callback stack associated with memobj. The registered user
callback functions are called in the reverse order in which they were registered. The user callback
functions are called and then the memory object's resources are freed and the memory object is
deleted. This provides a mechanism for the application (and libraries) using memobj
to be notified when the memory referenced by host_ptr, specified when the memory object
is created and used as the storage bits for the memory object, can be reused or freed.
When the user callback function is called by the implementation, the contents of the
memory region pointed to by host_ptr (if the memory object is created with
CL_MEM_USE_HOST_PTR) are undefined. The callback function is typically used by the application to
either free or reuse the memory region pointed to by host_ptr.
The behavior of calling expensive system routines, OpenCL API calls to create contexts or command-queues, or blocking OpenCL operations from the following list below, in a callback is undefined.
If an application needs to wait for completion of a routine from the above list in a callback, please use the non-blocking form of the function, and assign a completion callback to it to do the remainder of your work. Note that when a callback (or other code) enqueues commands to a command-queue, the commands are not required to begin execution until the queue is flushed. In standard usage, blocking enqueue calls serve this role by implicitly flushing the queue. Since blocking calls are not permitted in callbacks, those callbacks that enqueue commands on a command queue should either call clFlush on the queue before returning or arrange for clFlush to be called later on another thread.
The user callback function may not call OpenCL APIs with the memory object for which the callback function is invoked and for such cases the behavior of OpenCL APIs is considered to be undefined.
Returns CL_SUCCESS if the command-queue properties are successfully updated. Otherwise, it returns the following:
memobj is not a valid memory object.
pfn_notify is NULL.
public static Pointer clSVMAlloc(cl_context context, long flags, long size, int alignment)
Allocates a shared virtual memory (SVM) buffer that can be shared by the host and all devices in an OpenCL context that support shared virtual memory.
void * clSVMAlloc
(
|
cl_context context, |
| cl_svm_mem_flags flags, | |
| size_t size, | |
unsigned int alignment) |
context
A valid OpenCL context used to create the SVM buffer.
flags
A bit-field that is used to specify
allocation and usage information. The following
table describes the possible values for flags.
| cl_svm_mem_flags | Description |
|---|---|
CL_MEM_READ_WRITE
|
This flag specifies that the SVM buffer will be read and written by a kernel. This is the default. |
CL_MEM_WRITE_ONLY
|
This flag specifies that the SVM buffer will be written but not read by a kernel.
Reading from a SVM buffer created with
|
CL_MEM_READ_ONLY
|
This flag specifies that the SVM buffer object is a read-only memory object when used inside a kernel.
Writing to a SVM buffer created with
|
CL_MEM_SVM_FINE_GRAIN_BUFFER
|
This specifies that the application wants the OpenCL implementation to do a fine-grained allocation. |
CL_MEM_SVM_ATOMICS
|
This flag is valid only if
CL_MEM_SVM_FINE_GRAIN_BUFFER is specified in
flags. It is used to indicate that SVM atomic
operations can control visibility of memory accesses
in this SVM buffer.
|
size
The size in bytes of the SVM buffer to be allocated.
alignment
The minimum alignment in bytes that is required for the newly created buffer’s memory region. It must be a power of two up to the largest data type supported by the OpenCL device. For the full profile, the largest data type is long16. For the embedded profile, it is long16 if the device supports 64-bit integers; otherwise it is int16. If alignment is 0, a default alignment will be used that is equal to the size of largest data type supported by the OpenCL implementation.
If CL_MEM_SVM_FINE_GRAIN_BUFFER is not
specified, the buffer can be created as a coarse
grained SVM allocation. Similarly, if CL_MEM_SVM_ATOMICS
is not specified, the buffer can be
created without support for the OpenCL 2.0 SVM atomic
operations (refer to section 6.13.11 of
the OpenCL C 2.0 specification).
Calling clSVMAlloc does not itself
provide consistency for the shared memory region. When
the host can’t use the SVM atomic operations, it
must rely on OpenCL’s guaranteed memory
consistency at synchronization points. To initialize
a buffer to be shared with a kernel, the host
can create the buffer and use the resulting virtual
memory pointer to initialize the buffer’s
contents.
For SVM to be used efficiently, the host and any
devices sharing a buffer containing virtual
memory pointers should have the same endianness.
If the context passed to clSVMAlloc has
devices with mixed endianness and the OpenCL
implementation is unable to implement SVM
because of that mixed endianness,
clSVMAlloc will fail and return NULL.
Although SVM is generally not supported for image objects, clCreateImage may create an image from a buffer (a 1D image from a buffer or a 2D image from buffer) if the buffer specified in its image description parameter is a SVM buffer. Such images have a linear memory representation so their memory can be shared using SVM. However, fine grained sharing and atomics are not supported for image reads and writes in a kernel.
If clCreateBuffer
is called with a pointer returned by
clSVMAlloc as its
host_ptr argument, and
CL_MEM_USE_HOST_PTR is set in its flags argument,
clCreateBuffer
will succeed and return a
valid non-zero buffer object as long as the size
argument to
clCreateBuffer
is no larger than the
size argument passed in the original
clSVMAlloc call. The new
buffer object returned has the
shared memory as the underlying storage.
Locations in the buffer’s underlying shared memory
can be operated on using, e.g., atomic
operations if the device supports them.
Returns a valid non-NULL shared virtual memory address if the SVM buffer is
successfully allocated. Otherwise, like malloc, it returns a NULL pointer
value. clSVMAlloc will fail if:
context is not a valid context.
flags does not contain
CL_MEM_SVM_FINE_GRAIN_BUFFER but does contain
CL_MEM_SVM_ATOMICS.
flags do not follow
rules described for supported values in the table above.
CL_MEM_SVM_FINE_GRAIN_BUFFER or
CL_MEM_SVM_ATOMICS is specified in
flags and these are not supported
by at least one device in context.
flags are
not valid i.e. don’t match those defined in the table above.
size is 0 or > CL_DEVICE_MAX_MEM_ALLOC_SIZE
value for any device in context.
alignment is not a power of two
or the OpenCL implementation cannot support the
specified alignment for at least one device in context.
clSVMFree, Shared Virtual Memory Functions
public static void clSVMFree(cl_context context, Pointer svm_pointer)
Frees a shared virtual memory buffer allocated using clSVMAlloc.
void
clSVMFree
(
|
cl_context context, |
void *svm_pointer) |
context
A valid OpenCL context used to create the SVM buffer.
svm_pointer
Must be the value returned by a call to clSVMAlloc.
If a NULL pointer is passed in
svm_pointer, no action occurs.
Note that clSVMFree does not wait
for previously enqueued commands that may be using
svm_pointer to finish before freeing
svm_pointer. It is the responsibility
of the application to
make sure that enqueued commands that use
svm_pointer have finished before freeing
svm_pointer. This can be done by
enqueuing a blocking operation such as
clFinish,
clWaitForEvents,
clEnqueueReadBuffer
or by registering a callback with the events
associated with enqueued commands and when the
last enqueued comamnd has finished freeing
svm_pointer.
The behavior of using svm_pointer after
it has been freed is undefined. In addition, if a buffer
object is created using
clCreateBuffer
with svm_pointer, the buffer object must first be released
before the svm_pointer is freed.
The clEnqueueSVMFree API can also be used to enqueue a callback to free the shared virtual memory buffer allocated using clSVMAlloc or a shared system memory pointer.
clSVMAlloc, Shared Virtual Memory Functions
public static cl_sampler clCreateSamplerWithProperties(cl_context context, cl_sampler_properties properties, int[] errcode_ret)
Creates a sampler object.
cl_sampler clCreateSamplerWithProperties
(
|
cl_context context, |
| const cl_sampler_properties *sampler_properties, | |
cl_int *errcode_ret) |
context
Must be a valid OpenCL context.
sampler_properties
Specifies a list of sampler property names and
their corresponding values.
Each sampler property name is immediately followed
by the corresponding desired value. The
list is terminated with 0. The list of supported
properties is described in the table below. If a
supported property and its value is not specified in
sampler_properties, its default value will be
used. sampler_properties can be
NULL in which case the default values for supported sampler
properties will be used.
| cl_sampler_properties enum | Property Value | Description |
|---|---|---|
CL_SAMPLER_NORMALIZED_COORDS
|
cl_bool |
A boolean value that specifies whether the image coordinates specified are normalized or not.
The default value (i.e. the value used
if this property is not specified in
|
CL_SAMPLER_ADDRESSING_MODE
|
cl_addressing_mode |
Specifies how out-of-range image coordinates are handled when reading from an image. Valid values are:
The default is |
CL_SAMPLER_FILTER_MODE
|
cl_filter_mode |
Specifies the type of filter that must be applied when reading an image. Valid values are:
The default is |
If the cl_khr_mipmap_image
extension is supported, the following sampler
properties can be specified when a sampler object is
created using clCreateSamplerWithProperties:
| cl_sampler_properties enum | Property Value | Default Value |
|---|---|---|
CL_SAMPLER_MIP_FILTER_MODE
|
cl_filter_mode |
CL_FILTER_NONE
|
CL_SAMPLER_LOD_MIN
|
float |
0.0f
|
CL_SAMPLER_LOD_MAX
|
float |
MAXFLOAT
|
errcode_ret
Returns an appropriate error code. If
errcode_ret is NULL, no error code is returned.
A sampler object describes how to sample an image when the image is read in the kernel. The built-in functions to read from an image in a kernel take a sampler as an argument. The sampler arguments to the image read function can be sampler objects created using OpenCL functions and passed as argument values to the kernel or can be samplers declared inside a kernel.
For more information about working with samplers, see sampler_t
If the cl_khr_mipmap_image
extension is supported, the sampler properties
CL_SAMPLER_MIP_FILTER_MODE,
CL_SAMPLER_LOD_MIN and
CL_SAMPLER_LOD_MAX cannot be
specified with any samplers initialized in the OpenCL
program source. Only the default values for these
properties will be used. To create a sampler
with specific values for these properties, a
sampler object must be created with
clCreateSamplerWithProperties
and passed as an argument to a kernel.
Returns a valid non-zero sampler object and errcode_ret is set to
CL_SUCCESS if the sampler object is created successfully.
Otherwise, it returns a NULL value with one of the following error values returned in
errcode_ret:
context
is not a valid context.
sampler_properties is not a supported
property name, if the value specified for a supported property
name is not valid, or if the
same property name is specified more than once.
context
(i.e. CL_DEVICE_IMAGE_SUPPORT
specified in the table of OpenCL Device Queries for
clGetDeviceInfo
is CL_FALSE).
clRetainSampler, clReleaseSampler, clGetSamplerInfo sampler_t, cl_khr_mipmap_image
public static cl_sampler clCreateSampler(cl_context context, boolean normalized_coords, int addressing_mode, int filter_mode, int[] errcode_ret)
clCreateSamplerWithProperties(org.jocl.cl_context, org.jocl.cl_sampler_properties, int[]) instead.Creates a sampler object.
cl_sampler clCreateSampler
(
|
cl_contextcontext, |
| cl_boolnormalized_coords, | |
| cl_addressing_modeaddressing_mode, | |
| cl_filter_modefilter_mode, | |
cl_int*errcode_ret) |
context
Must be a valid OpenCL context.
normalized_coords
Determines if the image coordinates specified are normalized (if
normalized_coords is CL_TRUE) or not (if normalized_coords is CL_FALSE).
addressing_mode
Specifies how out-of-range image coordinates are handled when reading from
an image. This can be set to CL_ADDRESS_MIRRORED_REPEAT, CL_ADDRESS_REPEAT, CL_ADDRESS_CLAMP_TO_EDGE, CL_ADDRESS_CLAMP, and CL_ADDRESS_NONE.
filtering_mode
Specifies the type of filter that must be applied when reading an image. This can be CL_FILTER_NEAREST or CL_FILTER_LINEAR.
errcode_ret
Returns an appropriate error code. If errcode_ret is NULL, no error code is returned.
A sampler object describes how to sample an image when the image is read in the kernel. The built-in functions to read from an image in a kernel take a sampler as an argument. The sampler arguments to the image read function can be sampler objects created using OpenCL functions and passed as argument values to the kernel or can be samplers declared inside a kernel. In this section we discuss how sampler objects are created using OpenCL functions.
Returns a valid non-zero sampler object and errcode_ret is set to CL_SUCCESS if the sampler object is created successfully. Otherwise, it returns a NULL value with one of the following error values returned in errcode_ret:
context
is not a valid context.
addressing_mode,
filter_mode, or normalized_coords or a combination of these argument values are not valid.
context (i.e. CL_DEVICE_IMAGE_SUPPORT specified in the table of OpenCL Device Queries for clGetDeviceInfo is CL_FALSE).
public static int clRetainSampler(cl_sampler sampler)
Increments the sampler reference count.
cl_int
clRetainSampler(
|
cl_samplersampler) |
sampler
sampler being retained.
clCreateSampler performs an implicit retain.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
sampler is not a valid sampler object.
public static int clReleaseSampler(cl_sampler sampler)
Decrements the sampler reference count.
cl_int
clReleaseSampler
(
|
cl_samplersampler) |
The sampler object is deleted after the reference count
becomes zero and commands queued for execution on a command-queue(s) that use
sampler have finished.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
sampler is not a valid sampler object.
public static int clGetSamplerInfo(cl_sampler sampler, int param_name, long param_value_size, Pointer param_value, long[] param_value_size_ret)
Returns information about the sampler object.
cl_int
clGetSamplerInfo
(
|
cl_samplersampler, |
| cl_sampler_infoparam_name, | |
| size_tparam_value_size, | |
| void*param_value, | |
size_t*param_value_size_ret) |
sampler
Specifies the sampler being queried.
param_name
Specifies the information to query. The list of supported
param_name types and the information returned in
param_value by clGetSamplerInfo is described in the table below.
param_value
A pointer to memory where the appropriate result being queried is
returned. If param_value is NULL, it is ignored.
param_value_size
Specifies the size in bytes of memory pointed to by
param_value. This size must be greater than or equal to size of
return type as described in the table below.
param_value_size_ret
Returns the actual size in bytes of data copied to param_value.
If param_value_size_ret is NULL, it is ignored.
| cl_sampler_info | Return Type and Info. returned in param_value |
|---|---|
CL_SAMPLER_REFERENCE_COUNT
|
Return type: cl_uint
Return the |
CL_SAMPLER_CONTEXT
|
Return type: cl_context
Return the context specified when the sampler is created. |
CL_SAMPLER_ADDRESSING_MODE
|
Return type: cl_addressing_mode
Return the addressing mode value associated with
|
CL_SAMPLER_FILTER_MODE
|
Return type: cl_filter_mode
Return the filter mode value associated with
|
CL_SAMPLER_NORMALIZED_COORDS
|
Return type: cl_bool
Return the normalized coords value associated with
|
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
param_name is not valid, or if size
in bytes specified by param_value_size is less than return type as described in
the table above and param_value is not NULL
sampler is a not a valid sampler object.
public static cl_program clCreateProgramWithSource(cl_context context, int count, java.lang.String[] strings, long[] lengths, int[] errcode_ret)
Creates a program object for a context, and loads the source code specified by the text strings in
the strings array into the program object.
cl_program clCreateProgramWithSource
(
|
cl_contextcontext, |
| cl_uintcount, | |
| const char**strings, | |
| const size_t*lengths, | |
cl_int*errcode_ret) |
context
Must be a valid OpenCL context.
strings
An array of count pointers to optionally null-terminated character strings that make up the source code.
lengths
An array with the number of chars in each string (the string length). If
an element in lengths is zero, its accompanying string is null-terminated. If lengths is NULL, all strings in the strings argument are considered null-terminated. Any length value passed in that is greater than zero excludes the null terminator in its count.
errcode_ret
Returns an appropriate error code. If errcode_ret is NULL, no error code is returned.
The devices associated with the program object are the devices associated with context.
OpenCL allows applications to create a program object using the program source or binary and build appropriate program executables. This allows applications to determine whether they want to use the pre-built offline binary or load and compile the program source and use the executable compiled/linked online as the program executable. This can be very useful as it allows applications to load and build program executables online on its first instance for appropriate OpenCL devices in the system. These executables can now be queried and cached by the application. Future instances of the application launching will no longer need to compile and build the program executables. The cached executables can be read and loaded by the application, which can help significantly reduce the application initialization time.
An OpenCL program consists of a set of kernels that are identified as functions declared with the __kernel qualifier in the program source. OpenCL programs may also contain auxiliary functions and constant data that can be used by __kernel functions. The program executable can be generated online or offline by the OpenCL compiler for the appropriate target device(s).
clCreateProgramWithSource returns a valid non-zero program object and errcode_ret is set to
CL_SUCCESS if the program object is created successfully. Otherwise, it returns a NULL value
with one of the following error values returned in errcode_ret:
context is not a valid context.
count is zero or if strings
or any entry in strings is NULL.
public static cl_program clCreateProgramWithBinary(cl_context context, int num_devices, cl_device_id[] device_list, long[] lengths, byte[][] binaries, int[] binary_status, int[] errcode_ret)
Creates a program object for a context, and loads the binary bits specified by binary into the program object.
cl_program clCreateProgramWithBinary
(
|
cl_contextcontext, |
| cl_uintnum_devices, | |
| const cl_device_id*device_list, | |
| const size_t*lengths, | |
| const unsigned char**binaries, | |
| cl_int*binary_status, | |
cl_int*errcode_ret) |
context
Must be a valid OpenCL context.
device_list
A pointer to a list of devices that are in context. device_list must be a non-NULL
value. The binaries are loaded for devices specified in this list.
num_devices
The number of devices listed in device_list.
The devices associated with the program object will be the list of devices specified by
device_list. The list of devices specified by device_list must be devices associated with context.
lengths
An array of the size in bytes of the program binaries to be loaded for devices specified
by device_list.
binaries
An array of pointers to program binaries to be loaded for devices specified by device_list. For each device given by device_list[i], the pointer to the program binary for that device is given by binaries[i] and the length of this corresponding binary is given by lengths[i]. lengths[i] cannot be zero and binaries[i] cannot be a NULL pointer.
The program binaries specified by binaries contain the bits that describe the program executable that will be run on the device(s) associated with context. The program binary can consist of either or both of device-specific executable(s), and/or implementation-specific intermediate representation (IR) which will be converted to the device-specific executable.
binary_status
Returns whether the program binary for each device specified in device_list
was loaded successfully or not. It is an array of num_devices entries and
returns CL_SUCCESS in binary_status[i] if binary
was successfully loaded for device specified by device_list[i];
otherwise returns CL_INVALID_VALUE if lengths[i]
is zero or if binaries[i] is a NULL value or
CL_INVALID_BINARY in binary_status[i] if program
binary is not a valid binary for the
specified device. If binary_status is NULL, it is ignored.
errcode_ret
Returns an appropriate error code. If errcode_ret is NULL, no error code is
returned.
OpenCL allows applications to create a program object using the program source or binary and build appropriate program executables. This allows applications to determine whether they want to use the pre-built offline binary or load and compile the program source and use the executable compiled/linked online as the program executable. This can be very useful as it allows applications to load and build program executables online on its first instance for appropriate OpenCL devices in the system. These executables can now be queried and cached by the application. Future instances of the application launching will no longer need to compile and build the program executables. The cached executables can be read and loaded by the application, which can help significantly reduce the application initialization time.
Returns a valid non-zero program object and errcode_ret is set to CL_SUCCESS if the program object is created successfully. Otherwise, it returns a NULL value with one of the following error values returned in errcode_ret:
context is not a valid context.
device_list is NULL or num_devices
is zero; or if lengths or binaries are NULL or if any entry
in lengths[i] or binaries[i] is NULL.
device_list are not
in the list of devices associated with context.
binary_status will return specific status for each device.
public static cl_program clCreateProgramWithBuiltInKernels(cl_context context, int num_devices, cl_device_id[] device_list, java.lang.String kernel_names, int[] errcode_ret)
Creates a program object for a context, and loads the information related to the built-in kernels into a program object.
cl_program clCreateProgramWithBuiltInKernels
(
|
cl_contextcontext, |
| cl_uintnum_devices, | |
| const cl_device_id*device_list, | |
| const char*kernel_names, | |
cl_int*errcode_ret) |
context
Must be a valid OpenCL context.
num_devices
The number of devices listed in device_list.
device_list
A pointer to a list of devices that are in context.
device_list must be a non-NULL
value. The built-in kernels are loaded for devices specified in this list.
The devices associated with the program object will be the list of devices specified by
device_list. The list of devices specified by
device_list must be devices associated with context.
kernel_names
A semi-colon separated list of built-in kernel names.
Returns a valid non-zero program object and errcode_ret is set
to CL_SUCCESS if the program object is created successfully.
Otherwise, it returns a NULL value with one of the following error values returned
in errcode_ret:
context is not
a valid context.
device_list is NULL
or num_devices is zero;
kernel_names is NULL
or kernel_names contains a kernel name that is not supported
by any of the devices in device_list.
device_list are not in the list of devices associated with
context.
public static int clRetainProgram(cl_program program)
Increments the program reference count.
cl_int
clRetainProgram
(
|
cl_programprogram) |
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
program is not a valid program object.
public static int clReleaseProgram(cl_program program)
Decrements the program reference count.
cl_int clReleaseProgram
(
|
cl_programprogram) |
The program object is deleted after all kernel objects
associated with program have been deleted and the program reference count becomes zero.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
program is not a valid program object.
public static int clBuildProgram(cl_program program, int num_devices, cl_device_id[] device_list, java.lang.String options, BuildProgramFunction pfn_notify, java.lang.Object user_data)
Builds (compiles and links) a program executable from the program source or binary.
cl_int
clBuildProgram
(
|
cl_programprogram, |
| cl_uintnum_devices, | |
| const cl_device_id*device_list, | |
| const char*options, | |
| void(CL_CALLBACK *pfn_notify)(cl_program program, void *user_data), | |
void*user_data) |
program
The program object
device_list
A pointer to a list of devices associated with program. If device_list is NULL value, the program executable is built for all devices associated with program for which a source or binary has been loaded. If device_list is a non-NULL value, the program executable is built for devices specified in this list for which a source or binary has been loaded.
num_devices
The number of devices listed in device_list.
options
A pointer to a null-terminated string of characters that describes the build options to be used for building the program executable. The list of supported options is described in "Build Options" below.
pfn_notify
A function pointer to a notification routine. The notification routine is a callback function that an application can register and which will be called when the program executable has been built (successfully or unsuccessfully). If pfn_notify is not NULL, clBuildProgram does not need to wait for the build to complete and can return immediately. If pfn_notify is NULL, clBuildProgram does not return until the build has completed. This callback function may be called asynchronously by the OpenCL implementation. It is the application's responsibility to ensure that the callback function is thread-safe.
user_data
Passed as an argument when pfn_notify is called. user_data can be NULL.
OpenCL allows program executables to be built using the source or the binary. clBuildProgram must
be called for program created using
either clCreateProgramWithSource
or clCreateProgramWithBinary to build the program executable
for one or more devices associated with program.
The build options are categorized as pre-processor options, options for math intrinsics, options that control optimization and miscellaneous options. This specification defines a standard set of options that must be supported by an OpenCL compiler when building program executables online or offline. These may be extended by a set of vendor- or platform-specific options.
clBuildProgram.
Predefine name as a macro, with definition 1.
The contents of definition are tokenized and processed as if they appeared during translation phase three in a `#define' directive. In particular, the definition will be truncated by embedded newline characters.
Add the directory dir to the list of directories to be searched for header files.
Treat double precision floating-point constant as single precision constant.
This option controls how single precision and double precision denormalized numbers are handled. If specified as a build option, the single precision denormalized numbers may be flushed to zero; double precision denormalized numbers may also be flushed to zero if the optional extension for double precsion is supported. This is intended to be a performance hint and the OpenCL compiler can choose not to flush denorms to zero if the device supports single precision (or double precision) denormalized numbers.
This option is ignored for single precision numbers if the device does not support single precision denormalized numbers i.e. CL_FP_DENORM bit is not set in CL_DEVICE_SINGLE_FP_CONFIG.
This option is ignored for double precision numbers if the device does not support double precision or if it does support double precison but CL_FP_DENORM bit is not set in CL_DEVICE_DOUBLE_FP_CONFIG.
This flag only applies for scalar and vector single precision floating-point variables and computations on these floating-point variables inside a program. It does not apply to reading from or writing to image objects.
This option disables all optimizations. The default is optimizations are enabled.
This option allows the compiler to assume the strictest aliasing rules.
The following options control compiler behavior regarding floating-point arithmetic. These options trade off between performance and correctness and must be specifically enabled. These options are not turned on by default since it can result in incorrect output for programs which depend on an exact implementation of IEEE 754 rules/specifications for math functions.
Allow a * b + c to be replaced by a mad. The mad
computes a * b + c with reduced accuracy. For example, some OpenCL devices
implement mad as truncate the result of a * b before adding it to c.
Allow optimizations for floating-point arithmetic that ignore the signedness of zero. IEEE 754 arithmetic
specifies the distinct behavior of +0.0 and -0.0 values, which then prohibits
simplification of expressions such as x+0.0 or 0.0*x (even with -clfinite-math
only). This option implies that the sign of a zero result isn't significant.
Allow optimizations for floating-point arithmetic that (a) assume that arguments and results are valid, (b) may violate IEEE 754 standard and (c) may violate the OpenCL numerical compliance requirements as defined in section 7.4 for single-precision floating-point, section 9.3.9 for double-precision floating-point, and edge case behavior in section 7.5. This option includes the -cl-no-signed-zeros and -cl-mad-enable options.
Allow optimizations for floating-point arithmetic that assume that arguments and results are not NaNs or ∞. This option may violate the OpenCL numerical compliance requirements defined in section 7.4 for single-precision floating-point, section 9.3.9 for double-precision floating-point, and edge case behavior in section 7.5.
Sets the optimization options -cl-finite-math-only and -cl-unsafe-math-optimizations.
This allows optimizations for floating-point arithmetic that may violate the IEEE 754
standard and the OpenCL numerical compliance requirements defined in the specification in
section 7.4 for single-precision floating-point, section 9.3.9 for double-precision
floating-point, and edge case behavior in section 7.5. This option causes the preprocessor
macro __FAST_RELAXED_MATH__ to be defined in the OpenCL program.
Inhibit all warning messages.
Make all warnings into errors.
Determine the OpenCL C language version to use. A value for this option must be provided. Valid values are:
CL1.1 - Support all OpenCL C programs that use the OpenCL C language features defined in section 6 of the OpenCL 1.1 specification.
Calls to clBuildProgram with the -cl-std=CL1.1 option will fail
to build the program executable for any devices with CL_DEVICE_OPENCL_C_VERSION = OpenCL C 1.0.
If the -cl-std build option is not specified, the CL_DEVICE_OPENCL_C_VERSION is used to select the version of OpenCL C to be used when building the program executable for each device.
clBuildProgram returns CL_SUCCESS if the function is
executed successfully. Otherwise, it returns one of the following errors:
program is not a valid program object.
device_list is NULL
and num_devices is greater than zero, or if device_list is not NULL
and num_devices is zero.
pfn_notify is NULL
but user_data is not NULL.
device_list
are not in the list of devices associated with program.
program is created
with clCreateWithProgramWithBinary and
devices listed in device_list do not have a valid program binary loaded.
options are invalid.
device_list by a previous call to clBuildProgram for program has not
completed.
program is created with
clCreateProgramWithSource
and a compiler is not available i.e.
