high performance computing on graphics processing units: hgpu.org

High performance computing is a topic that has risen to the top in the era of digitalization, AI and automation. Therefore, the search for more cost and time effective ways to implement HPC work is always a subject extensively researched. One part of this is to have hardware that is capable to improve on these criteria. Different hardware usually have different code languages to implement these works though, cross-platform solution like Intel’s oneAPI framework is starting to gaining popularity. In this thesis, the capabilities of Intel’s oneAPI framework to implement and execute HPC benchmarks on different hardware platforms will be discussed. Using the hardware available through Intel’s DevCloud services, Intel’s Xeon Gold 6128, Intel’s UHD Graphics P630 and the Arria10 FPGA board were all chosen to use for implementation. The benchmarks that were chosen to be used were GEMM (General Matrix Multiplication) and BUDE (Bristol University Docking Engine). They were implemented using DPC++ (Data Parallel C++), Intel’s own SYCL-based C++ extension. The benchmarks were also tried to be improved upon with HPC speed-up methods like loop unrolling and some hardware manipulation. The performance for CPU and GPU were recorded and compared, as the FPGA implementation could not be preformed because of technical difficulties. The results are good comparison to related work, but did not improve much upon them. This because the hardware used is quite weak compared to industry standard. Though further research on the topic would be interesting, to compare a working FPGA implementation to the other results and results from other studies. This implementation also probably has the biggest improvement potential, so to see how good one could make it would be interesting. Also, testing some other more complex benchmarks could be interesting.