SWDEV-196326 - [hipclang-vdi-rocm]: [FBA-80]: Runtime error when all GPUs are hidden by ROCR_VISIBLE_DEVICES
- Adjusted hipGetDeviceCount to return "hipErrorNoDevice".
- This was done to match the same behaviour as HIP-HCC, and API spec for when no devices are found. Rather then return "count = 0" as it did.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/17789/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_device.cpp#22 edit
[ROCm/clr commit: bf395ba54a]
SWDEV-197488 - [Navi10][Navi14][19.30][CopySurfaceRegion] CopySurfaceRegion Failing Multiple Tests
- Try to optimize the condition for image buffer workaround. The new logic will attempt to validate the custom pitch with the HW requirement and use the backing store only if it doesn't match
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palmemory.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palmemory.hpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#76 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.hpp#29 edit
[ROCm/clr commit: 1ef3eda775]
SWDEV-2 - Change OpenCL version number from 2965 to 2966.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2713 edit
[ROCm/clr commit: a878c8b12f]
SWDEV-198556 - [HIP] Gnarly bug due to macros:
HIP_RETURN(ret) duplicates ret twice first by setting the last error
then via LogDebugInfo. So if HIP_RETURN has a function as a parameter,
the function would get called twice. So ihipMalloc and ihipMemcpy were
being called twice (and perhaps more functions).
Also logging the pointer returned by ihipMalloc so we can track memory
in logs more easily.
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_internal.hpp#33 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#65 edit
[ROCm/clr commit: 1ee23f0f43]
SWDEV-2 - Change OpenCL version number from 2964 to 2965.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2712 edit
[ROCm/clr commit: f161be4351]
* all thread local access now through single struct
* clean up old commented-out code, more use of GET_TLS()
* fewer calls to GET_TLS by passing tls as a funtion argument
* revert unnecessary change to printf
* fix failing tests due to TLS change
* fix merge conflicts in ihipOccupancyMaxActiveBlocksPerMultiprocessor
[ROCm/clr commit: f337ae1edb]
SWDEV-2 - Change OpenCL version number from 2963 to 2964.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2711 edit
[ROCm/clr commit: 058a25a812]
SWDEV-2 - Change OpenCL version number from 2962 to 2963.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2710 edit
[ROCm/clr commit: d54147832d]
...while including HIP main header file, which is inserted now after #indef controlling macro, or after #pragma once, if it's occurred earlier.
+ Add a couple of unit tests.
ToDo: Check backward compatibility on older clang versions.
[ROCm/clr commit: fedef02c37]
SWDEV-2 - Change OpenCL version number from 2961 to 2962.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2709 edit
[ROCm/clr commit: bcb8d9dc48]
SWDEV-197026 - GpuToGpuCL_VS2015 test terminates upon launching
1. Since amd::buffer inherits from amd::memory, make sure that the methods it overwrites have the same signature as it's parent's.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/17769/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/platform/memory.cpp#138 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/memory.hpp#111 edit
[ROCm/clr commit: fe6915a1bb]
SWDEV-180872 - Runtime support changes for Cooperative Group Features
- Taking into account of SGPRs usage to determine the block size
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_platform.cpp#35 edit
[ROCm/clr commit: 3d842e88ea]
SWDEV-193423 - HIP/VDI - Support for lazy hsa queue creation
- Add queue pool support for HSA HW queues. GPU_MAX_HW_QUEUES controls the pool size. The current default value is 4 (the number of active pipes on GPU).
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#132 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#38 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#81 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.hpp#24 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#314 edit
[ROCm/clr commit: 950dccb283]
* Added query of hipDeviceAttributeHdpMemFlushCntl and hipDeviceAttributeHdpRegFlushCntl
* Added NVCC blocker for the hip*FlushCntl test cases
[ROCm/clr commit: abe6776677]