AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
64,625 Commits 3 Branches 0 Tags
620ccbeb82a7ca14d4a06fc62b3cc8a3aacda782
Commit Graph

64625 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Kian Cossettini ec683aefa7 Added compatibility matrix for docker-build script (#268) 
- matrix -m argument for build-docker.sh that lists compatible OS + ROCm combinations.
- ${DISTRO} is now case-insensitive.
- Added note to README.md to mention this flag.
- Removed --build-arg AMDGPU_RPM=${ROCM_RPM}, which is no longer used

[ROCm/rocprofiler-systems commit: 67bc147780]
 2025-07-08 11:05:14 -04:00
Kian Cossettini 67bc147780 Added compatibility matrix for docker-build script (#268) 
- matrix -m argument for build-docker.sh that lists compatible OS + ROCm combinations.
- ${DISTRO} is now case-insensitive.
- Added note to README.md to mention this flag.
- Removed --build-arg AMDGPU_RPM=${ROCM_RPM}, which is no longer used
 2025-07-08 11:05:14 -04:00
Sang, Tao fb408b70d1 SWDEV-508776 - support VGPRs validation (#77) 
Add hipDeviceAttributeMaxAvailableVgprsPerThread attribute

[ROCm/hip commit: 3b6b7642a7]
 2025-07-08 10:03:57 -04:00
Sang, Tao 3b6b7642a7 SWDEV-508776 - support VGPRs validation (#77) 
Add hipDeviceAttributeMaxAvailableVgprsPerThread attribute
 2025-07-08 10:03:57 -04:00
Fei Zheng 09ec955554 PC Sampling: fix potential_end_offset (#792) 
* fix potential_end_offset

* format code: unrelated

[ROCm/rocprofiler-compute commit: 1b7445faa4]
 2025-07-08 08:52:01 -04:00
Fei Zheng 1b7445faa4 PC Sampling: fix potential_end_offset (#792) 
* fix potential_end_offset

* format code: unrelated
 2025-07-08 08:52:01 -04:00
Fei Zheng c867eaa9cd format with isort (#793) 
[ROCm/rocprofiler-compute commit: 239e6550f4]
 2025-07-08 08:51:20 -04:00
Fei Zheng 239e6550f4 format with isort (#793) 2025-07-08 08:51:20 -04:00
fxmarty-amd a91e3f74f3 fix normalization (#789) 
[ROCm/rocprofiler-compute commit: c58ee9e73b]
 2025-07-08 08:50:41 -04:00
fxmarty-amd c58ee9e73b fix normalization (#789) 2025-07-08 08:50:41 -04:00
Patel, Jaydeepkumar 068f506131 SWDEV-535070 - In windows 2 separate commands may not go back to back and hence actual time taken should be always more than expected but not necessary to be close. (#219) 
[ROCm/hip-tests commit: f94fe3c26c]
 2025-07-08 15:55:49 +05:30
Patel, Jaydeepkumar f94fe3c26c SWDEV-535070 - In windows 2 separate commands may not go back to back and hence actual time taken should be always more than expected but not necessary to be close. (#219) 2025-07-08 15:55:49 +05:30
Gollamandala, Srinivasarao f05c8ddb2b SWDEV-532640-[catch2][dtest]-Prefetch all arguments and keep 0 hidden args if possible-PerfTest (#242) 
* SWDEV-532640-[catch2][dtest]-Prefetch all arguments and keep 0 hidden args if possible-PerfTest

* SWDEV-532640-Addressed review comment

* SWDEV-532640-Fixed Neg clock time issue

* SWDEV-532640-Fixed Neg clock time issue

* SWDEV-532640-Addressed clang format issue

* SWDEV-532640-Fixed Clang Format issues

[ROCm/hip-tests commit: 2060125dfd]
 2025-07-08 15:24:52 +05:30
Gollamandala, Srinivasarao 2060125dfd SWDEV-532640-[catch2][dtest]-Prefetch all arguments and keep 0 hidden args if possible-PerfTest (#242) 
* SWDEV-532640-[catch2][dtest]-Prefetch all arguments and keep 0 hidden args if possible-PerfTest

