SWDEV-133818 - PAL support for Linux Pro: Coarse Grain SVM for OpenCL 2.0
1. This change enables OCL 2.0 on Linux for devices using PAL backend.
2. Set the alignment for Coarse Grain SVM allocations to be the gpu fragment size (2MB on Linux).
ReviewBoardURL = http://ocltc.amd.com/reviews/r/14437/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#52 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#46 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/memory.cpp#128 edit
SWDEV-2 - Change OpenCL version number from 2612 to 2613.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2360 edit
SWDEV-2 - Change OpenCL version number from 2611 to 2612.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2359 edit
SWDEV-2 - Change OpenCL version number from 2610 to 2611.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2358 edit
SWDEV-2 - Change OpenCL version number from 2609 to 2610.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2357 edit
SWDEV-2 - Change OpenCL version number from 2608 to 2609.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2356 edit
SWDEV-2 - Change OpenCL version number from 2607 to 2608.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2355 edit
SWDEV-79445 - OCL generic changes and code clean-up
- Remove pinOffset_ field, since the pinning offset can be combined with global offset_ field
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#75 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#44 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#50 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.hpp#16 edit
SWDEV-132899 - [gfx10][OCL]- Adding support for forcing WaveSize32 from runtime for testing on gfx10 HW emulator
Motivation: During testing ocltst on Windows on PAL/HSAIL/SC path on gfx10 HW emulator, it was found that SC uses WaveSize64 by default for compute kernels.
SC also has an interface that can be used for forcing the WaveSize to 32 or 64.
- Adding the "-force-wave-size-32" into compiler to be passed down to Finalizer/SC
- Adding environment variable "GPU_FORCE_WAVE_SIZE_32" that can be used from runtime to force WaveSize32 compilation in HSAIL/SC path
ReviewBoardURL = http://ocltc.amd.com/reviews/r/14364/
Affected files ...
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/gpu/hsail_be.cpp#69 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/OPTIONS.def#138 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#55 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#284 edit
SWDEV-2 - Change OpenCL version number from 2606 to 2607.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2354 edit
SWDEV-147487 - DX9/DX11 texture and OpenCL interop for YUY2
- Enable YUY2 support for DX11 and DX9. YUY2 contains just one plane of interleaved Y0UY1V components and can be mapped to (CL_RGBA, CL_UNSIGNED_INT8) with image width reduced by 2. YUY2 provides better quality due to 16bit data per pixel
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d11.cpp#23 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d9.cpp#33 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuresource.cpp#241 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#49 edit
SWDEV-2 - Change OpenCL version number from 2605 to 2606.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2353 edit
SWDEV-2 - Change OpenCL version number from 2604 to 2605.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2352 edit
SWDEV-143465 - AMDIL - Compiler Lib - Mark as unsupported all CI+ targets
1. Mark all CI+ targets as unsupported for AMDIL target mappings.
2. Let aclGetTargetInfo, aclGetTargetInfoFromChipID, aclGetDeviceInfo to report unsupported chips.
3. Fix aclReadFromMem in order to early determination of the target of binary in memory and reporting ACL_INVALID_TARGET if target is invalid, or ACL_UNSUPPORTED if chip is unsupported.
4. Add utility inline functions IsValidTarget, IsChipSupported, make getTargetMapping inline too, as it is used in the first two.
5. Fix affected tests.
[Testing] http://ocltc.amd.com:8111/viewModification.html?modId=98724&personal=true&init=1&tab=vcsModificationBuilds (clean)
[Reviewed] by Stas (http://ocltc.amd.com/reviews/r/14277)
Affected files ...
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/api/v0_8/acl.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/utils/v0_8/libUtils.cpp#9 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/utils/v0_8/libUtils.h#4 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/utils/v0_8/target_mappings.h#22 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/utils/v0_8/target_mappings_amdil.h#23 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/utils/v0_8/target_mappings_amdil64.h#22 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/target_mappings_amdil.h#49 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/target_mappings_amdil64.h#45 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/binary/BIF2xTo3x.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/binary/BIFBase.cpp#5 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/binary/BIFSymbol.cpp#14 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/complib/aclAPI.cpp#22 edit
SWDEV-2 - Change OpenCL version number from 2603 to 2604.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2351 edit
SWDEV-2 - Change OpenCL version number from 2602 to 2603.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2350 edit
SWDEV-2 - Change OpenCL version number from 2601 to 2602.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2349 edit
SWDEV-145716 - dGMA via OpenCL not working properly on AMD EPYC Ethanol platform with two WX9100/W9100s
- Add a stall and cache flushes before a barrier write in GSL and PAL
- Place temporary workarounds for CP prefetch of WRITE_DATA and the lack of SDMA marker in PAL
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#414 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#76 edit
SWDEV-2 - Change OpenCL version number from 2600 to 2601.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2348 edit
SWDEV-129762 - Remove following macros that are passed through the command line to the lightning compiler:
-D__AMD__=1
-D__devicename=1
-D__devicename__=1
-DFP_FAST_FMA=1
-DFP_FAST_FMAF=1
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#54 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#79 edit
SWDEV-2 - Change OpenCL version number from 2599 to 2600.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2347 edit
SWDEV-2 - Change OpenCL version number from 2598 to 2599.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2346 edit
SWDEV-2 - Change OpenCL version number from 2597 to 2598.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2345 edit
SWDEV-79445 - OCL generic changes and code clean-up
- Remove debugger checks from the dispatch path. There are no plans to enable debugger in the near future.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#74 edit
SWDEV-2 - Change OpenCL version number from 2596 to 2597.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2344 edit
SWDEV-145750 - SSG Player drop in performance observed when using the OCL Api in 18.10
- Keep persistent memory mapped all time for Linux and Win10
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#73 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#48 edit
SWDEV-102733 - Update some CMakeLists.txt files:
- when setting CMAKE_CXX_FLAGS, append to it rather than overwriting it.