CL_DEVICE_COMPILER_AVAILABLE specified in the table of OpenCL Device Queries
for clGetDeviceInfo is set
to CL_FALSE.
clBuildProgram does not return until the build has
completed.
program.
public static int clCompileProgram(cl_program program, int num_devices, cl_device_id[] device_list, java.lang.String options, int num_input_headers, cl_program[] input_headers, java.lang.String[] header_include_names, BuildProgramFunction pfn_notify, java.lang.Object user_data)
Compiles a programs source for all the devices or a specific device(s) in the OpenCL context
associated with program.
cl_int
clCompileProgram
(
|
cl_programprogram, |
| cl_uintnum_devices, | |
| const cl_device_id*device_list, | |
| const char*options, | |
| cl_uintnum_input_heaaders, | |
| const cl_program*input_heaaders, | |
| const char**heaader_include_names, | |
| void(CL_CALLBACK *pfn_notify)( cl_program program, void *user_data), | |
void*user_data) |
program
The program object that is the compilation target.
device_list
A pointer to a list of devices associated with program. If
device_list is a NULL value, the compile is performed for
all devices associated with program. If device_list is a
non-NULL value, the compile is performed for devices specified in this list.
num_devices
The number of devices listed in device_list.
options
A pointer to a null-terminated string of characters that describes the compilation options to be used for building the program executable. The list of supported options is as described below.
num_input_headers
Specifies the number of programs that describe headers in the array
referenced by input_headers.
input_headers
An array of program embedded headers created with clCreateProgramWithSource.
header_include_names
An array that has a one to one correspondence
with input_headers. Each entry in
header_include_names specifies the include name used by
source in program that comes from an embedded header.
The corresponding entry in input_headers identifies the
program object which contains the header source to be used. The embedded
headers are first searched before the headers in the list of directories
specified by the -I compile option (as described in section 5.6.4.1).
If multiple entries in header_include_names refer to
the same header name, the first one encountered will be used.
pfn_notify
A function pointer to a notification routine. The notification routine
is a callback function that an application can register and which will
be called when the program executable has been built (successfully
or unsuccessfully). If pfn_notify is not NULL,
clCompileProgram does not need to wait for the
compiler to complete and can return immediately once the compilation
can begin. The compilation can begin if the context, program whose
sources are being compiled, list of devices, input headers, programs
that describe input headers and compiler options specified are all
valid and appropriate host and device resources needed to perform
the compile are available. If pfn_notify is NULL,
clCompileProgram does not return until the compiler
has completed. This callback function may be called asynchronously by
the OpenCL implementation. It is the application's responsibility to
ensure that the callback function is thread-safe.
user_data
Passed as an argument when pfn_notify is
called. user_data can be NULL.
Compiles a program's source for all the devices or a specific device(s)
in the OpenCL context associated with program. The
pre-processor runs before the program sources are compiled. The compiled
binary is built for all devices associated with program
or the list of devices specified. The compiled binary can be queried using
clGetProgramInfo(program,
CL_PROGRAM_BINARIES, ...) and can be specified to
clCreateProgramWithBinary
to create a new program object.
The compiler options are categorized as pre-processor options, options for math intrinsics, options that control optimization and miscellaneous options. This specification defines a standard set of options that must be supported by the OpenCL C compiler when building program executables online or offline. These may be extended by a set of vendor- or platform specific options.
These options control the OpenCL C preprocessor which is run on each program source before actual compilation.
-D options are processed in the order they are given in the options argument to
clBuildProgram or or clCompileProgram.
Predefine name as a macro, with definition 1.
The contents of definition are tokenized and processed as
if they appeared during translation phase three in a `#define' directive. In
particular, the definition will be truncated by embedded newline characters.
Add the directory dir to the list of directories to be
searched for header files.
Treat double precision floating-point constant as single precision constant.
This option controls how single precision and double precision denormalized numbers are handled. If specified as a build option, the single precision denormalized numbers may be flushed to zero; double precision denormalized numbers may also be flushed to zero if the optional extension for double precsion is supported. This is intended to be a performance hint and the OpenCL compiler can choose not to flush denorms to zero if the device supports single precision (or double precision) denormalized numbers.
This option is ignored for single precision numbers if the
device does not support single precision denormalized numbers
i.e. CL_FP_DENORM bit is not set in
CL_DEVICE_SINGLE_FP_CONFIG.
This option is ignored for double precision numbers if the device
does not support double precision or if it does support double
precison but CL_FP_DENORM bit is not set in
CL_DEVICE_DOUBLE_FP_CONFIG.
This flag only applies for scalar and vector single precision floating-point variables and computations on these floating-point variables inside a program. It does not apply to reading from or writing to image objects.
The -cl-fp32-correctly-rounded-divide-sqrt build option to
clBuildProgram or clCompileProgram
allows an application to specify that single precision floating-point divide
(x/y and 1/x) and sqrt used in the program source are correctly rounded.
If this build option is not specified, the minimum numerical accuracy of
single precision floating-point divide and sqrt are as defined in section
7.4 of the OpenCL specification.
This build option can only be specified if the
CL_FP_CORRECTLY_ROUNDED_DIVIDE_SQRT is set
in CL_DEVICE_SINGLE_FP_CONFIG (as defined in
in the table of allowed values for param_name for
clGetDeviceInfo) for
devices that the program is being build. clBuildProgram
or clCompileProgram will fail to compile the program for
a device if the -cl-fp32-correctly-rounded-divide-sqrt option is specified
and CL_FP_CORRECTLY_ROUNDED_DIVIDE_SQRT is not set for
the device.
These options control various sorts of optimizations. Turning on optimization flags makes the compiler attempt to improve the performance and/or code size at the expense of compilation time and possibly the ability to debug the program.
This option disables all optimizations. The default is optimizations are enabled.
The following options control compiler behavior regarding floating-point arithmetic. These options trade off between performance and correctness and must be specifically enabled. These options are not turned on by default since it can result in incorrect output for programs which depend on an exact implementation of IEEE 754 rules/specifications for math functions.
Allow a * b + c to be replaced by a mad. The
mad computes a * b + c with reduced accuracy. For
example, some OpenCL devices implement mad as truncate the result
of a * b before adding it to c.
Allow optimizations for floating-point arithmetic that ignore the signedness of
zero. IEEE 754 arithmetic specifies the distinct behavior of +0.0
and -0.0 values, which then prohibits simplification of expressions
such as x+0.0 or 0.0*x (even with -clfinite-math
only). This option implies that the sign of a zero result isn't significant.
Allow optimizations for floating-point arithmetic that (a) assume that arguments and results are valid, (b) may violate IEEE 754 standard and (c) may violate the OpenCL numerical compliance requirements as defined in section 7.4 for single precision and double precision floating-point, and edge case behavior in section 7.5. This option includes the -cl-no-signed-zeros and -cl-mad-enable options.
Allow optimizations for floating-point arithmetic that assume that arguments and results are not NaNs or ∞. This option may violate the OpenCL numerical compliance requirements defined in section 7.4 for single precision and double precision floating point, and edge case behavior in section 7.5.
Sets the optimization options -cl-finite-math-only and
-cl-unsafe-math-optimizations. This allows optimizations for floating-point
arithmetic that may violate the IEEE 754 standard and the OpenCL numerical
compliance requirements defined in the specification in section 7.4 for
single-precision and double precision floating-point, and edge case
behavior in section 7.5. This option causes the preprocessor macro
__FAST_RELAXED_MATH__ to be defined in the OpenCL program.
Inhibit all warning messages.
Make all warnings into errors.
Determine the OpenCL C language version to use. A value for this option must be provided. Valid values are:
CL1.1 - Support all OpenCL C programs that use the OpenCL C language features defined in section 6 of the OpenCL 1.1 specification.
CL1.2 - Support all OpenCL C programs that use the OpenCL C language features defined in section 6 of the OpenCL 1.2 specification.
Calls to clBuildProgram or clCompileProgram
with the -cl-std=CL1.1 option will fail to compile the program for any devices
with CL_DEVICE_OPENCL_C_VERSION = OpenCL C 1.0. Calls to
clBuildProgram or clCompileProgram with
the -cl-std=CL1.2 option will fail to compile the program for any devices with
CL_DEVICE_OPENCL_C_VERSION = OpenCL C 1.0 or OpenCL C 1.1.
If the -cl-std build option is not specified, the
CL_DEVICE_OPENCL_C_VERSION is used to select the version of OpenCL
C to be used when compiling the program for each device.
This option allows the compiler to store information about the arguments of a kernel(s) in the program executable. The argument information stored includes the argument name, its type, the address and access qualifiers used. Refer to description of clGetKernelArgInfo on how to query this information.
Create a library of compiled binaries specified
in input_programs argument to
clLinkProgram.
Allows the linker to modify the library behavior based on one or more link options (described in Program Linking Options, below) when this library is linked with a program executable. This option must be specified with the -create-library option.
OpenCL 1.2 extends how programs are compiled and linked to support the following:
clCompileProgram returns CL_SUCCESS if
the function is executed successfully. Otherwise, it returns one of the following errors:
program is not
a valid program object.
device_list
is NULL and num_devices is greater than zero, or if
device_list is not NULL and num_devices
is zero.
num_input_headers is
zero and header_include_names or input_headers
are not NULL or if num_input_headers is not zero and
header_include_names or input_headers are NULL.
pfn_notify is NULL
but user_data is not NULL.
device_list are not in the list of devices associated with
program.
options are invalid.
device_list
by a previous call to clCompileProgram or
clBuildProgram for program has not completed.
CL_DEVICE_COMPILER_AVAILABLE specified
in in the table of allowed values for param_name for
clGetDeviceInfo
is set to CL_FALSE.
clCompileProgram does not return until the compile has
completed.
program.
For example, consider the following program source:
| #include <foo.h> #include <mydir/myinc.h> __kernel void image_filter (int n, int m, __constant float *filter_weights, __read_only image2d_t src_image, __write_only image2d_t dst_image) { ... } |
This kernel includes two headers foo.h and mydir/myinc.h. The following describes how these headers can be passed as embedded headers in program objects:
| cl_program foo_pg = clCreateProgramWithSource(context, 1, &foo_header_src, NULL, &err); cl_program myinc_pg = clCreateProgramWithSource(context, 1, &myinc_header_src, NULL, &err); // let's assume the program source described above is given // by program_A and is loaded via clCreateProgramWithSource cl_program input_headers[2] = { foo_pg, myinc_pg }; char * input_header_names[2] = { "foo.h", "mydir/myinc.h" }; clCompileProgram(program_A, 0, NULL, // num_devices & device_list NULL, // compile_options 2, // num_input_headers input_headers, input_header_names, NULL, NULL); // pfn_notify & user_data |
public static cl_program clLinkProgram(cl_context context, int num_devices, cl_device_id[] device_list, java.lang.String options, int num_input_programs, cl_program[] input_programs, BuildProgramFunction pfn_notify, java.lang.Object user_data, int[] errcode_ret)
Links a set of compiled program objects and libraries for all the devices or a specific device(s) in the OpenCL context and creates an executable.
cl_program
clLinkProgram
(
|
cl_contextcontext, |
| cl_uintnum_devices, | |
| const cl_device_id*device_list, | |
| const char*options, | |
| cl_uintnum_input_programs, | |
| const cl_program*input_programs, | |
| void(CL_CALLBACK *pfn_notify) (cl_program program, void *user_data), | |
| void*user_data, | |
cl_int*errcode_ret) |
context
Must be a valid OpenCL context.
device_list
A pointer to a list of devices that are in context.
If device_list is a NULL value, the link is performed
for all devices associated with context for which a
compiled object is available. If device_list is a
non-NULL value, the compile is performed for devices specified in this
list for which a source has been loaded.
num_devices
The number of devices listed in device_list.
options
A pointer to a null-terminated string of characters that describes the link options to be used for building the program executable. See clBuildProgram for a list of supported compiler and linker options.
num_input_programs
Specifies the number of programs in array referenced by input_programs.
input_programs
An array of program objects that are compiled binaries or libraries
that are to be linked to create the program executable. For each device
in device_list or if device_list
is NULL the list of devices associated with context,
the following cases occur:
All programs specified by input_programs
contain a compiled binary or library for the device. In this case,
a link is performed to generate a program executable for this device.
None of the programs contain a compiled binary or library for that device. In this case, no link is performed and there will be no program executable generated for this device.
All other cases will return a
CL_INVALID_OPERATION error.
pfn_notify
A function pointer to a notification routine. The notification routine is a callback function that an application can register and which will be called when the program executable has been built (successfully or unsuccessfully).
If pfn_notify is not NULL,
clLinkProgram does not need to wait for the linker
to complete and can return immediately once the linking operation can
begin. Once the linker has completed, the pfn_notify
callback function is called which returns the program object returned
by clLinkProgram. The application can query the link
status and log for this program object. This callback function may be called
asynchronously by the OpenCL implementation. It is the application's
responsibility to ensure that the callback function is thread-safe.
If pfn_notify is NULL, clLinkProgram
does not return until the linker has completed.
user_data
Will be passed as an argument when pfn_notify is called.
user_data can be NULL.
clLinkProgram creates a new program object which
contains this executable. The executable binary can be queried using
clGetProgramInfo(program,
CL_PROGRAM_BINARIES, ...) and can be specified to
clCreateProgramWithBinary
to create a new program object.
The devices associated with the returned program object will be the list of devices
specified by device_list or if device_list
is NULL it will be the list of devices associated with context.
The linking operation can begin if the context, list of devices, input programs and
linker options specified are all valid and appropriate host and device resources
needed to perform the link are available. If the linking operation can begin,
clLinkProgram returns a valid non-zero program object.
If pfn_notify is NULL, the errcode_ret will
be set to CL_SUCCESS if the link operation was successful and
CL_LINK_FAILURE if there is a failure to link the compiled
binaries and/or libraries.
If pfn_notify is not NULL, clLinkProgram
does not have to wait until the linker to complete and can return
CL_SUCCESS in errcode_ret if the linking
operation can begin. The pfn_notify callback function will
return a CL_SUCCESS or CL_LINK_FAILURE
if the linking operation was successful or not.
Otherwise clLinkProgram returns a NULL program object with an
appropriate error in errcode_ret. The application should query
the linker status of this program object to check if the link was successful or not.
The list of errors that can be returned are:
context is not a valid context.
device_list
is NULL and num_devices is greater than zero, or if
device_list is not NULL and num_devices
is zero.
num_input_programs
is zero and input_programs is NULL or if
num_input_programs is zero and input_programs
is not NULL or if num_input_programs is not zero and
input_programs is NULL.
input_programs are not valid program objects.
pfn_notify is
NULL but user_data is not NULL.
device_list are not in the list of devices associated with
context.
options are invalid
device_list by a previous call to
clCompileProgram
or clBuildProgram
for program has not completed.
input_programs
argument above are not followed.
CL_DEVICE_LINKER_AVAILABLE specified
in the table of allowed values for param_name for
clGetDeviceInfo
is set to CL_FALSE.
public static int clUnloadPlatformCompiler(cl_platform_id platform)
Allows the implementation to release the resources allocated by the OpenCL compiler for <>platform.
cl_int
clUnloadPlatformCompiler
(
|
cl_platform_idplatform) |
This is a hint from the application and does not guarantee
that the compiler will not be used in the future or that the
compiler will actually be unloaded by the implementation. Calls to
clBuildProgram,
clCompileProgram,
or clLinkProgram after
clUnloadPlatformCompiler will reload the compiler, if necessary,
to build the appropriate program executable.
clUnloadPlatformCompiler returns CL_SUCCESS
if the function is executed successfully. Otherwise, it returns one of the following
errors:
platform is not a valid platform.
public static int clUnloadCompiler()
Allows the implementation to release the resources allocated by the OpenCL compiler.
cl_int
clUnloadCompiler
(
|
void) |
This is a hint from the application and does not guarantee that the compiler will not be used in the future or that the compiler will actually be unloaded by the implementation. Calls to clBuildProgram after clUnloadCompiler will reload the compiler, if necessary, to build the appropriate program executable.
This call currently always returns CL_SUCCESS.
public static int clGetProgramInfo(cl_program program, int param_name, long param_value_size, Pointer param_value, long[] param_value_size_ret)
Returns information about the program object.
cl_int
clGetProgramInfo
(
|
cl_programprogram, |
| cl_program_infoparam_name, | |
| size_tparam_value_size, | |
| void*param_value, | |
size_t*param_value_size_ret) |
program
Specifies the program object being queried.
param_name
Specifies the information to query. The list of supported param_name types and the information returned in param_value by clGetProgramInfo is described in the table below.
| cl_program_info | Return Type and Info. returned in param_value |
|---|---|
CL_PROGRAM_REFERENCE_COUNT
|
Return type: cl_uint
Return the The reference count returned should be considered immediately stale. It is unsuitable for general use in applications. This feature is provided for identifying memory leaks. |
CL_PROGRAM_CONTEXT
|
Return type: cl_context
Return the context specified when the program object is created |
CL_PROGRAM_NUM_DEVICES
|
Return type: cl_uint
Return the number of devices associated with |
CL_PROGRAM_DEVICES
|
Return type: cl_device_id[]
Return the list of devices associated with the program object. This can be the devices associated with context on which the program object has been created or can be a subset of devices that are specified when a progam object is created using clCreateProgramWithBinary. |
CL_PROGRAM_SOURCE
|
Return type: char[]
Return the program source code specified by clCreateProgramWithSource. The source string returned is a concatenation of all source strings specified to clCreateProgramWithSource with a null terminator. The concatenation strips any nulls in the original source strings.
The actual number of characters that
represents the program source code
including the null terminator is returned
in |
CL_PROGRAM_BINARY_SIZES
|
Return type: size_t[]
Returns an array that contains the size
in bytes of the program binary for each
device associated with |
CL_PROGRAM_BINARIES
|
Return type: unsigned char *[]
Return the program binaries for all
devices associated with
Each entry in this array is used by the
implementation as the location in
memory where to copy the program
binary for a specific device, if there is a
binary available. To find out which
device the program binary in the array
refers to, use the
If an entry value in the array is NULL, the implementation skips copying the program binary for the specific device identified by the array index. |
param_value
A pointer to memory where the appropriate result being queried is returned.
If param_value is NULL, it is ignored.
param_value_size
Used to specify the size in bytes of memory pointed to by param_value.
This size must be greater than or equal to the size of return type as described in the table above.
param_value_size_ret
Returns the actual size in bytes of data copied to param_value.
If param_value_size_ret is NULL, it is ignored.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
param_name is not valid, or if size in
bytes specified by param_value_size is less than the size of return type as described
in the table above and param_value is not NULL.
program is not a valid program object.
public static int clGetProgramBuildInfo(cl_program program, cl_device_id device, int param_name, long param_value_size, Pointer param_value, long[] param_value_size_ret)
Returns build information for each device in the program object.
cl_int
clGetProgramBuildInfo
(
|
cl_program program, |
| cl_device_id device, | |
| cl_program_build_info param_name, | |
| size_t param_value_size, | |
| void *param_value, | |
size_t *param_value_size_ret) |
program
Specifies the program object being queried.
device
Specifies the device for which build information is being queried.
device must be a valid device associated with program.
param_name
Specifies the information to query. The list of supported param_name types and the
information returned in param_value by clGetProgramBuildInfo is
described in the table below.
| cl_program_buid_info | Return Type and Info. returned in param_value |
|---|---|
CL_PROGRAM_BUILD_STATUS
|
Return type: cl_build_status
Returns the build status of
CL_BUILD_NONE. The build status returned if no build has
been performed on the specified program object for
CL_BUILD_ERROR. The build status returned if the last call
to clBuildProgram on the specified program object for
CL_BUILD_SUCCESS. The build status returned if the last call
to clBuildProgram on the
specified program object for
CL_BUILD_IN_PROGRESS. The build status returned if the last call
to clBuildProgram on the
specified program object for |
| CL_PROGRAM_BUILD_OPTIONS |
Return type: char[]
Return the build options specified by the
If build status of |
| CL_PROGRAM_BUILD_LOG |
Return type: char[]
Return the build log when
clBuildProgram was called
for |
param_value
A pointer to memory where the appropriate result being queried is returned.
If param_value is NULL, it is ignored.
param_value_size
Specifies the size in bytes of memory pointed to by param_value. This size
must be greater than or equal to the size of return type as described in the table above.
param_value_size_ret
Returns the actual size in bytes of data copied to param_value.
If param_value_size_ret is NULL, it is ignored.
Returns CL_SUCCESS if the function is executed successfully. Otherwise it returns the following:
device
is not in the list of devices associated with program.
param_name
is not valid, or if size in bytes specified by param_value_size
is less than size of return type
and param_value is not NULL.
program
is a not a valid program object.
public static cl_kernel clCreateKernel(cl_program program, java.lang.String kernel_name, int[] errcode_ret)
Creates a kernal object.
cl_kernel clCreateKernel
(
|
cl_program program, |
| const char*kernel_name, | |
cl_int*errcode_ret) |
program
A program object with a successfully built executable.
kernel_name
A function name in the program declared with the __kernel qualifier
errcode_ret
Returns an appropriate error code. If errcode_ret is NULL, no error code is returned.
A kernel is a function declared in a program. A kernel is identified by the __kernel qualifier applied to any function in a program. A kernel object encapsulates the specific __kernel function declared in a program and the argument values to be used when executing this __kernel function.
clCreateKernel returns a valid non-zero kernel object and errcode_ret
is set to CL_SUCCESS if
the kernel object is created successfully. Otherwise, it returns a NULL value with one of the
following error values returned in errcode_ret:
program is not a valid program object.
program.
kernel_name is not found in program.
__kernel function
given by kernel_name such as the number of arguments, the argument types are not the
same for all devices for which the program executable has been built.
kernel_name is NULL.
public static int clCreateKernelsInProgram(cl_program program, int num_kernels, cl_kernel[] kernels, int[] num_kernels_ret)
Creates kernel objects for all kernel functions in a program object.
cl_int
clCreateKernelsInProgram
(
|
cl_program program, |
| cl_uintnum_kernels, | |
| cl_kernel*kernels, | |
cl_uint*num_kernels_ret) |
program
A program object with a successfully built executable.
num_kernels
The size of memory pointed to by kernels specified as the number of cl_kernel entries.
kernels
The buffer where the kernel objects for kernels in program will be returned. If kernels is NULL, it is ignored. If kernels is not NULL, num_kernels must be greater than or equal to the number of kernels in program.
num_kernels_ret
The number of kernels in program. If num_kernels_ret is NULL, it is ignored.
Creates kernel objects for all kernel functions in program. Kernel objects are not created for any __kernel functions in program that do not have the same function definition across all devices
for which a program executable has been successfully built.
Kernel objects can only be created once you have a program object with a valid program source
or binary loaded into the program object and the program executable has been successfully built
for one or more devices associated with program. No changes to the program executable are
allowed while there are kernel objects associated with a program object. This means that calls to
clBuildProgram return CL_INVALID_OPERATION if there are kernel objects attached to a
program object. The OpenCL context associated with program will be the context associated
with kernel. The list of devices associated with program are the devices associated with kernel.
Devices associated with a program object for which a valid program executable has been built
can be used to execute kernels declared in the program object.
Returns CL_SUCCESS if the kernel objects are successfully allocated. Otherwise, it returns one of the following errors:
program is not a valid program object.
program.
kernels is not NULL
and num_kernels is less than the number of kernels in program.
public static int clRetainKernel(cl_kernel kernel)
Increments the kernel object reference count.
cl_int
clRetainKernel
(
|
cl_kernelkernel) |
clCreateKernel or clCreateKernelsInProgram do an implicit retain.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
kernel is not a valid kernel object.
public static int clReleaseKernel(cl_kernel kernel)
Decrements the kernel reference count.
cl_int
clReleaseKernel
(
|
cl_kernelkernel) |
The kernel object is deleted once the number of instances that are retained
to kernel become zero and the kernel object is no longer needed by any
enqueued commands that use kernel.
Returns CL_SUCCESS if the kernel objects are successfully alloctaed. Otherwise, it returns one of the following errors:
kernel is not a valid kernel object.
public static int clSetKernelArg(cl_kernel kernel, int arg_index, long arg_size, Pointer arg_value)
Used to set the argument value for a specific argument of a kernel.
cl_int
clSetKernelArg
(
|
cl_kernelkernel, |
| cl_uintarg_index, | |
| size_targ_size, | |
const void*arg_value) |
kernel
A valid kernel object.
arg_index
The argument index. Arguments to the kernel are referred by indices that go from 0 for the leftmost argument to n - 1, where n is the total number of arguments declared by a kernel.
arg_value
A pointer to data that should be used as the argument value for argument specified
by arg_index. The argument data pointed to by arg_value is copied and the arg_value pointer can therefore be reused by the application after clSetKernelArg returns. The argument value specified is the value used by all API calls that enqueue kernel (clEnqueueNDRangeKernel and
clEnqueueTask) until the argument value is changed by a call to clSetKernelArg for kernel.
If the argument is a memory object (buffer or image), the arg_value entry will be a
pointer to the appropriate buffer or image object. The memory object must be created with the context
associated with the kernel object. A NULL value can also be specified if the argument is a buffer
object in which case a NULL value will be used as the value for the argument declared as a
pointer to __global or __constant memory in the kernel. If the
argument is declared with the __local qualifier, the arg_value
entry must be NULL. If the argument is of type sampler_t, the arg_value
entry must be a pointer to the sampler object.
If the argument is declared to be a pointer of a built-in or user defined type with
the __global or __constant qualifier, the memory object specified as
argument value must be a buffer object (or NULL). If the argument is declared with the __constant
qualifier, the size in bytes of the memory object cannot exceed CL_DEVICE_MAX_CONSTANT_BUFFER_SIZE and the
number of arguments declared with the __constant qualifier cannot exceed
CL_DEVICE_MAX_CONSTANT_ARGS.
The memory object specified as argument value must be a 2D image object if the argument is
declared to be of type image2d_t. The memory object specified as argument value must
be a 3D image object if argument is declared to be of type image3d_t.
For all other kernel arguments, the arg_value entry must be a pointer to the actual
data to be used as argument value.
arg_size
Specifies the size of the argument value. If the argument is a memory object, the size is
the size of the buffer or image object type. For arguments declared with the __local
qualifier, the size specified will be the size in bytes of the buffer that must be allocated
for the __local argument. If the argument is of type sampler_t,
the arg_size value must be equal to sizeof(cl_sampler). For all other
arguments, the size will be the size of argument type.
A kernel object does not update the reference count for objects such as memory, sampler
objects specified as argument values by clSetKernelArg. Users may not rely on a kernel object
to retain objects specified as argument values to the kernel.
Implementations shall not allow cl_kernel objects to hold reference counts to cl_kernel arguments, because no
mechanism is provided for the user to tell the kernel to release that ownership right. If the kernel holds ownership
rights on kernel args, that would make it impossible for the user to tell with certainty when he may safely release
user allocated resources associated with OpenCL objects such as the cl_mem backing store used with
CL_MEM_USE_HOST_PTR.
An OpenCL API call is considered to be thread-safe if the internal state as managed by OpenCL remains consistent when called simultaneously by multiple host threads. OpenCL API calls that are thread-safe allow an application to call these functions in multiple host threads without having to implement mutual exclusion across these host threads i.e. they are also re-entrant-safe.
All OpenCL API calls are thread-safe except clSetKernelArg, which is safe to call
from any host thread, and is safe to call re-entrantly so long as concurrent calls operate on
different cl_kernel objects. However, the behavior of the cl_kernel object is undefined if
clSetKernelArg is called from multiple host threads on the same cl_kernel object at the same
time.
