AI/rocm-systems
2
0
Derivar 0
Código Questões Pedidos de integração Operações Pacotes Planeamentos Lançamentos Wiki Trabalho
68 520 Cometimentos 3 Ramos 0 Etiquetas
3f2fbc18e936c2cd39149fd0409dd439f9187647
Gráfico de cometimentos

68520 Cometimentos

Este ramo
Este ramo
Todos os ramos
Autor(a) SHA1 Mensagem Data
vedithal-amd 6827330135 Fix tests on MI 100 (#609) 2025-03-13 12:07:03 -04:00
Benjamin Welton d2a89a467b rocr: Reset event_age when signals move 
Resets event_age when signals move. Prior to this PR, event_age
can become unaligned with hsa_event, causing hangs if the event_age
exceeds the true hsa_event age.
 2025-03-13 11:32:16 -04:00
Benjamin Welton e62422520a rocr: Reset event_age when signals move 
Resets event_age when signals move. Prior to this PR, event_age
can become unaligned with hsa_event, causing hangs if the event_age
exceeds the true hsa_event age.


[ROCm/ROCR-Runtime commit: d2a89a467b]
 2025-03-13 11:32:16 -04:00
Gill, Harkirat 36a965b5c7 [ROCm/ROCm#4476] Update amdsmi-cli-tool.md to include partition cmd (#179) 
Update amdsmi-cli-tool.md to include partition cmd

Signedoff-by: Gill, Harkirat <Harkirat.Gill@amd.com>
 2025-03-13 04:59:34 -05:00
Gill, Harkirat f722cec637 [ROCm/ROCm#4476] Update amdsmi-cli-tool.md to include partition cmd (#179) 
Update amdsmi-cli-tool.md to include partition cmd

Signedoff-by: Gill, Harkirat <Harkirat.Gill@amd.com>

[ROCm/amdsmi commit: 36a965b5c7]
 2025-03-13 04:59:34 -05:00
Emily Deng 42f79776cd kfdtest: Fix the childStatus is 0x7f error for KFDDBGTest.HitMemoryViolation 
For the case parent goes faster then child, and child hasn't call the second
raise(SIGSTOP), then parent's "waitpid(childPid, &childStatus, 0)" will return,
and the childStatus will be 0x137f, which is SIGSTOP signal id.

Signed-off-by: Emily Deng <Emily.Deng@amd.com>
 2025-03-13 13:38:46 +08:00
Emily Deng af293c4a61 kfdtest: Fix the childStatus is 0x7f error for KFDDBGTest.HitMemoryViolation 
For the case parent goes faster then child, and child hasn't call the second
raise(SIGSTOP), then parent's "waitpid(childPid, &childStatus, 0)" will return,
and the childStatus will be 0x137f, which is SIGSTOP signal id.

Signed-off-by: Emily Deng <Emily.Deng@amd.com>


[ROCm/ROCR-Runtime commit: 42f79776cd]
 2025-03-13 13:38:46 +08:00
Emily Deng 91ef44d3ec kfdtest: Fix DeviceSnapshot return fail error for KFDDBGTest.HitMemoryViolation 
For the case that the child goes to the second raise(SIGSTOP),
and parent sends PTRACE_CONT, than child exits. Parent will assert at
DeviceSnapshot, as in kfd_ioctl, couldn't get the mm from child pid.

Signed-off-by: Emily Deng <Emily.Deng@amd.com>
 2025-03-13 13:38:46 +08:00
Emily Deng 46bb10ff2d kfdtest: Fix DeviceSnapshot return fail error for KFDDBGTest.HitMemoryViolation 
For the case that the child goes to the second raise(SIGSTOP),
and parent sends PTRACE_CONT, than child exits. Parent will assert at
DeviceSnapshot, as in kfd_ioctl, couldn't get the mm from child pid.

Signed-off-by: Emily Deng <Emily.Deng@amd.com>


[ROCm/ROCR-Runtime commit: 91ef44d3ec]
 2025-03-13 13:38:46 +08:00
Mallya, Ameya Keshava abfd06e5de Added KWS check 
[ROCm/hip-tests commit: d985ea9821]
 2025-03-12 14:57:55 -07:00
Mallya, Ameya Keshava d985ea9821 Added KWS check 2025-03-12 14:57:55 -07:00
Mallya, Ameya Keshava 5b380e40b1 Adding rocm-ci-caller 
[ROCm/hip-tests commit: 43162400d7]
 2025-03-12 14:56:55 -07:00
Mallya, Ameya Keshava 43162400d7 Adding rocm-ci-caller 2025-03-12 14:56:55 -07:00
Mallya, Ameya Keshava bfd7b0dd3f small change to branch name 
[ROCm/hip commit: 5eeebdbf4f]
 2025-03-12 14:56:38 -07:00
Mallya, Ameya Keshava 5eeebdbf4f small change to branch name 2025-03-12 14:56:38 -07:00
Apurv Mishra 85c4b0020a kfdtest: limit GFX VRAM allocation to 1/4 sys mem 
reduce the allocated memory for GFX VRAM as
KFD Evict test faced intermittent page faults,
which can be due to larger GFX CS BO size
 2025-03-12 13:54:04 -04:00
Apurv Mishra 1e279a19c3 kfdtest: limit GFX VRAM allocation to 1/4 sys mem 
reduce the allocated memory for GFX VRAM as
KFD Evict test faced intermittent page faults,
which can be due to larger GFX CS BO size


