C Specification

To return profiling information for a command associated with an event when profiling is enabled, call the function

// Provided by CL_VERSION_1_0
cl_int clGetEventProfilingInfo(
    cl_event event,
    cl_profiling_info param_name,
    size_t param_value_size,
    void* param_value,
    size_t* param_value_size_ret);

Parameters

  • 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 Event Profiling Queries table.

  • param_value is 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 specified in the Event Profiling Queries table. If param_value is NULL, it is ignored.

  • param_value_size_ret returns the actual size in bytes of data being queried by param_name. If param_value_size_ret is NULL, it is ignored.

Description

Table 1. List of supported param_names by clGetEventProfilingInfo
Event Profiling Info Return Type Description

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.

If the cl_khr_command_buffer_multi_device extension is supported, for events returned by a command-buffer enqueue operation to multiple command-queues, the host time when the command-buffer has been enqueued across the command-queues is used.

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.

If the cl_khr_command_buffer_multi_device extension is supported, for events returned by a command-buffer enqueue operation to multiple command-queues, the host time is used when command-buffer commands have been submitted to any 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.

If the cl_khr_command_buffer_multi_device extension is supported, for events returned by a command-buffer enqueue operation to multiple command-queues, the host time is used when any device starts executing a command-buffer command.

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.

If the cl_khr_command_buffer_multi_device extension is supported, for events returned by a command-buffer enqueue operation to multiple command-queues, the host time is used when the last command-buffer command finishes execution on any device.

CL_PROFILING_COMMAND_COMPLETE

missing before version 2.0.

cl_ulong

A 64-bit value that describes the current device time counter in nanoseconds when the command identified by event and any child commands enqueued by this command on the device have finished execution.

If the cl_khr_command_buffer_multi_device extension is supported, for events returned by a command-buffer enqueue operation to multiple command-queues, the host time is used when the command-buffer has completed execution across all command-queues.

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.

If the cl_khr_command_buffer_multi_device extension is supported, and if no reliable device timer sources are available to inform the host side, or parallel runtime scheduling makes it impossible to identify a first/last command, then an implementation may fallback to reporting CL_PROFILING_COMMAND_SUBMIT and CL_PROFILING_COMMAND_COMPLETE for CL_PROFILING_COMMAND_START and CL_PROFILING_COMMAND_END respectively.

clGetEventProfilingInfo returns CL_SUCCESS if the function is executed successfully and the profiling information has been recorded. Otherwise, it returns one of the following errors:

  • CL_INVALID_EVENT if event is a not a valid event object.

  • CL_PROFILING_INFO_NOT_AVAILABLE if the CL_QUEUE_PROFILING_ENABLE flag is not set for the command-queue, if the execution status of the command identified by event is not CL_COMPLETE or if event is a user event object. Prior to OpenCL 3.0, implementations may return CL_PROFILING_INFO_NOT_AVAILABLE for an event created by clEnqueueSVMFree.
    If the cl_khr_command_buffer_multi_device extension is supported, and if event was created from a call to clEnqueueCommandBufferKHR, CL_PROFILING_INFO_NOT_AVAILABLE is returned if all the queues passed do not have CL_QUEUE_PROFILING_ENABLE set.

  • CL_INVALID_VALUE if param_name is not one of the supported values, or if the size in bytes specified by param_value_size is less than size of the return type specified in the Event Profiling Queries table and param_value is not a NULL value.

  • CL_OUT_OF_RESOURCES if there is a failure to allocate resources required by the OpenCL implementation on the device.

  • CL_OUT_OF_HOST_MEMORY if there is a failure to allocate resources required by the OpenCL implementation on the host.

See Also

CL_VERSION_1_0, cl_event, cl_profiling_info

Document Notes

For more information, see the OpenCL Specification

This page is extracted from the OpenCL Specification. Fixes and changes should be made to the Specification, not directly.

Copyright

Copyright 2014-2025 The Khronos Group Inc.

SPDX-License-Identifier: CC-BY-4.0