AI/rocm-systems
2
0 Форкнуть 0
Код Задачи Запросы на слияние Действия Пакеты Проекты Релизы Вики Активность
76 333 коммитов 3 Ветки 0 Теги
develop
Граф коммитов
76333 Коммитов
This Branch
This Branch
Все ветки
Автор SHA1 Сообщение Дата
gobhardw 64866d9aa4 SWDEV-387956 : Added CTF in --help option and Fixed plugin path 
Change-Id: I666084ddd4f77c4e1c012b6ca13d101e11dbc494


[ROCm/rocprofiler commit: 31c9bc44e1]
 2023-05-23 00:42:16 +05:30
Saleel Kudchadker a5715294fb SWDEV-301667 - Add a flag for gpuvm kernargs 
HIP_FORCE_DEV_KERNARG=1 will create a device allocation for kernel arg
segment. Flag is 0 by default.

Change-Id: Iaaf5a149f3be8596568878d5d272268baf067c60


[ROCm/clr commit: 5436d362b1]
 2023-05-22 11:23:48 -04:00
Saleel Kudchadker 5436d362b1 SWDEV-301667 - Add a flag for gpuvm kernargs 
HIP_FORCE_DEV_KERNARG=1 will create a device allocation for kernel arg
segment. Flag is 0 by default.

Change-Id: Iaaf5a149f3be8596568878d5d272268baf067c60
 2023-05-22 11:23:48 -04:00
Saleel Kudchadker 9394aa2671 SWDEV-384557 - Do not fall back to compute 
- Use regular copy API if we exhaust free SDMA engines and not fall back
to compute copy. Falling to compute is affecting performance for
numerous apps that are GPU bound

Change-Id: I75c767eff0b9f5ada324301c5c327fe2c23a9806


[ROCm/clr commit: 60d9a4ebab]
 2023-05-22 11:23:23 -04:00
Saleel Kudchadker 60d9a4ebab SWDEV-384557 - Do not fall back to compute 
- Use regular copy API if we exhaust free SDMA engines and not fall back
to compute copy. Falling to compute is affecting performance for
numerous apps that are GPU bound

Change-Id: I75c767eff0b9f5ada324301c5c327fe2c23a9806
 2023-05-22 11:23:23 -04:00
Alex Voicu e266f8834b SWDEV-301667 - Kernelarg gpuvm 
Add aligned, nontemporal `memcpy` for kernarg.

Change-Id: I5d8ac76904feaf793b45ec2ea5fbd1069be20068


[ROCm/clr commit: 06df9e2efd]
 2023-05-22 11:21:14 -04:00
Alex Voicu 06df9e2efd SWDEV-301667 - Kernelarg gpuvm 
Add aligned, nontemporal `memcpy` for kernarg.

Change-Id: I5d8ac76904feaf793b45ec2ea5fbd1069be20068
 2023-05-22 11:21:14 -04:00
Bill(Shuzhou) Liu 6b5406091a SWDEV-400644: Reset the mutex only if errors 
To prevent reset the mutex while using it, only reset the mutex
if it cannot acquire it.

Change-Id: I95e0ed1bf543f285ce81b4df9c51e16a88081d38


[ROCm/rocm_smi_lib commit: 160c99d12d]
 2023-05-22 11:20:44 -04:00
Bill(Shuzhou) Liu 160c99d12d SWDEV-400644: Reset the mutex only if errors 
To prevent reset the mutex while using it, only reset the mutex
if it cannot acquire it.

Change-Id: I95e0ed1bf543f285ce81b4df9c51e16a88081d38
 2023-05-22 11:20:44 -04:00
Bill(Shuzhou) Liu a4c1afe5d4 SWDEV-400644: Reset the mutex only if errors 
To prevent reset the mutex while using it, only reset the mutex
if it cannot acquire it.

Change-Id: I95e0ed1bf543f285ce81b4df9c51e16a88081d38


[ROCm/amdsmi commit: 160c99d12d]
 2023-05-22 11:20:44 -04:00
kjayapra-amd 62302ac4fa SWDEV-393910 - Adding CAS expanders under gfx941 tag. 
Change-Id: I2c4bcf56be419d1f037b8555ad254a2dc49d0c5b


