[HIP] [FIX] Memcpy Async functions on nvcc path.

+ in hipMemcpyDtoDAsync: cuMemcpyDtoD -> cuMemcpyDtoDAsync
+ in hipMemcpyDtoHAsync: cuMemcpyDtoH -> cuMemcpyDtoHAsync

P.S.
"The types CUstream and cudaStream_t are identical and may be used interchangeably", thus explicit c-like type cast is not needed, aka CUstream(stream).


[ROCm/hip commit: 6421a1e79e]

projects/hip/include/hip/nvcc_detail/hip_runtime_api.h

@@ -306,13 +306,13 @@ inline static hipError_t hipMemcpyHtoDAsync(hipDeviceptr_t dst,
 inline static hipError_t hipMemcpyDtoHAsync(void* dst,
                   hipDeviceptr_t src, size_t size, hipStream_t stream)
 {
-    return hipCUResultTohipError(cuMemcpyDtoH(dst, src, size));
+    return hipCUResultTohipError(cuMemcpyDtoHAsync(dst, src, size, stream));
 }
 
 inline static hipError_t hipMemcpyDtoDAsync(hipDeviceptr_t dst,
             hipDeviceptr_t src, size_t size, hipStream_t stream)
 {
-    return hipCUResultTohipError(cuMemcpyDtoD(dst, src, size));
+    return hipCUResultTohipError(cuMemcpyDtoDAsync(dst, src, size, stream));
 }
 
 inline static hipError_t hipMemcpy(void* dst, const void* src, size_t sizeBytes, hipMemcpyKind copyKind) {