There is an inherent race condition in the design of OpenCL that occurs between setting a kernel argument and using the kernel with clEnqueueNDRangeKernel or clEnqueueTask. Another host thread might change the kernel arguments between when a host thread sets the kernel arguments and then enqueues the kernel, causing the wrong kernel arguments to be enqueued. Rather than attempt to share cl_kernel objects among multiple host threads, applications are strongly encouraged to make additional cl_kernel objects for kernel functions for each host thread.
clSetKernelArg returns CL_SUCCESS if the function is
executed successfully. Otherwise, it returns one of the following errors:
kernel is not a valid kernel object.
arg_index is not a valid argument index.
arg_value specified is NULL for an argument that is not
declared with the __local qualifier or vice-versa.
arg_value is not a valid memory object.
sampler_t when
the specified arg_value is not a valid sampler object.
arg_size does not match the size of the
data type for an argument that is not a memory object or if the argument is a memory object
and arg_size != sizeof(cl_mem) or if arg_size is zero
and the argument is declared with the __local
qualifier or if the argument is a sampler and arg_size != sizeof(cl_sampler).
| __kernel void image_filter (int n, int m, __constant float *filter_weights, __read_only image2d_t src_image, __write_only image2d_t dst_image) { ... } |
Argument index values for image_filter will be 0 for n, 1 for m, 2 for
filter_weights, 3 for src_image and 4 for dst_image.
public static int clSetKernelArgSVMPointer(cl_kernel kernel, int arg_index, Pointer arg_value)
Used to set a SVM pointer as the argument value for a specific argument of a kernel.
cl_int
clSetKernelArgSVMPointer
(
|
cl_kernel kernel, |
| cl_uint arg_index, | |
const void *arg_value) |
kernel
A valid kernel object.
arg_index
The argument index. Arguments to the kernel are
referred by indices that go from 0
for the leftmost argument to n - 1,
where n is the total
number of arguments declared by a kernel.
arg_value
A pointer to the SVM pointer that should be used as the argument value for
argument specified by arg_index.
The SVM pointer specified is the value used by all
API calls that enqueue kernel
(clEnqueueNDRangeKernel)
until the argument value is changed by a call to
clSetKernelArgSVMPointer
for kernel.
The SVM pointer can only be used for arguments that
are declared to be a pointer to global or constant
memory. The SVM pointer value must
be aligned according to the argument’s type. For
example, if the argument is declared to be
global float4 *p, the SVM pointer
value passed for p must
be at a minimum aligned to a
float4. The SVM pointer value
specified as the argument value can be the pointer returned by
clSVMAlloc
or can be a pointer + offset into the SVM region.
All OpenCL API calls are thread-safe except
clSetKernelArg
and clSetKernelArgSVMPointer.
clSetKernelArg
and clSetKernelArgSVMPointer are safe
to call from any host thread, and safe to call re-entrantly so long as concurrent
calls operate on different cl_kernel objects.
However, the behavior of the cl_kernel object is undefined if
clSetKernelArg
or clSetKernelArgSVMPointer
are called from multiple host threads on the same
cl_kernel object at the same time. Please note that there
are additional limitations as to which OpenCL APIs may be called
from OpenCL callback functions -- please see section 5.11.
(Please refer to the OpenCL glossary for the OpenCL definition of thread-safe.
This definition may be different from usage of the term in other contexts.)
There is an inherent race condition in the design of OpenCL that occurs between setting a kernel argument and using the kernel with clEnqueueNDRangeKernel. Another host thread might change the kernel arguments between when a host thread sets the kernel arguments and then enqueues the kernel, causing the wrong kernel arguments to be enqueued. Rather than attempt to share cl_kernel objects among multiple host threads, applications are strongly encouraged to make additional cl_kernel objects for kernel functions for each host thread.
clSetKernelArgSVMPointer returns CL_SUCCESS if the
function is executed successfully. Otherwise, it returns one of the following errors:
kernel
is not a valid kernel object.
arg_index
is not a valid argument index.
arg_value
specified is not a valid value.
clSetKernelArg, clCreateKernel, clCreateKernelsInProgram, clReleaseKernel, clRetainKernel, clGetKernelInfo, clGetKernelWorkGroupInfo
public static int clSetKernelExecInfo(cl_kernel kernel, int param_name, long param_value_size, Pointer param_value)
Used to pass additional information other than argument values to a kernel.
cl_int
clSetKernelExecInfo
(
|
cl_kernel kernel , |
| cl_kernel_exec_info param_name , | |
| size_t param_value_size , | |
const void
*param_value
)
|
kernel
Specifies the kernel object being queried.
param_name
Specifies the information to be passed to
kernel. The list of supported
param_name types and the corresponding values passed in
param_value is described in the table below.
param_value_size
Specifies the size in bytes of the memory pointed to by
param_value.
param_value
A pointer to memory where the appropriate values
determined by param_name are specified.
| cl_kernel_exec_info | Type | Description |
|---|---|---|
CL_KERNEL_EXEC_INFO_SVM_PTRS
|
void *[] |
SVM pointers used by a kernel which
are not passed as arguments to
These non-argument SVM pointers
must be specified using
|
CL_KERNEL_EXEC_INFO_SVM_-
FINE_GRAIN_SYSTEM
|
cl_bool |
This flag indicates whether the kernel
uses pointers that are fine grain
system SVM allocations. These fine
grain system SVM pointers may be
passed as arguments or defined in
SVM buffers that are passed as
argumentsto |
1. Coarse-grain or fine-grain buffer SVM pointers
used by a kernel which are not passed as a
kernel arguments must be specified using
clSetKernelExecInfo with
CL_KERNEL_EXEC_INFO_SVM_PTRS.
For example, if SVM buffer A contains a pointer to
another SVM buffer B, and the kernel dereferences
that pointer, then a pointer to B must either
be passed as an argument in the call to that
kernel or it must be made available to the kernel
using clSetKernelExecInfo.
For example, we might pass extra SVM pointers as follows:
clSetKernelExecInfo(kernel,
CL_KERNEL_EXEC_INFO_SVM_PTRS,
num_ptrs * sizeof(void *),
extra_svm_ptr_list);
Here num_ptrs specifies the number
of additional SVM pointers while
extra_svm_ptr_list specifies a
pointer to memory containing those SVM pointers.
When calling clSetKernelExecInfo with
CL_KERNEL_EXEC_INFO_SVM_PTRS to specify
pointers to non-argument SVM buffers as extra arguments
to a kernel, each of these pointers can
be the SVM pointer returned by
clSVMAlloc
or can be a pointer + offset into the SVM region.
It is sufficient to provide one pointer for each SVM buffer used.
2. CL_KERNEL_EXEC_INFO_SVM_FINE_GRAIN_SYSTEM
is used to indicate whether SVM
pointers used by a kernel will refer to system allocations or not.
CL_KERNEL_EXEC_INFO_SVM_FINE_GRAIN_SYSTEM =
CL_FALSE indicates that the
OpenCL implementation may assume that system pointers
are not passed as kernel arguments
and are not stored inside SVM allocations
passed as kernel arguments.
CL_KERNEL_EXEC_INFO_SVM_FINE_GRAIN_SYSTEM =
CL_TRUE indicates that the OpenCL
implementation must assume that system pointers might
be passed as kernel arguments and/or
stored inside SVM allocations passed as kernel arguments.
In this case, if the device to which
the kernel is enqueued does not support system SVM pointers,
clEnqueueNDRangeKernel will
return a CL_INVALID_OPERATION error.
If none of the devices in the context
associated with kernel support fine-grain
system SVM allocations, clSetKernelExecInfo
will return a CL_INVALID_OPERATION error.
If clSetKernelExecInfo has not been called
with a value for
CL_KERNEL_EXEC_INFO_SVM_FINE_GRAIN_SYSTEM
the default value is used for this kernel attribute.
The defaule value depends on whether the device on which
the kernel is enqueued supports fine-grain system SVM
allocations. If so, the default value used is
CL_TRUE (system pointers might
be passed); otherwise, the default is CL_FALSE.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
kernel
is not a valid kernel object.
param_name
is not valid, if param_value
is NULL or if the size
specified by param_value_size
is not valid.
param_name =
CL_KERNEL_EXEC_INFO_SVM_FINE_GRAIN_SYSTEM
and param_value = CL_TRUE
but no devices in context
associated with kernel support
fine-grain system SVM allocations.
clCreateKernel, clGetKernelInfo, clGetKernelArgInfo, clCreateKernelsInProgram, clSetKernelArg, clGetKernelWorkGroupInfo, clEnqueueNDRangeKernel
public static int clGetKernelInfo(cl_kernel kernel, int param_name, long param_value_size, Pointer param_value, long[] param_value_size_ret)
Returns information about the kernel object.
cl_int
clGetKernelInfo
(
|
cl_kernelkernel, |
| cl_kernel_infoparam_name, | |
| size_tparam_value_size, | |
| void*param_value, | |
size_t*param_value_size_ret) |
kernel
Specifies the kernel object being queried.
param_name
Specifies the information to query. The list of supported param_name types and the
information returned in param_value by clGetKernelInfo is described in the table below.
param_value
A pointer to memory where the appropriate result being queried is returned. If param_value is NULL, it is ignored.
param_value_size
Used to specify the size in bytes of memory pointed to by param_value.
This size must be greater than or equal to size of return type as described in the table below.
| cl_kernel_info | Return Type | Info. returned in param_value |
|---|---|---|
CL_KERNEL_FUNCTION_NAME
|
char[] | Return the kernel function name. |
CL_KERNEL_NUM_ARGS
|
cl_uint |
Return the number of arguments to kernel.
|
CL_KERNEL_REFERENCE_COUNT
|
cl_uint |
Return the The reference count returned should be considered immediately stale. It is unsuitable for general use in applications. This feature is provided for identifying memory leaks. |
CL_KERNEL_CONTEXT
|
cl_context |
Return the context associated with kernel.
|
CL_KERNEL_PROGRAM
|
cl_program |
Return the program object associated with kernel.
|
param_value_size_ret
the actual size in bytes of data copied to param_value. If param_value_size_ret is NULL, it is ignored.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
param_name is not valid, or if size
in bytes specified by param_value_size is less than the size of return type as
described in the table above and param_value is not NULL
kernel is not a valid kernel object.
public static int clGetKernelArgInfo(cl_kernel kernel, int arg_indx, int param_name, long param_value_size, Pointer param_value, long[] param_value_size_ret)
Returns information about the arguments of a kernel.
cl_int
clGetKernelArgInfo
(
|
cl_kernel kernel , |
| cl_uint arg_indx , | |
| cl_kernel_arg_info param_name , | |
| size_t param_value_size , | |
| void *param_value , | |
size_t
*param_value_size_ret
)
|
kernel
Specifies the kernel object being queried.
arg_indx
The argument index. Arguments to the kernel are referred by indices that
go from 0 for the leftmost argument to n - 1, where
n is the total number of arguments declared by a kernel.
param_name
Specifies the argument information to query. The list of supported
param_name types and the information returned in
param_value by clGetKernelArgInfo
is described in the table below.
param_value
A pointer to memory where the appropriate result being queried is returned.
If param_value is NULL, it is ignored.
param_value_size
Used to specify the size in bytes of memory pointed to by param_value.
This size must be > size of return type as described in the table below.
| cl_kernel_arg_info | Return Type | Info. returned in param_value |
|---|---|---|
CL_KERNEL_ARG_ADDRESS_QUALIFIER
|
cl_kernel_arg_- address_qualifier |
Returns the address qualifier specified for the argument given by
If no address qualifier is specified, the default address
qualifier which is |
CL_KERNEL_ARG_ACCESS_QUALIFIER
|
cl_kernel_arg_- access_qualifier |
Returns the access qualifier specified for the argument given by
If argument is not an image type,
|
CL_KERNEL_ARG_TYPE_NAME
|
char[] |
Returns the type name specified for the argument given
by |
CL_KERNEL_ARG_TYPE_QUALIFIER
|
cl_kernel_arg- type_qualifier |
Returns the type qualifier specified for the argument
given by
NOTE: |
CL_KERNEL_ARG_NAME
|
char[] |
Returns the name specified for the argument given by |
param_value_size_ret
Returns the actual size in bytes of data copied to param_value.
If param_value_size_ret is NULL, it is ignored.
Kernel argument information is only available if the program
object associated with kernel is created with
clCreateProgramWithSource
and the program executable is built with the -cl-kernel-arg-info
option specified in options argument to
clBuildProgram or
clCompileProgram.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
arg_indx
is not a valid argument index.
param_name
is not valid, or if size in bytes specified by
param_value_size is < size of return type as
described in the table above and param_value is not NULL
kernel
is not a valid kernel object.
public static int clGetKernelWorkGroupInfo(cl_kernel kernel, cl_device_id device, int param_name, long param_value_size, Pointer param_value, long[] param_value_size_ret)
Returns information about the kernel object that may be specific to a device.
cl_int
clGetKernelWorkGroupInfo
(
|
cl_kernelkernel, |
| cl_device_iddevice, | |
| cl_kernel_work_group_infoparam_name, | |
| size_tparam_value_size, | |
| void*param_value, | |
size_t*param_value_size_ret) |
kernel
Specifies the kernel object being queried.
device
Identifies a specific device in the list of devices associated with kernel. The list of devices
is the list of devices in the OpenCL context that is associated with kernel. If the list of devices
associated with kernel is a single device, device can be a NULL value.
param_name
Specifies the information to query. The list of supported param_name types and the
information returned in param_value by clGetKernelWorkGroupInfo is described in the table below.
param_value
A pointer to memory where the appropriate result being queried is returned. If param_value is NULL, it is ignored.
param_value_size
Used to specify the size in bytes of memory pointed to by param_value.
This size must be greater than or equal to size of return type as described in the table below.
| cl_kernel_work_group_info | Return Type | Info. returned in param_value |
|---|---|---|
CL_KERNEL_WORK_GROUP_SIZE
|
size_t |
This provides a mechanism for the
application to query the maximum work-group size
that can be used to execute a kernel on a
specific device given by device. The
OpenCL implementation uses the
resource requirements of the kernel
(register usage etc.) to determine what
this work-group size should be.
|
CL_KERNEL_COMPILE_WORK_GROUP_SIZE
|
size_t[3] |
Returns the work-group size specified
by the __attribute__((reqd_work_gr
oup_size(X, Y, Z))) qualifier.
See Function Qualifiers.
If the work-group size is not specified
using the above attribute qualifier (0, 0,
0) is returned.
|
CL_KERNEL_LOCAL_MEM_SIZE
|
cl_ulong |
Returns the amount of local memory in bytes being used by a kernel. This includes local memory that may be needed by an implementation to execute the kernel, variables declared inside the kernel with the __local address qualifier and local memory to be allocated for arguments to the kernel declared as pointers with the __local address qualifier and whose size is specified with clSetKernelArg. If the local memory size, for any pointer argument to the kernel declared with the __local address qualifier, is not specified, its size is assumed to be 0. |
CL_KERNEL_PREFERRED_WORK_GROUP_SIZE_MULTIPLE
|
size_t | Returns the preferred multiple of workgroup size for launch. This is a performance hint. Specifying a workgroup size that is not a multiple of the value returned by this query as the value of the local work size argument to clEnqueueNDRangeKernelwill not fail to enqueue the kernel for execution unless the work-group size specified is larger than the device maximum. |
CL_KERNEL_PRIVATE_MEM_SIZE
|
cl_ulong | Returns the minimum amount of private memory, in bytes, used by each workitem in the kernel. This value may include any private memory needed by an implementation to execute the kernel, including that used by the language built-ins and variable declared inside the kernel with the __private qualifier. |
param_value_size_ret
Returns the actual size in bytes of data copied to param_value. If param_value_size_ret is NULL, it is ignored.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
device is not in the list of devices
associated with kernel or if device is NULL but there is more than
one device associated with kernel.
param_name is not valid, or if size in
bytes specified by param_value_size is less than the size of return type as described in
the table above and param_value is not NULL.
kernel is a not a valid kernel object.
public static int clWaitForEvents(int num_events,
cl_event[] event_list)
Waits on the host thread for commands identified by event objects to complete.
cl_int
clWaitForEvents
(
|
cl_uintnum_events, |
const cl_event*event_list) |
event_list
The events specified in event_list act as synchronization points.
Waits on the host thread for commands identified by event objects in event_list to
complete. A command is considered complete if its execution status is CL_COMPLETE
or a negative value.
If the cl_khr_gl_event extension is enabled, event objects can also be used to reflect the status of an OpenGL sync object. The sync object in turn refers to a fence command executing in an OpenGL command stream. This provides another method of coordinating sharing of buffers and images between OpenGL and OpenCL.
Returns CL_SUCCESS if the execution status of all
events in event_list is CL_COMPLETE.
Otherwise, it returns one of the following errors:
num_events is zero or event_list is NULL..
event_list do
not belong to the same context.
event_list
are not valid event objects.
event_list is a negative integer value.
public static int clGetEventInfo(cl_event event, int param_name, long param_value_size, Pointer param_value, long[] param_value_size_ret)
Returns information about the event object.
cl_int
clGetEventInfo
(
|
cl_eventevent, |
| cl_event_infoparam_name, | |
| size_tparam_value_size, | |
| void*param_value, | |
size_t*param_value_size_ret) |
event
Specifies the event object being queried.
param_value
A pointer to memory where the appropriate result being queried is returned. If param_value is NULL, it is ignored.
param_value_size
Specifies the size in bytes of memory pointed to by param_value. This size must be greater than or equal to the size of the return type as described in the table below.
param_value_size_ret
Returns the actual size in bytes of data copied to param_value. If
param_value_size_ret is NULL, it is ignored.
param_name
Specifies the information to query. The list of supported param_name types and the information returned in param_value by clGetEventInfo is described in the table below:
| cl_event_info | Return Type | Information returned in param_value |
|---|---|---|
CL_EVENT_COMMAND_QUEUE
|
cl_command_queue |
Return the command-queue associated with event.
For user event objects, a NULL value is returned.
|
CL_EVENT_CONTEXT
|
cl_context |
Return the context associated with event.
|
CL_EVENT_COMMAND_TYPE
|
cl_command_type |
Return the command associated with event.
Can be one of the following values:
CL_COMMAND_NDRANGE_KERNEL |
CL_EVENT_COMMAND_ EXECUTION_STATUS
|
cl_int |
Return the execution status of the command identified by event. The valid values are:
CL_QUEUED (command has been enqueued in the command-queue), CL_SUBMITTED (enqueued command has been submitted by the host to the device associated with the command-queue), CL_RUNNING (device is currently executing this command), CL_COMPLETE (the command has completed), or Error code given by a negative integer value. (command was abnormally terminated – this may be caused by a bad memory access etc.) These error codes come from the same set of error codes that are returned from the platform or runtime API calls as return values or The error code values are negative, and event state values are positive. The event state values are ordered from the largest value (CL_QUEUED) for the first or initial state to the smallest value (CL_COMPLETE or negative integer value) for the last or complete state. The value of CL_COMPLETE and CL_SUCCESS are the same. |
CL_EVENT_REFERENCE_COUNT
|
cl_uint |
Return the event reference count. The reference count returned should be considered immediately stale. It is unsuitable for general use in applications. This feature is provided for identifying memory leaks.
|
Using clGetEventInfo to determine if a command identified by event has finished execution (i.e. CL_EVENT_COMMAND_EXECUTION_STATUS returns CL_COMPLETE) is not a synchronization point. There are no guarantees that the memory objects being modified by command associated with event will be visible to other enqueued commands.
Returns CL_SUCCESS if the function executed successfully, or one of the errors below:
param_name is not valid, or if size in
bytes specified by param_value_size is less than size of return type as described
in the table above and param_value is not NULL.
param_name
cannot be queried for event.
event is not a valid
event object.
public static cl_event clCreateUserEvent(cl_context context, int[] errcode_ret)
Creates a user event object.
cl_event clCreateUserEvent
(
|
cl_contextcontext, |
cl_int*errcode_ret) |
context
A valid OpenCL context used to create the user event object.
errcode_ret
Returns an appropriate error code. If errcode_ret is NULL,
no error code is returned.
User events allow applications to enqueue commands that wait on a user event to finish before the command is executed by the device.
The execution status of the user event object created is set to CL_SUBMITTED.
Returns a valid non-zero buffer object and errcode_ret is set to CL_SUCCESS if
the user event object is created successfully. Otherwise, it returns a NULL value with one of the
following error values returned in errcode_ret:
context is not a valid context.
public static int clRetainEvent(cl_event event)
Increments the event reference count.
cl_int
clRetainEvent
(
|
cl_eventevent) |
event
Event object being retained.
The OpenCL commands that return an event perform an implicit retain.
Returns CL_SUCCESS if the function executed successfully, or one of the errors below:
event is not a valid event object.
public static int clReleaseEvent(cl_event event)
Decrements the event reference count.
cl_int
clReleaseEvent
(
|
cl_eventevent) |
event
Event object being released.
Decrements the event reference count. The event object is deleted once the reference count becomes zero, the specific command identified by this event has completed (or terminated) and there are no commands in the command-queues of a context that require a wait for this event to complete.
Returns CL_SUCCESS if the function executed successfully, or one of the errors below:
event is not a valid event object.
public static int clSetUserEventStatus(cl_event event, int execution_status)
Sets the execution status of a user event object.
cl_mem clSetUserEventStatus
(
|
cl_eventevent, |
cl_intexecution_status) |
event
A user event object created using clCreateUserEvent.
execution_status
Specifies the new execution status to be set and can be CL_COMPLETE or a negative integer value
to indicate an error. A negative integer value causes all enqueued commands that wait on this user event
to be terminated. clSetUserEventStatus can only be called once to change the execution
status of event.
Enqueued commands that specify user events in the event_wait_list argument of
clEnqueue*** commands must ensure that the status of these user events being waited on are
set using clSetUserEventStatus before any OpenCL APIs that release OpenCL objects except for
event objects are called; otherwise the behavior is undefined.
Returns CL_SUCCESS if the function was executed successfully. Otherwise, it returns one of the following errors
event is not a valid user event.
execution_status is not CL_COMPLETE
or a negative integer value.
execution_status for
event has already been changed by a previous call to
clSetUserEventStatus.
For example, the following code sequence will result in undefined behavior of clReleaseMemObject.
| ev1 = clCreateUserEvent(ctx, NULL); clEnqueueWriteBuffer(cq, buf1, CL_FALSE, ..., 1, &ev1, NULL; clEnqueueWriteBuffer(cq, buf2, CL_FALSE,...); clReleaseMemObject(buf2); clSetUserEventStatus(ev1, CL_COMPLETE); |
The following code sequence, however, works correctly.
| ev1 = clCreateUserEvent(ctx, NULL); clEnqueueWriteBuffer(cq, buf1, CL_FALSE, ..., 1, &ev1, NULL; clEnqueueWriteBuffer(cq, buf2, CL_FALSE,...); clSetUserEventStatus(ev1, CL_COMPLETE); clReleaseMemObject(buf2); |
public static int clSetEventCallback(cl_event event, int command_exec_callback_type, EventCallbackFunction pfn_notify, java.lang.Object user_data)
Registers a user callback function for a specific command execution status.
cl_int clSetEventCallback
(
|
cl_eventevent, |
| cl_int command_exec_callback_type , | |
| void (CL_CALLBACK *pfn_event_notify) (cl_event event, cl_int event_command_exec_status, void *user_data), | |
void*user_data) |
event
A valid event object.
command_exec_callback_type
The command execution status for which the callback is registered. The command execution callback value for which a callback can be registered is CL_COMPLETE. There is no guarantee that the callback functions registered for various execution status values for an event will be called in the exact order that the execution status of a command changes.
The callback function registered for a command_exec_callback_type value of
CL_COMPLETE will be called when the command has completed successfully or is abnormally terminated.
pfn_event_notify
The event callback function that can be registered by the application. This callback function may be called asynchronously by the OpenCL implementation. It is the application's responsibility to ensure that the callback function is thread-safe. The parameters to this callback function are:
event: the event object for which the callback function is invoked.
event_command_exec_status: the execution status of command for which
this callback function is invoked. See the table of values for
clGetEventInfoparam_value for the command execution status values. If the callback
is
called as the result of the command associated with event being abnormally terminated, an
appropriate error code for the error that caused the termination will be passed to
event_command_exec_status instead.
user_data: a pointer to user supplied data.
user_data
Will be passed as the user_data argument when pfn_notify
is called. user_data can be NULL.
The registered callback function will be called when the execution status of command associated with
event changes to the execution status specified by command_exec_status.
Each call to clSetEventCallback registers the specified user callback function on a
callback stack associated with event. The order in which the registered user callback
functions are called is undefined.
All callbacks registered for an event object must be called. All enqueued callbacks shall be called before the event object is destroyed. Callbacks must return promptly. The behavior of calling expensive system routines, OpenCL API calls to create contexts or command-queues, or blocking OpenCL operations from the following list below, in a callback is undefined.
If an application needs to wait for completion of a routine from the above l ist in a callback, please use the non-blocking form of the function, and assign a completion callback to it to do the remainder of your work. Note that when a callback (or other code) enqueues commands to a command-queue, the commands are not required to begin execution until the queue is flushed. In standard usage, blocking enqueue calls serve this role by implicitly flushing the queue. Since blocking calls are not permitted in callbacks, those callbacks that enqueue commands on a command queue should either call clFlush on the queue before returning or arrange for clFlush to be called later on another thread.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
event is not a valid event object.
pfn_event_notify is NULL or if
command_exec_callback_type is not CL_COMPLETE.
public static int clGetEventProfilingInfo(cl_event event, int param_name, long param_value_size, Pointer param_value, long[] param_value_size_ret)
Returns profiling information for the command associated with event if profiling is enabled.
cl_int
clGetEventProfilingInfo
(
|
cl_eventevent, |
| cl_profiling_infoparam_name, | |
| size_tparam_value_size, | |
| void*param_value, | |
size_t*param_value_size_ret) |
event
Specifies the event object.
param_name
Specifies the profiling data to query. The list of supported param_name types and the information returned in param_value by clGetEventProfilingInfo is described in the table of parameter queries below.
param_value_size
Specifies the size in bytes of memory pointed to by param_value.
This size must be greater than or equal to the size of return type as described in the table bolow.
param_value
A pointer to memory where the appropriate result being queried is returned. If
param_value is NULL, it is ignored.
param_value_size_ret
Returns the actual size in bytes of data copied to param_value. If
param_value_size_ret is NULL, it is ignored.
The following is a table of clGetEventProfilingInfo parameter queries
| cl_profiling_info | Return Type | Info. returned in param_value |
|---|---|---|
CL_PROFILING_COMMAND_QUEUED
|
cl_ulong |
A 64-bit value that describes the current
device time counter in nanoseconds when
the command identified by event is
enqueued in a command-queue by the
host.
|
CL_PROFILING_COMMAND_SUBMIT
|
cl_ulong |
A 64-bit value that describes the current
device time counter in nanoseconds when
the command identified by event that has
been enqueued is submitted by the host to
the device associated with the command-queue.
|
CL_PROFILING_COMMAND_START
|
cl_ulong |
A 64-bit value that describes the current
device time counter in nanoseconds when
the command identified by event starts
execution on the device.
|
CL_PROFILING_COMMAND_END
|
cl_ulong |
A 64-bit value that describes the current
device time counter in nanoseconds when
the command identified by event has
finished execution on the device.
|
The unsigned 64-bit values returned can be used to measure the time in nano-seconds consumed by OpenCL commands.
OpenCL devices are required to correctly track time across changes in device frequency and
power states. The CL_DEVICE_PROFILING_TIMER_RESOLUTION specifies the resolution of
the timer i.e. the number of nanoseconds elapsed before the timer is incremented.
Event objects can be used to capture profiling information that measure execution time of a
command. Profiling of OpenCL commands can be enabled either by using a command-queue
created with CL_QUEUE_PROFILING_ENABLE flag set in properties argument to
clCreateCommandQueue.
Returns CL_SUCCESS if the function is executed successfully and the profiling information has been recorded. Otherwise, it returns one of the following errors:
event is not CL_COMPLETE or if event is a user event
object.
param_name is not valid, or if size in bytes
specified by param_value_size is less than the size of return type as described in the above
table and param_value is not NULL.
event is a not a valid event object.
public static int clFlush(cl_command_queue command_queue)
Issues all previously queued OpenCL commands in a command-queue to the device associated with the command-queue.
cl_int
clFlush
(
|
cl_command_queuecommand_queue) |
Issues all previously queued OpenCL commands in command_queue to the device associated
with command_queue.
clFlush only guarantees that all queued commands to command_queue
get issued to the appropriate device. There is no guarantee that they will be complete after
clFlush returns.