[ROCm/clr commit: feb22250f3]
 2023-05-22 09:59:05 -04:00
kjayapra-amd feb22250f3 SWDEV-393910 - Adding CAS expanders under gfx941 tag. 
Change-Id: I2c4bcf56be419d1f037b8555ad254a2dc49d0c5b
 2023-05-22 09:59:05 -04:00
Maisam Arif 01bd64c718 AMD-SMI-CLI - Updated amdsmi_interface calls to new headers 
Change-Id: I031f08c912f2cc77bba3a6f4356b5121072fb71e
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
 2023-05-22 08:35:22 -05:00
Maisam Arif 09940e45df AMD-SMI-CLI - Updated amdsmi_interface calls to new headers 
Change-Id: I031f08c912f2cc77bba3a6f4356b5121072fb71e
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>


[ROCm/amdsmi commit: 01bd64c718]
 2023-05-22 08:35:22 -05:00
Jenkins 853c8565f9 SWDEV-299127 - Merge 'develop' into 'amd-staging' 
Change-Id: If894c952261ecf4254ce686b40579c274d3407df


[ROCm/hip commit: 04fc963b72]
 2023-05-21 11:10:21 +00:00
Jenkins 04fc963b72 SWDEV-299127 - Merge 'develop' into 'amd-staging' 
Change-Id: If894c952261ecf4254ce686b40579c274d3407df
 2023-05-21 11:10:21 +00:00
coleramos425 702f2c2df6 Display first X chars in --kernel-names (#115) 
Signed-off-by: coleramos425 <colramos@amd.com>


[ROCm/rocprofiler-compute commit: 14df0584b4]
 2023-05-19 16:25:50 -05:00
coleramos425 14df0584b4 Display first X chars in --kernel-names (#115) 
Signed-off-by: coleramos425 <colramos@amd.com>
 2023-05-19 16:25:50 -05:00
coleramos425 4721c370dc Comply to Python formatting 
Signed-off-by: coleramos425 <colramos@amd.com>


[ROCm/rocprofiler-compute commit: dc89d64f11]
 2023-05-19 16:10:20 -05:00
coleramos425 dc89d64f11 Comply to Python formatting 
Signed-off-by: coleramos425 <colramos@amd.com>
 2023-05-19 16:10:20 -05:00
coleramos425 75fcd17e99 Add LDSBanks for LDS bw calc (#107) 
Signed-off-by: coleramos425 <colramos@amd.com>


[ROCm/rocprofiler-compute commit: 514b91b210]
 2023-05-19 16:08:23 -05:00
coleramos425 514b91b210 Add LDSBanks for LDS bw calc (#107) 
Signed-off-by: coleramos425 <colramos@amd.com>
 2023-05-19 16:08:23 -05:00
Ziyue Yang 4430e4448f Limit MSCCL reduce unrolling to pow-2 cases to shrink kernel size (#746) 
[ROCm/rccl commit: ed252c30f4]
 2023-05-19 11:46:36 -07:00
Ziyue Yang ed252c30f4 Limit MSCCL reduce unrolling to pow-2 cases to shrink kernel size (#746) 2023-05-19 11:46:36 -07:00
coleramos425 48c41e43ce Enhance logging 
Signed-off-by: coleramos425 <colramos@amd.com>


[ROCm/rocprofiler-compute commit: d23efe461e]
 2023-05-19 13:38:19 -05:00
coleramos425 d23efe461e Enhance logging 
Signed-off-by: coleramos425 <colramos@amd.com>
 2023-05-19 13:38:19 -05:00
coleramos425 6b3ad11dc6 Remove private submodules 
Signed-off-by: coleramos425 <colramos@amd.com>


[ROCm/rocprofiler-compute commit: ae3f562b6c]
 2023-05-19 12:41:00 -05:00
coleramos425 ae3f562b6c Remove private submodules 
Signed-off-by: coleramos425 <colramos@amd.com>
 2023-05-19 12:41:00 -05:00
Ammar ELWazir f7e7255f10 Fixing Record ID in queues.cpp 
Change-Id: I39aa90cdf399f47272b710a5377841c29708dfda
 2023-05-19 16:56:22 +00:00
Ammar ELWazir 5b7f2441be Fixing Record ID in queues.cpp 
Change-Id: I39aa90cdf399f47272b710a5377841c29708dfda


[ROCm/rocprofiler commit: f7e7255f10]
 2023-05-19 16:56:22 +00:00
ROCm CI Service Account 90aeea4edc SWDEV-393199 - Added new include file for opengl interop mappings for nvidia (#3228) 
Change-Id: Ic823cec1eb972ece4029595ebf2d52f569af444f



