oneAPI CUDA to SYCL code migration and optimization practice
In this session, we’ll show you two hands-on demonstrations implementing oneAPI.
1. Learn about Intel® oneAPI SYCLomatic, a tool that converts CUDA code to SYCL, and practice converting CUDA code (mini-nbody) to SYCL using SYCLomatic. Let’s look at performance by running on CPU (SPR) and GPU (PVC) in Intel® Developer Cloud.
2. Analyze the performance of the Fortran program that performs matrix calculations using the Intel® oneAPI Vtune profiler, and apply Intel® oneAPI’s oneMKL library to the bottleneck section based on the performance analysis results to improve performance.
Intel® oneAPI provides not only compilers but also a variety of tools and libraries for developers.
Speaker(s)
Mr. Taehun Kim - Software Technical Consulting Engineer, Intel®
Taehun Kim is a software technical consulting engineer at Intel Korea having joined in 2022. He has worked at Cray, KIAPS and Samsung SDS, and has more than 20 years of experience in improving the SW performance of HPC. He holds a Ph.D in Environmental Atmospheric Science from Pukyong National University and a Master’s in Marine science from Pusan National University, S.Korea.
