Commit Graph

64836 Commits

Author SHA1 Message Date
Christophe Paquot e9d2abe721 Merge pull request #6 from StreamHPC/fix-batchmemopparams
fix typo in hipBatchMemOpParamsTocudaBatchMemOpParams
2025-07-08 14:51:46 -07:00
vedithal-amd f730199ef7 Fix util tests (#797)
* Fix profile tests
* Update known issue for corrupted memory chart

[ROCm/rocprofiler-compute commit: c51b9d16c3]
2025-07-08 17:15:09 -04:00
vedithal-amd c51b9d16c3 Fix util tests (#797)
* Fix profile tests
* Update known issue for corrupted memory chart
2025-07-08 17:15:09 -04:00
cfallows-amd 7862701993 Update roofline bins for rocm7 changes (#755)
* Update current bins to have rocm6 suffix. Add new rocm7 bins, built on rocm7.0 latest due to hip updates.

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

* Re-add rocm version check for roof bins.

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

* Rebuild roofline binaries on top of latest rocm7 (#16379) after recent mainline promotions.
Adjusting version and distro combinations of bins following rocm6 vs rocm 7 supported OS.
*rhel8 not supported on rocm7, also not built anymore
*sles15 not supported on rocm7 but is still being built
*ubuntu stays as 22.04 and above for rocm7

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

* Minor fixes after testing.

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

* Fixed bad copy after finding it in testing ctest.

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

* Remove runpath from new bin

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

* Rework target_binary map return in detect_roofline- we should not be returning maps of different sizes or with different keys for the same method. Expected output should be consistent in case we run into bad position, or for testing purposes. Manually tested all possible roofline bin expected cases to comfirm functionality and expected user output.

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

* Update changelog with new roofline distro minimums

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

---------

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

[ROCm/rocprofiler-compute commit: 3df0d1dded]
2025-07-08 16:51:50 -04:00
cfallows-amd 3df0d1dded Update roofline bins for rocm7 changes (#755)
* Update current bins to have rocm6 suffix. Add new rocm7 bins, built on rocm7.0 latest due to hip updates.

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

* Re-add rocm version check for roof bins.

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

* Rebuild roofline binaries on top of latest rocm7 (#16379) after recent mainline promotions.
Adjusting version and distro combinations of bins following rocm6 vs rocm 7 supported OS.
*rhel8 not supported on rocm7, also not built anymore
*sles15 not supported on rocm7 but is still being built
*ubuntu stays as 22.04 and above for rocm7

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

* Minor fixes after testing.

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

* Fixed bad copy after finding it in testing ctest.

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

* Remove runpath from new bin

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

* Rework target_binary map return in detect_roofline- we should not be returning maps of different sizes or with different keys for the same method. Expected output should be consistent in case we run into bad position, or for testing purposes. Manually tested all possible roofline bin expected cases to comfirm functionality and expected user output.

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

* Update changelog with new roofline distro minimums

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

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>
2025-07-08 16:51:50 -04:00
Kudchadker, Saleel 433c25eab0 SWDEV-539378 - Use agent of IPC memory owner (#570)
- Currently runtime just uses the local agent as it did not check for
  IPCShared()
- With this fix we query hsa_amd_pointer_info and get the right agent
  for the memory to pass it to the HSA copy api

[ROCm/clr commit: 46d766e4e2]
2025-07-08 12:02:01 -07:00
Kudchadker, Saleel 46d766e4e2 SWDEV-539378 - Use agent of IPC memory owner (#570)
- Currently runtime just uses the local agent as it did not check for
  IPCShared()
- With this fix we query hsa_amd_pointer_info and get the right agent
  for the memory to pass it to the HSA copy api
2025-07-08 12:02:01 -07:00
Belton-Schure, Aidan 88c1717658 SWDEV-515426 - Remove HIP_USE_RUNTIME_UNBUNDLER (#205)
* remove HIP_USE_RUNTIME_UNBUNDLER
* clang-format
* Generic to use comgr
* Remove HIP_ALWAYS_USE_NEW_COMGR_UNBUNDLING_ACTION flag
* Removes runtime unbundling unused and debug Code
* Removes stale functions

[ROCm/clr commit: 81238db679]
2025-07-08 21:45:31 +05:30
Belton-Schure, Aidan 81238db679 SWDEV-515426 - Remove HIP_USE_RUNTIME_UNBUNDLER (#205)
* remove HIP_USE_RUNTIME_UNBUNDLER
* clang-format
* Generic to use comgr
* Remove HIP_ALWAYS_USE_NEW_COMGR_UNBUNDLING_ACTION flag
* Removes runtime unbundling unused and debug Code
* Removes stale functions
2025-07-08 21:45:31 +05:30
xuchen-amd bac7fde4f4 Add tui cmake install. (#794)
[ROCm/rocprofiler-compute commit: 60a50e681b]
2025-07-08 11:18:26 -04:00
xuchen-amd 60a50e681b Add tui cmake install. (#794) 2025-07-08 11:18:26 -04:00
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