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

P4 to Git Change 1505728 by wchau@wchau_OCL_boltzmann on 2018/01/19 13:13:53

Browse Source 
SWDEV-137270 - Add findLocalWorkSize to OpenCL runtime ROC device
	- Add support for kernel using image argument
	- fix the issue of not using the max workgroup size specified by the environment variables "maxWorkGroupSize*"

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#33 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.hpp#19 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.cpp#31 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#50 edit
This commit is contained in:
foreman
2018-01-19 13:33:55 -05:00
parent edb9746999
commit 87ad3f9692
4 changed files with 110 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files
rocclr/runtime/device/rocm/rocsettings.cpp
+17
View File
@@ -142,6 +142,23 @@ void Settings::override() {
preferredWorkGroupSize_ = GPU_MAX_WORKGROUP_SIZE;
}
if (GPU_MAX_WORKGROUP_SIZE_2D_X != 0) {
maxWorkGroupSize2DX_ = GPU_MAX_WORKGROUP_SIZE_2D_X;
}
if (GPU_MAX_WORKGROUP_SIZE_2D_Y != 0) {
maxWorkGroupSize2DY_ = GPU_MAX_WORKGROUP_SIZE_2D_Y;
}
if (GPU_MAX_WORKGROUP_SIZE_3D_X != 0) {
maxWorkGroupSize3DX_ = GPU_MAX_WORKGROUP_SIZE_3D_X;
}
if (GPU_MAX_WORKGROUP_SIZE_3D_Y != 0) {
maxWorkGroupSize3DY_ = GPU_MAX_WORKGROUP_SIZE_3D_Y;
}
if (GPU_MAX_WORKGROUP_SIZE_3D_Z != 0) {
maxWorkGroupSize3DZ_ = GPU_MAX_WORKGROUP_SIZE_3D_Z;
}
if (!flagIsDefault(GPU_MAX_COMMAND_QUEUES)) {
commandQueues_ = GPU_MAX_COMMAND_QUEUES;
}