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

P4 to Git Change 1701409 by gandryey@gera-w8 on 2018/11/01 17:43:16

Browse Source 
SWDEV-79445 - OCL generic changes and code clean-up
	- Remove obsolete settings
	- Simplify some logic when runtime checks dimension override in the dispatch critical path

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_execute.cpp#29 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#233 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#323 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devkernel.cpp#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#599 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#333 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuprogram.cpp#246 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuresource.cpp#246 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpusettings.cpp#361 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpusettings.hpp#103 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#425 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp#184 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#60 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.hpp#20 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.cpp#39 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.hpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#300 edit
This commit is contained in:
foreman
2018-11-01 17:49:35 -04:00
parent 320c9a6375
commit 21f6e4337a
16 changed files with 62 additions and 172 deletions
Download Patch File Download Diff File Expand all files Collapse all files
rocclr/runtime/device/device.cpp
+7 -1
View File
@@ -573,7 +573,6 @@ namespace device {
Settings::Settings() : value_(0) {
assert((ClExtTotal < (8 * sizeof(extensions_))) && "Too many extensions!");
extensions_ = 0;
partialDispatch_ = false;
supportRA_ = true;
customHostAllocator_ = false;
waitCommand_ = AMD_OCL_WAIT_COMMAND;
@@ -581,6 +580,13 @@ Settings::Settings() : value_(0) {
enableHwDebug_ = false;
commandQueues_ = 200; //!< Field value set to maximum number
//!< concurrent Virtual GPUs for default
overrideLclSet = (!flagIsDefault(GPU_MAX_WORKGROUP_SIZE)) ? 1 : 0;
overrideLclSet |= (!flagIsDefault(GPU_MAX_WORKGROUP_SIZE_2D_X) ||
!flagIsDefault(GPU_MAX_WORKGROUP_SIZE_2D_Y)) ? 2 : 0;
overrideLclSet |= (!flagIsDefault(GPU_MAX_WORKGROUP_SIZE_3D_X) ||
!flagIsDefault(GPU_MAX_WORKGROUP_SIZE_3D_Y) ||
!flagIsDefault(GPU_MAX_WORKGROUP_SIZE_3D_Z)) ? 4 : 0;
}
void Memory::saveMapInfo(const void* mapAddress, const amd::Coord3D origin,