Commit Graph
64512 Commits
Author SHA1 Message Date
Chauncey Hui 27a162656e SWDEV-2 - Change OpenCL version number from 3407 to 3408
[ROCm/clr commit: e5122e3bc7]
2021-12-15 03:00:05 -05:00
Chauncey Hui e5122e3bc7 SWDEV-2 - Change OpenCL version number from 3407 to 3408 2021-12-15 03:00:05 -05:00
Jenkins 97b045950f SWDEV-299127 - Merge 'develop' into 'amd-staging'
Change-Id: Ifed915d87173b783770a2180320ccb746845dafe


[ROCm/hip commit: 2690a65d45]
2021-12-14 22:00:43 -05:00
Jenkins 2690a65d45 SWDEV-299127 - Merge 'develop' into 'amd-staging'
Change-Id: Ifed915d87173b783770a2180320ccb746845dafe
2021-12-14 22:00:43 -05:00
Harish Kasiviswanathan 16a9531a4d rocm_smi_lib: add stdbool.h needed for C90
'bool' keyword is supported only from C99 onwards. Include stdbool.h
for older compilers

Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Change-Id: I09fd5cf6eac20e7185e85a1123bc4826958b2b7c


[ROCm/rocm_smi_lib commit: 8de6ed2b8d]
2021-12-14 15:25:59 -05:00
Harish Kasiviswanathan 8de6ed2b8d rocm_smi_lib: add stdbool.h needed for C90
'bool' keyword is supported only from C99 onwards. Include stdbool.h
for older compilers

Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Change-Id: I09fd5cf6eac20e7185e85a1123bc4826958b2b7c
2021-12-14 15:25:59 -05:00
haoyuan2 7301a84351 SWDEV-303956 - align with CUDA to define float4 data type
Change-Id: I9ad1315e5899a8c0cf1812302b27010d88015f88


[ROCm/clr commit: 937415141c]
2021-12-14 15:22:43 -05:00
haoyuan2 937415141c SWDEV-303956 - align with CUDA to define float4 data type
Change-Id: I9ad1315e5899a8c0cf1812302b27010d88015f88
2021-12-14 15:22:43 -05:00
anusha GodavarthySurya a6227d8d87 SWDEV-313856, SWDEV-313907, SWDEV-313915 - Export StreamCapture APIs, handle few graph negitive senarios, set event, parallelstreams for endcapture
Change-Id: I3c6008e1a1195cd2e1a14ef24c943ef6b54033ab


[ROCm/clr commit: e3585209d7]
2021-12-14 05:54:13 -05:00
anusha GodavarthySurya e3585209d7 SWDEV-313856, SWDEV-313907, SWDEV-313915 - Export StreamCapture APIs, handle few graph negitive senarios, set event, parallelstreams for endcapture
Change-Id: I3c6008e1a1195cd2e1a14ef24c943ef6b54033ab
2021-12-14 05:54:13 -05:00
Saleel Kudchadker 42625f0527 SWDEV-313306 - Clear external signals
Crash was due to the fact that external signal structure was stale even
after destroyign the command. That is because we skipped wait due to a
missing check.
Detect external signals and dispatch a barrier in ReleaseGpuMemoryFence.
Also clear external_signals_ at ProfilingBegin.

Change-Id: I991387edcfe928b511bf5e780988ee131321ed5a


[ROCm/clr commit: 3239222516]
2021-12-13 23:03:33 -08:00
Saleel Kudchadker 3239222516 SWDEV-313306 - Clear external signals
Crash was due to the fact that external signal structure was stale even
after destroyign the command. That is because we skipped wait due to a
missing check.
Detect external signals and dispatch a barrier in ReleaseGpuMemoryFence.
Also clear external_signals_ at ProfilingBegin.

Change-Id: I991387edcfe928b511bf5e780988ee131321ed5a
2021-12-13 23:03:33 -08:00
Maneesh Gupta 4f37400363 Bump HIP version to 5.0 (#2435)
[ROCm/hip commit: df2e7fa198]
2021-12-13 13:56:55 +05:30
Maneesh Gupta df2e7fa198 Bump HIP version to 5.0 (#2435) 2021-12-13 13:56:55 +05:30
Maneesh Gupta 4ace90aa8e Update Jenkinsfile (#2436)
Temporarily disable tests that fail due to infra issues.

[ROCm/hip commit: 84721f7ab5]
2021-12-13 12:49:26 +05:30
Maneesh Gupta 84721f7ab5 Update Jenkinsfile (#2436)
Temporarily disable tests that fail due to infra issues.
2021-12-13 12:49:26 +05:30
Chauncey Hui 09b628c4e0 SWDEV-2 - Change OpenCL version number from 3406 to 3407
[ROCm/clr commit: 1b5de6e562]
2021-12-11 03:00:08 -05:00
Chauncey Hui 1b5de6e562 SWDEV-2 - Change OpenCL version number from 3406 to 3407 2021-12-11 03:00:08 -05:00
Sean Keely fce6ba052e Correct documentation typo.
ROCM_VISIBLE_DEVICES was used where ROCR_VISIBLE_DEVICES was
intended.

