Add extension for kernel concurrency on same stream

include/hip/hip_hcc.h

@@ -89,13 +89,23 @@ hipError_t hipHccGetAcceleratorView(hipStream_t stream, hc::accelerator_view** a
 
  * HIP/ROCm actually updates the start event when the associated kernel completes.
  */
+hipError_t hipExtModuleLaunchKernel(hipFunction_t f, uint32_t globalWorkSizeX,
+                                    uint32_t globalWorkSizeY, uint32_t globalWorkSizeZ,
+                                    uint32_t localWorkSizeX, uint32_t localWorkSizeY,
+                                    uint32_t localWorkSizeZ, size_t sharedMemBytes,
+                                    hipStream_t hStream, void** kernelParams, void** extra,
+                                    hipEvent_t startEvent = nullptr,
+                                    hipEvent_t stopEvent = nullptr,
+                                    uint32_t flags = 0);
+
 hipError_t hipHccModuleLaunchKernel(hipFunction_t f, uint32_t globalWorkSizeX,
                                     uint32_t globalWorkSizeY, uint32_t globalWorkSizeZ,
                                     uint32_t localWorkSizeX, uint32_t localWorkSizeY,
                                     uint32_t localWorkSizeZ, size_t sharedMemBytes,
                                     hipStream_t hStream, void** kernelParams, void** extra,
                                     hipEvent_t startEvent = nullptr,
-                                    hipEvent_t stopEvent = nullptr);
+                                    hipEvent_t stopEvent = nullptr)
+                                    __attribute__((deprecated("use hipExtModuleLaunchKernel instead")));;
 
 // doxygen end HCC-specific features
 /**