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
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
SWDEV-2 - Change OpenCL version number from 2965 to 2966.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2713 edit
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
SWDEV-2 - Change OpenCL version number from 2964 to 2965.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2712 edit
SWDEV-197464 - [HIP] Set GPU_SINGLE_ALLOC_PERCENT to 100 for hip.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#245 edit
* Enabled gcc for hip host code
* Adding tests for hip code + (gcc & g++), without kernels
* Excluding nvcc platforms for gcc and g++ tests + Addressing review comments
* minor code clean-up
* Add rocm include path
* Added relative path for library
* Hiding non supported functions for gcc
* Incorporating review comments
* 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
SWDEV-2 - Change OpenCL version number from 2963 to 2964.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2711 edit
SWDEV-2 - Change OpenCL version number from 2962 to 2963.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2710 edit
...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.
SWDEV-2 - Change OpenCL version number from 2961 to 2962.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2709 edit
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
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
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
* Added support of hipOccupancyMaxActiveBlocksPerMultiprocessor & hipOccupancyMaxActiveBlocksPerMultiprocessorWithFlags APIs
* Taking into account of SGPR usage to determine the max active blocks in hipOccupancyMaxActiveBlocksPerMultiprocessor()
foreman
lthakur
Rahul Garg
Jenkins
Evgeny Mankov
Maneesh Gupta
Alex Voicu
Sarbojit2019
Jeff Daily
wkwchau