P4 to Git Change 1101352 by gandryey@gera-dev-w7 on 2014/11/28 18:03:18

ECR #304775 - Make optimization for read map of USWC memory
	- If runtime detects USWC map with read operation, then it will switch to indirect map. This should improve map-read  performance on APU(s)  when USWC memory is used instead of frame buffer

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_memobj.cpp#72 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_svm.cpp#8 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/cpu/cpudevice.cpp#269 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/cpu/cpudevice.hpp#89 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#172 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#234 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#486 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.hpp#134 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpumemory.cpp#112 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpumemory.hpp#43 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuvirtual.cpp#340 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa/hsadevice.cpp#88 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa/hsadevice.hpp#45 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa/hsamemory.cpp#42 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa/hsamemory.hpp#27 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa/hsavirtual.cpp#98 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsadevice.cpp#21 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsadevice.hpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsamemory.cpp#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsamemory.hpp#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsavirtual.cpp#26 edit


[ROCm/clr commit: 6d464be252]

projects/clr/rocclr/runtime/device/cpu/cpudevice.cpp

@@ -1123,6 +1123,7 @@ Device::allocMapTarget(
     amd::Memory&        mem,
     const amd::Coord3D& origin,
     const amd::Coord3D& region,
+    uint                mapFlags,
     size_t*             rowPitch,
     size_t*             slicePitch)
 {

projects/clr/rocclr/runtime/device/cpu/cpudevice.hpp

@@ -143,6 +143,7 @@ public:
         amd::Memory&    mem,        //!< Abstraction layer memory object
         const amd::Coord3D& origin, //!< The map location in memory
         const amd::Coord3D& region, //!< The map region in memory
+        uint    mapFlags,           //!< Map flags
         size_t* rowPitch = NULL,    //!< Row pitch for the mapped memory
         size_t* slicePitch = NULL   //!< Slice for the mapped memory
         );