This feature was deprecated in the official pre-releases of Intel oneAPI Toolkit, but it might become useful while evaluating the performance of the C++17 OpenCL/SYCL-code delivered by running it on the various of acceleration targets with different hardware architecture.
In this blog, I will discuss how to use the Intel-LLVM/Clang compiler staging distribution ( ) to build and run the OpenCL/SYCL code on the Nvidia GPUs acceleration targets. In my previous blog ( ) I have thoroughly discussed how to build OpenMP 4.5 parallel code the Intel-LLVM/Clang compiler, supporting the Nvidia GPGPUs CUDA-NVPTX64 capabilities.
0 kommentar(er)