* SWDEV-532640-Addressed review comment

* SWDEV-532640-Fixed Neg clock time issue

* SWDEV-532640-Fixed Neg clock time issue

* SWDEV-532640-Addressed clang format issue

* SWDEV-532640-Fixed Clang Format issues
 2025-07-08 15:24:52 +05:30
Robin Voetter 2d5e4bd3fe fix typo in hipBatchMemOpParamsTocudaBatchMemOpParams 2025-07-08 11:10:45 +02:00
Manocha, Rahul 8e8dc41cf0 SWDEV-532420 - Fix kokkos P2P copy failure with vmheap (#426) 
Co-authored-by: Rahul Manocha <rmanocha@amd.com>

[ROCm/clr commit: 22b1ca4d8c]
 2025-07-07 17:27:13 -07:00
Manocha, Rahul 22b1ca4d8c SWDEV-532420 - Fix kokkos P2P copy failure with vmheap (#426) 
Co-authored-by: Rahul Manocha <rmanocha@amd.com>
 2025-07-07 17:27:13 -07:00
Pryor, Adam ca9d8c4bae Adam/bill cleanup (#209) 
Co-authored-by: Bill(Shuzhou) Liu <shuzhou.liu@amd.com>
 2025-07-07 15:41:22 -05:00
Pryor, Adam 07346922f5 Adam/bill cleanup (#209) 
Co-authored-by: Bill(Shuzhou) Liu <shuzhou.liu@amd.com>


[ROCm/rdc commit: ca9d8c4bae]
 2025-07-07 15:41:22 -05:00
Sajina PK 329183b112 Conditionally include backtraces in ROCPROFSYS_THROW based on verbosity (#272) 
* Conditionally include backtraces in ROCPROFSYS_THROW based on verbosity

Modify ROCPROFSYS_THROW to only include backtraces when:
  debug mode is enabled, OR
  verbose level is >= 2, OR
  running in CI environment

* Fix formatting errors

[ROCm/rocprofiler-systems commit: b0ff07b4fe]
 2025-07-07 14:14:02 -04:00
Sajina PK b0ff07b4fe Conditionally include backtraces in ROCPROFSYS_THROW based on verbosity (#272) 
* Conditionally include backtraces in ROCPROFSYS_THROW based on verbosity

Modify ROCPROFSYS_THROW to only include backtraces when:
  debug mode is enabled, OR
  verbose level is >= 2, OR
  running in CI environment

* Fix formatting errors
 2025-07-07 14:14:02 -04:00
Bhardwaj, Gopesh 99a7fe5ff0 Ignoring aligned attribute warning (#70) 
ignoring aligned attribute warning

[ROCm/roctracer commit: dd745ed9c7]
 2025-07-07 09:34:39 -05:00
Bhardwaj, Gopesh dd745ed9c7 Ignoring aligned attribute warning (#70) 
ignoring aligned attribute warning
 2025-07-07 09:34:39 -05:00
Swargam, Rambabu eb2710785e SWDEV-532647 - [catch2][dtest] Test cases for hipGetLastError on Kernel Failure (#247) 
* SWDEV-532647 - [catch2][dtest] Test cases for hipGetLastError on Kernel Failure

* SWDEV-532647 - Restricted to Linux, removed comment for mismatch error code

* SWDEV-532647 - Disabled tests for AMD due to hang issue

* SWDEV-532647 - Fixed clang format issues

[ROCm/hip-tests commit: 9741b347e5]
 2025-07-07 17:49:00 +05:30
Swargam, Rambabu 9741b347e5 SWDEV-532647 - [catch2][dtest] Test cases for hipGetLastError on Kernel Failure (#247) 
* SWDEV-532647 - [catch2][dtest] Test cases for hipGetLastError on Kernel Failure

* SWDEV-532647 - Restricted to Linux, removed comment for mismatch error code

* SWDEV-532647 - Disabled tests for AMD due to hang issue

* SWDEV-532647 - Fixed clang format issues
 2025-07-07 17:49:00 +05:30
Venkatesh, Anavena 882d176c50 SWDEV-526521 : Inter GPU copy performance improvements (#240) 
* SWDEV-532641 Inter GPU copy performance improvements

* SWDEV-532641 changed source data pointer type to vector type

[ROCm/hip-tests commit: feaa82ac46]
 2025-07-07 17:45:20 +05:30
Venkatesh, Anavena feaa82ac46 SWDEV-526521 : Inter GPU copy performance improvements (#240) 
* SWDEV-532641 Inter GPU copy performance improvements

