HaoCL: Harnessing Large-scale Heterogeneous Processors Made Easy

TL;DR

HaoCL is a programming framework that simplifies deploying large-scale heterogeneous clusters for deep learning and graph processing, enabling near-linear speedups with minimal overhead.

Contribution

HaoCL extends OpenCL semantics to distributed heterogeneous clusters, allowing direct application deployment without code modifications or hardware topology awareness.

Findings

Near-linear speedups on benchmarks

Negligible overhead in distributed environments

Supports existing applications without modifications

Abstract

The pervasive adoption of Deep Learning (DL) and Graph Processing (GP) makes it a de facto requirement to build large-scale clusters of heterogeneous accelerators including GPUs and FPGAs. The OpenCL programming framework can be used on the individual nodes of such clusters but is not intended for deployment in a distributed manner. Fortunately, the original OpenCL semantics naturally fit into the programming environment of heterogeneous clusters. In this paper, we propose a heterogeneity-aware OpenCL-like (HaoCL) programming framework to facilitate the programming of a wide range of scientific applications including DL and GP workloads on large-scale heterogeneous clusters. With HaoCL, existing applications can be directly deployed on heterogeneous clusters without any modifications to the original OpenCL source code and without awareness of the underlying hardware topologies and configurations. Our experiments show that HaoCL imposes a negligible overhead in a distributed environment, and provides near-linear speedups on standard benchmarks when computation or data size exceeds the capacity of a single node. The system design and the evaluations are presented in this demo paper.