P4 to Git Change 1147021 by yaxunl@yaxunl_stg_win50 on 2015/05/04 16:06:06

ECR #304775 - Wave limiter: Fix bug in adaptation.

	Dumped waves/simd value is incorrect.
	Should exit adptation only after the changed waves/simd value is applied.
	Added wave limiter manager to handle situation that one kernel is enqueued to more than one queues. Create wave limiter for each virtual device.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#245 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#283 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.hpp#109 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#360 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuwavelimiter.cpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuwavelimiter.hpp#3 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#70 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#76 edit

rocclr/runtime/platform/command.cpp

@@ -266,8 +266,8 @@ NDRangeKernelCommand::NDRangeKernelCommand(
 {
     parameters_ = kernel.parameters().capture(queue.device());
     auto& device = queue.device();
-    auto devKernel = kernel.getDeviceKernel(device);
-    profilingInfo_.setCallback(devKernel->getProfilingCallback());
+    auto devKernel = const_cast<device::Kernel*>(kernel.getDeviceKernel(device));
+    profilingInfo_.setCallback(devKernel->getProfilingCallback(queue.vdev()));
     fixme_guarantee(parameters_ != NULL && "out of memory");
     kernel_.retain();
 }