In several places aql packets were written to queue all at once
instead of doing the header atomically. These cases have been
fixed.
There were a few hsa_signal leaked that have been addressed.
There was some duplication of code that has been addressed.
Addresses ROCMOPS-456
Change-Id: Ia1869bc370f92e49ac560301df47741d5f76978e
In several places aql packets were written to queue all at once
instead of doing the header atomically. These cases have been
fixed.
There were a few hsa_signal leaked that have been addressed.
There was some duplication of code that has been addressed.
Addresses ROCMOPS-456
Change-Id: Ia1869bc370f92e49ac560301df47741d5f76978e
[ROCm/ROCR-Runtime commit: 081a2cc875]
The SDMA blacklist should contain all tests that use SDMA. It will
be applied to all ASICs that are know to have SDMA stability issues.
Change-Id: I53e723382c12f99bddf9c535000e27737a7ea1f6
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
The SDMA blacklist should contain all tests that use SDMA. It will
be applied to all ASICs that are know to have SDMA stability issues.
Change-Id: I53e723382c12f99bddf9c535000e27737a7ea1f6
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
[ROCm/ROCR-Runtime commit: 62ee7b4112]
The bus error bug was fixed from kfd driver and Thunk
Change-Id: Id02617fdc26f1c49307f90a0a939e05f22d739e7
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
[ROCm/ROCR-Runtime commit: be9ac578ef]
1. Use s_mov_b32 to move 0xcafe to s18. s_movk_i32 is a sign extention move
instruction. Oxcafe will be extended to 0xffffcafe which is not desired
2. Add wait to s_load_dword instruction to make sure memory read finish before
the next store instruction.
Change-Id: I665d1d471019edfaba5693e07cdc567d4103573f
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
1. Use s_mov_b32 to move 0xcafe to s18. s_movk_i32 is a sign extention move
instruction. Oxcafe will be extended to 0xffffcafe which is not desired
2. Add wait to s_load_dword instruction to make sure memory read finish before
the next store instruction.
Change-Id: I665d1d471019edfaba5693e07cdc567d4103573f
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
[ROCm/ROCR-Runtime commit: 5d163cd821]
Add support and testing for reading the Unique ID associated with a
specific GPU. This ID will persist across reboots, even if the GPU is
moved to a different machine. Note that this is per-GPU, not per-card,
as some cards have multiple GPUs, and each GPU will get a unique
identifier
Change-Id: Idce50c6febc2ceb1a4c1200d2489ec8b9d8fe174
[ROCm/rocm_smi_lib commit: 35d2807196]
Add support and testing for reading the Unique ID associated with a
specific GPU. This ID will persist across reboots, even if the GPU is
moved to a different machine. Note that this is per-GPU, not per-card,
as some cards have multiple GPUs, and each GPU will get a unique
identifier
Change-Id: Idce50c6febc2ceb1a4c1200d2489ec8b9d8fe174
Add support and testing for reading the Unique ID associated with a
specific GPU. This ID will persist across reboots, even if the GPU is
moved to a different machine. Note that this is per-GPU, not per-card,
as some cards have multiple GPUs, and each GPU will get a unique
identifier
Change-Id: Idce50c6febc2ceb1a4c1200d2489ec8b9d8fe174
[ROCm/amdsmi commit: 35d2807196]
The affinityStr string was not null-terminated but was passed to strlen(3).
