On The Design of a Light-weight FPGA Programming Framework for Graph Applications

TL;DR

This paper introduces JGraph, a lightweight FPGA programming system with a DSL and HLS translator for graph applications, enabling easier development with acceptable performance trade-offs.

Contribution

It presents the first FPGA-based graph programming system combining a DSL and a translator, reducing development complexity while maintaining high performance.

Findings

Achieves up to 300 MTEPS BFS traversal performance.

Enables rapid code generation within tens of seconds.

Simplifies FPGA graph programming with acceptable efficiency.

Abstract

FPGA accelerators designed for graph processing are gaining popularity. Domain Specific Language (DSL) frameworks for graph processing can reduce the programming complexity and development cost of algorithm design. However, accelerator-specific development requires certain technical expertise and significant effort to devise, implement, and validate the system. For most algorithm designers, the expensive cost for hardware programming experience makes FPGA accelerators either unavailable or uneconomic. Although general-purpose High-Level Synthesis (HLS) tools help to map high-level language to Hardware Description Languages (HDLs), the generated code is often inefficient and lengthy compared with the highly-optimized graph accelerators. One cannot make full use of an FPGA accelerator's capacity with low development cost. To easily program graph algorithms while keeping performance degradation acceptable, we propose a graph programming system named JGraph, which contains two main parts: 1) a DSL for graph atomic operations with a graph library for high-level abstractions including user-defined functions with parameters, 2) a light-weight HLS translator to generate high-performance HDL code, cooperating with a communication manager and a runtime scheduler. To the best of our knowledge, our work is the first graph programming system with DSL and translator on the FPGA platform. Our system can generate up to 300 MTEPS BFS traversal within tens of seconds.