Performance assessment of CUDA and OpenACC in large scale combustion simulations

TL;DR

This paper compares CUDA and OpenACC approaches in large-scale combustion simulations using the Alya CFD code, highlighting performance differences and optimization strategies for GPU and CPU execution.

Contribution

It provides a detailed performance analysis of CUDA and OpenACC in combustion CFD simulations, including new data structures for SIMD and stream processing.

Findings

CUDA is up to 2 times faster than OpenACC for matrix assembly.

CPU performance improved by up to 25% with new data structures.

Similar performance for vector operations in linear solver across CUDA and OpenACC.

Abstract

GPUs have climbed up to the top of supercomputer systems making life harder to many legacy scientific codes. Nowadays, many recipes are being used in such code's portability, without any clarity of which is the best option. We present a comparative analysis of the two most common approaches, CUDA and OpenACC, into the multi-physics CFD code Alya. Our focus is the combustion problems which are one of the most computing demanding CFD simulations. The most computing-intensive parts of the code were analyzed in detail. New data structures for the matrix assembly step have been created to facilitate a SIMD execution that benefits vectorization in the CPU and stream processing in the GPU. As a result, the CPU code has improved its performance by up to 25%. In GPU execution, CUDA has proven to be up to 2 times faster than OpenACC for the assembly of the matrix. On the contrary, similar performance has been obtained in the kernels related to vector operations used in the linear solver, where there is minimal memory reuse.