* SWDEV-532641 changed source data pointer type to vector type
 2025-07-07 17:45:20 +05:30
Swargam, Rambabu d9642dbbc2 SWDEV-532114 - [catch2][dtest] Test cases for hipMemGetHandleForAddessRange (#221) 
[ROCm/hip-tests commit: c217bb601c]
 2025-07-07 17:43:22 +05:30
Swargam, Rambabu c217bb601c SWDEV-532114 - [catch2][dtest] Test cases for hipMemGetHandleForAddessRange (#221) 2025-07-07 17:43:22 +05:30
Swargam, Rambabu b35d4e70ad SWDEV-491288 - [catch2][dtest] Stream Capture tests for Occupancy API's (#157) 
* SWDEV-491288 - [catch2][dtest] Stream Capture tests for Occupancy API's

* Modified Cmake file

[ROCm/hip-tests commit: ea366c7aa5]
 2025-07-07 17:42:45 +05:30
Swargam, Rambabu ea366c7aa5 SWDEV-491288 - [catch2][dtest] Stream Capture tests for Occupancy API's (#157) 
* SWDEV-491288 - [catch2][dtest] Stream Capture tests for Occupancy API's

* Modified Cmake file
 2025-07-07 17:42:45 +05:30
Apurv Mishra 3115384874 kfdtest: Temporarily blacklist KFDEvictTest suite 
blacklist the KFDEvictTest suite until the defects
SWDEV 535386 and 537002, where these test cases fail
inconsistently, are fixed

Signed-off-by: Apurv Mishra <Apurv.Mishra@amd.com>
 2025-07-04 11:47:20 -04:00
Apurv Mishra 6c89d61cef kfdtest: Temporarily blacklist KFDEvictTest suite 
blacklist the KFDEvictTest suite until the defects
SWDEV 535386 and 537002, where these test cases fail
inconsistently, are fixed

Signed-off-by: Apurv Mishra <Apurv.Mishra@amd.com>


[ROCm/ROCR-Runtime commit: 3115384874]
 2025-07-04 11:47:20 -04:00
Roy, Rakesh 05b674651c Fix find_if build error for RHEL10 (#499) 
overriding Jonathan's final approval ( as it is a long weekend in US/NA)
adding algorithm header to recognize stdlib's find_if looks fine

[ROCm/rocprofiler-sdk commit: 30e239d1b7]
 2025-07-04 09:20:23 -04:00
Roy, Rakesh 30e239d1b7 Fix find_if build error for RHEL10 (#499) 
overriding Jonathan's final approval ( as it is a long weekend in US/NA)
adding algorithm header to recognize stdlib's find_if looks fine
 2025-07-04 09:20:23 -04:00
Manocha, Rahul 85d0210da4 SWDEV-536749 - Skip building hipSquareGenericTargetOnly for static libs (#291) 
Co-authored-by: Rahul Manocha <rmanocha@amd.com>

[ROCm/hip-tests commit: 0bf7c809d6]
 2025-07-04 15:08:05 +05:30
Manocha, Rahul 0bf7c809d6 SWDEV-536749 - Skip building hipSquareGenericTargetOnly for static libs (#291) 
Co-authored-by: Rahul Manocha <rmanocha@amd.com>
 2025-07-04 15:08:05 +05:30
Castillo, Juan 8133e89e82 [SWDEV-539845] Add support for board voltage (#92) 
* Add the API and CLI to show the board voltage.

---------

Signed-off-by: Arif, Maisam <Maisam.Arif@amd.com>
Signed-off-by: Juan Castillo <juan.castillo@amd.com>
Co-authored-by: Liu, Shuzhou (Bill) <Shuzhou.Liu@amd.com>

[ROCm/rocm_smi_lib commit: bab82d98b7]
 2025-07-03 01:58:50 -05:00
Castillo, Juan bab82d98b7 [SWDEV-539845] Add support for board voltage (#92) 
* Add the API and CLI to show the board voltage.