Any blocking commands queued in a command-queue perform an implicit flush of the command-queue.
These blocking commands are
clEnqueueReadBuffer,
clEnqueueReadBufferRect, or
clEnqueueReadImage with
blocking_read set to CL_TRUE;
clEnqueueWriteBuffer,
clEnqueueWriteBufferRect, or
clEnqueueWriteImage with
blocking_write set to CL_TRUE;
clEnqueueMapBuffer or
clEnqueueMapImage with
blocking_map set to CL_TRUE;
or clWaitForEvents.
To use event objects that refer to commands enqueued in a command-queue as event objects to
wait on by commands enqueued in a different command-queue, the application must call a
clFlush or any blocking commands that perform an implicit flush of the command-queue where
the commands that refer to these event objects are enqueued.
Returns CL_SUCCESS if the function call was executed successfully. Otherwise, it returns one of the following:
command_queue is not a valid command-queue.
public static int clFinish(cl_command_queue command_queue)
Blocks until all previously queued OpenCL commands in a command-queue are issued to the associated device and have completed.
cl_int
clFinish
(
|
cl_command_queuecommand_queue) |
Blocks until all previously queued OpenCL commands in command_queue are issued to the
associated device and have completed.
clFinish does not return until all queued commands in
command_queue have been processed and completed. clFinish is also a synchronization point.
Returns CL_SUCCESS if the function call was executed successfully. Otherwise, it returns one of the following:
command_queue is not a valid command-queue.
public static int clEnqueueReadBuffer(cl_command_queue command_queue, cl_mem buffer, boolean blocking_read, long offset, long cb, Pointer ptr, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueue commands to read from a buffer object to host memory.
cl_int
clEnqueueReadBuffer
(
|
cl_command_queuecommand_queue, |
| cl_membuffer, | |
| cl_boolblocking_read, | |
| size_toffset, | |
| size_tcb, | |
| void*ptr, | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
cl_event*event) |
command_queue
Refers to the command-queue in which the read command will be
queued. command_queue and buffer must be created with the same OpenCL context.
buffer
Refers to a valid buffer object.
blocking_read
Indicates if the read operations are blocking or non-blocking. If blocking_read is CL_TRUE i.e. the read command is blocking, clEnqueueReadBuffer does not return until the buffer data has been read and copied into memory pointed to by ptr.
If blocking_read is CL_FALSE i.e. the read command is non-blocking, clEnqueueReadBuffer
queues a non-blocking read command and returns. The contents of the buffer that ptr points to
cannot be used until the read command has completed. The event argument returns an event
object which can be used to query the execution status of the read command. When the read
command has completed, the contents of the buffer that ptr points to can be used by the
application.
offset
The offset in bytes in the buffer object to read from.
cb
The size in bytes of data being read.
ptr
The pointer to buffer in host memory where data is to be read into.
event_wait_list
,
num_events_in_wait_list
event_wait_list and num_events_in_wait_list specify events that need to complete before this particular command can be executed. If event_wait_list is NULL, then this particular command
does not wait on any event to complete. If event_wait_list is NULL, num_events_in_wait_list must be 0. If event_wait_list is not NULL, the list of events pointed to by event_wait_list must be valid and num_events_in_wait_list must be greater than 0. The events specified in event_wait_list act as synchronization points. The context associated with events in event_wait_list and command_queue must be the same.
event
Returns an event object that identifies this particular read command and can be used
to query or queue a wait for this particular command to complete. event can be NULL in which
case it will not be possible for the application to query the status of this command or queue a
wait for this command to complete.
Calling clEnqueueReadBuffer to read a region of the buffer object with the ptr argument value
set to host_ptr + offset, where host_ptr is a pointer to the memory region specified when the
buffer object being read is created with CL_MEM_USE_HOST_PTR, must meet the following
requirements in order to avoid undefined behavior:
clEnqueueReadBuffer returns CL_SUCCESS if the function is
executed successfully. Otherwise, it returns one of the following errors:
command_queue is not a valid command-queue.
command_queue and buffer are not the same or if the context associated with command_queue and events in
event_wait_list are not the same.
buffer is not a valid buffer object.
offset, cb) is out of bounds or if ptr is a NULL value.
event_wait_list is NULL and
num_events_in_wait_list greater than 0, or event_wait_list is not NULL and num_events_in_wait_list is 0, or if event objects in event_wait_list are not valid events.
buffer is a sub-buffer object and offset
specified when the sub-buffer object is created is not aligned to CL_DEVICE_MEM_BASE_ADDR_ALIGN value for device associated with
queue.
event_wait_list is a negative integer value.
buffer.
java.lang.IllegalArgumentException - If blocking_read==false and
the given Pointer is not a Pointer to a direct buffer.public static int clEnqueueReadBufferRect(cl_command_queue command_queue, cl_mem buffer, boolean blocking_read, long[] buffer_offset, long[] host_offset, long[] region, long buffer_row_pitch, long buffer_slice_pitch, long host_row_pitch, long host_slice_pitch, Pointer ptr, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueue commands to read from a rectangular region from a buffer object to host memory.
cl_int
clEnqueueReadBufferRect
(
|
cl_command_queuecommand_queue, |
| cl_membuffer, | |
| cl_boolblocking_read, | |
| const size_tbuffer_origin[3], | |
| const size_thost_origin[3], | |
| const size_tregion[3], | |
| size_tbuffer_row_pitch, | |
| size_tbuffer_slice_pitch, | |
| size_thost_row_pitch, | |
| size_thost_slice_pitch, | |
| void*ptr, | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
cl_event*event) |
command_queue
Refers to the command-queue in which the read command will be
queued. command_queue and buffer must be created with the same OpenCL context.
buffer
Refers to a valid buffer object.
blocking_read
Indicates if the read operations are blocking or non-blocking. If blocking_read is CL_TRUE i.e. the read command is blocking, clEnqueueReadBufferRect does not return until the buffer data has been read and copied into memory pointed to by ptr.
If blocking_read is CL_FALSE i.e. the read command is non-blocking, clEnqueueReadBufferRect
queues a non-blocking read command and returns. The contents of the buffer that ptr points to
cannot be used until the read command has completed. The event argument argument returns an event object which can be used to query the execution status of the read command. When the read command has completed, the contents of the buffer that ptr points to can be used by the application.
buffer_origin
The (x, y, z) offset in the memory region associated with buffer. For a 2D rectangle region, the z value given by buffer_origin[2] should be 0. The offset in bytes is computed as buffer_origin[2] * buffer_slice_pitch + buffer_origin[1] * buffer_row_pitch + buffer_origin[0].
host_origin
The (x, y, z) offset in the memory region pointed to by ptr. For a 2D rectangle region, the z value given by host_origin[2] should be 0. The offset in bytes is computed as host_origin[2] * host_slice_pitch + host_origin[1] * host_row_pitch + host_origin[0].
region
The (width, height, depth) in bytes of the 2D or 3D rectangle being read or written. For a 2D rectangle copy, the depth value given by region[2] should be 1.
buffer_row_pitch
The length of each row in bytes to be used for the memory region associated with buffer. If buffer_row_pitch is 0, buffer_row_pitch is computed as region[0].
buffer_slice_pitch
The length of each 2D slice in bytes to be used for the memory region associated with buffer. If buffer_slice_pitch is 0, buffer_slice_pitch is computed as region[1] * buffer_row_pitch.
host_row_pitch
The length of each row in bytes to be used for the memory region pointed to by ptr. If host_row_pitch is 0, host_row_pitch is computed as region[0].
host_slice_pitch
The length of each 2D slice in bytes to be used for the memory region pointed to by ptr. If host_slice_pitch is 0, host_slice_pitch is computed as region[1] * host_row_pitch.
ptr
The pointer to buffer in host memory where data is to be read into.
event_wait_list
,
num_events_in_wait_list
event_wait_list and num_events_in_wait_list specify events that need to complete before this particular command can be executed. If event_wait_list is NULL, then this particular command
does not wait on any event to complete. If event_wait_list is NULL, num_events_in_wait_list must be 0. If event_wait_list is not NULL, the list of events pointed to by event_wait_list must be valid and num_events_in_wait_list must be greater than 0. The events specified in event_wait_list act as synchronization points. The context associated with events in event_wait_list and command_queue must be the same.
event
Returns an event object that identifies this particular read command and can be used
to query or queue a wait for this particular command to complete. event can be NULL in which
case it will not be possible for the application to query the status of this command or queue a
wait for this command to complete.
Calling clEnqueueReadBufferRect to read a region of the buffer object with the
ptr argument value set to host_ptr and host_origin,
buffer_origin values are the same, where host_ptr is a pointer to the
memory region specified when the buffer object being read is created with CL_MEM_USE_HOST_PTR, must meet the
same requirements given for clEnqueueReadBuffer.
clEnqueueReadBufferRect returns CL_SUCCESS if the function is
executed successfully. Otherwise, it returns one of the following errors:
command_queue is not a valid command-queue.
command_queue
and buffer are not the same or if the context associated with command_queue
and events in event_wait_list are not the same.
buffer is not a valid buffer object.
buffer_origin, region) is out of bounds.
event_wait_list is NULL and
num_events_in_wait_list greater than 0, or event_wait_list is not NULL and num_events_in_wait_list is 0, or if event objects in event_wait_list are not valid events.
buffer is a sub-buffer object and offset specified when the sub-buffer object is created is not aligned to CL_DEVICE_MEM_BASE_ADDR_ALIGN value for device associated with queue.
event_wait_list is a negative integer value.
buffer.
public static int clEnqueueWriteBuffer(cl_command_queue command_queue, cl_mem buffer, boolean blocking_write, long offset, long cb, Pointer ptr, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueue commands to write to a buffer object from host memory.
cl_int
clEnqueueWriteBuffer
(
|
cl_command_queuecommand_queue, |
| cl_membuffer, | |
| cl_boolblocking_write, | |
| size_toffset, | |
| size_tcb, | |
| const void*ptr, | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
cl_event*event) |
command_queue
Refers to the command-queue in which the write command will be
queued. command_queue and buffer must be created with the same OpenCL context.
buffer
Refers to a valid buffer object.
blocking_write
Indicates if the write operations are blocking or nonblocking.
If blocking_write is CL_TRUE, the OpenCL implementation copies the data referred to by ptr
and enqueues the write operation in the command-queue. The memory pointed to by ptr can be
reused by the application after the clEnqueueWriteBuffer call returns.
If blocking_write is CL_FALSE, the OpenCL implementation will use ptr to perform a nonblocking
write. As the write is non-blocking the implementation can return immediately. The
memory pointed to by ptr cannot be reused by the application after the call returns. The event
argument returns an event object which can be used to query the execution status of the write
command. When the write command has completed, the memory pointed to by ptr can then be
reused by the application.
offset
The offset in bytes in the buffer object to write to.
cb
The size in bytes of data being written.
ptr
The pointer to buffer in host memory where data is to be written from.
event_wait_list
,
num_events_in_wait_list
event_wait_list and num_events_in_wait_list specify events that need to complete before this particular command can be executed. If event_wait_list is NULL, then this particular command
does not wait on any event to complete. If event_wait_list is NULL, num_events_in_wait_list
must be 0. If event_wait_list is not NULL, the list of events pointed to by event_wait_list must
be valid and num_events_in_wait_list must be greater than 0. The events specified in
event_wait_list act as synchronization points. The context associated with events in
event_wait_list and command_queue must be the same.
event
Returns an event object that identifies this particular write command and can be used
to query or queue a wait for this particular command to complete. event can be NULL in which
case it will not be possible for the application to query the status of this command or queue a
wait for this command to complete.
Calling clEnqueueWriteBuffer to update the latest bits in a region of the buffer object with
the ptr argument value set to host_ptr + offset, where host_ptr
is a pointer to the memory region specified when the buffer object being written is created with CL_MEM_USE_HOST_PTR,
must meet the following requirements in order to avoid undefined behavior:
clEnqueueWriteBuffer returns CL_SUCCESS if the function is
executed successfully. Otherwise, it returns one of the following errors:
command_queue is not a valid command-queue.
command_queue and buffer are
not the same or if the context associated with command_queue and events in
event_wait_list are not the same.
buffer is not a valid buffer object.
offset,
cb) is out of bounds or if ptr is a NULL value.
event_wait_list is NULL and
num_events_in_wait_list greater than 0, or event_wait_list is not NULL
and num_events_in_wait_list is 0, or if event objects in event_wait_list are not valid events.
buffer is a sub-buffer object and offset
specified when the sub-buffer object is created is not aligned to CL_DEVICE_MEM_BASE_ADDR_ALIGN value for device associated
with queue.
event_wait_list is a negative integer value.
buffer.
public static int clEnqueueWriteBufferRect(cl_command_queue command_queue, cl_mem buffer, boolean blocking_write, long[] buffer_offset, long[] host_offset, long[] region, long buffer_row_pitch, long buffer_slice_pitch, long host_row_pitch, long host_slice_pitch, Pointer ptr, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueue commands to write a rectangular region to a buffer object from host memory.
cl_int
clEnqueueWriteBufferRect
(
|
cl_command_queuecommand_queue, |
| cl_membuffer, | |
| cl_boolblocking_write, | |
| const size_tbuffer_origin[3], | |
| const size_thost_origin[3], | |
| const size_tregion[3], | |
| size_tbuffer_row_pitch, | |
| size_tbuffer_slice_pitch, | |
| size_thost_row_pitch, | |
| size_thost_slice_pitch, | |
| void*ptr, | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
cl_event*event) |
command_queue
Refers to the command-queue in which the write command will be
queued. command_queue and buffer must be created with the same OpenCL context.
buffer
Refers to a valid buffer object.
blocking_write
Indicates if the write operations are blocking or non-blocking. If blocking_write is CL_TRUE, the OpenCL implementation copies the data referred to by ptr
and enqueues the write operation in the command-queue. The memory pointed to by ptr can be
reused by the application after the clEnqueueWriteBufferRect call returns.
If blocking_write is CL_FALSE, the OpenCL implementation will use ptr to perform a nonblocking write. As the write is non-blocking the implementation can return immediately. The memory pointed to by ptr cannot be reused by the application after the call returns. The event argument returns an event object which can be used to query the execution status of the write command. When the write command has completed, the memory pointed to by ptr can then be
reused by the application.
buffer_origin
The (x, y, z) offset in the memory region associated with buffer. For a 2D rectangle region, the z value given by buffer_origin[2] should be 0. The offset in bytes is computed as buffer_origin[2] * buffer_slice_pitch + buffer_origin[1] * buffer_row_pitch + buffer_origin[0].
host_origin
The (x, y, z) offset in the memory region pointed to by ptr. For a 2D rectangle region, the z value given by host_origin[2] should be 0. The offset in bytes is computed as host_origin[2] * host_slice_pitch + host_origin[1] * host_row_pitch + host_origin[0].
region
The (width, height, depth) in bytes of the 2D or 3D rectangle being read or written. For a 2D rectangle copy, the depth value given by region[2] should be 1.
buffer_row_pitch
The length of each row in bytes to be used for the memory region associated with buffer. If buffer_row_pitch is 0, buffer_row_pitch is computed as region[0].
buffer_slice_pitch
The length of each 2D slice in bytes to be used for the memory region associated with buffer. If buffer_slice_pitch is 0, buffer_slice_pitch is computed as region[1] * buffer_row_pitch.
host_row_pitch
The length of each row in bytes to be used for the memory region pointed to by ptr. If host_row_pitch is 0, host_row_pitch is computed as region[0].
host_slice_pitch
The length of each 2D slice in bytes to be used for the memory region pointed to by ptr. If host_slice_pitch is 0, host_slice_pitch is computed as region[1] * host_row_pitch.
ptr
The pointer to buffer in host memory where data is to be written from.
event_wait_list
,
num_events_in_wait_list
event_wait_list and num_events_in_wait_list specify events that need to complete before this particular command can be executed. If event_wait_list is NULL, then this particular command
does not wait on any event to complete. If event_wait_list is NULL, num_events_in_wait_list must be 0. If event_wait_list is not NULL, the list of events pointed to by event_wait_list must be valid and num_events_in_wait_list must be greater than 0. The events specified in event_wait_list act as synchronization points. The context associated with events in event_wait_list and command_queue must be the same.
event
Returns an event object that identifies this particular write command
and can be used to query or queue a wait for this particular command to
complete. event can be NULL in which
case it will not be possible for the application to query the status of
this command or queue a wait for this command to complete.
Calling clEnqueueWriteBufferRect to update the latest bits in a region of the buffer object with the ptr argument value set to host_ptr and host_origin, buffer_origin values are the same, where host_ptr is a pointer to the memory region specified when the buffer object being written is created with CL_MEM_USE_HOST_PTR, must meet the following requirements in order to avoid undefined behavior:
buffer_origin region) contains the latest bits when the enqueued write command begins execution.
clEnqueueWriteBufferRect returns CL_SUCCESS if the function is
executed successfully. Otherwise, it returns one of the following errors:
command_queue is not a valid command-queue.
command_queue and buffer are not the same or if the context associated with command_queue and events in
event_wait_list are not the same.
buffer is not a valid buffer object.
buffer_origin, region) is out of bounds or if ptr is a NULL value.
event_wait_list is NULL and
num_events_in_wait_list greater than 0, or event_wait_list is not NULL and num_events_in_wait_list is 0, or if event objects in event_wait_list are not valid events.
buffer is a sub-buffer object and offset specified when the sub-buffer object is created is not aligned to CL_DEVICE_MEM_BASE_ADDR_ALIGN value for device associated with queue.
event_wait_list is a negative integer value.
buffer.
public static int clEnqueueFillBuffer(cl_command_queue command_queue, cl_mem buffer, Pointer pattern, long pattern_size, long offset, long size, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command to fill a buffer object with a pattern of a given pattern size.
cl_int
clEnqueueFillBuffer
(
|
cl_command_queue command_queue , |
| cl_mem buffer , | |
| const void *pattern , | |
| size_t pattern_size , | |
| size_t offset , | |
| size_t size , | |
| cl_uint num_events_in_wait_list , | |
| const cl_event *event_wait_list , | |
cl_event
*event
)
|
command_queue
Refers to the command-queue in which the fill command will be queued.
The OpenCL context associated with command_queue
and buffer must be the same.
buffer
A valid buffer object.
pattern
A pointer to the data pattern of size pattern_size
in bytes. pattern will be used to fill a region
in buffer starting at offset
and is size bytes in size. The data pattern
must be a scalar or vector integer or floating-point data type. For
example, if buffer is to be filled with a pattern of
float4 values, then pattern will be a pointer
to a cl_float4 value and pattern_size
will be sizeof(cl_float4). The maximum value of
pattern_size is the size of the largest integer
or floating-point vector data type supported by the OpenCL device.
The memory associated with pattern can be reused or
freed after the function returns.
offset
The location in bytes of the region being filled in buffer
and must be a multiple of pattern_size.
size
The size in bytes of region being filled in buffer
and must be a multiple of pattern_size.
event_wait_list
,
num_events_in_wait_list
Specify events that need to complete before this particular
command can be executed. If event_wait_list
is NULL, then this particular command does not wait on any
event to complete. If event_wait_list is
NULL, num_events_in_wait_list must be 0. If
event_wait_list is not NULL, the list of events
pointed to by event_wait_list must be valid
and num_events_in_wait_list must be greater
than 0. The events specified in event_wait_list
act as synchronization points. The context associated with events in
event_wait_list and command_queue must
be the same. The memory associated with event_wait_list
can be reused or freed after the function returns.
event
Returns an event object that identifies this particular write
command and can be used to query or queue a wait for this particular
command to complete. event can be NULL in
which case it will not be possible for the application to query the
status of this command or queue a wait for this command to complete.
clEnqueueBarrierWithWaitList
can be used instead. If the event_wait_list
and the event arguments are not NULL, the
event argument should not refer to an element of the
event_wait_list array.
Enqueues a command to fill a buffer object with a pattern of a given pattern size. The
usage information which indicates whether the memory object can be read or written by
a kernel and/or the host and is given by the cl_mem_flags argument value
specified when buffer is created is ignored by clEnqueueFillBuffer.
clEnqueueFillBuffer returns CL_SUCCESS if
the function is executed successfully. Otherwise, it returns one of the following errors.
command_queue
is not a valid command-queue.
command_queue and buffer are not the same
or if the context associated with command_queue and events in
event_wait_list are not the same.
buffer is not
a valid buffer object.
offset or
offset + size require accessing elements
outside the buffer buffer object respectively.
pattern is NULL
or if pattern_size is 0 or if pattern_size
is not one of {1, 2, 4, 8, 16, 32, 64, 128}.
offset and
size are not a multiple of pattern_size.
event_wait_list is NULL and
num_events_in_wait_list > 0,
or event_wait_list is not NULL and
num_events_in_wait_list is 0, or if event objects in
event_wait_list are not valid events.
buffer
is a sub-buffer object and offset specified when the sub-buffer object is created
is not aligned to CL_DEVICE_MEM_BASE_ADDR_ALIGN value for
device associated with queue.
buffer.
public static int clEnqueueCopyBuffer(cl_command_queue command_queue, cl_mem src_buffer, cl_mem dst_buffer, long src_offset, long dst_offset, long cb, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command to copy from one buffer object to another.
cl_int clEnqueueCopyBuffer
(
|
cl_command_queuecommand_queue, |
| cl_memsrc_buffer, | |
| cl_memdst_buffer, | |
| size_tsrc_offset, | |
| size_tdst_offset, | |
| size_tcb, | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
cl_event*event) |
command_queue
The command-queue in which the copy command will be queued. The
OpenCL context associated with command_queue, src_buffer, and dst_buffer must be the same.
src_offset
The offset where to begin copying data from src_buffer.
dst_offset
The offset where to begin copying data into dst_buffer.
cb
Refers to the size in bytes to copy.
event_wait_list,
,
num_events_in_wait_list
Specify events that need to complete before this particular command can be executed. If event_wait_list is NULL, then this particular command does not wait on any event to complete. If event_wait_list is NULL, num_events_in_wait_list must be 0. If event_wait_list is not NULL, the list of events pointed to by event_wait_list must be valid and num_events_in_wait_list must be greater than 0. The events specified in
event_wait_list act as synchronization points. The context associated with events in event_wait_list and command_queue must be the same.
event
Returns an event object that identifies this particular copy command and can be used to
query or queue a wait for this particular command to complete. event can be NULL in which case it will not be possible for the application to query the status of this command or queue a wait for this command to complete. clEnqueueBarrier can be used instead.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
command_queue is not a valid command-queue.
command_queue, src_buffer, and
dst_buffer are not the same or if the context associated with command_queue and events
in event_wait_list are not the same.
src_buffer and dst_buffer are not valid buffer objects.
src_offset, dst_offset, cb, src_offset + cb, or dst_offset + cb
require accessing elements outside the src_buffer and dst_buffer buffer objects
respectively.
event_wait_list is NULL and
num_events_in_wait_list is greater than 0, or event_wait_list is not NULL and
num_events_in_wait_list is 0, or if event objects in event_wait_list are not valid events.
src_buffer and dst_buffer are the same
buffer object and the source and destination regions overlap.
src_buffer is a sub-buffer object
and offset specified when the sub-buffer object is created is not aligned to CL_DEVICE_MEM_BASE_ADDR_ALIGN
value for device associated with queue.
dst_buffer is a sub-buffer object
and offset specified when the sub-buffer object is created is not aligned to CL_DEVICE_MEM_BASE_ADDR_ALIGN
value for device associated with queue.
src_buffer or dst_buffer.
public static int clEnqueueCopyBufferRect(cl_command_queue command_queue, cl_mem src_buffer, cl_mem dst_buffer, long[] src_origin, long[] dst_origin, long[] region, long src_row_pitch, long src_slice_pitch, long dst_row_pitch, long dst_slice_pitch, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command to copy a rectangular region from the buffer object to another buffer object.
cl_int clEnqueueCopyBufferRect
(
|
cl_command_queuecommand_queue, |
| cl_memsrc_buffer, | |
| cl_memdst_buffer, | |
| const size_tsrc_origin[3], | |
| const size_tdst_origin[3], | |
| const size_tregion[3], | |
| size_tsrc_row_pitch, | |
| size_tsrc_slice_pitch, | |
| size_tdst_row_pitch, | |
| size_tdst_slice_pitch, | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
cl_event*event) |
command_queue
The command-queue in which the copy command will be queued. The
OpenCL context associated with command_queue, src_buffer, and dst_buffer must be the same.
src_origin
The (x, y, z) offset in the memory region associated with src_buffer. For a 2D rectangle region, the z value given by src_origin[2] should be 0. The offset in bytes is computed as src_origin[2] * src_slice_pitch + src_origin[1] * src_row_pitch + src_origin[0].
dst_origin
The (x, y, z) offset in the memory region associated with dst_buffer. For a 2D rectangle region, the z value given by dst_origin[2] should be 0. The offset in bytes is computed as dst_origin[2] * dst_slice_pitch + dst_origin[1] * dst_row_pitch + dst_origin[0].
region
The (width, height, depth) in bytes of the 2D or 3D rectangle being copied. For a
2D rectangle, the depth value given by region[2] should be 1.
src_row_pitch
The length of each row in bytes to be used for the memory region associated with src_buffer. If src_row_pitch is 0, src_row_pitch is computed as region[0].
src_slice_pitch
The length of each 2D slice in bytes to be used for the memory region associated with src_buffer. If src_slice_pitch is 0, src_slice_pitch is computed as region[1] * src_row_pitch.
dst_row_pitch
The length of each row in bytes to be used for the memory region associated with dst_buffer. If dst_row_pitch is 0, dst_row_pitch is computed as region[0].
dst_slice_pitch
The length of each 2D slice in bytes to be used for the memory region associated with dst_buffer. If dst_slice_pitch is 0, dst_slice_pitch is computed as region[1] * dst_row_pitch.
event_wait_list,
,
num_events_in_wait_list
Specify events that need to complete before this particular command can be executed. If event_wait_list is NULL, then this particular command does not wait on any event to complete. If event_wait_list is NULL, num_events_in_wait_list must be 0. If event_wait_list is not NULL, the list of events pointed to by event_wait_list must be valid and num_events_in_wait_list must be greater than 0. The events specified in
event_wait_list act as synchronization points. The context associated with events in event_wait_list and command_queue must be the same.
event
Returns an event object that identifies this particular copy command and can be used to
query or queue a wait for this particular command to complete. event can be NULL in which case it will not be possible for the application to query the status of this command or queue a wait for this command to complete. clEnqueueBarrier can be used instead.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
command_queue is not a valid command-queue.
command_queue, src_buffer, and
dst_buffer are not the same or if the context associated with command_queue and events
in event_wait_list are not the same.
src_buffer and dst_buffer are not valid buffer objects.
src_offset, region) or (dst_offset, region) require accessing elements outside the src_buffer and dst_buffer objects respectively.
event_wait_list is NULL and
num_events_in_wait_list is greater than 0, or event_wait_list is not NULL and
num_events_in_wait_list is 0, or if event objects in event_wait_list are not valid events.
src_buffer and dst_buffer are the same buffer object and the source and destination regions overlap.
src_buffer is a sub-buffer object and offset specified when the sub-buffer object is created is not aligned to CL_DEVICE_MEM_BASE_ADDR_ALIGN value for device associated with queue.
dst_buffer is a sub-buffer object and offset specified when the sub-buffer object is created is not aligned to CL_DEVICE_MEM_BASE_ADDR_ALIGN value for device associated with queue.
src_buffer or dst_buffer.
public static int clEnqueueReadImage(cl_command_queue command_queue, cl_mem image, boolean blocking_read, long[] origin, long[] region, long row_pitch, long slice_pitch, Pointer ptr, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command to read from a 2D or 3D image object to host memory.
cl_int
clEnqueueReadImage
(
|
cl_command_queuecommand_queue, |
| cl_memimage, | |
| cl_boolblocking_read, | |
| const size_torigin[3], | |
| const size_tregion[3], | |
| size_trow_pitch, | |
| size_tslice_pitch, | |
| void*ptr, | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
cl_event*event) |
command_queue
Refers to the command-queue in which the read command will be
queued. command_queue and image
must be created with the same OpenCL context.
image
Refers to a valid 2D or 3D image object.
blocking_read
Indicates if the read operations are blocking or non-blocking.
