76333 Commits

Author SHA1 Message Date
Mustafa Abduljabbar 4588da1888 Remove unneeded highestTransportType (#1461)
[ROCm/rccl commit: e6b179d627]
2024-12-16 13:28:47 -05:00
Mustafa Abduljabbar e6b179d627 Remove unneeded highestTransportType (#1461) 2024-12-16 13:28:47 -05:00
Xiaogang Chen ec457752dc kfdtest: update run_kfdtest.sh when HSA_TEST_GPUS_NUM is enable
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I68e4f4f8fd7397d3b39b3473638836e4531bef2b
2024-12-16 12:47:50 -05:00
Xiaogang Chen c1158a6c76 kfdtest: update run_kfdtest.sh when HSA_TEST_GPUS_NUM is enable
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I68e4f4f8fd7397d3b39b3473638836e4531bef2b


[ROCm/ROCR-Runtime commit: ec457752dc]
2024-12-16 12:47:50 -05:00
Xiaogang Chen cbb38606e3 kfdtest: Convert KFDSVMRangeTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: Ia4d55c38576c39b3768a847c60d70bda88f65740
2024-12-16 12:47:44 -05:00
Xiaogang Chen 2c102990ae kfdtest: Convert KFDSVMRangeTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: Ia4d55c38576c39b3768a847c60d70bda88f65740


[ROCm/ROCR-Runtime commit: cbb38606e3]
2024-12-16 12:47:44 -05:00
Xiaogang Chen 641f1f797d kfdtest: Convert KFDLocalMemoryTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: Iaf20ec15e85ed10998e9735881d3c029abedd3a4
2024-12-16 12:47:39 -05:00
Xiaogang Chen bebd577f6a kfdtest: Convert KFDLocalMemoryTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: Iaf20ec15e85ed10998e9735881d3c029abedd3a4


[ROCm/ROCR-Runtime commit: 641f1f797d]
2024-12-16 12:47:39 -05:00
Xiaogang Chen 10c9b98f6e kfdtest: Convert KFDMemoryTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I29d7fbb156a88b4df5be5f2fa0c20fbc47b108ed
2024-12-16 12:47:34 -05:00
Xiaogang Chen efa2d187f1 kfdtest: Convert KFDMemoryTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I29d7fbb156a88b4df5be5f2fa0c20fbc47b108ed


[ROCm/ROCR-Runtime commit: 10c9b98f6e]
2024-12-16 12:47:34 -05:00
Xiaogang Chen f229605b06 kfdtest: Convert KFDQMTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: Ia3582ab5b802ead4df267eeb280b8e7d37eb0ac2
2024-12-16 12:47:28 -05:00
Xiaogang Chen 3925a57cf2 kfdtest: Convert KFDQMTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: Ia3582ab5b802ead4df267eeb280b8e7d37eb0ac2


[ROCm/ROCR-Runtime commit: f229605b06]
2024-12-16 12:47:28 -05:00
Xiaogang Chen dbccf11ef8 kfdtest: Convert KFDExceptionTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I545ac485d13a3a56a3b352926ec71daa5b074862
2024-12-16 12:47:21 -05:00
Xiaogang Chen 513fa002e3 kfdtest: Convert KFDExceptionTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I545ac485d13a3a56a3b352926ec71daa5b074862


[ROCm/ROCR-Runtime commit: dbccf11ef8]
2024-12-16 12:47:21 -05:00
Xiaogang Chen 0357e2e139 kfdtest: Convert KFDEventTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: Id1dc91f654686f159adb1bc70907e11558ee4be0
2024-12-16 12:47:14 -05:00
Xiaogang Chen 8f28056009 kfdtest: Convert KFDEventTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: Id1dc91f654686f159adb1bc70907e11558ee4be0


[ROCm/ROCR-Runtime commit: 0357e2e139]
2024-12-16 12:47:14 -05:00
Xiaogang Chen fa31caddba kfdtest: Convert KFDCWSRTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I51646ebd95b2ef4820f7b503bd642deb05a86930
2024-12-16 12:47:08 -05:00
Xiaogang Chen 77aa32b913 kfdtest: Convert KFDCWSRTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I51646ebd95b2ef4820f7b503bd642deb05a86930


[ROCm/ROCR-Runtime commit: fa31caddba]
2024-12-16 12:47:08 -05:00
Xiaogang Chen 6c6daf66bf kfdtest: Convert KFDGWSTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I0901750b2ce55bd7f44425b01442d98f0faf12fd
2024-12-16 12:47:01 -05:00
Xiaogang Chen 92c4010903 kfdtest: Convert KFDGWSTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I0901750b2ce55bd7f44425b01442d98f0faf12fd