[ROCm/ROCR-Runtime commit: 85c4b0020a]
 2025-03-12 13:54:04 -04:00
Mallya, Ameya Keshava 61a6b9bf60 Added KWS check 
[ROCm/clr commit: cde722ad71]
 2025-03-12 10:12:06 -07:00
Mallya, Ameya Keshava cde722ad71 Added KWS check 2025-03-12 10:12:06 -07:00
Mallya, Ameya Keshava f5131f3cc1 Added KWS check 
[ROCm/hipother commit: a9b7bc22a8]
 2025-03-12 10:11:31 -07:00
Mallya, Ameya Keshava a9b7bc22a8 Added KWS check 2025-03-12 10:11:31 -07:00
Mallya, Ameya Keshava ca5da681e4 Added KWS check 
[ROCm/hip commit: a2490f4c31]
 2025-03-12 10:10:40 -07:00
Mallya, Ameya Keshava a2490f4c31 Added KWS check 2025-03-12 10:10:40 -07:00
Mallya, Ameya Keshava 5c27fe7c8e Added rocm-ci-caller 
[ROCm/clr commit: 35dcd43c59]
 2025-03-12 10:05:57 -07:00
Mallya, Ameya Keshava 35dcd43c59 Added rocm-ci-caller 2025-03-12 10:05:57 -07:00
Mallya, Ameya Keshava 5c955f0bfd Added rocm-ci-caller 
[ROCm/hipother commit: 95ee23540d]
 2025-03-12 10:03:47 -07:00
Mallya, Ameya Keshava 95ee23540d Added rocm-ci-caller 2025-03-12 10:03:47 -07:00
Mallya, Ameya Keshava 735a5196e4 Adding rocm-ci-caller 
[ROCm/hip commit: b4ac1d6c02]
 2025-03-12 09:59:08 -07:00
Mallya, Ameya Keshava b4ac1d6c02 Adding rocm-ci-caller 2025-03-12 09:59:08 -07:00
Gerardo Hernandez 8c9aa07b3a SWDEV-420237 - Add __reduce_add_sync() 
Change-Id: Ic8e4fab6b7aeb879d40b2c1419b30d1355a2bbdc


[ROCm/clr commit: 340d6bb69f]
 2025-03-12 03:20:49 -04:00
Gerardo Hernandez 340d6bb69f SWDEV-420237 - Add __reduce_add_sync() 
Change-Id: Ic8e4fab6b7aeb879d40b2c1419b30d1355a2bbdc
 2025-03-12 03:20:49 -04:00
Galantsev, Dmitrii e8ae64260f [SWDEV-509342] Fix uninstall script on older RPM based systems (#181) 
Change-Id: Ic85cd27e4460fbcdefab6fdd7e813a579c539525
 2025-03-11 20:12:59 -05:00
Galantsev, Dmitrii 603f3665c5 [SWDEV-509342] Fix uninstall script on older RPM based systems (#181) 
Change-Id: Ic85cd27e4460fbcdefab6fdd7e813a579c539525

[ROCm/amdsmi commit: e8ae64260f]
 2025-03-11 20:12:59 -05:00
Galantsev, Dmitrii 14e81725f6 [SWDEV-509342] Fix uninstall script on older RPM based systems 
Change-Id: Ic85cd27e4460fbcdefab6fdd7e813a579c539525
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
 2025-03-12 01:05:30 +00:00
Galantsev, Dmitrii 60704c3e36 [SWDEV-509342] Fix uninstall script on older RPM based systems 
Change-Id: Ic85cd27e4460fbcdefab6fdd7e813a579c539525
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: 14e81725f6]
 2025-03-12 01:05:30 +00:00
Yiannis Papadopoulos c7936334cf rocr/aie: Changing variable names 2025-03-11 19:35:21 -04:00
Yiannis Papadopoulos 566269e8b7 rocr/aie: Changing variable names 
[ROCm/ROCR-Runtime commit: c7936334cf]
 2025-03-11 19:35:21 -04:00
Yiannis Papadopoulos fb33e2e724 rocr/aie: Handle non-HSA_STATUS_SUCCESS during VisitRegion 2025-03-11 19:35:21 -04:00
Yiannis Papadopoulos 8e111ff2f0 rocr/aie: Handle non-HSA_STATUS_SUCCESS during VisitRegion 
[ROCm/ROCR-Runtime commit: fb33e2e724]
 2025-03-11 19:35:21 -04:00
Poag, Charis 48cb5529d2 [SWDEV-493274/SWDEV-514998] Add AMD SMI partition tests + Add Guest amd-smi static --partition (#127) 
* [SWDEV-493274/SWDEV-514998] Add AMD SMI partition tests + Add Guest amd-smi static --partition

