AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

P4 to Git Change 1599157 by gandryey@gera-ocl-lc on 2018/08/28 17:11:04

Browse Source 
SWDEV-79445 - OCL generic changes and code clean-up
	- Add devkerenle.cpp/hpp files for device::Kernel object
	- Move generic code for the arguments setup from the device layer to the abstraction layer
	- Update ROCr and PAL paths to utilize the generic logic for the arguments setup

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#226 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#313 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devkernel.cpp#1 add
... //depot/stg/opencl/drivers/opencl/runtime/device/devkernel.hpp#1 add
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#328 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.hpp#130 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#61 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.hpp#20 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#40 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.hpp#24 edit
... //depot/stg/opencl/drivers/opencl/runtime/runtimedefs#51 edit


[ROCm/clr commit: 5cfeb120ed]
This commit is contained in:
foreman
2018-08-28 17:30:29 -04:00
parent cb01e0e6ea
commit 0eb2d36332
10 changed files with 1052 additions and 1832 deletions
Download Patch File Download Diff File Expand all files Collapse all files
projects/clr/rocclr/runtime/device/gpu/gpukernel.cpp
+1 -2
View File
@@ -823,7 +823,6 @@ Kernel::Kernel(const std::string& name, const Device& gpuDev, const Program& pro
workGroupInfo_.privateMemSize_ = hwPrivateSize_;
// Default wavesPerSimdHint_
workGroupInfo_.wavesPerSimdHint_ = ~0U;
hsa_ = false;
}
Kernel::~Kernel() {
@@ -3127,7 +3126,7 @@ HSAILKernel::HSAILKernel(std::string name, HSAILProgram* prog, std::string compi
extraArgumentsNum_(extraArgsNum),
waveLimiter_(this, (prog->isNull() ? 1 : dev().getAttribs().numberOfCUsperShaderArray) *
dev().hwInfo()->simdPerCU_) {
hsa_ = true;
flags_.hsa_ = true;
}
HSAILKernel::~HSAILKernel() {