A walkthrough of converting a code from parallel C++ ray-tracing code to CUDA, and the work needed to make that CUDA code run on CPU using parallel for_each() and then converted the code to SYCL 2020.

In this article, we will port Raytracing in One Weekend, the already converted parallel code to CUDA, make CUDA run on CPU and then port again to SYCL 2020 via Intel® Data-Parallel C++ (DPC++) toolkit. DPC++ is ISO C++ plus Khronos SYCL with community extensions eventually making their way into the final standard. As time of article writing, the SYCL 2020 specification has been released for public review as a provisional specification for developers to provide their valuable feedback before the final version is published and ratified.