SWDEV-107075 - [OCL][VG10] Conformance RQ Mipmaps tests are failing. Adding a temporary workaround for Vega10 to disable sDMA transfers for MemToImage and ImageToMem for 1Darray image format for now and use Kernles instead until the failures can be root-caused and fixed.
GPU_DISABLE_SDMA_IMG_MEM_IMG environment variable was also added to quickly enable back the sDMA for testing and continuing the current failure investigation.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/12194/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#22 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.hpp#8 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#265 edit
[ROCm/clr commit: 7403de545e]
SWDEV-107075 - [OCL][VG10] Conformance RQ Mipmaps tests are failing. Adding a temporary workaround for Vega10 to disable sDMA transfers for MemToImage and ImageToMem for 1Darray image format for now and use Kernles instead until the failures can be root-caused and fixed.
GPU_DISABLE_SDMA_IMG_MEM_IMG environment variable was also added to quickly enable back the sDMA for testing and continuing the current failure investigation.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/12194/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#22 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.hpp#8 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#265 edit
SWDEV-2 - Change OpenCL version number from 2339 to 2340.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2086 edit
[ROCm/clr commit: 4b86b7c587]
SWDEV-2 - Change OpenCL version number from 2339 to 2340.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2086 edit
1. Moved half device functions around so that script can catch the signatures
2. Generated docs for half precision apis
Change-Id: Iee27658e3a639fdb02af135e71841dc6427f15e2
[ROCm/clr commit: 706a032a29]
1. Moved half device functions around so that script can catch the signatures
2. Generated docs for half precision apis
Change-Id: Iee27658e3a639fdb02af135e71841dc6427f15e2
1. Moved half device functions around so that script can catch the signatures
2. Generated docs for half precision apis
Change-Id: Iee27658e3a639fdb02af135e71841dc6427f15e2
1. Commented out unsupported device math functions
2. Moved function signatures to the top of implementation snippets
3. Added script to generate markdown documentation for device math apis
4. Added the generated file from the script which should be present everytime
Change-Id: Ic579dd8b8fdffa6e1b4d4f5f3fd8a803f4dcaac7
[ROCm/clr commit: 3d4dcee35d]
1. Commented out unsupported device math functions
2. Moved function signatures to the top of implementation snippets
3. Added script to generate markdown documentation for device math apis
4. Added the generated file from the script which should be present everytime
Change-Id: Ic579dd8b8fdffa6e1b4d4f5f3fd8a803f4dcaac7
1. Commented out unsupported device math functions
2. Moved function signatures to the top of implementation snippets
3. Added script to generate markdown documentation for device math apis
4. Added the generated file from the script which should be present everytime
Change-Id: Ic579dd8b8fdffa6e1b4d4f5f3fd8a803f4dcaac7
1. Fixed compilation issues for tests
2. Added missing intrinsics + math functions
3. Disabled some device functions as they are causing linking error with HCC
Change-Id: I79d52c4c7a539cc8ef40580247ad97ffcb975f09
[ROCm/clr commit: 41a46effef]
1. Fixed compilation issues for tests
2. Added missing intrinsics + math functions
3. Disabled some device functions as they are causing linking error with HCC
Change-Id: I79d52c4c7a539cc8ef40580247ad97ffcb975f09
1. Fixed compilation issues for tests
2. Added missing intrinsics + math functions
3. Disabled some device functions as they are causing linking error with HCC
Change-Id: I79d52c4c7a539cc8ef40580247ad97ffcb975f09
SWDEV-95919 - Fix num-of-waves PerfCounter is 0 on Baffin.
Counters are clockgated on Fiji and above. Need to program the RLC_PERFMON_CLK_CNTL register thru IDeviceSetClockMode(), so that meaningful data is recorded. We leave kmd/pplib to keep track of the OCL process to restore the RLC_PERFMON_CLK_CNTL register when the OCL process is killed.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#41 edit
[ROCm/clr commit: e826e296d4]
SWDEV-95919 - Fix num-of-waves PerfCounter is 0 on Baffin.
