P4 to Git Change 1079952 by yaxunl@yaxunl_stg_win50 on 2014/09/23 12:31:16

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
This commit is contained in:
foreman
2014-09-23 12:44:50 -04:00
parent 5ef908c5e7
commit 16f8ca9aae
8 changed files with 119 additions and 76 deletions
+3
View File
@@ -51,6 +51,7 @@ namespace amd {
std::vector<Device*> *Device::devices_ = NULL;
bool Device::isHsaDeviceAvailable_ = false;
bool Device::isGpuDeviceAvailable_ = false;
AppProfile Device::appProfile_;
#if defined(WITH_HSA_DEVICE)
AppProfile* Device::oclhsaAppProfile_ = NULL;
@@ -150,6 +151,8 @@ Device::init()
assert(!Runtime::initialized() && "initialize only once");
bool ret = false;
devices_ = NULL;
appProfile_.init();
// IMPORTANT: Note that we are initialiing HSA stack first and then
// GPU stack. The order of initialization is signiicant and if changed