ECR #399840 - OpenCL Runtime HW Debug support development - add support to the VI asics & support the use case of debug registeration in a pre-dispatch callback function
** Cross branch check-in with CL1131894
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_debugger_amd.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudebugmanager.cpp#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#501 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.hpp#139 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gputrap.hpp#2 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#355 edit
[ROCm/clr commit: 95596795fc]
EPR #010002 - Change OpenCL version number from 1758 to 1759.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1505 edit
[ROCm/clr commit: 3da2bd1161]
ECR #304775 - Mipmaps support
- Create views for the specified mip level in the transfer operations
- OCL requires just one mip level transfer. Thus we could keep the original blit kernels and just create a view for the specified mip level.
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_memobj.cpp#75 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#500 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/memory.cpp#119 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/memory.hpp#90 edit
[ROCm/clr commit: f20ddcf1ce]
EPR #010002 - Change OpenCL version number from 1757 to 1758.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1504 edit
[ROCm/clr commit: 65421eb202]
ECR #377625 - Refactor amdil function support. Move the code from linker.cpp to llvm32 to facilitate porting linker.cpp to llvm36.
Also made changes to respect user specified noinline attribute and added options to allow a list of functions to be inlined or not inlined to facilitate debugging.
Affected files ...
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/common/linker.cpp#119 edit
... //depot/stg/opencl/drivers/opencl/compiler/llvm32/include/llvm/AMDILFuncSupport.h#1 add
... //depot/stg/opencl/drivers/opencl/compiler/llvm32/lib/Linker/AMDILFuncSupport.cpp#1 add
[ROCm/clr commit: cc17b01cee]
EPR #010002 - Change OpenCL version number from 1756 to 1757.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1503 edit
[ROCm/clr commit: 6b505035c0]
EPR #010002 - Change OpenCL version number from 1755 to 1756.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1502 edit
[ROCm/clr commit: f24223953a]
EPR #010002 - Change OpenCL version number from 1754 to 1755.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1501 edit
[ROCm/clr commit: 848605153d]
EPR #394115 - Adding the environment variable "GPU_SELECT_COMPUTE_RINGS_ID" to select a specific compute queue for OCL submission. This EV was requested from KMD team for testing the CWSR demo on CZ.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/7082/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#354 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp#111 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.h#44 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#226 edit
[ROCm/clr commit: 0494cd6ace]
EPR #010002 - Change OpenCL version number from 1753 to 1754.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1500 edit
[ROCm/clr commit: 034de4c607]
EPR #415603 - [CQE OCL][QR][CPU] 29 of 34 SPIR tests failed in all CPUs due to CL#1127589.
Two changes:
1. OCL builtin needs to be demangled.
2. setupLoaderObject() needs to be moved into dll and called through comp lib interface since it needs to reset function pointers of several comp lib interface.
Otherwise it will use function pointers of the static comp lib and causes strange errors.
Affected files ...
... //depot/stg/opencl/drivers/opencl/compiler/lib/api/v0_8/acl.cpp#26 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/api/v0_8/aclLoaders.cpp#11 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/common/v0_8/if_acl.cpp#62 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/common/v0_8/if_acl.h#2 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/include/v0_8/aclFunctors.h#4 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/include/v0_8/aclStructs.h#15 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/include/v0_8/aclTypes.h#5 edit
... //depot/stg/opencl/drivers/opencl/compiler/llvm32/lib/Linker/AMDFixupKernelModule.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/complib/CLAssumptionCheck.cpp#40 edit
[ROCm/clr commit: eca7138cd1]
EPR #010002 - Change OpenCL version number from 1752 to 1753.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1499 edit
[ROCm/clr commit: 36782c8b2a]
EPR #414133 - HSA HLC: fixed device enqueue code for no-capture case
A dead store to a context structure may be generated by clang, while our code was only
expecting a bitcast.
Affected files ...
