Toward Heterogeneous, Distributed, and Energy-Efficient Computing with SYCL

TL;DR

This paper discusses extending the SYCL programming model to improve heterogeneous, distributed, and energy-efficient high-performance computing, focusing on task distribution and energy optimization techniques.

Contribution

It introduces new SYCL extensions for workload distribution across clusters and energy-efficient computing, enhancing high-level programming for heterogeneous systems.

Findings

Extended SYCL semantics for advanced features

Proposed task distribution techniques for clusters

Energy optimization strategies for heterogeneous systems

Abstract

Programming modern high-performance computing systems is challenging due to the need to efficiently program GPUs and accelerators and to handle data movement between nodes. The C++ language has been continuously enhanced in recent years with features that greatly increase productivity. In particular, the C++-based SYCL standard provides a powerful programming model for heterogeneous systems that can target a wide range of devices, including multicore CPUs, GPUs, FPGAs, and accelerators, while providing high-level abstractions. This presentation introduces our research efforts to design a SYCL-based high-level programming interface that provides advanced techniques such as task distribution and energy optimization. The key insight is that SYCL semantics can be easily extended to provide advanced features for easy integration into existing SYCL programs. In particular, we will highlight two SYCL extensions that are designed to deal with workload distribution on accelerator clusters (Celerity) and with energy-efficient computing (SYnergy).