Change-Id: I644a546f3c9dd0b50898ef8a21dbb8f5c3a36926
2021-12-10 16:19:30 -06:00
Sean Keely ef1f4724c3 Correct documentation typo.
ROCM_VISIBLE_DEVICES was used where ROCR_VISIBLE_DEVICES was
intended.

Change-Id: I644a546f3c9dd0b50898ef8a21dbb8f5c3a36926


[ROCm/ROCR-Runtime commit: fce6ba052e]
2021-12-10 16:19:30 -06:00
haoyuan2 86520ebd83 SWDEV-311585 - workaround dynamic loading functional issue in Blender
Change-Id: I815724c0bdcb712e40ec1ed11b9632fab7243f69


[ROCm/clr commit: d1a491b30b]
2021-12-10 11:52:15 -08:00
haoyuan2 d1a491b30b SWDEV-311585 - workaround dynamic loading functional issue in Blender
Change-Id: I815724c0bdcb712e40ec1ed11b9632fab7243f69
2021-12-10 11:52:15 -08:00
German Andryeyev c759986e28 SWDEV-300515 - Apply CU granularity on the CU count
Report granularity for possible app query

Change-Id: I98857c6f4cc7ae590927ea35ce57d181abe7860b


[ROCm/clr commit: f613831471]
2021-12-10 10:47:28 -05:00
German Andryeyev f613831471 SWDEV-300515 - Apply CU granularity on the CU count
Report granularity for possible app query

Change-Id: I98857c6f4cc7ae590927ea35ce57d181abe7860b
2021-12-10 10:47:28 -05:00
Chauncey Hui aac7266191 SWDEV-2 - Change OpenCL version number from 3405 to 3406
[ROCm/clr commit: 7abd2827b5]
2021-12-10 03:00:08 -05:00
Chauncey Hui 7abd2827b5 SWDEV-2 - Change OpenCL version number from 3405 to 3406 2021-12-10 03:00:08 -05:00
haoyuan2 9735c1b617 SWDEV-290298 - add a flag to indicate the primary context active status
Change-Id: Id13d132923fcef697b689e75b6aa04060923a2ad


[ROCm/clr commit: 981ef060fb]
2021-12-09 23:32:16 -05:00
haoyuan2 981ef060fb SWDEV-290298 - add a flag to indicate the primary context active status
Change-Id: Id13d132923fcef697b689e75b6aa04060923a2ad
2021-12-09 23:32:16 -05:00
haoyuan2 248a738674 SWDEV-290298 - add a flag to indicate the primary context active status
Change-Id: Ia31790706d3f855bc1eedf5ef874e471


[ROCm/clr commit: 439af94dd9]
2021-12-09 23:28:54 -05:00
haoyuan2 439af94dd9 SWDEV-290298 - add a flag to indicate the primary context active status
Change-Id: Ia31790706d3f855bc1eedf5ef874e471
2021-12-09 23:28:54 -05:00
Alex Sierra 2dbee30232 kfdtest: free user ptr buffer at SetGetAttributesTest
Explicitly free the user buffer ptr before test's tear down. Otherwise
the svm_bo object will never be released, causing a BUG error. Due to
a late callback to svm_migrate_page_free when prange not longer exist.

Also did cosmetic adjustments.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Change-Id: I989c62de8a9634faa84e42def956cecb3f84e329
2021-12-09 18:22:20 -06:00
Alex Sierra 2ce2ce8229 kfdtest: free user ptr buffer at SetGetAttributesTest
Explicitly free the user buffer ptr before test's tear down. Otherwise
the svm_bo object will never be released, causing a BUG error. Due to
a late callback to svm_migrate_page_free when prange not longer exist.

Also did cosmetic adjustments.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Change-Id: I989c62de8a9634faa84e42def956cecb3f84e329


[ROCm/ROCR-Runtime commit: 2dbee30232]
2021-12-09 18:22:20 -06:00
Ajay f00e0a2df4 SWDEV-273235 - Linux: catch2 test packaging
Change-Id: I5b4e44b367d9310a66ea70c31c3e15ad45589166


[ROCm/clr commit: 9ed0c29bb6]
2021-12-09 17:51:25 -05:00
Ajay 9ed0c29bb6 SWDEV-273235 - Linux: catch2 test packaging
Change-Id: I5b4e44b367d9310a66ea70c31c3e15ad45589166
2021-12-09 17:51:25 -05:00
Sarbojit Sarkar 4630f3ade0 SWDEV-314254 - Fix for hipMemcpy3D test crash
Change-Id: Iac70bfe0d351cfb5b56fefc9a6487d3f26f2b4ef