[ROCm/ROCR-Runtime commit: 6c6daf66bf]
2024-12-16 12:47:01 -05:00
Xiaogang Chen 759ca45f54 kfdtest: convert KFDGraphicsInterop into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I590be9ea063b0d115641aa5b40be4c376377c1dd
2024-12-16 12:46:55 -05:00
Xiaogang Chen a17b24b062 kfdtest: convert KFDGraphicsInterop into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I590be9ea063b0d115641aa5b40be4c376377c1dd


[ROCm/ROCR-Runtime commit: 759ca45f54]
2024-12-16 12:46:55 -05:00
Xiaogang Chen dd1801df41 kfdtest: convert KFDPerfCountersTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I29124147394b69c7fb5533a0e54d375d06b1ec13
2024-12-16 12:46:49 -05:00
Xiaogang Chen 35939040ba kfdtest: convert KFDPerfCountersTest into multi-GPU test framework
Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I29124147394b69c7fb5533a0e54d375d06b1ec13


[ROCm/ROCR-Runtime commit: dd1801df41]
2024-12-16 12:46:49 -05:00
Xiaogang Chen c69e660e7a kfdtest: Update KFDMultiProcessTest class to support kfdtest run on multiple gpu
Update KFDMultiProcessTest class to fork process on gpu wise.

Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: Ibb12d64b4cbc5f082d737fd8d8a74233b75be13e
2024-12-16 12:46:42 -05:00
Xiaogang Chen 23a24fb48a kfdtest: Update KFDMultiProcessTest class to support kfdtest run on multiple gpu
Update KFDMultiProcessTest class to fork process on gpu wise.

Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: Ibb12d64b4cbc5f082d737fd8d8a74233b75be13e


[ROCm/ROCR-Runtime commit: c69e660e7a]
2024-12-16 12:46:42 -05:00
Xiaogang Chen b4943d718b kfdtest: Implement an infracture to support kfdtest run on multi gpu
Update class KFDBaseComponentTest to have kfdtest run on multi gpu under google test framework.

Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: If139c4fc6cf062fb800ff171c69cbf9604f98278
2024-12-16 12:46:32 -05:00
Xiaogang Chen 58e0937fb4 kfdtest: Implement an infracture to support kfdtest run on multi gpu
Update class KFDBaseComponentTest to have kfdtest run on multi gpu under google test framework.

Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: If139c4fc6cf062fb800ff171c69cbf9604f98278


[ROCm/ROCR-Runtime commit: b4943d718b]
2024-12-16 12:46:32 -05:00
Xiaogang Chen 665e6f80bf kfdtest: Add an env variable to control kfdtest on multi gpu
Add HSA_TEST_GPUS_NUM env variable that controls gpu number kfdtest uses.

This env variable will be used by following patches.

Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I800042f93d4e0955040f450e9b5cf09927971323
2024-12-16 12:46:25 -05:00
Xiaogang Chen 7ca6b20d3f kfdtest: Add an env variable to control kfdtest on multi gpu
Add HSA_TEST_GPUS_NUM env variable that controls gpu number kfdtest uses.

This env variable will be used by following patches.

Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I800042f93d4e0955040f450e9b5cf09927971323


[ROCm/ROCR-Runtime commit: 665e6f80bf]
2024-12-16 12:46:25 -05:00
Xiaogang Chen 36a82593ed kfdtest: Extend gtest log functions
Extend Google test log functions to extend kfdtest running on multiple gpu.

Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I6d8de92fec606309756423b3a6fa2af3558c0517
2024-12-16 12:46:16 -05:00
Xiaogang Chen b8279a6de1 kfdtest: Extend gtest log functions
Extend Google test log functions to extend kfdtest running on multiple gpu.

Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I6d8de92fec606309756423b3a6fa2af3558c0517


[ROCm/ROCR-Runtime commit: 36a82593ed]
2024-12-16 12:46:16 -05:00
Xiaogang Chen e1fdd6fb5f kfdtest: Separate LLVM initialization and instantiation
Assembler function from LLVM is not multi-thread safe and is ASIC dependent.
To extend kfdtest to test on multiple GPU separate LLVM initialization and
assembler instantiation. Each test uses its own assembler.

Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I94c996e807b81d8b19361b450be985b12042477c
2024-12-16 12:46:07 -05:00
Xiaogang Chen ca76e3fde0 kfdtest: Separate LLVM initialization and instantiation
Assembler function from LLVM is not multi-thread safe and is ASIC dependent.
To extend kfdtest to test on multiple GPU separate LLVM initialization and
assembler instantiation. Each test uses its own assembler.