... //depot/stg/opencl/drivers/opencl/compiler/llvm36/lib/Transforms/Scalar/AMDLowerEnqueueKernel.cpp#6 edit
[ROCm/clr commit: 51f603a4cc]
EPR #010002 - Change OpenCL version number from 1751 to 1752.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1498 edit
[ROCm/clr commit: 0428e6eb52]
EPR #010002 - Change OpenCL version number from 1750 to 1751.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1497 edit
[ROCm/clr commit: e0a8c76219]
EPR #010002 - Change OpenCL version number from 1749 to 1750.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1496 edit
[ROCm/clr commit: 3207f16588]
EPR #415638 - Improve APU performance
- Force remote allocation of local and persistent memory to Remote from RemoteUSWC:
- Use gpu copy for remote/pinned image/buffer.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpublit.cpp#114 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuresource.cpp#211 edit
[ROCm/clr commit: 637492a7dd]
EPR #010002 - Change OpenCL version number from 1748 to 1749.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1495 edit
[ROCm/clr commit: 1976010ccd]
EPR #414789 - fixed the failure of svm atomics failure with mulitple device support. The failure was caused by the svm allocation for the devices which don't support platform stomics svm.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.cpp#35 edit
[ROCm/clr commit: 13e7ed43f0]
EPR #010002 - Change OpenCL version number from 1747 to 1748.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1494 edit
[ROCm/clr commit: 6c6105c698]
EPR #413960 - Platform Atomics on CZ.
1. Since CMMQS can support 4G atomics range on CZ, the atomics range on KV is reverted to 4G.
2. On KV, the platform atomics is implemented by using ATC/IOMMU. But on CZ, it should be implemented without using ATC/IOMMU due to HW changes. So, _svmAtomicsUsingIOMMU is introduced to differentiate the two implementations.
3. _priSupport was renamed _svmAtomics due to different implementation on KV vs CZ.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpusettings.cpp#304 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/include/cal/cal.h#33 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp#109 edit
[ROCm/clr commit: bec936b08b]
EPR #010002 - Change OpenCL version number from 1746 to 1747.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1493 edit
[ROCm/clr commit: ea4b4650c5]
EPR #010002 - Change OpenCL version number from 1745 to 1746.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1492 edit
[ROCm/clr commit: eeb5da2ac2]
ECR #304775 - In addition to CL#1126564
- Keep just tile index field from the parent
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuresource.cpp#209 edit
[ROCm/clr commit: a8349b692f]
ECR #304775 - Use the tiling index from the parent object instead of forcing it to 0.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuresource.cpp#208 edit
[ROCm/clr commit: fb80e6657b]
EPR #010002 - Change OpenCL version number from 1744 to 1745.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1491 edit
[ROCm/clr commit: 3bb911a606]
ECR #304775 - Enable TC compatible htile mode by default.
- The feature is available on VI+, but interop just requires different tiling mode.
- In the future we may need another way to control this feature for interop.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp#108 edit
[ROCm/clr commit: ac68112eaf]
EPR #010002 - Change OpenCL version number from 1743 to 1744.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1490 edit
[ROCm/clr commit: 973748fba9]
EPR #405824 - Back out changelist 1125022 because of failures in Linux.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#497 edit
[ROCm/clr commit: 348bfd35d9]
EPR #010002 - Change OpenCL version number from 1742 to 1743.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1489 edit
[ROCm/clr commit: 3446badda8]
EPR #010002 - Change OpenCL version number from 1741 to 1742.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1488 edit
[ROCm/clr commit: eb14d64068]
EPR #010002 - Change OpenCL version number from 1740 to 1741.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1487 edit
[ROCm/clr commit: a8de6ca08f]
EPR #010002 - Change OpenCL version number from 1739 to 1740.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1486 edit
[ROCm/clr commit: 06eef1ea0f]
EPR #010002 - Change OpenCL version number from 1738 to 1739.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1485 edit
[ROCm/clr commit: 797c89da4e]
EPR #010002 - Change OpenCL version number from 1737 to 1738.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1484 edit
[ROCm/clr commit: 9ed8da78bb]
ECR #399840 - OpenCL Runtime HW Debug support development
- use device to control debugger registration and exception notification so that debug event will not be tied to any particular queue.
- use aqlCodeInfo parameter for clHwDbgMapKernelCodeAMD() to be consistent with clHwDbgGetAqlPacketInfoAMD()
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_debugger_amd.cpp#6 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_debugger_amd.h#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudebugmanager.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudebugmanager.hpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#352 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.hpp#127 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLContext.cpp#70 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLContext.h#43 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hwdebug.cpp#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hwdebug.hpp#6 edit
[ROCm/clr commit: 3e53caa02e]