Publication Type
ORNL Report
Publication Date
Abstract
We describe the experience of converting a CUDA implementation of a parallel graph coloring algorithm to SYCL. The goals are for our work to be useful to application and compiler developers by providing a detailed description of a migration path between CUDA and SYCL. We will describe how CUDA functions are mapped to SYCL functions. Evaluating the CUDA and SYCL implementations show that the performance of SYCL and CUDA kernels are comparable over the test graph set on NVIDIA P100 and V100 GPUs. The SYCL program also allows for performance evaluation using the OpenCL and Level Zero interfaces and power profiling on an Intel computing platform