Signed-off-by: Felix Abecassis <fabecassis@nvidia.com>
[ROCm/rccl commit: 37e4f8729e]
SWDEV-2 - Change OpenCL version number from 2928 to 2929.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2676 edit
[ROCm/clr commit: 88689fd351]
SWDEV-2 - Change OpenCL version number from 2928 to 2929.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2676 edit
SWDEV-184710 - Support hipLaunchCooperativeKernelMultiDevice()
- Clean-up the loop for the launch on each device
- Add hipExtLaunchMultiKernelMultiDevice()
http://ocltc.amd.com/reviews/r/17573/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_module.cpp#29 edit
[ROCm/clr commit: bca0438b69]
SWDEV-184710 - Support hipLaunchCooperativeKernelMultiDevice()
- Clean-up the loop for the launch on each device
- Add hipExtLaunchMultiKernelMultiDevice()
http://ocltc.amd.com/reviews/r/17573/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_module.cpp#29 edit
SWDEV-184710 - Support hipLaunchCooperativeKernelMultiDevice()
- Clean-up the loop for the launch on each device
- Add hipExtLaunchMultiKernelMultiDevice()
http://ocltc.amd.com/reviews/r/17573/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_module.cpp#29 edit
[ROCm/hip commit: fd634d58f1]
SWDEV-184710 - Support hipLaunchCooperativeKernelMultiDevice()
- Clean-up the loop for the launch on each device
- Add hipExtLaunchMultiKernelMultiDevice()
http://ocltc.amd.com/reviews/r/17573/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_module.cpp#29 edit
SWDEV-190204 - [CQE OCL][NAVI 14] "Unsupported device(gfx1012) for the test! " for OCLPerfCounters which is subtest of oclruntime.
Fix the ID converstion array.
Tests:
1. run the test in Navi 10.
2. http://ocltc.amd.com:8111/viewModification.html?modId=122114&personal=true&tab=vcsModificationBuilds
3. The CQE has confirmed the idea fixed the issue in Navi14
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcounters.cpp#22 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/runtime/OCLPerfCounters.cpp#48 edit
[ROCm/clr commit: 866533ef00]
SWDEV-190204 - [CQE OCL][NAVI 14] "Unsupported device(gfx1012) for the test! " for OCLPerfCounters which is subtest of oclruntime.
Fix the ID converstion array.
Tests:
1. run the test in Navi 10.
2. http://ocltc.amd.com:8111/viewModification.html?modId=122114&personal=true&tab=vcsModificationBuilds
3. The CQE has confirmed the idea fixed the issue in Navi14
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcounters.cpp#22 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/runtime/OCLPerfCounters.cpp#48 edit
SWDEV-2 - Change OpenCL version number from 2927 to 2928.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2675 edit
[ROCm/clr commit: ea0d95d424]
SWDEV-2 - Change OpenCL version number from 2927 to 2928.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2675 edit
* [hip] implement the hipExtLaunchMultiKernelMultiDevice API
* add a guard to check the HCC version for acquire_locked_hsa_queue() API which was introdued in HCC for ROCm 2.5
* modified code based on the requested changes
* changes to lock all streams before launching kernels for each device and unlock them after the dispatches
* check each stream to be valid before starting to lock all the streams
[ROCm/clr commit: d6ad690cb6]
* [hip] implement the hipExtLaunchMultiKernelMultiDevice API
* add a guard to check the HCC version for acquire_locked_hsa_queue() API which was introdued in HCC for ROCm 2.5
* modified code based on the requested changes
* changes to lock all streams before launching kernels for each device and unlock them after the dispatches
* check each stream to be valid before starting to lock all the streams
* [hip] implement the hipExtLaunchMultiKernelMultiDevice API
* add a guard to check the HCC version for acquire_locked_hsa_queue() API which was introdued in HCC for ROCm 2.5
* modified code based on the requested changes
* changes to lock all streams before launching kernels for each device and unlock them after the dispatches
* check each stream to be valid before starting to lock all the streams
[ROCm/hip commit: 96dc74897d]
* [hip] implement the hipExtLaunchMultiKernelMultiDevice API
* add a guard to check the HCC version for acquire_locked_hsa_queue() API which was introdued in HCC for ROCm 2.5
* modified code based on the requested changes
* changes to lock all streams before launching kernels for each device and unlock them after the dispatches
* check each stream to be valid before starting to lock all the streams
* Implement the hipOccupancyMaxPotentialBlockSize function
* Replaced hipGetDeviceProperties() call by ihipGetDeviceProperties() in ihipOccupancyMaxPotentialBlockSize()
* Add test for hipOccupancyMaxPotentialBlockSize in Module API
* Added extern declaration for ihipGetDeviceProperties() to be accessed inside ihipOccupancyMaxPotentialBlockSize()
* fixed hipOccupancyMaxPotentialBlockSize test build issue
* Fix hipOccupancyMaxPotentialBlockSize dtest
* Add BUILD_CMD in hipOccupancyMaxPotentialBlockSize dtest
* Revert "Add BUILD_CMD in hipOccupancyMaxPotentialBlockSize dtest"
This reverts commit 0480ff56f1441fc515d2c26ce33783e303423938.