If blocking_read is CL_TRUE i.e. the read command is blocking, clEnqueueReadImage does not return until the
buffer data has been read and copied into memory pointed to by ptr.
If blocking_read is CL_FALSE i.e. map operation is non-blocking, clEnqueueReadImage queues a non-blocking read command and returns. The contents of the buffer that ptr points to cannot be used until the read command has completed. The event argument returns an event object which can be used to query the execution status of the read command. When the read command has completed, the contents of the buffer that ptr points to can be used by the application.
origin
Defines the (x, y, z) offset in pixels in the image from where to read. If image is a 2D image object, the z value given by origin[2] must be 0.
region
Defines the (width, height, depth) in pixels of the 2D or 3D rectangle being read. If image is a 2D image object, the depth value given by region[2] must be 1.
row_pitch
The length of each row in bytes. This value must be greater than or equal to the element size in bytes * width. If row_pitch is set to 0, the appropriate row pitch is calculated
based on the size of each element in bytes multiplied by width.
slice_pitch
Size in bytes of the 2D slice of the 3D region of a 3D image being read. This must be 0 if image is a 2D image. This value must be greater than or equal to row_pitch * height. If slice_pitch is set to 0, the appropriate slice pitch is calculated based on the row_pitch * height.
ptr
The pointer to a buffer in host memory where image data is to be read from.
event_wait_list
,
num_events_in_wait_list
Specify events that need to complete before this particular command can be executed. If event_wait_list is NULL, then this particular command does not wait on any event to complete. If event_wait_list is NULL, num_events_in_wait_list must be 0. If event_wait_list is not NULL, the list of events pointed to by event_wait_list must
be valid and num_events_in_wait_list must be greater than 0. The events specified in event_wait_list act as synchronization points. The context associated with events in event_wait_list and command_queue must be the same.
event
Returns an event object that identifies this particular read command and can be used to
query or queue a wait for this particular command to complete. event can be NULL in which case it will not be possible for the application to query the status of this command or queue a wait for this command to complete.
Calling clEnqueueReadImage to read a region of the image with the ptr argument value set to host_ptr + (origin[2] * image slice pitch + origin[1] * image row pitch + origin[0] *
bytes per pixel), where host_ptr is a pointer to the memory region specified when the image being read is created with CL_MEM_USE_HOST_PTR, must meet the following requirements in order to avoid undefined behavior:
row_pitch and slice_pitch argument values in clEnqueueReadImage must be set to
the image row pitch and slice pitch.
clEnqueueReadImage returns CL_SUCCESS if the function is
executed successfully. Otherwise, it returns one of the following errors.
command_queue
is not a valid command-queue.
command_queue and
image are not the same or if the context associated with
command_queue
and events in event_wait_list are not the same.
image is
not a valid image object.
origin and region is out of bounds or if
ptr is a NULL value.
image is a
2D image object and origin[2]
is not equal to 0 or region[2] is not equal to 1 or
slice_pitch is not equal to 0.
event_wait_list is NULL and
num_events_in_wait_list greater than 0, or event_wait_list
is not NULL and num_events_in_wait_list is 0, or if event objects in
event_wait_list are not valid events.
image are not
supported by device associated with queue.
event_wait_list is a negative integer value.
command_queue does not support images (i.e. CL_DEVICE_IMAGE_SUPPORT
specified in the table of OpenCL Device Queries
for clGetDeviceInfo is CL_FALSE).
image.
public static int clEnqueueWriteImage(cl_command_queue command_queue, cl_mem image, boolean blocking_write, long[] origin, long[] region, long input_row_pitch, long input_slice_pitch, Pointer ptr, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command to write to a 2D or 3D image object from host memory.
cl_int
clEnqueueWriteImage
(
|
cl_command_queuecommand_queue, |
| cl_memimage, | |
| cl_boolblocking_write, | |
| const size_torigin[3], | |
| const size_tregion[3], | |
| size_tinput_row_pitch, | |
| size_tinput_slice_pitch, | |
| const void* ptr, | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
cl_event*event) |
command_queue
Refers to the command-queue in which the write command will be
queued. command_queue and image
must be created with the same OpenCL context.
image
Refers to a valid 2D or 3D image object.
blocking_write
Indicates if the write operation is blocking or non-blocking.
If blocking_write is CL_TRUE the OpenCL implementation copies the data referred to by ptr and enqueues the write command in the command-queue. The memory pointed to by ptr can be reused by the application after the clEnqueueWriteImage call returns.
If blocking_write is CL_FALSE the OpenCL implementation will use ptr to perform a nonblocking write. As the write is non-blocking the implementation can return immediately. The memory pointed to by ptr cannot be reused by the application after the call returns. The event argument returns an event object which can be used to query the execution status of the write
command. When the write command has completed, the memory pointed to by ptr can then be reused by the application.
origin
Defines the (x, y, z) offset in pixels in the image from where to write. If image is a 2D image object, the z value given by origin[2] must be 0.
region
Defines the (width, height, depth) in pixels of the 2D or 3D rectangle being written. If image is a 2D image object, the depth value given by region[2] must be 1.
input_row_pitch
The length of each row in bytes. This value must be greater than or equal to the element size in bytes * width. If input_row_pitch is set to 0, the appropriate row pitch is calculated based on the size of each element in bytes multiplied by width.
input_slice_pitch
Size in bytes of the 2D slice of the 3D region of a 3D image being written. This must be 0 if image is a 2D image. This value must be greater than or equal to row_pitch * height. If input_slice_pitch is set to 0, the appropriate slice pitch is calculated based on the row_pitch * height.
ptr
The pointer to a buffer in host memory where image data is to be written to.
event_wait_list
,
num_events_in_wait_list
Specify events that need to complete before this particular command can be executed. If event_wait_list is NULL, then this particular command does not wait on any event to complete. If event_wait_list is NULL, num_events_in_wait_list must be 0. If event_wait_list is not NULL, the list of events pointed to by event_wait_list must
be valid and num_events_in_wait_list must be greater than 0. The events specified in event_wait_list act as synchronization points. The context associated with events in event_wait_list and command_queue must be the same.
event
Returns an event object that identifies this particular write command and can be used to
query or queue a wait for this particular command to complete. event can be NULL in which
case it will not be possible for the application to query the status of this command or queue a
wait for this command to complete.
Calling clEnqueueWriteImage to update the latest bits in a region of the image with the
ptr argument value set to host_ptr + (origin[2] * image slice pitch + origin[1] * image row pitch
+ origin[0] * bytes per pixel), where host_ptr is a pointer to the memory region specified when
the image being written is created with CL_MEM_USE_HOST_PTR, must meet the following requirements in order to avoid undefined behavior:
input_row_pitch and input_slice_pitch argument values in clEnqueueWriteImage
must be set to the image row pitch and slice pitch.
clEnqueueWriteImage return CL_SUCCESS if the function is
executed successfully. Otherwise, it returns one of the following errors.
command_queue is not a valid command-queue.
command_queue and image
are not the same or if the context associated with command_queue and events
in event_wait_list are not the same.
image is not a valid image object.
origin and region
is out of bounds or if ptr is a NULL value.
image is a 2D image object and origin[2] is not equal to 0 or
region[2] is not equal to 1 or slice_pitch is not equal to 0.
event_wait_list is NULL and
num_events_in_wait_list greater than 0, or event_wait_list is not NULL and
num_events_in_wait_list is 0, or if event objects in event_wait_list are not valid events.
image are not supported by device associated with queue.
command_queue does not
support images (i.e. CL_DEVICE_IMAGE_SUPPORT specified in the table of OpenCL Device Queries
for clGetDeviceInfo is CL_FALSE).
event_wait_list is a negative integer value.
image.
public static int clEnqueueFillImage(cl_command_queue command_queue, cl_mem image, Pointer fill_color, long[] origin, long[] region, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command to fill an image object with a specified color.
cl_int
clEnqueueFillImage
(
|
cl_command_queuecommand_queue, |
| cl_memimage, | |
| const void*fill_color, | |
| const size_t*origin, | |
| const size_t*region, | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
cl_event*event) |
command_queue
Refers to the command-queue in which the fill command will be queued. The
OpenCL context associated with command_queue and image must be the same.
image
A valid image object.
fill_color
The fill color. The fill color is a four component RGBA floating-point color value if
the image channel data type is not an unnormalized
signed and unsigned integer type, is a four component signed integer value if
the image channel data type is an unnormalized signed integer
type and is a four component unsigned integer value if the image
channel data type is an unormalized unsigned integer type. The fill color will be
converted to the appropriate image channel format and order associated with
image.
origin
Defines the (x, y, z) offset in pixels in the 1D, 2D, or
3D image, the (x, y) offset and the image index in the
image array or the (x) offset and the image index in the 1D image array. If
image is a 2D image object, origin[2]
must be 0. If image is a 1D image or 1D image buffer
object, origin[1] and origin[2]
must be 0. If image is a 1D image array object,
origin[2] must be 0. If image
is a 1D image array object, origin[1] describes the
image index in the 1D image array. If image is a 2D
image array object, origin[2] describes the image
index in the 2D image array.
region
Defines the (width, height, depth) in pixels of the
1D, 2D or 3D rectangle, the (width, height) in pixels
of the 2D rectangle and the number of images of a 2D image array or the
(width) in pixels of the 1D rectangle and the number
of images of a 1D image array. If image is a 2D image
object, region[2] must be 1. If image
is a 1D image or 1D image buffer object, region[1]
and region[2] must be 1. If image
is a 1D image array object, region[2] must be 1.
event_wait_list
,
num_events_in_wait_list
Specify events that need to complete before this particular
command can be executed. If event_wait_list
is NULL, then this particular command does not wait on any
event to complete. If event_wait_list is
NULL, num_events_in_wait_list must be 0. If
event_wait_list is not NULL, the list of events
pointed to by event_wait_list must be valid
and num_events_in_wait_list must be greater
than 0. The events specified in event_wait_list
act as synchronization points. The context associated with events in
event_wait_list and command_queue must
be the same. The memory associated with event_wait_list
can be reused or freed after the function returns.
event
Returns an event object that identifies this particular write
command and can be used to query or queue a wait for this particular
command to complete. event can be NULL in
which case it will not be possible for the application to query the
status of this command or queue a wait for this command to complete.
clEnqueueBarrierWithWaitList
can be used instead. If the event_wait_list
and the event arguments are not NULL, the
event argument should not refer to an element of the
event_wait_list array.
The usage information which indicates whether the memory object can be read or
written by a kernel and/or the host and is given by the cl_mem_flags
argument value specified when image is created is ignored by
clEnqueueFillImage.
clEnqueueFillImage return CL_SUCCESS if the function is
executed successfully. Otherwise, it returns one of the following errors.
command_queue
is not a valid command-queue.
command_queue and image are not the
same or if the context associated with command_queue
and events in event_wait_list are not the same.
image is
not a valid image object.
fill_color is NULL.
origin and region is out of bounds or if
ptr is a NULL value.
origin
and region do not follow rules described in the argument
description for origin and region.
event_wait_list is NULL and
num_events_in_wait_list > 0,
or event_wait_list is not NULL and
num_events_in_wait_list is 0, or if event objects in
event_wait_list are not valid events.
image
are not supported by device associated with queue.
image are not supported by device
associated with queue.
image.
public static int clEnqueueCopyImage(cl_command_queue command_queue, cl_mem src_image, cl_mem dst_image, long[] src_origin, long[] dst_origin, long[] region, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command to copy image objects.
cl_int
clEnqueueCopyImage
(
|
cl_command_queuecommand_queue, |
| cl_memsrc_image, | |
| cl_memdst_image, | |
| const size_tsrc_origin[3], | |
| const size_tdst_origin[3], | |
| const size_tregion[3], | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
cl_event*event) |
command_queue
Refers to the command-queue in which the copy command will be queued. The
OpenCL context associated with command_queue, src_image and dst_image must be the same.
src_origin
Defines the starting (x, y, z) location in pixels in src_image from where to start the data copy. If src_image is a 2D image object, the z value given by src_origin[2] must be 0.
dst_origin
Defines the starting (x, y, z) location in pixels in dst_image from where to start the data copy. If dst_image is a 2D image object, the z value given by dst_origin[2] must be 0.
region
Defines the (width, height, depth) in pixels of the 2D or 3D rectangle to copy. If src_image or dst_image is a 2D image object, the depth value given by region[2] must be 1.
event_wait_list
,
num_events_in_wait_list
Specify events that need to complete before this particular command can be executed. If event_wait_list is NULL, then this particular command does not wait on any event to complete. If event_wait_list is NULL, num_events_in_wait_list must be 0. If event_wait_list is not NULL, the list of events pointed to by event_wait_list must be valid and num_events_in_wait_list must be greater than 0. The events specified in event_wait_list act as synchronization points. The context associated with events in event_wait_list and command_queue must be the same.
event
Returns an event object that identifies this particular copy command and can be used to query or queue a wait for this particular command to complete. event can be NULL in which case it will not be possible for the application to query the status of this command or queue a wait for this command to complete. clEnqueueBarrier can be used instead.
It is currently a requirement that the src_image and dst_image image memory objects for clEnqueueCopyImage must have the exact same image format (i.e. the cl_image_format descriptor specified when src_image and dst_image are created must match).
src_image and dst_image can be 2D or 3D image objects
allowing us to perform the following actions:
clEnqueueCopyImage returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
command_queue is not a valid command-queue.
command_queue, src_image
and dst_image are not the same or if the context associated with command_queue and events
in event_wait_list are not the same.
src_image and dst_image are not valid image objects.
src_image and dst_image do not use the same
image format.
src_origin
and src_origin + region refers to a region outside src_image,
or if the 2D or 3D rectangular region specified by dst_origin and dst_origin + region
refers to a region outside dst_image.
src_image is a 2D image object and src_origin[2]
is not equal to 0 or region[2] is not equal to 1.
dst_image is a 2D image object and dst_origin[2]
is not equal to 0 or region[2] is not equal to 1.
event_wait_list is NULL and
num_events_in_wait_list greater than 0, or event_wait_list is not NULL
and num_events_in_wait_list is 0, or if event objects in event_wait_list are not valid events.
src_image are not supported by device associated with queue.
dst_image are not supported by device associated with queue.
src_image or dst_image.
command_queue does not support images
(i.e. CL_DEVICE_IMAGE_SUPPORT specified in the table of OpenCL Device Queries
for clGetDeviceInfo is CL_FALSE).
src_image and dst_image are the
same image object and the source and destination regions overlap.
public static int clEnqueueCopyImageToBuffer(cl_command_queue command_queue, cl_mem src_image, cl_mem dst_buffer, long[] src_origin, long[] region, long dst_offset, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command to copy an image object to a buffer object.
cl_int
clEnqueueCopyImageToBuffer
(
|
cl_command_queuecommand_queue, |
| cl_memsrc_image, | |
| cl_mem dst_buffer, | |
| const size_tsrc_origin[3], | |
| const size_tregion[3], | |
| size_tdst_offset, | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
cl_event*event) |
command_queue
Must be a valid command-queue. The OpenCL context associated with command_queue, src_image, and dst_buffer must be the same.
src_image
A valid image object.
dst_buffer
A valid buffer object.
src_origin
Defines the (x, y, z) offset in pixels in the image from where to copy. If src_image is a 2D image object, the z value given by src_origin[2] must be 0.
region
Defines the (width, height, depth) in pixels of the 2D or 3D rectangle to copy. If src_image is a 2D image object, the depth value given by region[2] must be 1.
dst_offset
The offset where to begin copying data into dst_buffer. The size in bytes of the region to be copied referred to as dst_cb is computed as width * height * depth * bytes/image element if src_image is a 3D image object and is computed as width * height * bytes/image element if src_image is a 2D image object.
event_wait_list
,
num_events_in_wait_list
Specify events that need to complete before this
particular command can be executed. If event_wait_list is NULL, then this particular command does not wait on any event to complete. If event_wait_list is NULL, num_events_in_wait_list must be 0. If event_wait_list is not NULL, the list of events pointed to by event_wait_list must be valid and num_events_in_wait_list must be greater than 0. The events specified in event_wait_list act as synchronization points. The context associated with events in event_wait_list and command_queue must be the same.
event
Returns an event object that identifies this particular copy command and can be used to
query or queue a wait for this particular command to complete. event can be NULL in which case it will not be possible for the application to query the status of this command or queue a wait for this command to complete. clEnqueueBarrier can be used instead.
clEnqueueCopyImageToBuffer returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
command_queue is not a valid command-queue.
command_queue, src_image and dst_buffer are not the same or if the context associated with command_queue and events in event_wait_list are not the same.
src_image is not a valid image object and dst_buffer is not a valid buffer object.
src_origin and src_origin + region refers to a region outside src_image, or if the region specified by dst_offset and dst_offset + dst_cb refers to a region outside dst_buffer.
src_image is a 2D image object and src_origin[2] is not equal to 0 or region[2] is not equal to 1.
event_wait_list is NULL and num_events_in_wait_list greater than 0, or event_wait_list is not NULL and num_events_in_wait_list is 0, or if event objects in event_wait_list are not valid events.
dst_buffer is a sub-buffer object
and offset specified when the sub-buffer object is created is not aligned to CL_DEVICE_MEM_BASE_ADDR_ALIGN
value for device associated with queue.
src_image are not supported by device associated with queue.
command_queue does not support images
(i.e. CL_DEVICE_IMAGE_SUPPORT specified in the table of OpenCL Device Queries
for clGetDeviceInfo is CL_FALSE).
src_image or dst_buffer.
public static int clEnqueueCopyBufferToImage(cl_command_queue command_queue, cl_mem src_buffer, cl_mem dst_image, long src_offset, long[] dst_origin, long[] region, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command to copy a buffer object to an image object.
cl_int
clEnqueueCopyBufferToImage
(
|
cl_command_queuecommand_queue, |
| cl_memsrc_buffer, | |
| cl_mem dst_image, | |
| size_tsrc_offset, | |
| const size_tdst_origin[3], | |
| const size_tregion[3], | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
cl_event*event) |
command_queue
A valid command-queue. The OpenCL context associated with
command_queue, src_buffer, and dst_image must be the same.
src_buffer
A valid buffer object.
dst_image
A valid image object.
src_offset
The offset where to begin copying data from src_buffer.
dst_origin
The (x, y, z) offset in pixels where to begin copying data to dst_image. If dst_image is a 2D image object, the z value given by dst_origin[2] must be 0.
region
Defines the (width, height, depth) in pixels of the 2D or 3D rectangle to copy. If dst_image is a 2D image object, the depth value given by region[2] must be 1.
The size in bytes of the region to be copied from src_buffer referred to as src_cb is computed as width * height * depth * bytes/image element if dst_image is a 3D image object and is computed as width * height * bytes/image element if dst_image is a 2D image object.
event_wait_list
,
num_events_in_wait_list
Specify events that need to complete before this particular command can be executed. If event_wait_list is NULL, then this particular command does not wait on any event to complete. If event_wait_list is NULL, num_events_in_wait_list must be 0. If event_wait_list is not NULL, the list of events pointed to by event_wait_list must be valid and num_events_in_wait_list must be greater than 0. The events specified in event_wait_list act as synchronization points. The context associated with events in event_wait_list and command_queue must be the same.
event
Returns an event object that identifies this particular copy command and can be used to
query or queue a wait for this particular command to complete. event can be NULL in which case it will not be possible for the application to query the status of this command or queue a wait for this command to complete. clEnqueueBarrier can be used instead.
clEnqueueCopyBufferToImage returns CL_SUCCESS if the function is executed successfully.
Otherwise, it returns one of the following errors:
command_queue is not a valid command-queue.
command_queue, src_buffer and
dst_image are not the same or if the context associated with command_queue and events
in event_wait_list are not the same.
src_buffer is not a valid buffer object and dst_image is not a valid image object.
dst_origin and
dst_origin + region refers to a region outside dst_origin, or if the region specified
by src_offset and src_offset + src_cb refers to a region outside
src_buffer.
dst_image is a 2D image object and dst_origin[2] is not equal to 0
or region[2] is not equal to 1.
event_wait_list is NULL and
num_events_in_wait_list greater than 0, or event_wait_list is not NULL and
num_events_in_wait_list is 0, or if event objects in event_wait_list are not valid events.
src_buffer is a sub-buffer object and offset
specified when the sub-buffer object is created is not aligned to CL_DEVICE_MEM_BASE_ADDR_ALIGN value for device associated with
queue.
dst_image are not supported by device associated with queue.
command_queue does not support images
(i.e. CL_DEVICE_IMAGE_SUPPORT specified in the table of OpenCL Device Queries
for clGetDeviceInfo is CL_FALSE).
src_buffer or dst_image.
public static java.nio.ByteBuffer clEnqueueMapBuffer(cl_command_queue command_queue, cl_mem buffer, boolean blocking_map, long map_flags, long offset, long cb, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event, int[] errcode_ret)
Enqueues a command to map a region of the buffer object given by buffer into the host address space and returns a pointer to this mapped region.
void * clEnqueueMapBuffer
(
|
cl_command_queuecommand_queue, |
| cl_membuffer, | |
| cl_boolblocking_map, | |
| cl_map_flagsmap_flags, | |
| size_toffset, | |
| size_tcb, | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
| cl_event*event, | |
cl_int*errcode_ret) |
command_queue
Must be a valid command-queue.
blocking_map
Indicates if the map operation is blocking or non-blocking.
If blocking_map is CL_TRUE, clEnqueueMapBuffer does not return until the specified region in buffer can be mapped.
If blocking_map is CL_FALSE i.e. map operation is non-blocking, the pointer to the mapped region returned by clEnqueueMapBuffer cannot be used until the map command has completed. The event argument returns an event object which can be used to query the execution status of the map command. When the map command is completed, the application can access the contents of the mapped region using the pointer returned by clEnqueueMapBuffer.
map_flags
Is a bit-field and can be set to CL_MAP_READ to indicate that the region specified by (offset, cb) in the buffer object is being mapped for reading, and/or CL_MAP_WRITE to indicate that the region specified by (offset, cb) in the buffer object is being mapped for writing.
buffer
A valid buffer object. The OpenCL context associated with command_queue and buffer must be the same.
offset,
cb
The offset in bytes and the size of the region in the buffer object that is being mapped.
event_wait_list,
num_events_in_wait_list
Specify events that need to complete before this
particular command can be executed. If event_wait_list is NULL, then this particular command
does not wait on any event to complete. If event_wait_list is NULL, num_events_in_wait_list
must be 0. If event_wait_list is not NULL, the list of events pointed to by event_wait_list must
be valid and num_events_in_wait_list must be greater than 0. The events specified in
event_wait_list act as synchronization points. The context associated with events in
event_wait_list and command_queue must be the same.
event
Returns an event object that identifies this particular copy command and can be used to query or queue a wait for this particular command to complete. event can be NULL in which case it will not be possible for the application to query the status of this command or queue a wait for this command to complete.
errcode_ret
Returns an appropriate error code. If errcode_ret is NULL, no error code is returned.
If the buffer object is created with CL_MEM_USE_HOST_PTR set in mem_flags, the host_ptr specified in clCreateBuffer is guaranteed to contain the latest bits in the region being mapped when the clEnqueueMapBuffer command has completed; and the pointer value returned by clEnqueueMapBuffer will be derived from the host_ptr specified when the buffer object is created.
Mapped buffer objects are unmapped using clEnqueueUnmapMemObject.
The contents of the regions of a memory object mapped for writing (i.e. CL_MAP_WRITE is set in map_flags argument to clEnqueueMapBuffer or clEnqueueMapImage) are considered to be undefined until this region is unmapped. Reads and writes by a kernel executing on a device to a memory region(s) mapped for writing are undefined.
Multiple command-queues can map a region or overlapping regions of a memory object for
reading (i.e. map_flags = CL_MAP_READ). The contents of the regions of a memory object mapped for reading can also be read by kernels executing on a device(s). The behavior of writes by a kernel executing on a device to a mapped region of a memory object is undefined. Mapping (and unmapping) overlapped regions of a buffer or image memory object for writing is undefined.
The behavior of OpenCL function calls that enqueue commands that write or copy to regions of a memory object that are mapped is undefined.
The pointer returned maps a region starting at offset and is at least cb bytes in size. The result of a memory access outside this region is undefined.
clEnqueueMapBuffer will return a pointer to the mapped region if the function is executed successfully. The errcode_ret is set to CL_SUCCESS.
A NULL pointer is returned otherwise with one of the following error values returned in errcode_ret:
command_queue is not a valid command-queue.
command_queue and buffer are not the
same or if the context associated with
command_queue and events
in event_wait_list are not the same.
buffer is not a valid buffer object.
offset, cb) is out of bounds or if
values specified in map_flags are not valid
event_wait_list is NULL and
num_events_in_wait_list greater than 0, or event_wait_list is not NULL and
num_events_in_wait_list is 0, or if event objects in event_wait_list are not valid events.
event_wait_list is a negative integer value.
buffer is a sub-buffer object and
offset specified when the sub-buffer object is created is not aligned to CL_DEVICE_MEM_BASE_ADDR_ALIGN
value for device associated with queue.
CL_MEM_USE_HOST_PTR
or CL_MEM_ALLOC_HOST_PTR.
buffer.
public static java.nio.ByteBuffer clEnqueueMapImage(cl_command_queue command_queue, cl_mem image, boolean blocking_map, long map_flags, long[] origin, long[] region, long[] image_row_pitch, long[] image_slice_pitch, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event, int[] errcode_ret)
Enqueues a command to map a region of an image object into the host address space and returns a pointer to this mapped region.
void * clEnqueueMapImage
(
|
cl_command_queuecommand_queue, |
| cl_memimage, | |
| cl_boolblocking_map, | |
| cl_map_flagsmap_flags, | |
| const size_torigin[3], | |
| const size_tregion[3], | |
| size_t*image_row_pitch, | |
| size_t*image_slice_pitch, | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
| cl_event*event, | |
cl_int*errcode_ret) |
command_queue
Must be a valid command-queue.
image
A valid image object. The OpenCL context associated with command_queue and image must be the same.
blocking_map
Indicates if the map operation is blocking or non-blocking. If blocking_map is CL_TRUE, clEnqueueMapImage does not return until the specified region in image can be mapped.