---------

Signed-off-by: Arif, Maisam <Maisam.Arif@amd.com>
Signed-off-by: Juan Castillo <juan.castillo@amd.com>
Co-authored-by: Liu, Shuzhou (Bill) <Shuzhou.Liu@amd.com>
 2025-07-03 01:58:50 -05:00
Cheruvally, Aravindan d1c281a87e SWDEV-530465 Update share/doc/<pkgnm> License folder (#86) 
Update share/doc/ folder for license/docs to reflect correct package name.
Signed-off-by: Cheruvally, Aravindan <Aravindan.Cheruvally@amd.com>

[ROCm/rocm_smi_lib commit: 55ab9b2bda]
 2025-07-03 01:56:50 -05:00
Cheruvally, Aravindan 55ab9b2bda SWDEV-530465 Update share/doc/<pkgnm> License folder (#86) 
Update share/doc/ folder for license/docs to reflect correct package name.
Signed-off-by: Cheruvally, Aravindan <Aravindan.Cheruvally@amd.com>
 2025-07-03 01:56:50 -05:00
cfallows-amd 30466f6bfa Adjust csv output list for test_block_SPI for MI350 (#785) 
Adjusting expected output list for test_block_SPI for MI350 series products.
Run formatter.

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>

[ROCm/rocprofiler-compute commit: 61a9381edf]
 2025-07-03 01:58:11 -04:00
cfallows-amd 61a9381edf Adjust csv output list for test_block_SPI for MI350 (#785) 
Adjusting expected output list for test_block_SPI for MI350 series products.
Run formatter.

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
 2025-07-03 01:58:11 -04:00
Xie, Pengda 8e5921174f SWDEV-540576 - Abort if user request a core dump (#653) 
* SWDEV-539414 - Return error status from runtime handler when HIP_SKIP_ABORT_ON_GPU_ERROR is false

* SWDEV-539414 - default handler when GPU core file is generated

* SWDEV-540576 - Abort if user request a core dump

Change-Id: I9e2c640acf559880bd13641de9103e660ef822a3

---------

Co-authored-by: Assiouras, Ioannis <Ioannis.Assiouras@amd.com>
Co-authored-by: agunashe <ajay.gunashekar@amd.com>

[ROCm/clr commit: 9c1bff0ae7]
 2025-07-03 00:29:14 +05:30
Xie, Pengda 9c1bff0ae7 SWDEV-540576 - Abort if user request a core dump (#653) 
* SWDEV-539414 - Return error status from runtime handler when HIP_SKIP_ABORT_ON_GPU_ERROR is false

* SWDEV-539414 - default handler when GPU core file is generated

* SWDEV-540576 - Abort if user request a core dump

Change-Id: I9e2c640acf559880bd13641de9103e660ef822a3

---------

Co-authored-by: Assiouras, Ioannis <Ioannis.Assiouras@amd.com>
Co-authored-by: agunashe <ajay.gunashekar@amd.com>
 2025-07-03 00:29:14 +05:30
jamessiddeley-amd 94ea0fbf2f additional-code-coverage-compute (#763) 
* added additional functions to test_utils.py

* added code coverage for db_connector.py

* Update test_profile_general.py

Added additional roofline test cases

Signed-off-by: jamessiddeley-amd <James.Siddeley@amd.com>

* updated coverage mi_gpu_spec.py 73% -> 94%

* added parser.py coverage

* removed redundant comments

* added test_utils and test_db_connector

---------

Signed-off-by: jamessiddeley-amd <James.Siddeley@amd.com>

[ROCm/rocprofiler-compute commit: a6463f5e98]
 2025-07-02 13:29:10 -04:00
jamessiddeley-amd a6463f5e98 additional-code-coverage-compute (#763) 
* added additional functions to test_utils.py

* added code coverage for db_connector.py

* Update test_profile_general.py

Added additional roofline test cases

Signed-off-by: jamessiddeley-amd <James.Siddeley@amd.com>

* updated coverage mi_gpu_spec.py 73% -> 94%

* added parser.py coverage

* removed redundant comments

* added test_utils and test_db_connector

---------

Signed-off-by: jamessiddeley-amd <James.Siddeley@amd.com>
 2025-07-02 13:29:10 -04:00
Galantsev, Dmitrii d312e309c4 Exposed the energy count and current socket power metrics to profilers like PAPI (#225) 
[ROCm/rocm_smi_lib commit: 6c32364d19]
 2025-07-02 09:50:09 -05:00
Galantsev, Dmitrii 6c32364d19 Exposed the energy count and current socket power metrics to profilers like PAPI (#225) 2025-07-02 09:50:09 -05:00
Adam McDaniel b3caa4972c Exposed the energy count and current socket power metrics to profilers like PAPI 
[ROCm/rocm_smi_lib commit: f688c9938d]
 2025-07-02 09:47:17 -05:00