- some linker flags, -Wl,--unresolved-symbols=report-all being one of them, requires -shared-libasan if using -fsanitize=address.
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/CMakeLists.txt#13 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/loaders/elf/utils/libelf/CMakeLists.txt#2 edit
... //depot/stg/opencl/drivers/opencl/runtime/CMakeLists.txt#9 edit
... //depot/stg/opencl/drivers/opencl/tools/clinfo/CMakeLists.txt#5 edit
SWDEV-2 - Change OpenCL version number from 2595 to 2596.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2343 edit
SWDEV-2 - Change OpenCL version number from 2594 to 2595.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2342 edit
SWDEV-132899 - [OCL][GFX10] OCLCreateImage[3] fails for the image type 1Darray
Issue: FillImage blit kernel is not working properly on gfx10 if the image type is 1Darray (i.e., it only fills the first slice/layer and ignores the rest of the layers when number of layers >1)
Root cause: gfx10 HW expects the number of layers in Z component
Fix: To fix this issue we swap the Y and Z components if the image type is 1Darray for gfx10+ in image blit kernels.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/14281/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palblit.cpp#17 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#42 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.hpp#14 edit
SWDEV-2 - Change OpenCL version number from 2593 to 2594.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2341 edit
SWDEV-2 - Change OpenCL version number from 2592 to 2593.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2340 edit
SWDEV-143465 - Revert of #1516121
[Reason]
A plenty of tests are failed.
After the changing stack logic a lot of tests should be fixed, a lot - to be removed from testing.
#1516121 will be submitted again after renewal/removal of all the failed tests.
Affected files ...
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/backends/common/v0_8/if_acl.cpp#10 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/common/v0_8/if_acl.cpp#98 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#583 edit
SWDEV-2 - Change OpenCL version number from 2591 to 2592.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2339 edit
SWDEV-143465 - Stop building static C++ kernels on CI+
Changed stack logic:
1. Stop supporting AMDIL on CI+ devices: "AMDIL doesn't support device ..." will be reported.
2. Stop handling OpenCL extension options in RT: if "-x spir" or "-x clc++" option is specified, it wouldn't force legacy AMDIL compiler anymore.
3. Start reporting error on "-legacy" option in HSAIL compiler. If we reach HSAIL compiler, then it means that there are conflicting options. Report them all, possible options are: -frontend=edg, -cl-std=CL2.0 (>= 2.0), -binary_is_spirv.
Already submitted changes in stack logic:
1. Start reporting error for SI devices on HSAIL path.
2. Start handling OpenCL extension options on HSAIL path: report error on "-x spir" or "-x clc++" options.
[Testing]
rga offline for all the targets supported by HSAIL and AMDIL (from Family_SI up to Family_VI):
tahiti, pitcairn, capeverde, spectre, spooky, kalindi, hawaii, oland, bonaire, hainan, carrizo, iceland, tonga, fiji, stoney, baffin, ellesmere.
[Reviewed] by German and Stas (http://ocltc.amd.com/reviews/r/14270)
Affected files ...
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/backends/common/v0_8/if_acl.cpp#9 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/common/v0_8/if_acl.cpp#97 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#582 edit
SWDEV-2 - Change OpenCL version number from 2590 to 2591.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2338 edit
SWDEV-143465 - Fix crashes while mixed work with hsail and amdil (legacy) paths
Redirect (where it is possible) ACL API calls from HSAIL lib to legacy AMDIL lib if target is AMDIL.
For those functions (aclCreateFromBinary, aclReadFromMem), where redirect is impossible, explicit loadLibrary for AMDIL lib and call of corresponding function from AMDIL lib is performed.
[Reviewed] by Stas (http://ocltc.amd.com/reviews/r/14238)
[Testing] rga offline for all the targets supported by HSAIL and AMDIL (from Family_SI up to Family_VI):
tahiti, pitcairn, capeverde, spectre, spooky, kalindi, hawaii, oland, bonaire, hainan, carrizo, iceland, tonga, fiji, stoney, baffin, ellesmere.
Affected files ...
... //depot/stg/opencl/drivers/opencl/compiler/lib/api/v0_8/acl.cpp#45 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/api/v0_8/aclValidation.cpp#8 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/api/v0_8/aclValidation.h#3 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/libUtils.cpp#29 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/libUtils.h#30 edit
SWDEV-2 - Change OpenCL version number from 2589 to 2590.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2337 edit
SWDEV-2 - Change OpenCL version number from 2588 to 2589.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2336 edit
SWDEV-2 - Change OpenCL version number from 2587 to 2588.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2335 edit
foreman