* Disable hipOccupancyMaxPotentialBlockSize dtest on NVCC
* move extern declaration of ihipGetDeviceProperties to hip_module.cpp
* Update the limiation of 32 wavefronts per CU and 800/512 SGPRs for VI/pre-VI chips to calculate the occupancy
[ROCm/clr commit: 28c34ead70]
* Implement the hipOccupancyMaxPotentialBlockSize function
* Replaced hipGetDeviceProperties() call by ihipGetDeviceProperties() in ihipOccupancyMaxPotentialBlockSize()
* Add test for hipOccupancyMaxPotentialBlockSize in Module API
* Added extern declaration for ihipGetDeviceProperties() to be accessed inside ihipOccupancyMaxPotentialBlockSize()
* fixed hipOccupancyMaxPotentialBlockSize test build issue
* Fix hipOccupancyMaxPotentialBlockSize dtest
* Add BUILD_CMD in hipOccupancyMaxPotentialBlockSize dtest
* Revert "Add BUILD_CMD in hipOccupancyMaxPotentialBlockSize dtest"
This reverts commit 0480ff56f1441fc515d2c26ce33783e303423938.
* Disable hipOccupancyMaxPotentialBlockSize dtest on NVCC
* move extern declaration of ihipGetDeviceProperties to hip_module.cpp
* Update the limiation of 32 wavefronts per CU and 800/512 SGPRs for VI/pre-VI chips to calculate the occupancy
* Implement the hipOccupancyMaxPotentialBlockSize function
* Replaced hipGetDeviceProperties() call by ihipGetDeviceProperties() in ihipOccupancyMaxPotentialBlockSize()
* Add test for hipOccupancyMaxPotentialBlockSize in Module API
* Added extern declaration for ihipGetDeviceProperties() to be accessed inside ihipOccupancyMaxPotentialBlockSize()
* fixed hipOccupancyMaxPotentialBlockSize test build issue
* Fix hipOccupancyMaxPotentialBlockSize dtest
* Add BUILD_CMD in hipOccupancyMaxPotentialBlockSize dtest
* Revert "Add BUILD_CMD in hipOccupancyMaxPotentialBlockSize dtest"
This reverts commit 0480ff56f1441fc515d2c26ce33783e303423938.
* Disable hipOccupancyMaxPotentialBlockSize dtest on NVCC
* move extern declaration of ihipGetDeviceProperties to hip_module.cpp
* Update the limiation of 32 wavefronts per CU and 800/512 SGPRs for VI/pre-VI chips to calculate the occupancy
[ROCm/hip commit: d492f1fd6b]
* Implement the hipOccupancyMaxPotentialBlockSize function
* Replaced hipGetDeviceProperties() call by ihipGetDeviceProperties() in ihipOccupancyMaxPotentialBlockSize()
* Add test for hipOccupancyMaxPotentialBlockSize in Module API
* Added extern declaration for ihipGetDeviceProperties() to be accessed inside ihipOccupancyMaxPotentialBlockSize()
* fixed hipOccupancyMaxPotentialBlockSize test build issue
* Fix hipOccupancyMaxPotentialBlockSize dtest
* Add BUILD_CMD in hipOccupancyMaxPotentialBlockSize dtest
* Revert "Add BUILD_CMD in hipOccupancyMaxPotentialBlockSize dtest"
This reverts commit 0480ff56f1441fc515d2c26ce33783e303423938.
* Disable hipOccupancyMaxPotentialBlockSize dtest on NVCC
* move extern declaration of ihipGetDeviceProperties to hip_module.cpp
* Update the limiation of 32 wavefronts per CU and 800/512 SGPRs for VI/pre-VI chips to calculate the occupancy
Chris Freehill
Felix Kuehling
Oak Zeng
Kent Russell
Felix Abecassis
Evgeny
foreman
Evgeny Mankov
Aryan Salmanpour
wkwchau
Maneesh Gupta
Wenkai Du