OpenCL + OpenSHMEM Hybrid Programming Model for the Adapteva Epiphany Architecture

TL;DR

This paper introduces a hybrid OpenCL and OpenSHMEM programming model tailored for the Adapteva Epiphany architecture, enhancing device-level programming by addressing OpenCL's limitations in memory and inter-core communication.

Contribution

It presents a novel hybrid programming approach combining OpenCL and OpenSHMEM for Epiphany, improving performance and addressing OpenCL's architectural incompatibilities.

Findings

Hybrid model improves matrix multiplication performance

Addresses OpenCL's memory and communication limitations

Demonstrates scalability on Epiphany architecture

Abstract

There is interest in exploring hybrid OpenSHMEM + X programming models to extend the applicability of the OpenSHMEM interface to more hardware architectures. We present a hybrid OpenCL + OpenSHMEM programming model for device-level programming for architectures like the Adapteva Epiphany many-core RISC array processor. The Epiphany architecture comprises a 2D array of low-power RISC cores with minimal uncore functionality connected by a 2D mesh Network-on-Chip (NoC). The Epiphany architecture offers high computational energy efficiency for integer and floating point calculations as well as parallel scalability. The Epiphany-III is available as a coprocessor in platforms that also utilize an ARM CPU host. OpenCL provides good functionality for supporting a co-design programming model in which the host CPU offloads parallel work to a coprocessor. However, the OpenCL memory model is inconsistent with the Epiphany memory architecture and lacks support for inter-core communication. We propose a hybrid programming model in which OpenSHMEM provides a better solution by replacing the non-standard OpenCL extensions introduced to achieve high performance with the Epiphany architecture. We demonstrate the proposed programming model for matrix-matrix multiplication based on Cannon's algorithm showing that the hybrid model addresses the deficiencies of using OpenCL alone to achieve good benchmark performance.