SWDEV-133851 - [CQE OCL][1.2][LNX-PRO] A subtest from OCLcompiler is failing due to faulty cl#1458879
- If pinning failed and allocation was forced to system memory, then copy the original data
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#577 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#64 edit
[ROCm/clr commit: af98be0351]
SWDEV-2 - Change OpenCL version number from 2507 to 2508.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2255 edit
[ROCm/clr commit: 2276473e9d]
SWDEV-2 - Change OpenCL version number from 2506 to 2507.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2254 edit
[ROCm/clr commit: 75653253bb]
SWDEV-2 - Change OpenCL version number from 2505 to 2506.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2253 edit
[ROCm/clr commit: c7ea67c7c6]
SWDEV-95919 - Expose coutners by instances and not number of counters. Also expose EA and RMI instances.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/13502/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcounters.cpp#15 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/runtime/OCLPerfCounters.cpp#41 edit
[ROCm/clr commit: db63366bcb]
SWDEV-2 - Change OpenCL version number from 2504 to 2505.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2252 edit
[ROCm/clr commit: 4460abcd9c]
SWDEV-132899 - [OCL][GFX10] Add support for GFX10
Adjusting WaveFrontSize for Null Devices based on the gfxip (the WaveFrontSize is 32 for gfxip10)
ReviewBoardURL = http://ocltc.amd.com/reviews/r/13486/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#63 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#37 edit
[ROCm/clr commit: cb4585939d]
SWDEV-2 - Change OpenCL version number from 2503 to 2504.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2251 edit
[ROCm/clr commit: b236524590]
SWDEV-2 - Change OpenCL version number from 2502 to 2503.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2250 edit
[ROCm/clr commit: c7dbd490b0]
SWDEV-86035 - Switch back to 8 CBs due to HW hangs with HWSC on VI.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#59 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#32 edit
[ROCm/clr commit: e53571d05b]
SWDEV-118564 - [OCL-LC-ROCm] Remove options, which have already been moved to AMDGPUToolChain by https://reviews.llvm.org/rL312524
In order to have similar set of optipons for online and offline compilation a mechanism of setting default options in AMDGPUToolChain was implemented by https://reviews.llvm.org/rL312524. That commit also sets two default options in AMDGPUToolChain: -m64 and -O3 (the latter only set if there is no -O{N} option in the args). The commit has already reached amd-common.
The current change relates to LC only and removes setting of -m64 from compileImpl_LC() as it is set later in TranslateArgs(); for online -O{N} is set as before by RT and stays unchanged in AMDGPUToolChain; for offline it is set to -O3 by TranslateArgs() if no -O{N} is passed through args.
Also remove comments regarding "-x cl" as it is now correctly set in OpenCL driver.
Review: http://ocltc.amd.com/reviews/r/13454/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcompiler.cpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/roccompiler.cpp#36 edit
[ROCm/clr commit: a348a08391]
SWDEV-2 - Change OpenCL version number from 2501 to 2502.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2249 edit
[ROCm/clr commit: 5b85bc981c]
SWDEV-2 - Change OpenCL version number from 2500 to 2501.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2248 edit
[ROCm/clr commit: 61de12fb47]
SWDEV-120036 - Supporting the cl_amd_device_attribute_query on the ROC device - Back out changelist 1459984
- not all device attributes are supported, will re-submit the changes when every attribute is supported.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#64 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.cpp#26 edit
[ROCm/clr commit: fb18f128c9]
SWDEV-111439 - Add query for preferred constant size
- fixed a mistake of using 64KiB for the size, which should be 16KiB.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#576 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#62 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#63 edit
[ROCm/clr commit: a851cc152c]
SWDEV-2 - Change OpenCL version number from 2499 to 2500.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2247 edit
[ROCm/clr commit: f8bc731619]
SWDEV-2 - Change OpenCL version number from 2498 to 2499.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2246 edit
[ROCm/clr commit: 040f46d584]
SWDEV-129129 - [[CQE OCL][Vega vs Fiji] Upto 12% Performance drop observed on VEGA10 compared to FIJI while running BlackMagic Davinci Resolve
More benchmark tuning:
- Keep system memory locked in the resource cache. That removes huge amount of lock/unlock calls to OS due to the resource creation and destruciton
- Reduce the command buffer size to 256 commands and incrrease the amount of CBs to 16
- Increase the amount of resident resources to 2048
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#574 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palmemory.cpp#17 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#37 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#58 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#31 edit
[ROCm/clr commit: 4066449a8b]
foreman
Maneesh Gupta
Kent Knox
Rahul Garg
Siu Chi Chan
Evgeny Mankov
wsttiger
Ben Sander
Wen-Heng (Jack) Chung
Aaron Enye Shi