P4 to Git Change 1507569 by gandryey@gera-w8 on 2018/01/24 17:56:10

SWDEV-142271 - Performance drop is observed in Ocean Surface Simulation of Compubenchcl in 17.50 when compared to 17.Q4.1
	- Rewrite the adaptive mode for waveliimiter. Make sure the performance feedback corresponds to the right wave count. Add the new sampling logic to find the best number, based on average performance.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#295 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuwavelimiter.cpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuwavelimiter.hpp#10 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.hpp#15 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#71 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#39 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palwavelimiter.cpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palwavelimiter.hpp#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#80 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#88 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#282 edit

rocclr/runtime/platform/command.cpp

@@ -61,7 +61,8 @@ uint64_t Event::recordProfilingInfo(cl_int status, uint64_t timeStamp) {
     default:
       profilingInfo_.end_ = timeStamp;
       if (profilingInfo_.callback_ != NULL) {
-        profilingInfo_.callback_->callback(timeStamp - profilingInfo_.start_);
+        profilingInfo_.callback_->callback(timeStamp - profilingInfo_.start_,
+            profilingInfo_.waves_);
       }
       break;
   }
@@ -227,7 +228,8 @@ NDRangeKernelCommand::NDRangeKernelCommand(HostQueue& queue, const EventWaitList
   parameters_ = kernel.parameters().capture(queue.device());
   auto& device = queue.device();
   auto devKernel = const_cast<device::Kernel*>(kernel.getDeviceKernel(device));
-  profilingInfo_.setCallback(devKernel->getProfilingCallback(queue.vdev()));
+  profilingInfo_.setCallback(devKernel->getProfilingCallback(
+    queue.vdev()), devKernel->getWavesPerSH(queue.vdev()));
   fixme_guarantee(parameters_ != NULL && "out of memory");
   kernel_.retain();
 }