foreman
239faab75e
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
[ROCm/clr commit: 16f8ca9aae]
26 строки
632 B
C++
26 строки
632 B
C++
//
|
|
// Copyright (c) 2014 Advanced Micro Devices, Inc. All rights reserved.
|
|
//
|
|
|
|
#include "top.hpp"
|
|
#include "utils/debug.hpp"
|
|
#include "device/appprofile.hpp"
|
|
#include "device/gpu/gpuappprofile.hpp"
|
|
|
|
namespace gpu {
|
|
|
|
AppProfile::AppProfile()
|
|
: amd::AppProfile()
|
|
, enableHighPerformanceState_(IS_LINUX ? false : true)
|
|
, reportAsOCL12Device_(false)
|
|
{
|
|
propertyDataMap_.insert(DataMap::value_type("HighPerfState",
|
|
PropertyData(DataType_Boolean, &enableHighPerformanceState_)));
|
|
|
|
propertyDataMap_.insert(DataMap::value_type("OCL12Device",
|
|
PropertyData(DataType_Boolean, &reportAsOCL12Device_)));
|
|
}
|
|
|
|
}
|
|
|