If blocking_map is CL_FALSE i.e. map operation is non-blocking, the pointer to the mapped region returned by clEnqueueMapImage cannot be used until the map command has completed. The event argument returns an event object which can be used to query the execution status of the map command. When the map command is completed, the application can access the contents of the mapped region using the pointer returned by clEnqueueMapImage.
map_flags
Is a bit-field and can be set to CL_MAP_READ to indicate that the region specified by (origin, region) in the image object is being mapped for reading, and/or CL_MAP_WRITE to indicate that the region specified by (origin, region) in the image object is being mapped for writing.
origin,
region
Define the (x, y, z) offset in pixels and (width, height, depth) in pixels of the 2D or 3D rectangle region that is to be mapped. If image is a 2D image object, the z value given by origin[2] must be 0 and the depth value given by region[2] must be 1.
image_row_pitch
Returns the scan-line pitch in bytes for the mapped region. This must be a non-NULL value.
image_slice_pitch
Returns the size in bytes of each 2D slice for the mapped region. For a 2D image, zero is returned if this argument is not NULL. For a 3D image, image_slice_pitch must be a non-NULL value.
event_wait_list
,
num_events_in_wait_list
Specify events that need to complete before clEnqueueMapImage can be executed. If event_wait_list is NULL, then clEnqueueMapImage does not wait on any event to complete. If event_wait_list is NULL, num_events_in_wait_list must be 0. If event_wait_list is not NULL, the list of events pointed to by event_wait_list must be valid and num_events_in_wait_list must be greater than 0. The events specified in event_wait_list act as synchronization points. The context associated with events in event_wait_list and command_queue must be the same.
event
Returns an event object that identifies this particular copy command and can be used to query or queue a wait for this particular command to complete. event can be NULL in which case it will not be possible for the application to query the status of this command or queue a wait for this command to complete.
errcode_ret
Returns an appropriate error code. If errcode_ret is NULL, no error code is returned.
If the image object is created with CL_MEM_USE_HOST_PTR set in mem_flags, the
following will be true:
host_ptr specified in clCreateImage2d
or clCreateImage3d is guaranteed to contain the latest bits
in the region being mapped when the clEnqueueMapImage command has completed.
clEnqueueMapImage will be derived from
the host_ptr specified when the image object is created.
Mapped image objects are unmapped using clEnqueueUnmapMemObject.
The contents of the regions of a memory object mapped for writing (i.e. CL_MAP_WRITE is set
in map_flags argument to clEnqueueMapBuffer or clEnqueueMapImage) are considered to be
undefined until this region is unmapped. Reads and writes by a kernel executing on a device to a
memory region(s) mapped for writing are undefined.
Multiple command-queues can map a region or overlapping regions of a memory object for
reading (i.e. map_flags = CL_MAP_READ). The contents of the regions of a memory object
mapped for reading can also be read by kernels executing on a device(s). The behavior of writes
by a kernel executing on a device to a mapped region of a memory object is undefined.
Mapping (and unmapping) overlapped regions of a memory object for writing is
undefined.
The behavior of OpenCL function calls that enqueue commands that write or copy to regions of a memory object that are mapped is undefined.
The pointer returned maps a 2D or 3D region starting at origin and is at least (image_row_pitch * region[1]) pixels in size for a 2D image, and is at least (image_slice_pitch * region[2]) pixels in size for a 3D image. The result of a memory access outside this region is undefined.
clEnqueueMapImage will return a pointer to the mapped region if the function is executed successfully.
The errcode_ret is set to CL_SUCCESS.
A NULL pointer is returned otherwise with one of the following error values returned in
errcode_ret:
command_queue is not a valid command-queue.
command_queue and image
are not the same or if the context associated with command_queue and events
in event_wait_list are not the same.
image is not a valid image object.
origin, origin+region) is out of bounds or if
values specified in map_flags are not valid.
image is a 2D image object and origin[2] is not equal to 0 or
region[2] is not equal to 1.
image_row_pitch is NULL.
image is a 3D image object and image_slice_pitch is NULL.
event_wait_list is NULL and
num_events_in_wait_list greater than 0, or event_wait_list is not NULL and
num_events_in_wait_list is 0, or if event objects in event_wait_list are not valid events.
image are not supported by device associated with queue.
CL_MEM_USE_HOST_PTR
or CL_MEM_ALLOC_HOST_PTR.
buffer.
event_wait_list
is a negative integer value.
command_queue does not support
images (i.e. CL_DEVICE_IMAGE_SUPPORT specified in the table of OpenCL Device Queries
for clGetDeviceInfo.
public static int clEnqueueUnmapMemObject(cl_command_queue command_queue, cl_mem memobj, java.nio.ByteBuffer mapped_ptr, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command to unmap a previously mapped region of a memory object.
cl_int clEnqueueUnmapMemObject
(
|
cl_command_queuecommand_queue, |
| cl_memmemobj, | |
| void*mapped_ptr, | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
cl_event*event) |
command_queue
Must be a valid command-queue.
memobj
A valid memory object. The OpenCL context associated with command_queue and memobj must be the same.
mapped_ptr
The host address returned by a previous call to clEnqueueMapBuffer or
clEnqueueMapImage for memobj.
event_wait_list
,
num_events_in_wait_list
Specify events that need to complete before clEnqueueUnmapMemObject can be executed. If event_wait_list is NULL, then clEnqueueUnmapMemObject does not wait on any event to complete. If event_wait_list is NULL, num_events_in_wait_list must be 0. If event_wait_list is not NULL, the list of events pointed to by event_wait_list must be valid and num_events_in_wait_list must be greater than 0. The events specified in event_wait_list act as synchronization points. The context associated with events in event_wait_list and command_queue must be the same.
event
Returns an event object that identifies this particular copy command and can be used to query or queue a wait for this particular command to complete. event can be NULL in which
case it will not be possible for the application to query the status of this command or queue a
wait for this command to complete. clEnqueueBarrier can be used instead.
Reads or writes from the host using the pointer returned by clEnqueueMapBuffer or clEnqueueMapImage are considered to be complete.
clEnqueueMapBuffer and clEnqueueMapImage increment the mapped count of the memory
object. The initial mapped count value of a memory object is zero. Multiple calls to
clEnqueueMapBuffer or clEnqueueMapImage on the same memory object will increment this
mapped count by appropriate number of calls. clEnqueueUnmapMemObject decrements the
mapped count of the memory object.
clEnqueueMapBuffer and clEnqueueMapImage act as synchronization points for a region of the buffer object being mapped.
clEnqueueUnmapMemObject returns CL_SUCCESS if the function is executed successfully.
Otherwise, it returns one of the following errors:.
command_queue is not a valid command-queue.
memobj is not a valid memory object.
mapped_ptr is not a valid pointer returned by
clEnqueueMapBuffer or
clEnqueueMapImage for memobj.
event_wait_list is NULL and
num_events_in_wait_list greater than 0, or event_wait_list is not NULL and
num_events_in_wait_list is 0, or if event objects in event_wait_list are
not valid events.
command_queue
and memobj are not the same or if the context associated with command_queue
and events in event_wait_list are not the same.
public static int clEnqueueMigrateMemObjects(cl_command_queue command_queue, int num_mem_objects, cl_mem[] mem_objects, long flags, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command to indicate which device a set of memory objects should be associated with.
cl_int
clEnqueueMigrateMemObjects
(
|
cl_command_queue command_queue , |
| cl_uint num_mem_objects , | |
| const cl_mem *mem_objects , | |
| cl_mem_migration_flags flags , | |
| cl_uint num_events_in_wait_list , | |
| const cl_event *event_wait_list , | |
cl_event
*event
)
|
command_queue
A valid command-queue. The specified set of memory objects in
mem_objects will be migrated to the OpenCL device
associated with command_queue or to the host if the
CL_MIGRATE_MEM_OBJECT_HOST has been specified.
num_mem_objects
The number of memory objects specified in mem_objects.
mem_objects
A pointer to a list of memory objects.
flags
A bit-field that is used to specify migration options. The table below describes the possible values for flags.
| cl_mem_migration flags | Description |
|---|---|
CL_MIGRATE_MEM_OBJECT_HOST
|
This flag indicates that the specified set of memory objects are to be migrated to the host, regardless of the target command-queue. |
CL_MIGRATE_MEM_OBJECT_-
CONTENT_UNDEFINED
|
This flag indicates that the contents of the set of memory
objects are undefined after migration. The specified set
of memory objects are migrated to the device associated with
command_queue without incurring the overhead
of migrating their contents.
|
event_wait_list, num_events_in_wait_list
Specify events that need to complete before this particular
command can be executed. If event_wait_list
is NULL, then this particular command does not wait on any
event to complete. If event_wait_list is
NULL, num_events_in_wait_list must be 0. If
event_wait_list is not NULL, the list of events
pointed to by event_wait_list must be valid
and num_events_in_wait_list must be greater
than 0. The events specified in event_wait_list
act as synchronization points. The context associated with events in
event_wait_list and command_queue must
be the same. The memory associated with event_wait_list
can be reused or freed after the function returns.
event
Returns an event object that identifies this particular command and
can be used to query or queue a wait for this particular command
to complete. event can be NULL in which case
it will not be possible for the application to query the status of
this command or queue a wait for this command to complete. If the
event_wait_list and the event
arguments are not NULL, the event argument should not
refer to an element of the event_wait_list array.
This section describes a mechanism for assigning which device an OpenCL memory object resides. A user may wish to have more explicit control over the location of their memory objects on creation. This could be used to:
Typically, memory objects are implicitly migrated to a device
for which enqueued commands, using the memory object, are targeted.
clEnqueueMigrateMemObjects allows this migration to be explicitly
performed ahead of the dependent commands. This allows a user to preemptively change
the association of a memory object, through regular command queue scheduling, in
order to prepare for another upcoming command. This also permits an application to
overlap the placement of memory objects with other unrelated operations before
these memory objects are needed potentially hiding transfer latencies. Once
the event, returned from clEnqueueMigrateMemObjects,
has been marked CL_COMPLETE the memory objects specified
in mem_objects have been successfully migrated to the device
associated with command_queue. The migrated memory object shall
remain resident on the device until another command is enqueued that either implicitly
or explicitly migrates it away.
clEnqueueMigrateMemObjects can also be used to direct the initial
placement of a memory object, after creation, possibly avoiding the initial overhead
of instantiating the object on the first enqueued command to use it.
The user is responsible for managing the event dependencies, associated with this
command, in order to avoid overlapping access to memory objects. Improperly specified
event dependencies passed to clEnqueueMigrateMemObjects could
result in undefined results.
clEnqueueMigrateMemObjects returns CL_SUCCESS
if the function is executed successfully. Otherwise, it returns one of the following
errors:
command_queue
is not a valid command_queue.
command_queue and memory objects in memobj
are not the same or if the context associated with command_queue
and events in event_wait_list are not the same.
mem_objs is not a valid memory object.
num_mem_objects
is zero or if mem_objects is NULL.
flags is
not 0 or is not any of the values described in the table above.
event_wait_list is NULL and
num_events_in_wait_list > 0,
or event_wait_list is not NULL and
num_events_in_wait_list is 0, or if event objects in
event_wait_list are not valid events.
mem_objects.
public static int clEnqueueNDRangeKernel(cl_command_queue command_queue, cl_kernel kernel, int work_dim, long[] global_work_offset, long[] global_work_size, long[] local_work_size, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command to execute a kernel on a device.
cl_int
clEnqueueNDRangeKernel
(
|
cl_command_queuecommand_queue, |
| cl_kernelkernel, | |
| cl_uintwork_dim, | |
| const size_t*global_work_offset, | |
| const size_t*global_work_size, | |
| const size_t*local_work_size, | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
cl_event*event) |
command_queue
A valid command-queue. The kernel will be queued for execution on the device associated with command_queue.
kernel
A valid kernel object. The OpenCL context associated with kernel and command_queue must be the same.
work_dim
The number of dimensions used to specify the global work-items and work-items
in the work-group. work_dim must be greater than zero and less than or
equal to CL_DEVICE_MAX_WORK_ITEM_DIMENSIONS.
global_work_offset
global_work_offset can be used to specify an array
of work_dim unsigned values that describe the offset used to calculate
the global ID of a work-item. If global_work_offset is NULL,
the global IDs start at offset (0, 0, ... 0).
global_work_size
Points to an array of work_dim unsigned values that describe the number of global work-items in work_dim dimensions that will execute the kernel function. The total number of global work-items is computed as global_work_size[0] *...* global_work_size[work_dim - 1].
The values specified in global_work_size + corresponding values specified in global_work_offset cannot exceed the range given by the sizeof(size_t) for the device on which the kernel execution will be enqueued. The sizeof(size_t) for a device can be determined using CL_DEVICE_ADDRESS_BITS in the table of OpenCL Device Queries for clGetDeviceInfo. If, for example, CL_DEVICE_ADDRESS_BITS = 32, i.e. the device uses a 32-bit address space, size_t is a 32-bit unsigned integer and global_work_size values must be in the range 1 .. 2^32 - 1. Values outside this range return a CL_OUT_OF_RESOURCES error.
local_work_size
Points to an array of work_dim unsigned values that describe the number of work-items that make up a work-group (also referred to as the size of the work-group) that will execute the kernel specified by kernel. The total number of work-items in a work-group is computed as local_work_size[0] *... * local_work_size[work_dim - 1]. The total number of work-items in the work-group must be less than or equal to the
CL_DEVICE_MAX_WORK_GROUP_SIZE value specified in table of OpenCL Device Queries for clGetDeviceInfo and the number of work-items specified in local_work_size[0],... local_work_size[work_dim - 1] must be less than or
equal to the corresponding values specified by CL_DEVICE_MAX_WORK_ITEM_SIZES[0],....
CL_DEVICE_MAX_WORK_ITEM_SIZES[work_dim - 1]. The explicitly specified local_work_size will be used to determine how to break the global work-items specified by global_work_size into appropriate work-group instances. If local_work_size is specified, the values specified in global_work_size[0],... global_work_size[work_dim - 1] must be evenly divisible by the corresponding values specified in local_work_size[0],... local_work_size[work_dim - 1].
The work-group size to be used for kernel can also be specified in the program source using the __attribute__((reqd_work_group_size(X, Y, Z)))qualifier. In this case the size of work group specified by local_work_size must match the value specified by the reqd_work_group_size __attribute__ qualifier.
local_work_size can also be a NULL value in which case the OpenCL implementation will determine how to be break the global work-items into appropriate work-group instances.
See note for more information.
These work-group instances are executed in parallel across multiple compute units or concurrently on the same compute unit.
Each work-item is uniquely identified by a global identifier. The global ID, which can be read inside the kernel, is computed using the value given by global_work_size and global_work_offset. In addition, a work-item is also identified within a work-group by a unique local ID. The local ID, which can also be read by the kernel, is computed using the value given by local_work_size. The starting local ID is always (0, 0, ... 0).
event_wait_list
and
num_events_in_wait_list
Specify events that need to complete before this
particular command can be executed. If event_wait_list is NULL, then this particular command does not wait on any event to complete. If event_wait_list is NULL, num_events_in_wait_list
must be 0. If event_wait_list is not NULL, the list of events pointed to by event_wait_list must be valid and num_events_in_wait_list must be greater than 0. The events specified in
event_wait_list act as synchronization points. The context associated with events in event_wait_list and command_queue must be the same.
event
Returns an event object that identifies this particular kernel execution instance. Event objects are unique and can be used to identify a particular kernel execution instance later on. If event is NULL, no event will be created for this kernel execution instance and therefore it will not be possible for the application to query or queue a wait for this particular kernel execution instance.
Returns CL_SUCCESS if the kernel execution was successfully queued. Otherwise, it returns one of the following errors:
command_queue.
command_queue is not a
valid command-queue.
kernel is not a valid kernel object.
command_queue
and kernel is not the same or if the context associated
with command_queue and events in event_wait_list are not the same.
work_dim is not a valid value
(i.e. a value between 1 and 3).
global_work_size is NULL, or
if any of the values specified in global_work_size[0], ...global_work_size
[work_dim - 1] are 0 or exceed the range given by the sizeof(size_t) for the
device on which the kernel execution will be enqueued.
global_work_size
+ the corresponding values in global_work_offset for any dimensions is greater
than the sizeof(size_t) for the device on which the kernel execution will be enqueued.
local_work_size is
specified and number of work-items specified by global_work_size is not evenly
divisable by size of work-group given by local_work_size or does not match the
work-group size specified for kernel using
the
__attribute__
((reqd_work_group_size(X, Y, Z))) qualifier in program source.
local_work_size is specified and the total number of work-items in the work-group computed as local_work_size[0] *... local_work_size[work_dim - 1] is greater than the value specified by CL_DEVICE_MAX_WORK_GROUP_SIZE in the table of OpenCL Device Queries for clGetDeviceInfo.
local_work_size is NULL and the __attribute__((reqd_work_group_size(X, Y, Z))) qualifier is used to declare the work-group size for kernel in the program source.
local_work_size[0], ... local_work_size[work_dim - 1] is greater than the corresponding values specified by CL_DEVICE_MAX_WORK_ITEM_SIZES[0], ....
CL_DEVICE_MAX_WORK_ITEM_SIZES[work_dim - 1].
offset specified when the sub-buffer object
is created is not aligned to CL_DEVICE_MEM_BASE_ADDR_ALIGN value for device associated with queue.
queue.
kernel on the command-queue because of insufficient resources needed to execute the kernel.
For example, the explicitly specified local_work_size causes a failure to execute the kernel
because of insufficient resources such as registers or local memory. Another example would be the number of
read-only image args used in kernel exceed the CL_DEVICE_MAX_READ_IMAGE_ARGS
value for device or the number of write-only image args used in kernel exceed
the CL_DEVICE_MAX_WRITE_IMAGE_ARGS value for device or the number of samplers used
in kernel exceed CL_DEVICE_MAX_SAMPLERS for device.
kernel.
event_wait_list is NULL
and num_events_in_wait_list > 0, or event_wait_list is not NULL
and num_events_in_wait_list is 0, or if event objects in event_wait_list
are not valid events.
public static int clEnqueueTask(cl_command_queue command_queue, cl_kernel kernel, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command to execute a kernel on a device.
cl_int
clEnqueueTask
(
|
cl_command_queuecommand_queue, |
| cl_kernelkernel, | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
cl_event*event) |
command_queue
A valid command-queue. The kernel will be queued for execution on the
device associated with command_queue.
kernel
A valid kernel object. The OpenCL context associated with kernel and command_queue must be the same.
num_events_in_wait_list
and event_wait_list
Specify events that need to complete before this
particular command can be executed. If event_wait_list is NULL, then this particular command
does not wait on any event to complete. If event_wait_list is NULL, num_events_in_wait_list must be 0. If event_wait_list is not NULL, the list of events pointed to by event_wait_list must be valid and num_events_in_wait_list must be greater than 0. The events specified in event_wait_list act as synchronization points. The context associated with events in event_wait_list and command_queue must be the same.
event
Returns an event object that identifies this particular kernel execution instance. Event objects are unique and can be used to identify a particular kernel execution instance later on. If event is NULL, no event will be created for this kernel execution instance and therefore it will not be possible for the application to query or queue a wait for this particular kernel execution instance.
The kernel is executed using a single work-item.
clEnqueueTask is equivalent to calling clEnqueueNDRangeKernel with work_dim = 1,
global_work_offset = NULL, global_work_size[0] set to 1, and local_work_size[0] set to 1.
Returns CL_SUCCESS if the kernel execution was successfully queued, or one of the errors below:
command_queue.
command_queue is not a valid command-queue.
kernel is not a valid kernel object.
command_queue
and kernel is not the same or if the context associated with command_queue
and events in event_wait_list are not the same.
kernel using the __attribute__((reqd_work_group_size(X, Y, Z))) qualifier in program source and is not (1, 1, 1).
offset specified when the sub-buffer object
is created is not aligned to CL_DEVICE_MEM_BASE_ADDR_ALIGN value for device associated with queue.
queue.
kernel on the command-queue because of insufficient resources needed to execute the kernel.
kernel.
event_wait_list is NULL
and num_events_in_wait_list is greater than 0, or event_wait_list is not
NULL and num_events_in_wait_list is 0, or if event objects in event_wait_list
are not valid events.
public static int clEnqueueNativeKernel(cl_command_queue command_queue, EnqueueNativeKernelFunction user_func, java.lang.Object args, long cb_args, int num_mem_objects, cl_mem[] mem_list, Pointer[] args_mem_loc, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command to execute a native C/C++ function not compiled using the OpenCL compiler.
cl_int
clEnqueueNativeKernel
(
|
cl_command_queuecommand_queue, |
| void(*user_func)(void *), | |
| void*args, | |
| size_tcb_args, | |
| cl_uintnum_mem_objects, | |
| const cl_mem*mem_list, | |
| const void**args_mem_loc, | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
cl_event*event) |
command_queue
A valid command-queue. A native user function can only be executed on a command-queue created on a device that has CL_EXEC_NATIVE_KERNEL capability set in CL_DEVICE_EXECUTION_CAPABILITIES as specified in the table of OpenCL Device Queries for clGetDeviceInfo.
user_func
A pointer to a host-callable user function.
args
A pointer to the args list that user_func should be called with.
cb_args
The size in bytes of the args list that args points to.
The data pointed to by args and cb_args bytes in size will be copied and a pointer to this copied region will be passed to user_func. The copy needs to be done because the memory objects (cl_mem values) that args may contain need to be modified and replaced by appropriate pointers to global memory. When clEnqueueNativeKernel returns, the memory region pointed to by args can be reused by the application.
num_mem_objects
The number of buffer objects that are passed in args.
mem_list
A list of valid buffer objects, if num_mem_objects is greater than 0. The buffer object values
specified in mem_list are memory object handles (cl_mem values) returned by clCreateBuffer or NULL.
args_mem_loc
A pointer to appropriate locations that args points to where memory object handles (cl_mem values) are stored. Before the user function is executed, the memory object handles are replaced by pointers to global memory.
event_wait_list
and
num_events_in_wait_list
Specify events that need to complete before this
particular command can be executed. If event_wait_list is NULL, then this particular command does not wait on any event to complete. If event_wait_list is NULL, num_events_in_wait_list
must be 0. If event_wait_list is not NULL, the list of events pointed to by event_wait_list must be valid and num_events_in_wait_list must be greater than 0. The events specified in
event_wait_list act as synchronization points. The context associated with events in event_wait_list and command_queue must be the same.
event
Returns an event object that identifies this particular kernel execution instance. Event objects are unique and can be used to identify a particular kernel execution instance later on. If event is NULL, no event will be created for this kernel execution instance and therefore it will not be possible for the application to query or queue a wait for this particular kernel execution instance.
The data pointed to by args and cb_args bytes in size will be copied and a pointer to this copied region will be passed to user_func. The copy needs to be done because the memory objects
(cl_mem values) that args may contain need to be modified and replaced by appropriate pointers to global memory. When clEnqueueNativeKernel returns, the memory region pointed to by args can be reused by the application.
Returns CL_SUCCESS if the user function execution instance was successfully queued, or one of the errors below:
command_queue is not a valid command-queue.
command_queue
and events in event-wait_list are not the same.
user_func is NULL.
args is a NULL value and
cb_args is greater than 0, or if args is a NULL
value and num_mem_objects is greater than 0.
args is not NULL and
cb_args is 0.
num_mem_objects is greater than 0
and mem_list or args_mem_loc are NULL.
num_mem_objects = 0 and
mem_list or args_mem_loc are not NULL.
command_queue cannot execute the native kernel.
mem_list are not valid or are not buffer objects.
kernel on the command-queue because of insufficient resources
needed to execute the kernel.
kernel.
event_wait_list is NULL
and num_events_in_wait_list is greater than 0, or event_wait_list
is not NULL and num_events_in_wait_list is 0, or if event objects
in event_wait_list are not valid events.
public static int clEnqueueMarkerWithWaitList(cl_command_queue command_queue, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a marker command which waits for either a list of events to complete, or all previously enqueued commands to complete.
cl_int
clEnqueueMarkerWithWaitList
(
|
cl_command_queue command_queue , |
| cl_uint num_events_in_wait_list , | |
| const cl_event *event_wait_list , | |
cl_event
*event
)
|
command_queue
A valid command-queue.
event_wait_list
num_events_in_wait_list
These functions specify events that need to complete before this particular command can be executed.
If event_wait_list is NULL,
num_events_in_wait_list must be 0. If
event_wait_list is not NULL, the list of events
pointed to by event_wait_list must be valid
and num_events_in_wait_list must be greater
than 0. The events specified in event_wait_list
act as synchronization points. The context associated with events in
event_wait_list and command_queue must
be the same. The memory associated with event_wait_list
can be reused or freed after the function returns.
If event_wait_list is NULL, then this
particular command waits until all previous enqueued commands to
command_queue have completed.
event
Returns an event object that identifies this particular command.
Event objects are unique and can be used to identify this marker
command later on. event can be NULL in which case
it will not be possible for the application to query the status of
this command or queue a wait for this command to complete. If the
event_wait_list and the event
arguments are not NULL, the event argument should not
refer to an element of the event_wait_list array.
Enqueues a marker command which waits for either a list of events to complete,
or if the list is empty it waits for all commands previously enqueued in
command_queue to complete before it completes. This command returns
an event which can be waited on, i.e. this event can be waited on to insure that all
events either in the event_wait_list or all previously enqueued
commands, queued before this command to command_queue, have completed.
Returns CL_SUCCESS if the function executed successfully, or one of the errors below:
command_queue
is not a valid command-queue.
event_wait_list is NULL and
num_events_in_wait_list > 0, or event_wait_list
is not NULL and num_events_in_wait_list is 0, or if event
objects in event_wait_list are not valid events.
public static int clEnqueueBarrierWithWaitList(cl_command_queue command_queue, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
A synchronization point that enqueues a barrier operation.
cl_int
clEnqueueBarrierWithWaitList
(
|
cl_command_queue command_queue , |
| cl_uint num_events_in_wait_list , | |
| const cl_event *event_wait_list , | |
cl_event
*event
)
|
command_queue
A valid command queue.
event_wait_list
,
num_events_in_wait_list
Specify events that need to complete before this particular command can be executed.
If event_wait_list is NULL,
num_events_in_wait_list must be 0. If
event_wait_list is not NULL, the list of events
pointed to by event_wait_list must be valid
and num_events_in_wait_list must be greater
than 0. The events specified in event_wait_list
act as synchronization points. The context associated with events in
event_wait_list and command_queue must
be the same. The memory associated with event_wait_list
can be reused or freed after the function returns.
If event_wait_list is NULL, then this particular command
waits until all previous enqueued commands to command_queue have completed.
event
Returns an event object that identifies this particular command. Event
objects are unique and can be used to identify this barrier command
later on. event can be NULL in which case it
will not be possible for the application to query the status of
this command or queue a wait for this command to complete. If the
event_wait_list and the event
arguments are not NULL, the event argument should not
refer to an element of the event_wait_list array.
Enqueues a barrier command which waits for either a list of events to complete,
or if the list is empty it waits for all commands previously enqueued in
command_queue to complete before it completes. This command blocks
command execution, that is, any following commands enqueued after it do not execute
until it completes. This command returns an event which can be
waited on, i.e. this event can be waited on to insure that all events either in the
event_wait_list or all previously enqueued commands, queued before
this command to command_queue, have completed.
Returns CL_SUCCESS if the function was successfully executed. Otherwise, it returns one of the following errors:
command_queue
is not a valid command-queue.
event_wait_list is NULL and
num_events_in_wait_list > 0,
or event_wait_list is not NULL and
num_events_in_wait_list is 0, or if event objects in
event_wait_list are not valid events.
public static int clSetPrintfCallback(cl_context context, PrintfCallbackFunction pfn_notify, java.lang.Object user_data)
public static int clEnqueueSVMFree(cl_command_queue command_queue, int num_svm_pointers, Pointer[] svm_pointers, SVMFreeFunction pfn_free_func, java.lang.Object user_data, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command to free the shared virtual memory allocated using clSVMAlloc or a shared system memory pointer.
cl_int clEnqueueSVMFree
(
|
cl_command_queue command_queue, |
| cl_uint num_svm_pointers , | |
| void *svm_pointers[] , | |
| void (CL_CALLBACK *pfn_free_func) ( cl_command_queue queue, cl_uint num_svm_pointers, void *svm_pointers[]), | |
| void *user_data), | |
| void *user_data, | |
| cl_uint num_events_in_wait_list, | |
| const cl_event *event_wait_list, | |
cl_event *event) |
command_queue
A valid host command-queue.
svm_pointers and num_svm_pointers
Specify shared virtual memory pointers to be freed. Each
pointer in svm_pointers that was
allocated using
clSVMAlloc
must have been allocated from the
same context from which command_queue
was created. The memory associated with
svm_pointers can be reused or
freed after the function returns.
pfn_free_func
Specifies the callback
function to be called to free the SVM pointers.
pfn_free_func takes four arguments:
queue which is the command queue in which
clEnqueueSVMFree was enqueued, the
count and list of SVM pointers to free and user_data
which is a pointer to user specified data.
