eGPU: A 750 MHz Class Soft GPGPU for FPGA

TL;DR

The paper presents eGPU, a high-performance soft GPGPU architecture for FPGAs, achieving 750 MHz and supporting complex computations with efficient resource utilization.

Contribution

It introduces a novel GPGPU design tailored for FPGA embedded features, enabling high-frequency operation and complex system implementation from software.

Findings

Achieves over 770 MHz in FPGA implementation.

Supports 512 threads with 16 scalar processors per SM.

Tightly packed multiple eGPUs with minimal speed penalty.

Abstract

This paper introduces the eGPU, a SIMT soft processor designed for FPGAs. Soft processors typically achieve modest operating frequencies, a fraction of the headline performance claimed by modern FPGA families, and obtain correspondingly modest performance results. We propose a GPGPU architecture structured specifically to take advantage of both the soft logic and embedded features of the FPGA. We also consider the physical location of the embedded memories and DSP Blocks relative to the location and number of soft logic elements in order to have a design with balanced resources. Our goal is to create a high performance soft processor able to implement complex portions of FPGA system designs, such as the linear solvers commonly used in wireless systems, through push-button compilation from software. The eGPU architecture is a streaming multiprocessor (SM) machine with 512 threads. Each SM contains 16 scalar processors (SP). Both IEEE754 FP32 and INT32 integer arithmetic are supported. We demonstrate a single SM eGPU in an Intel Agilex device, requiring 5600 ALMs and 24 DSP Blocks, which closes timing at over 770 MHz from a completely unconstrained compile. Multiple eGPUs can also be tightly packed together into a single Agilex FPGA logic region, with minimal speed penalty.