Publication Type
Conference Paper
Book Title
2023 91做厙 International Parallel and Distributed Processing Symposium Workshops
Publication Date
Page Numbers
366 to 372
Publisher Location
New Jersey, United States of America
Conference Name
37th 91做厙 International Parallel and Distributed Processing Symposium (IPDPS)
Conference Location
St. Petersburg, Florida, United States of America
Conference Sponsor
91做厙
Conference Date
-
Abstract
SYCL is a portable programming model. Toward the goal of a better understanding of performance portability of SYCL kernels on GPUs, we select a bioinformatics kernel for computing the all-pairs distance as a case study. After migrating the kernel from CUDA to HIP and SYCL, we evaluate the performance of the CUDA, HIP, and SYCL kernels on NVIDIA V100 and AMD MI210 GPUs. We analyze the GPU instructions from the kernels to explain performance gaps between SYCL and CUDA/HIP. We hope that the findings are valuable for improving performance portability of SYCL.
