Migrating CUDA to oneAPI: A Smith-Waterman Case Study

TL;DR

This paper demonstrates the migration of a CUDA-based bioinformatics sequence alignment tool to oneAPI's DPC++ using dpct, showing successful portability and comparable or improved performance across different GPU architectures.

Contribution

It provides a case study on porting CUDA code to oneAPI DPC++ for bioinformatics, highlighting the effectiveness of dpct and performance benefits.

Findings

dpct effectively facilitates CUDA to DPC++ migration

Migrated code maintains cross-architecture portability

Performance is comparable or slightly better (+5%) than CUDA version

Abstract

To face the programming challenges related to heterogeneous computing, Intel recently introduced oneAPI, a new programming environment that allows code developed in Data Parallel C++ (DPC++) language to be run on different devices such as CPUs, GPUs, FPGAs, among others. To tackle CUDA-based legacy codes, oneAPI provides a compatibility tool (dpct) that facilitates the migration to DPC++. Due to the large amount of existing CUDA-based software in the bioinformatics context, this paper presents our experiences porting SW#db, a well-known sequence alignment tool, to DPC++ using dpct. From the experimental work, it was possible to prove the usefulness of dpct for SW#db code migration and the cross-GPU vendor, cross-architecture portability of the migrated DPC++ code. In addition, the performance results showed that the migrated DPC++ code reports similar efficiency rates to its CUDA-native counterpart or even better in some tests (approximately +5%).