If pfn_free_func is NULL, all pointers specified in
svm_pointers must be allocated using
clSVMAlloc
and the OpenCL implementation will free
these SVM pointers. pfn_free_func must
be a valid callback function if any SVM pointer to be
freed is a shared system memory pointer i.e. not allocated
using clSVMAlloc.
If pfn_free_func
is a valid callback function, the OpenCL implementation
will call pfn_free_func to free all the
SVM pointers specified in svm_pointers.
user_data
Will be passed as the
user_data argument when pfn_free_func
is called. user_data can be NULL.
event_wait_list and num_events_in_wait_list
Specify events that need to complete before
clEnqueueSVMFree can be executed. If
event_wait_list is NULL, then
clEnqueueSVMFree
does not wait on any event to complete. If
event_wait_list is NULL,
num_events_in_wait_list
must be 0. If event_wait_list is not
NULL, the list of events pointed to by
event_wait_list must
be valid and num_events_in_wait_list
must be greater than 0. The events specified in
event_wait_list act as synchronization
points. The context associated with events in
event_wait_list and
command_queue must be the same.
The memory associated with
event_wait_list can be
reused or freed after the function returns.
event
Returns an event object that
identifies this particular command and can be used to query or
queue a wait for this particular command to complete.
event can be NULL in which case it will
not be possible for the application to query the
status of this command or queue a wait for this
command to complete. If the event_wait_list
and the event arguments are not NULL,
the event
argument should not refer to an element of the
event_wait_list array.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
command_queue is not a valid host command-queue.
num_svm_pointers is 0 or if
svm_pointers is NULL or if any of
the pointers specified in svm_pointers
array is NULL.
event_wait_list is NULL and
num_events_in_wait_list > 0, or
event_wait_list is not NULL and
num_events_in_wait_list is 0, or
if event objects in event_wait_list
are not valid events.
Shared Virtual Memory Functions
public static int clEnqueueSVMMemcpy(cl_command_queue command_queue, boolean blocking_copy, Pointer dst_ptr, Pointer src_ptr, long size, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command to do a memcpy operation.
cl_int clEnqueueSVMMemcpy
(
|
cl_command_queue command_queue, |
| cl_bool blocking_copy , | |
| void *dst_ptr , | |
| const void *src_ptr , | |
| size_t size , | |
| cl_uint num_events_in_wait_list, | |
| const cl_event *event_wait_list, | |
cl_event *event) |
command_queue
Refers to the host command-queue in which the
read / write command will be
queued. command_queue and
buffer must be created
with the same OpenCL context.
blocking_copy
Indicates if the copy operation is blocking or non-blocking.
If blocking_copy is CL_TRUE
i.e. the copy command is blocking, clEnqueueSVMMemcpy
does not return until the buffer data has been
copied into memory pointed to by dst_ptr.
If blocking_copy is CL_FALSE
i.e. the copy command is non-blocking,
clEnqueueSVMMemcpy queues a non-blocking
copy command and returns. The contents of
the buffer that dst_ptr point to cannot
be used until the copy command has completed. The event
argument returns an event object which can be used to
query the execution status of the read
command. When the copy command has completed, the
contents of the buffer that dst_ptr
points to can be used by the application.
size
The size in bytes of data being copied.
dst_ptr
The pointer to a memory region where data is copied to.
src_ptr
The pointer to a memory region where data is copied from.
If dst_ptr and/or src_ptr are
allocated using clSVMAlloc
then they must be allocated from the
same context from which command_queue was created.
Otherwise the behavior is undefined.
event_wait_list and num_events_in_wait_list
Specify events that need to complete before
clEnqueueSVMMemcpy can be executed. If
event_wait_list is NULL, then
clEnqueueSVMMemcpy
does not wait on any event to complete. If
event_wait_list is NULL,
num_events_in_wait_list
must be 0. If event_wait_list is not
NULL, the list of events pointed to by
event_wait_list must
be valid and num_events_in_wait_list
must be greater than 0. The events specified in
event_wait_list act as synchronization
points. The context associated with events in
event_wait_list and
command_queue must be the same.
The memory associated with
event_wait_list can be
reused or freed after the function returns.
event
Returns an event object that
identifies this particular command and can be used to query or
queue a wait for this particular command to complete.
event can be NULL in which case it will
not be possible for the application to query the
status of this command or queue a wait for this
command to complete. If the event_wait_list
and the event arguments are not NULL,
the event
argument should not refer to an element of the
event_wait_list array.
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
command_queue is not a valid host command-queue.
command_queue and events in
event_wait_list are not the same.
event_wait_list is NULL and
num_events_in_wait_list > 0, or
event_wait_list is not NULL and
num_events_in_wait_list is 0, or
if event objects in event_wait_list
are not valid events.
event_wait_list
is a negative integer value.
dst_ptr or src_ptr are NULL.
size is 0.
dst_ptr,
src_ptr and size result in
an overlapping copy.
Shared Virtual Memory Functions
public static int clEnqueueSVMMemFill(cl_command_queue command_queue, Pointer svm_ptr, Pointer pattern, long pattern_size, long size, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command to fill a region in memory with a pattern of a given pattern size.
cl_int
clEnqueueSVMMemFill
(
|
cl_command_queue command_queue , |
| void *svm_ptr , | |
| const void *pattern , | |
| size_t pattern_size , | |
| size_t size , | |
| cl_uint num_events_in_wait_list , | |
| const cl_event *event_wait_list , | |
cl_event
*event
)
|
command_queue
Refers to the host command-queue in which the fill command will be queued.
The OpenCL context associated with command_queue
and SVM pointer referred to by svm_ptr must be the same.
svm_ptr
A pointer to a memory region that will be filled with
pattern. It must be aligned to
pattern_size bytes. If
svm_ptr is allocated using
clSVMAlloc
then it must be allocated from the
same context from which
command_queue was created.
Otherwise the behavior is undefined.
pattern
A pointer to the data pattern of size pattern_size
in bytes. pattern will be used to fill a region
in buffer starting at svm_ptr
and is size bytes in size. The data pattern
must be a scalar or vector integer or floating-point data type. For
example, if region pointed to by svm_ptr
is to be filled with a pattern of
float4 values, then pattern will be a pointer
to a cl_float4 value and pattern_size
will be sizeof(cl_float4). The maximum value of
pattern_size is the size of the largest integer
or floating-point vector data type supported by the OpenCL device.
The memory associated with pattern can be reused or
freed after the function returns.
size
The size in bytes of region being filled starting with svm_ptr
and must be a multiple of pattern_size.
event_wait_list
,
num_events_in_wait_list
Specify events that need to complete before this particular
command can be executed. If event_wait_list
is NULL, then this particular command does not wait on any
event to complete. If event_wait_list is
NULL, num_events_in_wait_list must be 0. If
event_wait_list is not NULL, the list of events
pointed to by event_wait_list must be valid
and num_events_in_wait_list must be greater
than 0. The events specified in event_wait_list
act as synchronization points. The context associated with events in
event_wait_list and command_queue must
be the same. The memory associated with event_wait_list
can be reused or freed after the function returns.
event
Returns an event object that identifies this particular write
command and can be used to query or queue a wait for this particular
command to complete. event can be NULL in
which case it will not be possible for the application to query the
status of this command or queue a wait for this command to complete.
clEnqueueBarrierWithWaitList
can be used instead. If the event_wait_list
and the event arguments are not NULL, the
event argument should not refer to an element of the
event_wait_list array.
clEnqueueSVMMemFill returns CL_SUCCESS if
the function is executed successfully. Otherwise, it returns one of the following errors.
command_queue
is not a valid host command-queue.
command_queue and events in
event_wait_list are not the same.
svm_ptr is NULL.
svm_ptr is not aligned to pattern_size bytes.
pattern is NULL
or if pattern_size is 0 or if pattern_size
is not one of {1, 2, 4, 8, 16, 32, 64, 128}.
size
is not a multiple of pattern_size.
event_wait_list is NULL and
num_events_in_wait_list > 0,
or event_wait_list is not NULL and
num_events_in_wait_list is 0, or if event objects in
event_wait_list are not valid events.
Shared Virtual Memory Functions
public static int clEnqueueSVMMap(cl_command_queue command_queue, boolean blocking_map, long flags, Pointer svm_ptr, long size, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command that will allow the host to update a region of a SVM buffer.
cl_int clEnqueueSVMMap
(
|
cl_command_queue command_queue, |
| cl_bool blocking_map, | |
| cl_map_flags map_flags, | |
| void *svm_ptr, | |
| size_t size, | |
| cl_uint num_events_in_wait_list, | |
| const cl_event *event_wait_list, | |
cl_event *event) |
command_queue
Must be a valid host command-queue.
blocking_map
Indicates if the map operation is blocking or
non-blocking.
If blocking_map is CL_TRUE,
clEnqueueSVMMap does not return until the application can
access the contents of the SVM region specified by
svm_ptr and size on the host.
If blocking_map is CL_FALSE
i.e. map operation is non-blocking, the region specified by
svm_ptr and size
cannot be used until the map command has completed.
The event argument
returns an event object which can be used to query
the execution status of the map command.
When the map command is completed, the application
can access the contents of the region
specified by svm_ptr and
size.
map_flags
A bit-bield with the following supported values.
| cl_map_flags | Description |
|---|---|
CL_MAP_READ
|
This flag specifies that the region being mapped in the memory object is being mapped for reading.
The pointer returned by
|
CL_MAP_WRITE
|
This flag specifies that the region being mapped in the memory object is being mapped for writing.
The pointer returned by
|
CL_MAP_WRITE_INVALIDATE_REGION
|
This flag specifies that the region being mapped in the memory object is being mapped for writing.
The contents of the region being mapped are to be discarded.
This is typically the case
when the region being mapped is overwritten by the host. This
flag allows the implementation
to no longer guarantee that the pointer returned by
|
svm_ptr and size
A pointer to a memory region and size in bytes
that will be updated by the
host. If svm_ptr is allocated using
clSVMAlloc
then it must be allocated from the same context
from which command_queue was created.
Otherwise the behavior is undefined.
event_wait_list,
num_events_in_wait_list
Specify events that need to complete before this particular
command can be executed. If event_wait_list
is NULL, then this particular command does not wait on any
event to complete. If event_wait_list is
NULL, num_events_in_wait_list must be 0. If
event_wait_list is not NULL, the list of events
pointed to by event_wait_list must be valid
and num_events_in_wait_list must be greater
than 0. The events specified in event_wait_list
act as synchronization points. The context associated with events in
event_wait_list and command_queue must
be the same. The memory associated with event_wait_list
can be reused or freed after the function returns.
event
Returns an event object that identifies this particular command
and can be used to query or queue a wait for this particular command
to complete. event can be NULL in which case
it will not be possible for the application to query the status of
this command or queue a wait for this command to complete.
clEnqueueBarrierWithWaitList
can be used instead. If the
event_wait_list and the event
arguments are not NULL, the event argument should not
refer to an element of the event_wait_list array.
Note that since we are enqueuing a command with a SVM buffer, the region is already mapped in the host address space.
clEnqueueSVMMap, and clEnqueueSVMUnmap act as synchronization points for the region of the SVM buffer specified in these calls.
clEnqueueSVMMap returns CL_SUCCESS
if the function is executed successfully. Otherwise,
it returns one of the following errors:
command_queue
is not a valid host command-queue.
command_queue
and events in event_wait_list are not the same.
svm_ptr is NULL.
size
is 0 or if values specified in map_flags are not valid.
event_wait_list is NULL and
num_events_in_wait_list > 0,
or event_wait_list is not NULL and
num_events_in_wait_list is 0, or if event objects in
event_wait_list are not valid events.
event_wait_list is a negative
integer value.
Shared Virtual Memory Functions
public static int clEnqueueSVMUnmap(cl_command_queue command_queue, Pointer svm_ptr, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Enqueues a command to indicate that the host has completed
updating the region given by
svm_ptr and which was specified in a
previous call to clEnqueueSVMMap.
cl_int
clEnqueueSVMUnmap
(
|
cl_command_queue command_queue , |
| void *svm_ptr, | |
| cl_uint num_events_in_wait_list , | |
| const cl_event *event_wait_list , | |
cl_event
*event
)
|
command_queue
Must be a valid host command-queue.
svm_ptr
A pointer that was specified in a previous call to
clEnqueueSVMMap.
If svm_ptr is
allocated using clSVMAlloc
then it must be allocated from the same context from which
command_queue was created.
Otherwise the behavior is undefined.
event_wait_list
,
num_events_in_wait_list
Specify events that need to complete before
clEnqueueSVMUnmap can be
executed. If event_wait_list is NULL, then
clEnqueueSVMUnmap does not wait on
any event to complete. If event_wait_list
is NULL, num_events_in_wait_list must be 0. If
event_wait_list is not NULL, the list of events
pointed to by event_wait_list must be valid
and num_events_in_wait_list must be greater
than 0. The events specified in event_wait_list
act as synchronization points. The context associated with events in
event_wait_list and command_queue must
be the same. The memory associated with event_wait_list
can be reused or freed after the function returns.
event
Returns an event object that identifies this particular command
and can be used to query or queue a wait for this particular
command to complete. event can be NULL in
which case it will not be possible for the application to query the
status of this command or queue a wait for this command to complete.
clEnqueueBarrierWithWaitList
can be used instead.
If the event_wait_list and the event arguments are not NULL,
the event argument should not refer to an
element of the event_wait_list array.
clEnqueueSVMMap, and clEnqueueSVMUnmap act as synchronization points for the region of the SVM buffer specified in these calls.
If a coarse-grained SVM buffer is currently mapped for writing, the application must ensure that the SVM buffer is unmapped before any enqueued kernels or commands that read from or write to this SVM buffer or any of its associated cl_mem buffer objects begin execution; otherwise the behavior is undefined.
If a coarse-grained SVM buffer is currently mapped for reading, the application must ensure that the SVM buffer is unmapped before any enqueued kernels or commands that write to this memory object or any of its associated cl_mem buffer objects begin execution; otherwise the behavior is undefined.
A SVM buffer is considered as mapped if there are one or more active mappings for the SVM buffer irrespective of whether the mapped regions span the entire SVM buffer.
The above note does not apply to fine-grained SVM buffers (fine-grained buffers allocated using clSVMAlloc or fine-grained system allocations).
clEnqueueSVMUnmap returns CL_SUCCESS
if the function is executed successfully. Otherwise, it returns one of the following
errors:
command_queue
is not a valid host command-queue.
command_queue and events in
event_wait_list are not the same.
svm_ptr is NULL.
event_wait_list is NULL and
num_events_in_wait_list > 0,
or event_wait_list is not NULL and
num_events_in_wait_list is 0, or if event objects in
event_wait_list are not valid events.
Shared Virtual Memory Functions
public static int clEnqueueMarker(cl_command_queue command_queue, cl_event event)
Enqueues a marker command.
cl_int
clEnqueueMarker
(
|
cl_command_queuecommand_queue, |
cl_event*event) |
Enqueues a marker command to command_queue. The marker command is not completed until
all commands enqueued before it have completed. The marker command returns an event which
can be waited on, i.e. this event can be waited on to ensure that all commands which have been queued before the market command have been completed.
complete.
Returns CL_SUCCESS if the function executed successfully, or one of the errors below:
command_queue is not a valid command-queue.
event is a NULL value.
public static int clEnqueueWaitForEvents(cl_command_queue command_queue, int num_events, cl_event[] event_list)
Enqueues a wait for a specific event or a list of events to complete before any future commands queued in the command-queue are executed.
cl_int
clEnqueueWaitForEvents
(
|
cl_command_queuecommand_queue, |
| cl_uintnum_events, | |
const cl_event*event_list) |
command_queue
A valid command-queue.
num_events
Specifies the number of events given by event_list.
event_list
Events specified in event_list act as synchronization points. The context associated
with events in event_list and command_queue must be the same.
Each event in event_list must be a valid event object returned by a previous call
to the following:
The context associated with events in event_list and
command_queue must be the same.
Returns CL_SUCCESS if the function was successfully executed, or one of the errors below:
command_queue
is not a valid command-queue.
command_queue and events in event_list are not the same.
num_events is zero or
event_list is NULL.
event_list are not valid events.
public static int clEnqueueBarrier(cl_command_queue command_queue)
A synchronization point that enqueues a barrier operation.
cl_int
clEnqueueBarrier
(
|
cl_command_queuecommand_queue) |
clEnqueueBarrier is a synchronization point that ensures that all
queued commands in command_queue have finished execution before the next
batch of commands can begin execution.
Returns CL_SUCCESS if the function was successfully executed, or one of the errors below:
command_queue
is not a valid command-queue.
public static cl_mem clCreateFromGLBuffer(cl_context context, long flags, int bufobj, int[] errcode_ret)
Creates an OpenCL buffer object from an OpenGL buffer object.
cl_mem
clCreateFromGLBuffer
(
|
cl_contextcontext, |
| cl_mem_flagsflags, | |
| GLuintbufobj, | |
cl_int* errcode_ret) |
context
A valid OpenCL context created from an OpenGL context.
flags
A bit-field that is used to specify usage information.
Refer to the table for
clCreateBuffer
for a description of flags. Only
CL_MEM_READ_ONLY, CL_MEM_WRITE_ONLY and CL_MEM_READ_WRITE values specified in the table at clCreateBuffer
can be used.
bufobj
The name of a GL buffer object. The data store of the GL buffer object must have have been previously created by calling OpenGL function glBufferData, although its contents need not be initialized. The size of the data store will be used to determine the size of the CL buffer object.
errcode_ret
Returns an appropriate error code as described below. If errcode_ret is NULL, no error code is returned.
The size of the GL buffer object data store at the time clCreateFromGLBuffer is called will be used as the size of buffer object returned by clCreateFromGLBuffer. If the state of a GL buffer object is modified through the GL API (e.g. glBufferData) while there exists a corresponding CL buffer object, subsequent use of the CL buffer object will result in undefined behavior.
The clRetainMemObject and clReleaseMemObject functions can be used to retain and release the buffer object.
Returns a valid non-zero OpenCL buffer object and errcode_ret is set
to CL_SUCCESS if the buffer object is created successfully. Otherwise, it returns a NULL value
with one of the following error values returned in errcode_ret:
context is not a valid context or was
not created from a GL context.
flags are not valid.
bufobj is not a GL buffer object or is a
GL buffer object but does not have an existing data store.
public static cl_mem clCreateFromGLTexture(cl_context context, long flags, int target, int miplevel, int texture, int[] errcode_ret)
Creates an OpenCL image object, image array object, or image buffer object from an OpenGL texture object, texture array object, texture buffer object, or a single face of an OpenGL cubemap texture object.
cl_mem
clCreateFromGLTexture
(
|
cl_context context, |
| cl_mem_flags flags, | |
| GLenum texture_target, | |
| GLint miplevel, | |
| GLuint texture, | |
cl_int * errcode_ret) |
context
A valid OpenCL context created from an OpenGL context.
flags
A bit-field that is used to
specify usage information. Refer to the table for
clCreateBuffer
for a description of flags. Only the values
CL_MEM_READ_ONLY, CL_MEM_WRITE_ONLY
and CL_MEM_READ_WRITE can be used.
texture_target
texture_target
This value must be one of GL_TEXTURE_1D,
GL_TEXTURE_1D_ARRAY,
GL_TEXTURE_BUFFER, GL_TEXTURE_2D,
GL_TEXTURE_2D_ARRAY, GL_TEXTURE_3D,
GL_TEXTURE_CUBE_MAP_POSITIVE_X,
GL_TEXTURE_CUBE_MAP_POSITIVE_Y,
GL_TEXTURE_CUBE_MAP_POSITIVE_Z,
GL_TEXTURE_CUBE_MAP_NEGATIVE_X,
GL_TEXTURE_CUBE_MAP_NEGATIVE_Y,
GL_TEXTURE_CUBE_MAP_NEGATIVE_Z, or
GL_TEXTURE_RECTANGLE.
(GL_TEXTURE_RECTANGLE requires OpenGL 3.1.
Alternatively, GL_TEXTURE_RECTANGLE_ARB may be
specified if the OpenGL extension GL_ARB_texture_rectangle is supported.)
texture_target is used only to define the image type
of texture. No reference to a bound GL texture object
is made or implied by this parameter.
If the cl_khr_gl_msaa_sharing
extension is enabled, texture_target
may be
GL_TEXTURE_2D_MULTISAMPLE or
GL_TEXTURE_2D_MULTISAMPLE_ARRAY.
If texture_target is
GL_TEXTURE_2D_MULTISAMPLE,
clCreateFromGLTexture
creates an
OpenCL 2D multi-sample image object from
an OpenGL 2D multi-sample texture
If texture_target is
GL_TEXTURE_2D_MULTISAMPLE_ARRAY,
clCreateFromGLTexture
creates an OpenCL 2D multi-sample array
image object from an OpenGL 2D multi-sample
texture.
miplevel
The mipmap level to be used. If
texture_target is GL_TEXTURE_BUFFER,
miplevel must be 0. Implementations may return
CL_INVALID_OPERATION for miplevel values > 0
texture
The name of a GL 1D, 2D, 3D, 1D array,
2D array, cubemap, rectangle or buffer texture object. The texture object
must be a complete texture as per OpenGL rules on texture completeness. The
texture format and dimensions defined by OpenGL for the
specified miplevel of the texture will be used to create
the OpenCL image memory object. Only GL texture objects with an internal
format that maps to appropriate image channel order and data type specified
in tables 5.5 and 5.6 (see
cl_image_format)
may be used to create the OpenCL image memory object.
errcode_ret
Returns an appropriate error code as described
below. If errcode_ret is NULL, no error code is returned.
If the state of a GL texture object is modified through the GL API
(e.g. glTexImage2D, glTexImage3D or
the values of the texture parameters GL_TEXTURE_BASE_LEVEL
or GL_TEXTURE_MAX_LEVEL are modified) while there exists a
corresponding CL image object, subsequent use of the CL image object will result in
undefined behavior.
The clRetainMemObject and clReleaseMemObject functions can be used to retain and release the image objects.
The OpenCL specification in section 9.7 defines how to
share data with texture and buffer objects in a parallel OpenGL implementation,
but does not define how the association between an OpenCL context and an OpenGL
context or share group is established. This extension defines optional attributes
to OpenCL context creation routines which associate a GL context or share group
object with a newly created OpenCL context. If this extension is supported
by an implementation, the string "cl_khr_gl_sharing" will be present in the
CL_DEVICE_EXTENSIONS
string described in the table of allowed values for param_name
for clGetDeviceInfo
or in the CL_PLATFORM_EXTENSIONS
string described in the table of allowed values for param_name
for clGetPlatformInfo.
This section discusses OpenCL functions that allow applications to use OpenGL buffer, texture, and renderbuffer objects as OpenCL memory objects. This allows efficient sharing of data between OpenCL and OpenGL. The OpenCL API may be used to execute kernels that read and/or write memory objects that are also OpenGL objects.
An OpenCL image object may be created from an OpenGL texture or renderbuffer object. An OpenCL buffer object may be created from an OpenGL buffer object.
OpenCL memory objects may be created from OpenGL objects
if and only if the OpenCL context has been created from an OpenGL share group
object or context. OpenGL share groups and contexts are created using platform
specific APIs such as EGL, CGL, WGL, and GLX. On MacOS X, an OpenCL context may
be created from an OpenGL share group object using the OpenCL platform extension
cl_apple_gl_sharing. On other platforms including Microsoft Windows, Linux/Unix and
others, an OpenCL context may be created from an OpenGL context using the Khronos
platform extension cl_khr_gl_sharing. Refer to the platform
documentation for your OpenCL implementation, or visit the Khronos Registry at
http://www.khronos.org/registry/cl/ for more information.
Any supported OpenGL object defined within the GL share group object, or the share group associated with the GL context from which the CL context is created, may be shared, with the exception of the default OpenGL objects (i.e. objects named zero), which may not be shared.
The table below (Table 9.4) describes the list of GL texture internal formats and the corresponding CL image formats. If a GL texture object with an internal format from the table below is successfully created by OpenGL, then there is guaranteed to be a mapping to one of the corresponding CL image format(s) in that table. Texture objects created with other OpenGL internal formats may (but are not guaranteed to) have a mapping to a CL image format; if such mappings exist, they are guaranteed to preserve all color components, data types, and at least the number of bits/component actually allocated by OpenGL for that format.
| GL internal format | CL image format (channel order, channel data type) |
|---|---|
GL_RGBA8
|
CL_RGBA, CL_UNORM_INT8 or CL_BGRA, CL_UNORM_INT8
|
GL_SRGBA8_ALPHA8
|
CL_sRGBA, CL_UNORM_INT8
|
GL_RGBA, GL_UNSIGNED_INT_8_8_8_8_REV |
CL_RGBA, CL_UNORM_INT8
|
GL_BGRA, GL_UNSIGNED_INT_8_8_8_8_REV |
CL_BGRA, CL_UNORM_INT8
|
GL_RGBA8I, GL_RGBA8I_EXT
|
CL_RGBA, CL_SIGNED_INT8
|
GL_RGBA16I, GL_RGBA16I_EXT
|
CL_RGBA, CL_SIGNED_INT16
|
GL_RGBA32I, GL_RGBA32I_EXT
|
CL_RGBA, CL_SIGNED_INT32
|
GL_RGBA8UI, GL_RGBA8UI_EXT
|
CL_RGBA, CL_UNSIGNED_INT8
|
GL_RGBA16UI, GL_RGBA16UI_EXT
|
CL_RGBA, CL_UNSIGNED_INT16
|
GL_RGBA32UI, GL_RGBA32UI_EXT
|
CL_RGBA, CL_UNSIGNED_INT32
|
GL_RGBA8_SNORM
|
CL_RGBA, CL_SNORM_INT8
|
GL_RGBA16
|
CL_RGBA, CL_UNORM_INT16
|
GL_RGBA16_SNORM
|
CL_RGBA, CL_SNORM_INT166
|
GL_RGBA16F, GL_RGBA16F_ARB
|
CL_RGBA, CL_HALF_FLOAT
|
GL_RGBA32F, GL_RGBA32F_ARB
|
CL_RGBA, CL_FLOAT
|
GL_R8
|
CL_R, CL_UNORM_INT8
|
GL_R8_SNORM
|
CL_R, CL_SNORM_INT8
|
GL_R16
|
CL_R, CL_UNORM_INT16
|
GL_R16_SNORM
|
CL_R, CL_SNORM_INT16
|
GL_R16F
|
CL_R, CL_HALF_FLOAT
|
GL_R32F
|
CL_R, CL_FLOAT
|
GL_R8I
|
CL_R, CL_SIGNED_INT8
|
GL_R16I
|
CL_R, CL_SIGNED_INT16
|
GL_R32I
|
CL_R, CL_SIGNED_INT32
|
GL_R8UI
|
CL_R, CL_UNSIGNED_INT8
|
GL_R16UI
|
CL_R, CL_UNSIGNED_INT16
|
GL_R32UI
|
CL_R, CL_UNSIGNED_INT32
|
GL_RG8
|
CL_RG, CL_UNORM_INT8
|
GL_RG8_SNORM
|
CL_RG, CL_SNORM_INT8
|
GL_RG16
|
CL_RG, CL_UNORM_INT16
|
GL_RG16_SNORM
|
CL_RG, CL_SNORM_INT16
|
GL_RG16F
|
CL_RG, CL_HALF_FLOAT
|
GL_RG32F
|
CL_RG, CL_FLOAT
|
GL_RG8I
|
CL_RG, CL_SIGNED_INT8
|
GL_RG16I
|
CL_RG, CL_SIGNED_INT16
|
GL_RG32I
|
CL_RG, CL_SIGNED_INT32
|
GL_RG8UI
|
CL_RG, CL_UNSIGNED_INT8
|
GL_RG16UI
|
CL_RG, CL_UNSIGNED_INT16
|
GL_RG32UI
|
CL_RG, CL_UNSIGNED_INT32
|
If the cl_khr_gl_depth_images extension is enabled, the following new image formats are added to table 9.4 in section 9.6.3.1 of the OpenCL 2.0 extension specification. If a GL texture object with an internal format from table 9.4 is successfully created by OpenGL, then there is guaranteed to be a mapping to one of the corresponding CL image format(s) in that table.
| GL internal format | CL image format (channel order, channel data type) |
|---|---|
GL_DEPTH_COMPONENT32F
|
CL_DEPTH, CL_FLOAT
|
GL_DEPTH_COMPONENT16
|
CL_DEPTH, CL_UNORM_INT16
|
GL_DEPTH24_STENCIL8
|
CL_DEPTH_STENCIL, CL_UNORM_INT24
|
GL_DEPTH32F_STENCIL8
|
CL_DEPTH_STENCIL, CL_FLOAT
|
An OpenCL memory object created from an OpenGL object
(hereinafter refered to as a "shared CL/GL object") remains valid as long as the
corresponding GL object has not been deleted. If the GL object is deleted through the GL
API (e.g. glDeleteBuffers, glDeleteTextures,
or glDeleteRenderbuffers), subsequent use of the CL buffer or image
object will result in undefined behavior, including but not limited to possible CL errors
and data corruption, but may not result in program termination.
