SWDEV-86035 - Add PAL backend to OpenCL
- Add (PAL) suffix to the driver version
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#556 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#21 edit
SWDEV-101383 - [RS_DVR][MGPU] Slave GPU is blocked from going into BACO when DVR process is active (no recording or instant replay)
- Fix a memory leak
- Also make sure to use VALIDATE_ONLY flag properly as bindExternalDevice can be called even during context creation for which we cant close the adaper
ReviewBoardURL = http://ocltc.amd.com/reviews/r/11330/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#555 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp#174 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.h#62 edit
SWDEV-101448 - [CQE OCL][Brahma][PERF][QR] ~21% perf drop is observed with lulesh-cl subtest of ComputeApps tests : Faulty CL # 1306133
- Use the logic for transfer size before CL#1306133
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpublit.cpp#124 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palblit.cpp#10 edit
SWDEV-101383 - Back out CL1310033 as it is causing Carrizo Win 10 Sanity test to crash at ocltst module ocldx.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#553 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp#172 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.h#61 edit
SWDEV-101383 - [RS_DVR][MGPU] Slave GPU is blocked from going into BACO when DVR process is active (no recording or instant replay)
- if the OS is Win10, no need to do extensive adapter init.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/11241/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#552 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp#171 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.h#60 edit
SWDEV-79278 - [OpenCL][PAL] force Vega10(gfx9)(aka: Greenland) to use PAL backend
ReviewBoardURL = http://ocltc.amd.com/reviews/r/11279/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#551 edit
SWDEV-79445 - OCL generic changes and code clean-up
- Improve image fill performance with multiple writes in a single thread. The current split has 3 regions
Affected files ...
... //depot/stg/opencl/drivers/opencl/library/common.hsa/src/blitKernels.cl#4 edit
... //depot/stg/opencl/drivers/opencl/library/common/src/blitKernels.cl#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpublit.cpp#123 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpublit.hpp#40 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palblit.cpp#8 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palblit.hpp#4 edit
SWDEV-86035 - Enable PAL for GFX9 by default
- GPU_ENABLE_PAL=0 will force GSL backend for GFX9
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#550 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#19 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#256 edit
SWDEV-101206 - [CQE OCL][Perf][G][QR] Upto ~9% Performance drop observed while running Video Composition subtest of Compubench; Faulty CL#1306133
- Use the original logic without DMA flush. Flush on staging write helps with a blocking op only, but currently VDI doesn't have that information.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpublit.cpp#122 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palblit.cpp#7 edit
SWDEV-79445 - OCL generic changes and code clean-up
- Update staging copy path with a flush so CPU copy and SDMA transfer could run asynchronously.
- Tune chunk size for transfers
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpublit.cpp#121 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palblit.cpp#6 edit
SWDEV-95905 - OpenCL on PAL - Device Enqueue
- Move disapatch funciton outside of the compiler lib. Client must provide 4 new functions to the scheduler: GetCmdTemplateHeaderSize(), GetCmdTemplateDispatchSize(),EmptyCmdTemplateDispatch(), RunCmdTemplateDispatch().
http://ocltc.amd.com/reviews/r/11142/
Affected files ...
... //depot/stg/opencl/drivers/opencl/library/hsa/hsail/src/devenq/schedule.cl#13 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuschedcl.cpp#34 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palschedcl.cpp#2 edit
SWDEV-95135 - Fix OpenCL build after removing legacy asics from OpenGL.
This is a minimal change to fix the build.
Some more code could be removed because the expression (asic_id < GSL_ATIASIC_ID_TAHITI_P) should never be true, since GSL_ATIASIC_ID_TAHITI_P is the minimum asic id.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/10808/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp#169 edit
SWDEV-76911 - Set output pipeline of multi-shader compilation in the same way driver sets. Fill output shader pointers only if they will be generated based on the input shaders, otherwise NULL.
ReviewBoardURL = http://dxreview.amd.com/r/20059/
Affected files ...
... //depot/stg/sc/Src/Dev/TestEngine.cpp#512 edit
SWDEV-95095 - Bristol Ridge parts report their OpenCL device ID name as "Carrizo"
- Detect the ASIC revision for the name swap with Bristo Ridgel instead of Carrizo
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpucompiler.cpp#154 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#548 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp#168 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/backend.h#13 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcompiler.cpp#2 edit
SWDEV-79445 - Fix a TC regression after CL#1273440
- Add the both conditions to the restrictions: sorce and destination alignment
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp#167 edit
SWDEV-94881 - [OpenCL]increasing the size limit of image buffer to 2^27 which is for the moment at 65536
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudefs.hpp#136 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldefs.hpp#3 edit
SWDEV-94161 - [Adobe Photoshop] TDR is observed while applying Blur effect on the selected portion of an Image
- Restore back the original condition for SDMA restriction (CL#1195487). The root cause wasn't identified and probably somewhere in GSL, since PAL backend works fine.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp#166 edit
SWDEV-94524 - [OCL] Call to clBuildProgram crashes amdocl64.dll
- Detect offline device and return a fake srd handle. Compiler must reload binary for a specific device in order for the binary to have proper functionality
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuprogram.cpp#226 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#5 edit
SWDEV-86170 - Need OCL changes for Compute Unit Reservation
- Add support for RT and Medium priority queues
- Use the new packet for the CU mask programming. It will allow CU reservation for RT queue in KMD.
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_command.cpp#11 edit
... //depot/stg/opencl/drivers/opencl/library/hsa/hsail/src/devenq/schedule.cl#12 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#546 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.hpp#159 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpumemory.cpp#127 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#402 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.hpp#139 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLContext.cpp#81 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLContext.h#52 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp#165 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/backend.h#12 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/commandqueue.cpp#22 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/commandqueue.hpp#17 edit
SWDEV-90482 - [Afterswitch] Interop from OpenGL to OpenCL is broken in one driver and crashes in another
- Make sure SRD resource is reported to OS if program contains static samplers
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#314 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuprogram.hpp#67 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.hpp#4 edit
SWDEV-92245 - [CQE OCL][QR][G] Multiple 32/64 bit Bolt sample crashes on all CPUs. FaultyCL#1257532
- Bolt calls map/unmap with the same region twice. Add a counter for the same region to track that case
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#195 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#272 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#401 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#6 edit
SWDEV-90482 - [Afterswitch] Interop from OpenGL to OpenCL is broken in one driver and crashes in another
Fixed the crash by restoring the order where we bind the external device.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/10195/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#544 edit
SWDEV-86378 - Apply the sDMA L2T work-around to T2L as well.
HW confirms T2L also has issues.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp#164 edit
SWDEV-90618 - cl_kernel_info_amd always returns 0 when working via HSAIL path
- Don't access GPU device specific data for offline compilation
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#313 edit
SWDEV-89454 - The memory pointed by m_nativeDisplayHandle should be freed at IOL.
The memory pointed by m_nativeDisplayHandle is allocated in IOL, so it should be freed at IOL as well. Otherwise, the error of "double free or corruption" happens.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp#162 edit
SWDEV-89711 - Adding EGL interop capability:
- Remove Context::Info::type_ and only use flags_, it's more accurate and type_ was just redundant
- Plumbing work for EGL at the top of the API layer.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/9965/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d10.cpp#11 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d11.cpp#18 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d9.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_gl.cpp#48 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_gl_amd.hpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/cpu/cpudevice.hpp#94 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#269 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#542 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.hpp#157 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsadevice.cpp#56 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsadevice.hpp#25 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.cpp#40 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.hpp#24 edit
foreman