Changes:
    - Added amd-smi static --partition for guest systems
    - Added C++ tests for memory and compute (accelerator) partitions
    - Added Python tests for amdsmi_get_gpu_vram_info(),
       amdsmi_get_gpu_accelerator_partition_profile_config()
    - Updated Python tests for
      amdsmi_get_gpu_accelerator_partition_profile()
      Now includes more profile and resource detail
    - Added amdsmi_get_gpu_xcd_counter();
      Tests provided for both C++/Python APIs
    - Added AmdSmiVramType & AmdSmiVramVendor: they were missing
      python testing required adding.

Change-Id: Ib6549d8ccc5fb68726f38745b87c78f890186022
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
 2025-03-11 16:38:46 -05:00
Poag, Charis 267fa91e8a [SWDEV-493274/SWDEV-514998] Add AMD SMI partition tests + Add Guest amd-smi static --partition (#127) 
* [SWDEV-493274/SWDEV-514998] Add AMD SMI partition tests + Add Guest amd-smi static --partition

Changes:
    - Added amd-smi static --partition for guest systems
    - Added C++ tests for memory and compute (accelerator) partitions
    - Added Python tests for amdsmi_get_gpu_vram_info(),
       amdsmi_get_gpu_accelerator_partition_profile_config()
    - Updated Python tests for
      amdsmi_get_gpu_accelerator_partition_profile()
      Now includes more profile and resource detail
    - Added amdsmi_get_gpu_xcd_counter();
      Tests provided for both C++/Python APIs
    - Added AmdSmiVramType & AmdSmiVramVendor: they were missing
      python testing required adding.

Change-Id: Ib6549d8ccc5fb68726f38745b87c78f890186022
Signed-off-by: Charis Poag <Charis.Poag@amd.com>

[ROCm/amdsmi commit: 48cb5529d2]
 2025-03-11 16:38:46 -05:00
Apurv Mishra de8f8f076d kfdtest: add blacklist for RHEL9 system 
add tests for exclusion when running kfdtest
on RHEL9 system, tested with Navi 31

Signed-off-by: Apurv Mishra <apurv.mishra@amd.com>
 2025-03-11 16:40:25 -04:00
Apurv Mishra 77f4bbfdf1 kfdtest: add blacklist for RHEL9 system 
add tests for exclusion when running kfdtest
on RHEL9 system, tested with Navi 31

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


[ROCm/ROCR-Runtime commit: de8f8f076d]
 2025-03-11 16:40:25 -04:00
Galantsev, Dmitrii f5a4402ce5 RVS - Use config files and make GPU aware 
Change-Id: I7a5c80ed4e6122d102e494d1ae38b4b7d40c42cd
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
 2025-03-11 15:39:16 -05:00
Galantsev, Dmitrii 68c02bda78 RVS - Use config files and make GPU aware 
Change-Id: I7a5c80ed4e6122d102e494d1ae38b4b7d40c42cd
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/rdc commit: f5a4402ce5]
 2025-03-11 15:39:16 -05:00
Kandula, Venkateshwar reddy 2a33544c0e SWDEV-518356: added check to avoid out of range hip host to device. (#267) 
added check to avoid out of range.

Co-authored-by: Venkateshwar Reddy Kandula <vkandula@amd.com>

[ROCm/rocprofiler-sdk commit: 8735ae4eb0]
 2025-03-11 15:37:59 -05:00
Kandula, Venkateshwar reddy 8735ae4eb0 SWDEV-518356: added check to avoid out of range hip host to device. (#267) 
added check to avoid out of range.

Co-authored-by: Venkateshwar Reddy Kandula <vkandula@amd.com>
 2025-03-11 15:37:59 -05:00
Bhardwaj, Gopesh b7dc66ad8b Updated changelog for 6.4 (#21) 2025-03-11 11:31:08 -07:00
Bhardwaj, Gopesh 978fbca608 Updated changelog for 6.4 (#21) 
[ROCm/rocprofiler commit: b7dc66ad8b]
 2025-03-11 11:31:08 -07:00
Sajina PK 3ca3d63d5c Fix for excluding JPEG and VCN activity test. (#135) 
JPEG activity recording is currently only supported on MI300 serries.
VCN activity is supported in MI100 also but there is a bug currently being fixed by FW.

- Currently only testing the Activity verification tests for MI300
- Also moves the Jpeg image copying code to after the package is found.

[ROCm/rocprofiler-systems commit: e605e5d33f]
 2025-03-11 14:12:28 -04:00