The CL context and corresponding command-queues are dependent on the existence of the GL share group object, or the share group associated with the GL context from which the CL context is created. If the GL share group object or all GL contexts in the share group are destroyed, any use of the CL context or command-queue(s) will result in undefined behavior, which may include program termination. Applications should destroy the CL command-queue(s) and CL context before destroying the corresponding GL share group or contexts.
In order to ensure data integrity, the application is responsible for synchronizing access to shared CL/GL objects by their respective APIs. Failure to provide such synchronization may result in race conditions and other undefined behavior including non-portability between implementations.
Prior to calling clEnqueueAcquireGLObjects,
the application must ensure that any pending GL operations which access the objects
specified in mem_objects have completed. This may be accomplished
portably by issuing and waiting for completion of a glFinish
command on all GL contexts with pending references to these objects. Implementations
may offer more efficient synchronization methods; for example on some platforms calling
glFlush may be sufficient, or synchronization may be implicit within
a thread, or there may be vendor-specific extensions that enable placing a fence in the
GL command stream and waiting for completion of that fence in the CL command queue. Note
that no synchronization methods other than glFinish are portable
between OpenGL implementations at this time.
When the extension
cl_khr_egl_event
is supported: Prior to calling
clEnqueueAcquireGLObjects,
the application must ensure that any pending
EGL or EGL client API operations which access
the objects specified in mem_objects have
completed.
If the
cl_khr_egl_event
extension is supported and the EGL context in question supports fence
sync objects, explicit synchronisation can be achieved
as set out in section 5.7.1.
If the
cl_khr_egl_event
extension is not supported, completion of EGL client API commands
may be determined by issuing and waiting for completion of commands such as
glFinish or
vgFinish on all client API
contexts with pending references to these objects. Some
implementations may offer other efficient
synchronization methods. If such methods exist they
will be described in platform-specific documentation.
Note that no synchronization methods other than
glFinish and vgFinish
are portable between all
EGL client API implementations and all OpenCL
implementations. While this is the only way to
ensure completion that is portable to all platforms,
these are expensive operation and their use
should be avoided if the
cl_khr_egl_event extension
is supported on a platform.
Similarly, after calling
clEnqueueReleaseGLObjects, the application is responsible
for ensuring that any pending OpenCL operations which access the objects specified
in mem_objects have completed prior to executing subsequent GL
commands which reference these objects. This may be accomplished portably by calling
clWaitForEvents with the
event object returned by clEnqueueReleaseGLObjects, or by calling
clFinish. As above, some
implementations may offer more efficient methods.
The application is responsible for maintaining the proper order of operations if the CL and GL contexts are in separate threads.
If a GL context is bound to a thread other than the one in which
clEnqueueReleaseGLObjects is called, changes to any of the objects in
mem_objects may not be visible to that context without additional steps
being taken by the application. For an OpenGL 3.1 (or later) context, the requirements
are described in Appendix D ("Shared Objects and Multiple Contexts") of the OpenGL 3.1
Specification. For prior versions of OpenGL, the requirements are implementation-dependent.
Attempting to access the data store of an OpenGL object after it has been acquired by OpenCL and before it has been released will result in undefined behavior. Similarly, attempting to access a shared CL/GL object from OpenCL before it has been acquired by the OpenCL command queue, or after it has been released, will result in undefined behavior.
If the cl_khr_gl_event extension is supported, then the OpenCL implementation will ensure that any such pending OpenGL operations are complete for an OpenGL context bound to the same thread as the OpenCL context. This is referred to as implicit synchronization.
Returns a valid non-zero OpenCL image object and errcode_ret
is set to CL_SUCCESS if the image object is created
successfully. Otherwise, it returns a NULL value with one of the following error
values returned in errcode_ret:
context is not
a valid context or was not created from a GL context.
flags are not valid or if value specified in
texture_target is not one of the values specified in the
description of texture_target.
miplevel
is less than the value of levelbase
(for OpenGL implementations) or zero (for OpenGL ES implementations); or
greater than the value of q (for both OpenGL and OpenGL
ES). levelbase and q
are defined for the texture in section 3.8.10 (Texture Completeness) of the OpenGL
2.1 specification and section 3.7.10 of the OpenGL ES 2.0.
miplevel is
greater than zero and the OpenGL implementation does not support creating from
non-zero mipmap levels.
texture is not
a GL texture object whose type matches texture_target, if the
specified miplevel of texture is not defined,
or if the width or height of the specified miplevel is zero
or if the GL texture object is incomplete.
texture is a GL texture object
created with a border width value greater than zero.
cl_khr_gl_sharing, clCreateBuffer, clCreateFromGLBuffer
public static cl_mem clCreateFromGLTexture2D(cl_context context, long flags, int target, int miplevel, int texture, int[] errcode_ret)
clCreateFromGLTexture(cl_context, long, int, int, int, int[])Creates an OpenCL 2D image object from an OpenGL 2D texture object, or a single face of an OpenGL cubemap texture object.
cl_mem
clCreateFromGLTexture2D
(
|
cl_contextcontext, |
| cl_mem_flagsflags, | |
| GLenumtexture_target, | |
| GLintmiplevel, | |
| GLuinttexture, | |
cl_int*errcode_ret) |
context
A valid OpenCL context created from an OpenGL context.
flags
A bit-field that is used to specify usage information. Refer to
the table for
clCreateBuffer
for a description of flags. Only CL_MEM_READ_ONLY, CL_MEM_WRITE_ONLY and CL_MEM_READ_WRITE
values specified in the table for clCreateBuffer
may be used.
texture_target
Must be one of GL_TEXTURE_2D, GL_TEXTURE_CUBE_MAP_POSITIVE_X,
GL_TEXTURE_CUBE_MAP_POSITIVE_Y, GL_TEXTURE_CUBE_MAP_POSITIVE_Z,
GL_TEXTURE_CUBE_MAP_NEGATIVE_X, GL_TEXTURE_CUBE_MAP_NEGATIVE_Y,
GL_TEXTURE_CUBE_MAP_NEGATIVE_Z, or GL_TEXTURE_RECTANGLE. texture_target is
used only to define the image type of texture. No reference to a bound GL
texture object is made or implied by this parameter.
Using GL_TEXTURE_RECTANGLE for texture_target requires OpenGL 3.1. Alternatively, GL_TEXTURE_RECTANGLE_ARB may be specified if the OpenGL extension GL_ARB_texture_rectangle is supported.
miplevel
The mipmap level to be used. Implementations may return CL_INVALID_OPERATION for miplevel values greater than 0.
texture
The name of a GL 2D, cubemap or rectangle texture object. The
texture object must be a complete texture as per OpenGL rules on
texture completeness. The texture format and
dimensions defined by OpenGL for the specified miplevel
of the texture will be used to create the 2D image object. Only GL texture
objects with an internal format that maps to appropriate image channel order
and data type specified in the table of supported Image Channel Order
Values and the table of supported Image Channel Data Types for
cl_image_format
may be used to create a 2D image object.
errcode_ret
Returns an appropriate error code as described below.
If errcode_ret is NULL, no error code is returned.
Returns a valid non-zero OpenCL image object and errcode_ret is
set to CL_SUCCESS if the image object is
created successfully. Otherwise, it returns a NULL
value with one of the following error values returned in errcode_ret:
context
is not a valid context or was not created from a GL context.
flags are not valid or if value specified in
texture_target is not one of the values specified
in the description of texture_target.
miplevel is less
than the value of levelbase (for OpenGL
implementations) or zero (for OpenGL ES implementations); or greater than the value of
q (for both OpenGL and OpenGL ES).
levelbase and q
are defined for the texture in section 3.8.10 (Texture Completeness) of the OpenGL 2.1 specification and section 3.7.10 of the OpenGL ES 2.0 specification.
miplevel
is greater than zero and the OpenGL implementation does not support creating from non-zero mipmap levels.
texture
is not a GL texture object whose type matches
texture_target, if the specified miplevel of
texture is not defined,
or if the width or height
of the specified miplevel is zero.
texture
is a GL texture object created with a border width value greater than zero.
public static cl_mem clCreateFromGLTexture3D(cl_context context, long flags, int target, int miplevel, int texture, int[] errcode_ret)
clCreateFromGLTexture(cl_context, long, int, int, int, int[])Creates an OpenCL 3D image object from an OpenGL 3D texture object.
cl_mem
clCreateFromGLTexture3D
(
|
cl_contextcontext, |
| cl_mem_flagsflags, | |
| GLenumtexture_target, | |
| GLintmiplevel, | |
| GLuinttexture, | |
cl_int* errcode_ret) |
context
A valid OpenCL context created from an OpenGL 3D context.
flags
A bit-field that is used to specify usage information. Refer to
the table for
clCreateBuffer
for a description of flags. Only the valuesCL_MEM_READ_ONLY, CL_MEM_WRITE_ONLY and CL_MEM_READ_WRITE can be used.
texture_target
texture_target is used only to define the image
type of texture. Must be GL_TEXTURE_3D. No reference to
a bound GL texture object is made or implied by this parameter.
miplevel
The mipmap level to be used.
texture
The name of a GL 3D texture object. The texture object must be a
complete texture as per OpenGL rules on texture completeness. The
texture format and dimensions defined by OpenGL
for the specified miplevel of the texture will be
used to create the 3D image object. Only GL texture objects with an
internal format that maps to appropriate image channel order and data
type specified in the table of supported Image Channel Order Values
and the table of supported Image Channel Data Types at
cl_image_format can be used to create the 3D image object.
errcode_ret
Returns an appropriate error code as described below.
If errcode_ret is NULL, no error code is returned.
If the state of a GL texture object is modified through the GL API (e.g. the OpenGL functions
glTexImage2D, glTexImage3D,
or the values of the texture parameters GL_TEXTURE_BASE_LEVEL or
GL_TEXTURE_MAX_LEVEL are modified) while there exists a corresponding CL image object,
subsequent use of the CL image object will result in undefined behavior.
The
clRetainMemObject
and
clReleaseMemObject
functions can be used to retain and release
the image objects.
Returns a valid non-zero OpenCL image object and errcode_ret is
set to CL_SUCCESS if the image object is
created successfully. Otherwise, it returns a NULL
value with one of the following error values returned in errcode_ret:
context
is not a valid context or was not created from a GL context.
.
flags
are not valid or if value specified in texture_target is not one of the
values specified in the description of texture_target.
miplevel is less than the
value of levelbase (for OpenGL implementations) or zero
(for OpenGL ES implementations); or greater than the value of q (for both OpenGL
and OpenGL ES). levelbase and q are
defined for the texture in section 3.8.10 (Texture Completeness) of the OpenGL 2.1 specification
and section 3.7.10 of the OpenGL ES 2.0.
miplevel is greater
than zero and the OpenGL implementation does not support creating from non-zero mipmap levels.
texture is not a
GL texture object whose type matches texture_target, if the
specified miplevel of texture is not defined,
or if the width or height of the specified miplevel is zero.
public static cl_mem clCreateFromGLRenderbuffer(cl_context context, long flags, int renderbuffer, int[] errcode_ret)
Creates an OpenCL 2D image object from an OpenGL renderbuffer object.
cl_mem
clCreateFromGLRenderbuffer
(
|
cl_contextcontext, |
| cl_mem_flagsflags, | |
| GLuintrenderbuffer, | |
cl_int* errcode_ret) |
context
A valid OpenCL context created from an OpenGL context.
flags
A bit-field that is used to specify usage information. Refer to the table at clCreateBuffer for a description of flags. Only CL_MEM_READ_ONLY, CL_MEM_WRITE_ONLY, and CL_MEM_READ_WRITE values specified in the table at clCreateBuffer can be used.
renderbuffer
The name of a GL renderbuffer object. The renderbuffer storage must be
specified before the image object can be created. The renderbuffer
format and dimensions defined by OpenGL will be used to create the 2D image object. Only GL renderbuffers with
internal formats that map to appropriate image channel order and data type specified in the table of supported Image Channel Order Values and
the table of supported Image Channel Data Types for cl_image_format
can be used to create the 2D image object.
errcode_ret
Returns an appropriate error code as described below.
If errcode_ret is NULL, no error code is returned.
If the state of a GL renderbuffer object is modified through the GL API (i.e. changes to the
dimensions or format used to represent pixels of the GL renderbuffer using appropriate GL API
calls such as glRenderbufferStorage) while there exists a corresponding CL image object,
subsequent use of the CL image object will result in undefined behavior.
The clRetainMemObject and clReleaseMemObject functions can be used to retain and release the image objects.
The table below describes the list of GL renderbuffer internal formats and the corresponding CL image formats. If a GL renderbuffer object with an internal format from the table below is successfully created by OpenGL, then there is guaranteed to be a mapping to one of the corresponding CL image format(s) in that table. Renderbuffer objects created with other OpenGL internal formats may (but are not guaranteed to) have a mapping to a CL image format; if such mappings exist, they are guaranteed to preserve all color components, data types, and at least the number of bits/component actually allocated by OpenGL for that format.
| GL internal format | CL image format (channel order, channel data type) |
|---|---|
| GL_RGBA8 | CL_RGBA, CL_UNORM_INT8 or CL_BGRA, CL_UNORM_INT8 |
| GL_RGBA16 | CL_RGBA, CL_UNORM_INT16 |
| GL_RGBA8I, GL_RGBA8I_EXT | CL_RGBA, CL_SIGNED_INT8 |
| GL_RGBA16I, GL_RGBA16I_EXT | CL_RGBA, CL_SIGNED_INT16 |
| GL_RGBA32I, GL_RGBA32I_EXT | CL_RGBA, CL_SIGNED_INT32 |
| GL_RGBA8UI, GL_RGBA8UI_EXT | CL_RGBA, CL_UNSIGNED_INT8 |
| GL_RGBA16UI, GL_RGBA16UI_EXT | CL_RGBA, CL_UNSIGNED_INT16 |
| GL_RGBA32UI, GL_RGBA32UI_EXT | CL_RGBA, CL_UNSIGNED_INT32 |
| GL_RGBA16F, GL_RGBA16F_ARB | CL_RGBA, CL_HALF_FLOAT |
| GL_RGBA32F, GL_RGBA32F_ARB | CL_RGBA, CL_FLOAT |
Returns a valid non-zero OpenCL image object and errcode_ret
is set to CL_SUCCESS if the image object is created successfully. Otherwise, it returns a NULL
value with one of the following error values returned in errcode_ret:
context is not
a valid context or was not created from a GL context.
flags are not valid.
renderbuffer
is not a GL renderbuffer object or if the width or height of renderbuffer is zero.
renderbuffer is a multi-sample
GL renderbuffer object.
public static int clGetGLObjectInfo(cl_mem memobj, int[] gl_object_type, int[] gl_object_name)
Query an OpenGL memory object used to create an OpenCL memory object.
cl_int
clGetGLObjectInfo
(
|
cl_memmemobj, |
| cl_gl_object_type*gl_object_type, | |
GLuint*gl_object_name) |
gl_object_type
Returns the type of GL object attached to memobj and can be
CL_GL_OBJECT_BUFFER,
CL_GL_OBJECT_TEXTURE2D,
CL_GL_OBJECT_TEXTURE3D, or
CL_GL_OBJECT_RENDERBUFFER.
If gl_object_type is NULL, it is ignored.
gl_object_name
Returns the GL object name used to create memobj. If gl_object_name is NULL,
it is ignored.
The OpenGL object used to create the OpenCL memory object and information about the object type i.e. whether it is a texture, renderbuffer, or buffer object can be queried using this function.
Returns CL_SUCCESS if the call was executed successfully. Otherwise, it returns one of the following errors:
memobj is not a valid OpenCL memory object
memobj.
public static int clGetGLTextureInfo(cl_mem memobj, int param_name, long param_value_size, Pointer param_value, long[] param_value_size_ret)
Returns additional information about the GL texture object associated with a memory object.
cl_int
clGetGLTextureInfo
(
|
cl_memmemobj, |
| cl_gl_texture_infoparam_name, | |
| size_tparam_value_size, | |
| void*param_value, | |
size_t*param_value_size_ret) |
param_name
Specifies what additional information about the GL texture object associated with
memobj to query. The list of supported
param_name types and the information returned in
param_value by
clGetGLTextureInfo
is described in the table below.
param_value
A pointer to memory where the result being queried is returned. If param_value
is NULL, it is ignored.
param_value_size
Specifies the size in bytes of memory pointed to by param_value.
This size must be >= size of return type as described in the table below.
param_value_size_ret
Returns the actual size in bytes of data copied to param_value. If
param_value_size_ret is NULL, it is ignored.
| cl_gl_texture_info | Return Type | Information returned in param_value |
|---|---|---|
CL_GL_TEXTURE_TARGET
|
GLenum |
The texture_target argument specified in
clCreateGLTexture2D or
clCreateGLTexture3D.
|
CL_GL_MIPMAP_LEVEL
|
GLint |
The miplevel argument specified in
clCreateGLTexture2D or
clCreateGLTexture3D.
|
Returns CL_SUCCESS if the function is executed successfully. Otherwise, it returns one of the following errors:
memobj is not a valid OpenCL
memory object
memobj.
param_name is not valid, or if size
in bytes specified by param_value_size is less than the size of return type as
described in the table above and param_value is not NULL, or if
param_value and param_value_size_ret are NULL.
public static int clEnqueueAcquireGLObjects(cl_command_queue command_queue, int num_objects, cl_mem[] mem_objects, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Acquire OpenCL memory objects that have been created from OpenGL objects.
cl_int
clEnqueueAcquireGLObjects
(
|
cl_command_queuecommand_queue, |
| cl_uintnum_objects, | |
| const cl_mem*mem_objects, | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
cl_event*event) |
command_queue
A valid command-queue. All devices used to create the OpenCL context
associated with command_queue must support acquiring shared CL/GL objects.
This constraint is enforced at context creation time.
num_objects
The number of memory objects to be acquired in mem_objects.
mem_objects
A pointer to a list of CL memory objects that correspond to GL objects.
event_wait_list
,
num_events_in_wait_list
Specify events that need to complete before this
particular command can be executed. If event_wait_list is NULL, then this particular command
does not wait on any event to complete. If event_wait_list is NULL,
num_events_in_wait_list
must be 0. If event_wait_list is not NULL,
the list of events pointed to by event_wait_list must
be valid and num_events_in_wait_list must be greater than 0.
The events specified in
event_wait_list act as synchronization points.
event
Returns an event object that identifies this command and can be used to query or queue a
wait for the command to complete. event can be NULL in which
case it will not be possible for the application to query the status of this command or queue
a wait for this command to complete.
When the cl_khr_gl_event extension is enabled, If an OpenGL context is bound to the current thread, then any OpenGL commands which:
mem_objects list, and
will complete before execution of any OpenCL commands following the
clEnqueueAcquireGLObjects
which affect or access any of those memory objects. If a non-NULL event object is
returned, it will report completion only after completion of such OpenGL commands.
These
objects need to be acquired before they can be used by any OpenCL commands queued to a
command-queue. The OpenGL objects are acquired by the OpenCL context associated with
command_queue and can therefore be used by all command-queues associated with the OpenCL
context.
In order to ensure data integrity, the application is responsible for synchronizing access to shared CL/GL objects by their respective APIs. Failure to provide such synchronization may result in race conditions and other undefined behavior including non-portability between implementations.
Prior to calling clEnqueueAcquireGLObjects, the application
must ensure that any pending GL operations which access the objects specified in
mem_objects have completed. This may be accomplished portably
by issuing and waiting for completion of a
glFinish command on
all GL contexts with pending references to these objects. Implementations may
offer more efficient synchronization methods; for example on some platforms
calling glFlush
may be sufficient, or synchronization may be implicit within a thread, or
there may be vendor-specific extensions that enable placing a fence in the
GL command stream and waiting for completion of that fence in the
CL command queue. Note that no synchronization methods other than
glFinish are
portable between OpenGL implementations at this time.
Similarly, after calling clEnqueueReleaseGLObjects,
the application is responsible for ensuring that any pending OpenCL operations
which access the objects specified in mem_objects have
completed prior to executing subsequent GL commands which reference these objects. This
may be accomplished portably by calling clWaitForEvents with the event object returned by
clEnqueueReleaseGLObjects, or by calling glFinish. As above, some implementations may
offer more efficient methods.
The application is responsible for maintaining the proper order of operations if the CL and GL contexts are in separate threads.
If a GL context is bound to a thread other than the one in which clEnqueueReleaseGLObjects
is called, changes to any of the objects in mem_objects may not be visible to that context without
additional steps being taken by the application. For an OpenGL 3.1 (or later) context, the
requirements are described in Appendix G ("Shared Objects and Multiple Contexts") of the
OpenGL 3.1 Specification. For prior versions of OpenGL, the requirements are implementationdependent.
Attempting to access the data store of an OpenGL object after it has been acquired by OpenCL and before it has been released will result in undefined behavior. Similarly, attempting to access a shared CL/GL object from OpenCL before it has been acquired by the OpenCL command queue, or after it has been released, will result in undefined behavior.
Returns CL_SUCCESS if the function is executed successfully. If
num_objects is 0 and mem_objects is NULL
the function does nothing and returns CL_SUCCESS.
Otherwise, it returns one of the following errors:
num_objects is zero and
mem_objects is not a NULL value or if num_objects > 0
and mem_objects is NULL.
mem_objects
are not valid OpenCL memory objects.
command_queue is not a
valid command-queue.
command_queue
was not created from an OpenGL context.
mem_objects
have not been created from a GL object(s).
event_wait_list
is NULL and num_events_in_wait_list > 0, or
event_wait_list is not NULL and
num_events_in_wait_list is 0, or if event objects in
event_wait_list are not valid events.
public static int clEnqueueReleaseGLObjects(cl_command_queue command_queue, int num_objects, cl_mem[] mem_objects, int num_events_in_wait_list, cl_event[] event_wait_list, cl_event event)
Release OpenCL memory objects that have been created from OpenGL objects.
cl_int
clEnqueueReleaseGLObjects
(
|
cl_command_queuecommand_queue, |
| cl_uintnum_objects, | |
| const cl_mem*mem_objects, | |
| cl_uintnum_events_in_wait_list, | |
| const cl_event*event_wait_list, | |
cl_event*event) |
command_queue
A valid command-queue.
num_objects
The number of memory objects to be released in mem_objects.
mem_objects
A pointer to a list of CL memory objects that correspond to GL objects.
event_wait_list
,
num_events_in_wait_list
These parameters specify events that need to complete before this
command can be executed. If event_wait_list is NULL, then this particular command
does not wait on any event to complete. If event_wait_list is NULL,
num_events_in_wait_list
must be 0. If event_wait_list is not NULL,
the list of events pointed to by event_wait_list must
be valid and num_events_in_wait_list must be greater than 0.
The events specified in
event_wait_list act as synchronization points.
event
Returns an event object that identifies this particular read/write
command and can be used to query or queue a wait for the command to complete.
event can be NULL in which case it will not be possible
for the application to query the status of this command or queue a wait
for this command to complete.
When the cl_khr_gl_event extension is enabled, If an OpenGL context is bound to the current thread, then any OpenGL commands which:
mem_objects list, and
will not execute until after execution of any OpenCL commands preceding the
clEnqueueReleaseGLObjects
which affect or access any of those memory objects. If a non-NULL event object is
returned, it will report completion before execution of such OpenGL commands.
These objects need to be released before they can be used by OpenGL.
The OpenGL objects are released by the OpenCL context associated with command_queue.
In order to ensure data integrity, the application is responsible for synchronizing access to shared CL/GL objects by their respective APIs. Failure to provide such synchronization may result in race conditions and other undefined behavior including non-portability between implementations.
Prior to calling clEnqueueAcquireGLObjects, the application
must ensure that any pending GL operations which access the objects specified in
mem_objects have completed. This may be accomplished portably
by issuing and waiting for completion of a
glFinish command on
all GL contexts with pending references to these objects. Implementations may
offer more efficient synchronization methods; for example on some platforms
calling glFlush
may be sufficient, or synchronization may be implicit within a thread, or
there may be vendor-specific extensions that enable placing a fence in the
GL command stream and waiting for completion of that fence in the
CL command queue. Note that no synchronization methods other than
glFinish are
portable between OpenGL implementations at this time.
Similarly, after calling clEnqueueReleaseGLObjects,
the application is responsible for ensuring that any pending OpenCL operations
which access the objects specified in mem_objects have
completed prior to executing subsequent GL commands which reference these objects. This
may be accomplished portably by calling clWaitForEvents with the event object returned by
clEnqueueReleaseGLObjects, or by calling glFinish. As above, some implementations may
offer more efficient methods.
The application is responsible for maintaining the proper order of operations if the CL and GL contexts are in separate threads.
If a GL context is bound to a thread other than the one in which clEnqueueReleaseGLObjects
is called, changes to any of the objects in mem_objects may not be visible to that context without
additional steps being taken by the application. For an OpenGL 3.1 (or later) context, the
requirements are described in Appendix G ("Shared Objects and Multiple Contexts") of the
OpenGL 3.1 Specification. For prior versions of OpenGL, the requirements are implementationdependent.
Attempting to access the data store of an OpenGL object after it has been acquired by OpenCL and before it has been released will result in undefined behavior. Similarly, attempting to access a shared CL/GL object from OpenCL before it has been acquired by the OpenCL command queue, or after it has been released, will result in undefined behavior.
clEnqueueReleaseGLObjects returns CL_SUCCESS if the function is executed successfully. If num_objects is 0 and mem_objects is NULL the function does nothing and returns CL_SUCCESS. Otherwise, it returns one of the following errors:
num_objects is zero
and mem_objects is not a NULL value or if
num_objects > 0 and mem_objects is NULL.
mem_objects are not valid OpenCL memory objects.
command_queue
is not a valid command-queue.
command_queue was not created from an OpenGL context.
mem_objects
have not been created from a GL object(s).
event_wait_list is
NULL and num_events_in_wait_list > 0, or event_wait_list
is not NULL and num_events_in_wait_list is 0, or if event objects in
event_wait_list are not valid events.
public static java.nio.ByteBuffer allocateAligned(int size,
int alignment)
size - The size of the bufferalignment - The alignment, in bytes