Update cl_arm_thread_limit_hint extension spec
Signed-off-by: Kevin Petit <kevin.petit@arm.com>
diff --git a/extensions/arm/cl_arm_thread_limit_hint.txt b/extensions/arm/cl_arm_thread_limit_hint.txt
index f3d662a..bf124eb 100644
--- a/extensions/arm/cl_arm_thread_limit_hint.txt
+++ b/extensions/arm/cl_arm_thread_limit_hint.txt
@@ -8,11 +8,12 @@
Contributors
- Robert Elliott, ARM
+ Robert Elliott, ARM Ltd.
+ Kévin Petit, ARM Ltd.
Contact
- Robert Elliott, ARM (robert.elliott 'at' ARM.com)
+ Kévin Petit, ARM Ltd. (kevin.petit 'at' ARM.com)
IP Status
@@ -20,7 +21,7 @@
Version
- Revision: #2, Feb 23rd, 2015
+ Revision: #3, Sept 28th, 2017
Number
@@ -40,10 +41,10 @@
Overview
- This extension provides a way for an application to provide a hint for the
- maximum threads to run concurrently on a compute unit. This results in a
- limit in the threads used by a kernel instance on some devices and results
- in a lower pressure on caches.
+ This extension enables an application to provide a hint for the maximum
+ number of threads allowed to run concurrently on a compute unit. This
+ results in a limit in the threads used by a kernel instance on devices
+ that support it, lowering pressure on caches.
Header File
@@ -68,8 +69,9 @@
The attribute can be specified as part of the declaration of a kernel and
provides a hint to the implementation that using fewer threads is desired.
- The hint must be the value 64, 128 or 256, and the hint cannot be provided
- without an explicit size.
+ The implementation will accept any number between 0 and
+ CL_DEVICE_MAX_WORK_GROUP_SIZE and choose the closest number that can be
+ used.
If the hint is larger than the maximum workgroup size supported by the
kernel for that device, it is not honored.
@@ -79,14 +81,14 @@
If the hint is not honored, a warning will be produced on context_notify.
- The hint will be honored on architectures which support this feature.
+ The hint will be honored on devices which support this feature.
New Tokens
OpenCL kernel code now has access to:
#pragma OPENCL EXTENSION cl_arm_thread_limit_hint : enable
- The define cl_arm_thread_limit_hint is also present
+ The define cl_arm_thread_limit_hint is also present.
Interactions with other extensions
@@ -124,3 +126,5 @@
Revision: #1, Feb 2nd, 2015 - Initial revision
Revision: #2, Feb 23rd, 2015 - Tidied up some of the language, added _hint
to the extension to be more consistent with other extensions.
+ Revision: #3, Sept 28th, 2017 - Relaxed the constraints on the number of
+ threads accepted. Clarified the wording.
