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/rocm/rocsettings.cpp
-7
View File
@@ -17,7 +17,6 @@ Settings::Settings() {
// Set this to true when we drop the flag
doublePrecision_ = ::CL_KHR_FP64;
pollCompletion_ = ENVVAR_HSA_POLL_KERNEL_COMPLETION;
enableLocalMemory_ = HSA_LOCAL_MEMORY_ENABLE;
enableCoarseGrainSVM_ = HSA_ENABLE_COARSE_GRAIN_SVM;
@@ -32,7 +31,6 @@ Settings::Settings() {
maxWorkGroupSize3DZ_ = 4;
kernargPoolSize_ = HSA_KERNARG_POOL_SIZE;
signalPoolSize_ = HSA_SIGNAL_POOL_SIZE;
// Determine if user is requesting Non-Coherent mode
// for system memory. By default system memory is
@@ -43,7 +41,6 @@ Settings::Settings() {
nonCoherentMode = getenv("OPENCL_USE_NC_MEMORY_POLICY");
enableNCMode_ = (nonCoherentMode) ? true : false;
partialDispatch_ = GPU_PARTIAL_DISPATCH;
commandQueues_ = 100; //!< Field value set to maximum number
//!< concurrent Virtual GPUs for ROCm backend
@@ -158,10 +155,6 @@ void Settings::override() {
commandQueues_ = GPU_MAX_COMMAND_QUEUES;
}
if (!flagIsDefault(GPU_IMAGE_DMA)) {
commandQueues_ = GPU_IMAGE_DMA;
}
if (!flagIsDefault(GPU_XFER_BUFFER_SIZE)) {
xferBufSize_ = GPU_XFER_BUFFER_SIZE * Ki;
}