P4 to Git Change 1809277 by gandryey@gera-win10 on 2019/06/11 17:34:13

SWDEV-180872 - Runtime support changes for Cooperative Group Features
	- Initial implementation of the core functionality. Disabled by default. Use GPU_ENABLE_COOP_GROUPS=1 to enable the feature.
	- Runtime uses device queue for cooperative executions with a synchronization on the launched queue.
	- The current implementation is pure runtime change and it can work if only one app uses this feature. No ROCr/KFD support was added or tested
	- Only inline assembler was tested

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_device.cpp#20 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_device_runtime.cpp#15 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.def.in#15 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.map.in#17 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_module.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_platform.cpp#32 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#338 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#606 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.hpp#171 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palblit.cpp#31 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palblit.hpp#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#142 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.hpp#39 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palschedcl.cpp#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#135 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#61 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.cpp#32 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.hpp#12 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#127 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#37 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocschedcl.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#75 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.hpp#23 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#94 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#92 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#311 edit

rocclr/runtime/platform/command.cpp

@@ -226,8 +226,13 @@ void Command::enqueue() {
 const Context& Command::context() const { return queue_->context(); }
 
 NDRangeKernelCommand::NDRangeKernelCommand(HostQueue& queue, const EventWaitList& eventWaitList,
-                                           Kernel& kernel, const NDRangeContainer& sizes, uint32_t sharedMemBytes)
-    : Command(queue, CL_COMMAND_NDRANGE_KERNEL, eventWaitList), kernel_(kernel), sizes_(sizes), sharedMemBytes_(sharedMemBytes) {
+                                           Kernel& kernel, const NDRangeContainer& sizes,
+                                           uint32_t sharedMemBytes, uint32_t extraParam)
+    : Command(queue, CL_COMMAND_NDRANGE_KERNEL, eventWaitList)
+    , kernel_(kernel)
+    , sizes_(sizes)
+    , sharedMemBytes_(sharedMemBytes)
+    , extraParam_(extraParam) {
   auto& device = queue.device();
   auto devKernel = const_cast<device::Kernel*>(kernel.getDeviceKernel(device));
   profilingInfo_.setCallback(devKernel->getProfilingCallback(
@@ -393,7 +398,7 @@ bool MigrateMemObjectsCommand::validateMemory() {
 cl_int NDRangeKernelCommand::captureAndValidate() {
   const amd::Device& device = queue()->device();
   // Validate the kernel before submission
-  if (!queue()->device().validateKernel(kernel(), queue()->vdev())) {
+  if (!queue()->device().validateKernel(kernel(), queue()->vdev(), cooperativeGroups())) {
     return CL_OUT_OF_RESOURCES;
   }