- Added cuda and cudart linking for nvcc path in hipcc
- Added hipMemcpyHtoD and hipMemcpyDtoH for nvcc path
- Changed hipDeviceptr to hipDeviceptr_t
- Fixed hipMemcpy*to* API signatues
Change-Id: I6ef076b507f92502efda475c83dcdcdd462afc37
[ROCm/clr commit: fb0c432095]
SWDEV-2 - Change OpenCL version number from 2210 to 2211.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1957 edit
[ROCm/clr commit: 97cbf919ba]
- Moved HIP_INIT_API from internal to all public apis
- renamed hipLaunchModuleKernel to hipModuleLaunchKernel
- Changed tests according to the changed api
Change-Id: I822ff63c7c5b7dad340ece49456baf9d89428e9f
[ROCm/clr commit: 71991ed8f8]
SWDEV-2 - Change OpenCL version number from 2209 to 2210.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1956 edit
[ROCm/clr commit: dfd10f4c8c]
SWDEV-2 - Change OpenCL version number from 2208 to 2209.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1955 edit
[ROCm/clr commit: 0f68300697]
- Added memcpy and memset device functions
- Added test for memcpy and memset
Change-Id: Icd21a8dd964953b86d5e92889bf1664bee647219
[ROCm/clr commit: 5e7c396bcd]
- Added NVCC support for module APIs
- Changed hipFunction and hipModule data types to hipFunction_t and hipModule_t
- Created new intenal ihipModuleGetFunction as it is used twice
- Changed test to match with the new data types
Change-Id: I300a1c7fd40ed7065b1b8b9de97e3a06b96ed729
[ROCm/clr commit: 74a8fb132d]
SWDEV-2 - Change OpenCL version number from 2207 to 2208.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1954 edit
[ROCm/clr commit: f2b2b57a65]
SWDEV-94610 - Wait on every kernel dispatch if env.GPU_FLUSH_ON_EXECUTION is set.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#9 edit
[ROCm/clr commit: 08f5a25e7b]
SWDEV-101354 - HSA HLC: fix unify metadata pass
When we link multiple modules we have metadata duplicated, so after we link with our library bitcode is twice bigger than needs to be.
Besides we did not unify llvm.ident metadata since llvm 3.6 merge.
Fix that:
1. Add llvm.ident to the processing;
2. Do not duplicate strings within unified metadata;
3. Run unification pass post link, not before the link.
Now since our library is compiled for OpenCL 2.0 we will always get OCL version 2.0 as a maximum. That is not really correct, and since
the pass was not really working before that would lead to regression, as we would fail to identify correct kernel's OpenCL version and
perform simplifications for 1.2. Now the pass will pick the first version, which shall represent the kernel module. That might not be
100% correct because we may have several kernel modules, but a proper fix would require to correctly identify library as 1.2, which is
troublesome. In the current state that just keeps the status quo.
Testing: smoke, precheckin
Reviewed by Evgeny Mankov
Affected files ...
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/common/linker.cpp#152 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/linker/include/AMDFixupKernelModule.h#2 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/linker/lib/AMDFixupKernelModule.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/linker/tools/opencl-link/opencl-link.cpp#10 edit
... //depot/stg/opencl/drivers/opencl/compiler/llvm/lib/Transforms/Scalar/AMDUnifyMetadata.cpp#2 edit
[ROCm/clr commit: 82f13f6ba1]
SWDEV-1306648 - Add OptimizeLLVMBitcode to the ROCm-OpenCL-Driver. Call the optimizer in roc::HSAILProgram::linkImpl, between linking with the bitcode built-in libraries and code generation. Use the default optimization level, with at a minimum -strip -instcombine -always-inline.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#13 edit
[ROCm/clr commit: ed1144e0c0]
SWDEV-2 - Change OpenCL version number from 2206 to 2207.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1953 edit
[ROCm/clr commit: ff561c4f21]
SWDEV-2 - Change OpenCL version number from 2205 to 2206.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1952 edit
[ROCm/clr commit: 0a76bb941c]
- Corrected the hipModule.cpp test to minimal code
- Added hipModuleUnload API
- Added hipModuleUnload API test
Change-Id: I9c40337043d7972a570b795e1bfc104bd2c4d8aa
[ROCm/clr commit: 768287f2a2]
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
[ROCm/clr commit: 862e3a1a79]
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
[ROCm/clr commit: 53a0c0add6]
SWDEV-2 - Change OpenCL version number from 2204 to 2205.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1951 edit
[ROCm/clr commit: ce1ae03c57]
- The module kernel launch is now in sync with commands in its stream
- Moved launch kernel inside ihipStream
Change-Id: Ic00cfcf4882bf81b6203c36881a52575ea68b529
[ROCm/clr commit: c0fbe7891c]
SWDEV-2 - Change OpenCL version number from 2203 to 2204.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1950 edit
[ROCm/clr commit: 8b645f00ac]
Aditya Atluri
Ben Sander
foreman
Rahul Garg
Maneesh Gupta
Evgeny Mankov