Signed-off-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Change-Id: I94c996e807b81d8b19361b450be985b12042477c


[ROCm/ROCR-Runtime commit: e1fdd6fb5f]
2024-12-16 12:46:07 -05:00
Rambabu Swargam 6c7ed09ca0 SWDEV-490555 - [catch2][dtest] Additional tests for hipMemcpyDtoA and hipMemcpy2DArrayToArray
Change-Id: Icd0e4c35cc0cf60f2e943c4f4da39de23a8c1e5b


[ROCm/hip-tests commit: 92b717da81]
2024-12-16 12:13:01 -05:00
Rambabu Swargam 92b717da81 SWDEV-490555 - [catch2][dtest] Additional tests for hipMemcpyDtoA and hipMemcpy2DArrayToArray
Change-Id: Icd0e4c35cc0cf60f2e943c4f4da39de23a8c1e5b
2024-12-16 12:13:01 -05:00
Giovanni baraldi bcc709c174 SWDEV-495749: Adding SIMD_UTILIZATION metric
Change-Id: I38afd5db02de7a416d11274823bc4a0c326f1fbe
2024-12-16 10:22:57 -06:00
Giovanni baraldi 2baa5bd4ab SWDEV-495749: Adding SIMD_UTILIZATION metric
Change-Id: I38afd5db02de7a416d11274823bc4a0c326f1fbe


[ROCm/rocprofiler commit: bcc709c174]
2024-12-16 10:22:57 -06:00
Ziyue Yang 987dfc3b5d Fix MSCCL algorithm loading order (#1460)
[ROCm/rccl commit: 83c5eb7378]
2024-12-16 07:41:17 -08:00
Ziyue Yang 83c5eb7378 Fix MSCCL algorithm loading order (#1460) 2024-12-16 07:41:17 -08:00
David Yat Sin 5da1889fb7 rocr: Avoid deadlock due to queue signal not updated
Make sure waiting_ count for queue signal is always > 0 so that we
always call hsaKmtWaitOnEvent to force hsaKmtWaitOnEvent to return.

Remove incorrect warning print when running in debug mode.

Call internal Signal::WaitAny instead of AMD::hsa_amd_signal_wait_any
to avoid extra function calls.

Change-Id: I9e41b704643e4e8ee7402b1379b1c30ff4c544ef
2024-12-16 10:25:19 -05:00
David Yat Sin 95ee8b36d7 rocr: Avoid deadlock due to queue signal not updated
Make sure waiting_ count for queue signal is always > 0 so that we
always call hsaKmtWaitOnEvent to force hsaKmtWaitOnEvent to return.

Remove incorrect warning print when running in debug mode.

Call internal Signal::WaitAny instead of AMD::hsa_amd_signal_wait_any
to avoid extra function calls.

Change-Id: I9e41b704643e4e8ee7402b1379b1c30ff4c544ef


[ROCm/ROCR-Runtime commit: 5da1889fb7]
2024-12-16 10:25:19 -05:00
Yiltan Temucin b622528559 Bump rocSHMEM version
[ROCm/rocshmem commit: 3185428ad8]
2024-12-16 08:54:12 -06:00
Yiltan Temucin 3185428ad8 Bump rocSHMEM version 2024-12-16 08:54:12 -06:00
Yiltan Temucin 9928cc24ef Updated README.md
[ROCm/rocshmem commit: 28b41ea648]
2024-12-16 08:54:12 -06:00
Yiltan Temucin 28b41ea648 Updated README.md 2024-12-16 08:54:12 -06:00
Ioannis Assiouras 7670376748 SWDEV-489255 - Update stack size limit in rocvirtual
Change-Id: I2aac9d211f64b3d6c121d8b010d215dcbdeac3aa


[ROCm/clr commit: a808c4b23a]
2024-12-16 09:30:39 -05:00
Ioannis Assiouras a808c4b23a SWDEV-489255 - Update stack size limit in rocvirtual
Change-Id: I2aac9d211f64b3d6c121d8b010d215dcbdeac3aa
2024-12-16 09:30:39 -05:00
David Galiffi 4297f75f83 Update VERSION to 0.2.0
[ROCm/rocprofiler-systems commit: 1f8b4bf67d]
2024-12-16 06:05:42 -05:00
David Galiffi 1f8b4bf67d Update VERSION to 0.2.0 2024-12-16 06:05:42 -05:00