+ Source files are the first to go. It is needed for in-place hipification in order to avoid errors with included but already hipified header files.
+ More extensions support for batch processing.
[ROCm/clr commit: ba87bcba5c]
+ Source files are the first to go. It is needed for in-place hipification in order to avoid errors with included but already hipified header files.
+ More extensions support for batch processing.
+ Source files are the first to go. It is needed for in-place hipification in order to avoid errors with included but already hipified header files.
+ More extensions support for batch processing.
[ROCm/hip commit: b1fad7915b]
+ Source files are the first to go. It is needed for in-place hipification in order to avoid errors with included but already hipified header files.
+ More extensions support for batch processing.
SWDEV-2 - Change OpenCL version number from 2947 to 2948.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2695 edit
[ROCm/clr commit: c340320539]
SWDEV-2 - Change OpenCL version number from 2947 to 2948.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2695 edit
SWDEV-79445 - Don't use amdgizcl. This has been unnecessary for a long time.
Affected files ...
... //depot/stg/opencl/drivers/opencl/CMakeLists.txt#23 edit
[ROCm/clr commit: d5b18e32f4]
SWDEV-79445 - Don't use amdgizcl. This has been unnecessary for a long time.
Affected files ...
... //depot/stg/opencl/drivers/opencl/CMakeLists.txt#23 edit
SWDEV-79445 - Don't use amdgizcl. This has been unnecessary for a long time.
Affected files ...
... //depot/stg/opencl/drivers/opencl/CMakeLists.txt#23 edit
[ROCm/clr commit: 3ee86b8db7]
SWDEV-79445 - Don't use amdgizcl. This has been unnecessary for a long time.
Affected files ...
... //depot/stg/opencl/drivers/opencl/CMakeLists.txt#23 edit
SWDEV-195023 - [CQE OCL][Navi10][RESOLVE] corruption seen in thumbnail for mxf clip after enabling temporal denoiser in Davinci resolve app
- Add a workaround for missing custom pitch in gfx10 HW. It can be disabled with GPU_IMAGE_BUFFER_WAR=0. Workaround implements double copy with an image without pitch.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palmemory.cpp#26 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palmemory.hpp#12 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#89 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.hpp#24 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#138 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#62 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#313 edit
[ROCm/clr commit: 582fae6820]
SWDEV-195023 - [CQE OCL][Navi10][RESOLVE] corruption seen in thumbnail for mxf clip after enabling temporal denoiser in Davinci resolve app
- Add a workaround for missing custom pitch in gfx10 HW. It can be disabled with GPU_IMAGE_BUFFER_WAR=0. Workaround implements double copy with an image without pitch.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palmemory.cpp#26 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palmemory.hpp#12 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#89 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.hpp#24 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#138 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#62 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#313 edit
Allow user specified profiles if the HSAIL note is not found.
Konstantin reviewed and approved. HSAIL note is not generated by LLVM.
Change-Id: I40fbfbaedd6787b6a716507918f698d02007afe1
Allow user specified profiles if the HSAIL note is not found.
Konstantin reviewed and approved. HSAIL note is not generated by LLVM.
Change-Id: I40fbfbaedd6787b6a716507918f698d02007afe1
[ROCm/ROCR-Runtime commit: 465a8eb40b]
Compard to gfx900, e.g., Vega 10, gfx906 adds extra counter events.
A typical difference is on TCC-EA that gfx906 (e.g., Vega 20) has 2
EAs per TCC, while only one single EA/TCC on gfx900. As such,
additional counters must be profiled to get correct results. This
patch adds one extra events to specifically handle gfx906.
Change-Id: Id6c9d37548a102c80bbfddcfa11e77d20f17431a
Compard to gfx900, e.g., Vega 10, gfx906 adds extra counter events.
A typical difference is on TCC-EA that gfx906 (e.g., Vega 20) has 2
EAs per TCC, while only one single EA/TCC on gfx900. As such,
additional counters must be profiled to get correct results. This
patch adds one extra events to specifically handle gfx906.
Change-Id: Id6c9d37548a102c80bbfddcfa11e77d20f17431a
[ROCm/rocprofiler commit: ca9a714b77]
SWDEV-79445 - OCL generic changes and code clean-up
1. Fill out out NULL entries in the cltrace dispatch table with original api calls.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/17691/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_icd_amd.h#21 edit
... //depot/stg/opencl/drivers/opencl/tools/cltrace/cltrace.cpp#16 edit
[ROCm/clr commit: b88bbb4a04]
SWDEV-79445 - OCL generic changes and code clean-up
1. Fill out out NULL entries in the cltrace dispatch table with original api calls.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/17691/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_icd_amd.h#21 edit
... //depot/stg/opencl/drivers/opencl/tools/cltrace/cltrace.cpp#16 edit
To validate cache and memory blocks profiling, this patch prepares
tests to profile dedicated kernels using specified counters, to
compare the profiled results against expected ones, and further
show the test is a fail or pass. Tests here are focusing on cache
hit/miss, memory fetch/write size.
Change-Id: Icbc8096a6e15256dec66297597a57c7665a533b8
To validate cache and memory blocks profiling, this patch prepares
tests to profile dedicated kernels using specified counters, to
compare the profiled results against expected ones, and further
show the test is a fail or pass. Tests here are focusing on cache
hit/miss, memory fetch/write size.
Change-Id: Icbc8096a6e15256dec66297597a57c7665a533b8
[ROCm/rocprofiler commit: 8b445d2c00]
Evgeny Mankov
Maneesh Gupta
foreman
Evgeny
Wenkai Du
Sean Keely
Xianwei Zhang
Jenkins