16f8ca9aae
ECR #377625 - Workaround for Blender performance issue. Lower available VGPRs to improve waves per CU. Added BuildOptsAppend to OCL app profile. Read BuildOptsAppend and append to build options. Added specific wave optimization option for Blender. Affected files ... ... //depot/stg/opencl/drivers/opencl/appprofiles/oclappprofile.xml#7 edit ... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/gpu/scwrapper/SI/scCompileSI.cpp#45 edit ... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/OPTIONS.def#116 edit ... //depot/stg/opencl/drivers/opencl/runtime/device/appprofile.cpp#10 edit ... //depot/stg/opencl/drivers/opencl/runtime/device/appprofile.hpp#8 edit ... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#170 edit ... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#230 edit ... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuappprofile.cpp#10 edit ... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuappprofile.hpp#6 edit ... //depot/stg/opencl/drivers/opencl/runtime/platform/program.cpp#63 edit
31 wiersze
560 B
C++
31 wiersze
560 B
C++
//
|
|
// Copyright (c) 2014 Advanced Micro Devices, Inc. All rights reserved.
|
|
//
|
|
|
|
#ifndef GPUAPPPROFILE_HPP_
|
|
#define GPUAPPPROFILE_HPP_
|
|
|
|
#include <string>
|
|
#include <map>
|
|
|
|
namespace gpu {
|
|
|
|
class AppProfile : public amd::AppProfile
|
|
{
|
|
public:
|
|
AppProfile();
|
|
|
|
//! return the value of enableHighPerformanceState_
|
|
bool enableHighPerformanceState() const { return enableHighPerformanceState_; }
|
|
bool reportAsOCL12Device() const { return reportAsOCL12Device_; }
|
|
|
|
private:
|
|
|
|
bool enableHighPerformanceState_;
|
|
bool reportAsOCL12Device_;
|
|
};
|
|
|
|
}
|
|
|
|
#endif
|