[ROCm/clr commit: aedbad0109]
2021-12-09 11:46:52 -05:00
Sarbojit Sarkar aedbad0109 SWDEV-314254 - Fix for hipMemcpy3D test crash
Change-Id: Iac70bfe0d351cfb5b56fefc9a6487d3f26f2b4ef
2021-12-09 11:46:52 -05:00
Chauncey Hui 9b2abd8370 SWDEV-2 - Change OpenCL version number from 3404 to 3405
[ROCm/clr commit: 84af5eed4e]
2021-12-09 03:00:06 -05:00
Chauncey Hui 84af5eed4e SWDEV-2 - Change OpenCL version number from 3404 to 3405 2021-12-09 03:00:06 -05:00
Hao Zhou 6d2fbad79e Merge amd-staging into amd-master
Signed-off-by: Hao Zhou <Hao.Zhou@amd.com>
Change-Id: Ic324e60cd33d0db539537a978710d9c87c1dbd2e


[ROCm/rocm_smi_lib commit: 3ef213258b]
2021-12-09 10:24:19 +08:00
Hao Zhou 3ef213258b Merge amd-staging into amd-master
Signed-off-by: Hao Zhou <Hao.Zhou@amd.com>
Change-Id: Ic324e60cd33d0db539537a978710d9c87c1dbd2e
2021-12-09 10:24:19 +08:00
Jenkins 952bd4ca7f SWDEV-299127 - Merge 'develop' into 'amd-staging'
Change-Id: I8fd76e89d27ce4f5769aaafae0608dd1cf0f4187


[ROCm/hip commit: 609a0cd177]
2021-12-08 19:12:47 -05:00
Jenkins 609a0cd177 SWDEV-299127 - Merge 'develop' into 'amd-staging'
Change-Id: I8fd76e89d27ce4f5769aaafae0608dd1cf0f4187
2021-12-08 19:12:47 -05:00
Jeremy Newton fb6409b090 SWDEV-306262 - Add ocl-icd subpackages
These packages contains only the ICD loader (libopencl.so). This allows
legacy opencl (PAL) to use these packages instead of duplicating these
packages in both builds.

This also resolves a licensing issue where OCL ICD is licensed as
Apache, while opencl is MIT. Having a separate package avoid license
confusion.

Signed-off-by: Jeremy Newton <Jeremy.Newton@amd.com>
Change-Id: I3dd29239841da7f5dc767419a9bc35d9046e9936


[ROCm/clr commit: cb1e7cd48d]
2021-12-08 16:15:59 -05:00
Jeremy Newton cb1e7cd48d SWDEV-306262 - Add ocl-icd subpackages
These packages contains only the ICD loader (libopencl.so). This allows
legacy opencl (PAL) to use these packages instead of duplicating these
packages in both builds.

This also resolves a licensing issue where OCL ICD is licensed as
Apache, while opencl is MIT. Having a separate package avoid license
confusion.

Signed-off-by: Jeremy Newton <Jeremy.Newton@amd.com>
Change-Id: I3dd29239841da7f5dc767419a9bc35d9046e9936
2021-12-08 16:15:59 -05:00
German Andryeyev 5ad02b78c4 SWDEV-305016 - Improve MGPU scaling in Tensorflow
Add a threshold for ROCR/SDMA P2P transfers. ROCR copy path
requires extra barriers in compute for synchronization. That costs
extra performance with tiny transfers.
Reduce active wait time to 10us. Tensorflow uses extra thread
per GPU with constant hipEventQuery() calls. Longer active waits
in ROCr affect CPU performance.

Change-Id: I9020358438615fa2d4617f862f00a562f0a588e7


[ROCm/clr commit: 008133cf41]
2021-12-08 11:59:37 -05:00
German Andryeyev 008133cf41 SWDEV-305016 - Improve MGPU scaling in Tensorflow
Add a threshold for ROCR/SDMA P2P transfers. ROCR copy path
requires extra barriers in compute for synchronization. That costs
extra performance with tiny transfers.
Reduce active wait time to 10us. Tensorflow uses extra thread
per GPU with constant hipEventQuery() calls. Longer active waits
in ROCr affect CPU performance.

Change-Id: I9020358438615fa2d4617f862f00a562f0a588e7
2021-12-08 11:59:37 -05:00
Elena Sakhnovitch 5553c7fb40 [rocm_smi.py] remove \r symbol at print
Remove carriage return at the end of the line in printLog function.
On linux end of line is encoded with \n, not \n\r.

Change-Id: If3835d773033b53a7f25b4a0284df359a6f9555d


[ROCm/rocm_smi_lib commit: 1aeb27c4c9]
2021-12-08 10:13:56 -05:00
Elena Sakhnovitch 1aeb27c4c9 [rocm_smi.py] remove \r symbol at print
Remove carriage return at the end of the line in printLog function.
On linux end of line is encoded with \n, not \n\r.

Change-Id: If3835d773033b53a7f25b4a0284df359a6f9555d
2021-12-08 10:13:56 -05:00
Maneesh Gupta 9602e94c5b SWDEV-314299 - chomp HIP_CLANG_TARGET
HIP_CLANG_TARGET can contain newline. chomp it to avoid warnings since we use the result in file stat

[ROCm/hip commit: cddb52549b]
2021-12-08 17:02:31 +05:30
Maneesh Gupta cddb52549b SWDEV-314299 - chomp HIP_CLANG_TARGET
HIP_CLANG_TARGET can contain newline. chomp it to avoid warnings since we use the result in file stat
2021-12-08 17:02:31 +05:30