e-GPU: An Open-Source and Configurable RISC-V Graphic Processing Unit for TinyAI Applications

TL;DR

This paper introduces e-GPU, an open-source, configurable RISC-V GPU platform optimized for TinyAI edge devices, demonstrating significant performance and energy efficiency improvements through integration with a lightweight programming framework and real-world benchmarks.

Contribution

The work presents a novel open-source RISC-V GPU architecture tailored for TinyAI, including a lightweight programming framework and integration with an energy-efficient platform, optimized for ultra-low-power edge applications.

Findings

e-GPU achieves up to 15.1x speed-up on TinyBio workloads.

Energy consumption is reduced by up to 3.1x with high-range configuration.

The system operates within a 28 mW power budget.

Abstract

Graphics processing units (GPUs) excel at parallel processing, but remain largely unexplored in ultra-low-power edge devices (TinyAI) due to their power and area limitations, as well as the lack of suitable programming frameworks. To address these challenges, this work introduces embedded GPU (e-GPU), an open-source and configurable RISC-V GPU platform designed for TinyAI devices. Its extensive configurability enables area and power optimization, while a dedicated Tiny-OpenCL implementation provides a lightweight programming framework tailored to resource-constrained environments. To demonstrate its adaptability in real-world scenarios, we integrate the e-GPU with the eXtendible Heterogeneous Energy-Efficient Platform (X-HEEP) to realize an accelerated processing unit (APU) for TinyAI applications. Multiple instances of the proposed system, featuring varying e-GPU configurations, are implemented in TSMC's 16 nm SVT CMOS technology and are operated at 300 MHz and 0.8 V. Their area and leakage characteristics are analyzed to ensure alignment with TinyAI constraints. To assess both runtime overheads and computational efficiency, we employ two benchmarks: General Matrix Multiply (GeMM) and bio-signal processing (TinyBio) workloads. The GeMM benchmark is used to quantify the scheduling overhead introduced by the Tiny-OpenCL framework. The results show that the delay becomes negligible for matrix sizes larger than 256x256 (or equivalent problem sizes). The TinyBio benchmark is then used to evaluate performance and energy improvements over the baseline host under pure processing conditions. The results indicate that the high-range e-GPU configuration with 16 threads achieves up to a 15.1x speed-up and reduces energy consumption by up to 3.1x, while incurring only a 2.5x area overhead and operating within a 28 mW power budget.