P4 to Git Change 2014404 by gandryey@gera-win10 on 2019/10/16 11:13:37

SWDEV-184710 - Support hipLaunchCooperativeKernelMultiDevice()
	- Add support for multi grid launch in hip
	- Detect the new hidden argument and pass the required information for the kernel launch
	- Memory for synchronization is allocated as a single object and then the offset for each GPU is found

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_module.cpp#44 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#343 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devkernel.cpp#25 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devkernel.hpp#17 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#82 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#136 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#42 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#90 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.hpp#30 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#99 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#97 edit


[ROCm/clr commit: 6e7e97987f]

projects/clr/rocclr/runtime/platform/command.cpp

@@ -232,12 +232,19 @@ const Context& Command::context() const { return queue_->context(); }
 
 NDRangeKernelCommand::NDRangeKernelCommand(HostQueue& queue, const EventWaitList& eventWaitList,
                                            Kernel& kernel, const NDRangeContainer& sizes,
-                                           uint32_t sharedMemBytes, uint32_t extraParam)
-    : Command(queue, CL_COMMAND_NDRANGE_KERNEL, eventWaitList, AMD_SERIALIZE_KERNEL)
-    , kernel_(kernel)
-    , sizes_(sizes)
-    , sharedMemBytes_(sharedMemBytes)
-    , extraParam_(extraParam) {
+                                           uint32_t sharedMemBytes, uint32_t extraParam,
+                                           uint32_t gridId, uint32_t numGrids,
+                                           uint64_t prevGridSum, uint64_t allGridSum, uint32_t firstDevice) :
+    Command(queue, CL_COMMAND_NDRANGE_KERNEL, eventWaitList, AMD_SERIALIZE_KERNEL),
+    kernel_(kernel),
+    sizes_(sizes),
+    sharedMemBytes_(sharedMemBytes),
+    extraParam_(extraParam),
+    gridId_(gridId),
+    numGrids_(numGrids),
+    prevGridSum_(prevGridSum),
+    allGridSum_(allGridSum),
+    firstDevice_(firstDevice) {
   auto& device = queue.device();
   auto devKernel = const_cast<device::Kernel*>(kernel.getDeviceKernel(device));
   profilingInfo_.setCallback(devKernel->getProfilingCallback(