Counters are clockgated on Fiji and above. Need to program the RLC_PERFMON_CLK_CNTL register thru IDeviceSetClockMode(), so that meaningful data is recorded. We leave kmd/pplib to keep track of the OCL process to restore the RLC_PERFMON_CLK_CNTL register when the OCL process is killed.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#41 edit
SWDEV-2 - Change OpenCL version number from 2338 to 2339.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2085 edit
[ROCm/clr commit: 37ff2e2294]
SWDEV-2 - Change OpenCL version number from 2338 to 2339.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2085 edit
1. All fp32, fp64 math device/host functions should be in math_functions.h/.cpp
2. All fp32, fp64 fast math intrinsics for device/host functions should be in device_functions.h/.cpp
3. All the device code implementations should be in device_util.h/.cpp
4. Hence, made changes appropriately by moving code and creating new header files
5. Added math_functions.cpp/.h
6. Changed #ifndef signature to make sure no conflicts between headers with same names in hip/hip_runtime.h and hip/hcc_detail/hip_runtime.h
7. Changed tests to fit the code changes, making them to include appropriate headers
8. Added math_functions.cpp to CMakeLists.txt
9. Some of the tests are still broken, mostly host math functions will fix them in next commit
10. TODO: FIX compilation issues for host math functions
Change-Id: I7a17637d7e294a7d224ffba932c1a08668febd26
[ROCm/clr commit: d23b6b8694]
1. All fp32, fp64 math device/host functions should be in math_functions.h/.cpp
2. All fp32, fp64 fast math intrinsics for device/host functions should be in device_functions.h/.cpp
3. All the device code implementations should be in device_util.h/.cpp
4. Hence, made changes appropriately by moving code and creating new header files
5. Added math_functions.cpp/.h
6. Changed #ifndef signature to make sure no conflicts between headers with same names in hip/hip_runtime.h and hip/hcc_detail/hip_runtime.h
7. Changed tests to fit the code changes, making them to include appropriate headers
8. Added math_functions.cpp to CMakeLists.txt
9. Some of the tests are still broken, mostly host math functions will fix them in next commit
10. TODO: FIX compilation issues for host math functions
Change-Id: I7a17637d7e294a7d224ffba932c1a08668febd26
1. All fp32, fp64 math device/host functions should be in math_functions.h/.cpp
2. All fp32, fp64 fast math intrinsics for device/host functions should be in device_functions.h/.cpp
3. All the device code implementations should be in device_util.h/.cpp
4. Hence, made changes appropriately by moving code and creating new header files
5. Added math_functions.cpp/.h
6. Changed #ifndef signature to make sure no conflicts between headers with same names in hip/hip_runtime.h and hip/hcc_detail/hip_runtime.h
7. Changed tests to fit the code changes, making them to include appropriate headers
8. Added math_functions.cpp to CMakeLists.txt
9. Some of the tests are still broken, mostly host math functions will fix them in next commit
10. TODO: FIX compilation issues for host math functions
Change-Id: I7a17637d7e294a7d224ffba932c1a08668febd26
1. Added usad, umulhi, urhadd
2. Corrected implementation of __hadd, __hradd
3. TODO: __sad(). It gets tricky as ISA sees them as unsigned
Change-Id: Ibd2c2133b462f9393f3990355706386c79256bba
[ROCm/clr commit: 9ca135ac2e]
1. Added usad, umulhi, urhadd
2. Corrected implementation of __hadd, __hradd
3. TODO: __sad(). It gets tricky as ISA sees them as unsigned
Change-Id: Ibd2c2133b462f9393f3990355706386c79256bba
1. Added usad, umulhi, urhadd
2. Corrected implementation of __hadd, __hradd
3. TODO: __sad(). It gets tricky as ISA sees them as unsigned
Change-Id: Ibd2c2133b462f9393f3990355706386c79256bba
1. Fixed build issues with new Integer intrinsics
2. Changed tests to work exactly as CUDA code
3. Still some integer intrinsics need to be supported
Change-Id: Ie6f4171259cf4da517436895d4f6f01e01f59b11
[ROCm/clr commit: f0ea51c786]
1. Fixed build issues with new Integer intrinsics
2. Changed tests to work exactly as CUDA code
3. Still some integer intrinsics need to be supported
Change-Id: Ie6f4171259cf4da517436895d4f6f01e01f59b11
1. Fixed build issues with new Integer intrinsics
2. Changed tests to work exactly as CUDA code
3. Still some integer intrinsics need to be supported
Change-Id: Ie6f4171259cf4da517436895d4f6f01e01f59b11
SWDEV-2 - Change OpenCL version number from 2337 to 2338.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2084 edit
[ROCm/clr commit: 109d738014]
SWDEV-2 - Change OpenCL version number from 2337 to 2338.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2084 edit
Ben Sander
foreman
Rahul Garg
Aditya Atluri
Ramesh Errabolu