[ROCm/hip commit: d0448aa4c4]
 2023-05-19 09:23:31 -07:00
ROCm CI Service Account d0448aa4c4 SWDEV-393199 - Added new include file for opengl interop mappings for nvidia (#3228) 
Change-Id: Ic823cec1eb972ece4029595ebf2d52f569af444f
 2023-05-19 09:23:31 -07:00
Sam Wu 4020f56590 set rocm-docs-core v0.11.0 (#3232) 
[ROCm/hip commit: 9590069f9b]
 2023-05-19 09:22:53 -07:00
Sam Wu 9590069f9b set rocm-docs-core v0.11.0 (#3232) 2023-05-19 09:22:53 -07:00
David Yat Sin a1f3b619a7 Add mutex when reserving scratch 
This prevents race condition when creating queues concurrently.

Change-Id: I5ea9714926fe06e1719fcb2559cb485063355e4f
 2023-05-19 11:05:13 -04:00
David Yat Sin 255a645c3b Add mutex when reserving scratch 
This prevents race condition when creating queues concurrently.

Change-Id: I5ea9714926fe06e1719fcb2559cb485063355e4f


[ROCm/ROCR-Runtime commit: a1f3b619a7]
 2023-05-19 11:05:13 -04:00
Dalibor Stanisavljevic 1bc1d431d8 SWDEV-384793 - Clean up API 
Change-Id: I441b315d32df59a454e06d521e5ca8b2c229451a
Signed-off-by: Dalibor Stanisavljevic <Dalibor.Stanisavljevic@amd.com>
 2023-05-19 16:40:26 +02:00
Dalibor Stanisavljevic d95be94e51 SWDEV-384793 - Clean up API 
Change-Id: I441b315d32df59a454e06d521e5ca8b2c229451a
Signed-off-by: Dalibor Stanisavljevic <Dalibor.Stanisavljevic@amd.com>


[ROCm/amdsmi commit: 1bc1d431d8]
 2023-05-19 16:40:26 +02:00
Ioannis Assiouras fce1d56110 SWDEV-401495 - Removed hip_hcc.def.in 
Change-Id: Ia84503f0b9582f32de819f4ff95630fb024cd613


[ROCm/clr commit: 9d06e8c2d3]
 2023-05-19 11:47:07 +01:00
Ioannis Assiouras 9d06e8c2d3 SWDEV-401495 - Removed hip_hcc.def.in 
Change-Id: Ia84503f0b9582f32de819f4ff95630fb024cd613
 2023-05-19 11:47:07 +01:00
Sam Wu 74dce41f4f update documentation dependencies via requirements 
rocm-docs-core v0.11.0

Change-Id: I2ecc8c6015b9bb186e1b3241eb84bcbda9c46152
 2023-05-18 13:29:08 -06:00
Sam Wu 4b5c27bf33 update documentation dependencies via requirements 
rocm-docs-core v0.11.0

Change-Id: I2ecc8c6015b9bb186e1b3241eb84bcbda9c46152


[ROCm/rdc commit: 74dce41f4f]
 2023-05-18 13:29:08 -06:00
Ziyue Yang 73c6d51454 fix min, max and avg (#745) 
[ROCm/rccl commit: 11676267b5]
 2023-05-18 11:02:59 -07:00
Ziyue Yang 11676267b5 fix min, max and avg (#745) 2023-05-18 11:02:59 -07:00
Sam Wuиsamjwu 2707b6c6c1 Update documentation requirements (#743) 
Co-authored-by: samjwu <samjwu@users.noreply.github.com>

[ROCm/rccl commit: edb2ee1a44]
 2023-05-18 10:52:35 -06:00
Sam Wuиsamjwu edb2ee1a44 Update documentation requirements (#743) 
Co-authored-by: samjwu <samjwu@users.noreply.github.com>
 2023-05-18 10:52:35 -06:00
Wen-Heng (Jack) Chung 1bafe9c240 Merge pull request #742 from whchung/skip_done_event_msccl 
Allow skipping doneEvent inside MSCCL.

[ROCm/rccl commit: eba4e9e100]
 2023-05-18 10:17:20 -05:00
Wen-Heng (Jack) Chung eba4e9e100 Merge pull request #742 from whchung/skip_done_event_msccl 
Allow skipping doneEvent inside MSCCL.
 2023-05-18 10:17:20 -05:00
Wenkai Du f119977daa Fix merge error (#744) 
[ROCm/rccl commit: 403cda6322]
 2023-05-18 08:09:27 -07:00
Wenkai Du 403cda6322 Fix merge error (#744) 2023-05-18 08:09:27 -07:00