为混合神经网络设计专用指令，让RISC-V GPU提速56倍
Accelerating HDC-CNN Hybrid Models Using Custom Instructions on RISC-V GPUs
- 在RISC-V GPU上添加4类专用指令加速超维计算
- 微基准测试显示最高性能提升56.2倍，能效显著改善
- 适合研究低功耗、可编程硬件加速器的开发者
基于神经网络的机器学习发展迅速，但训练与推理所需的高能耗仍是主要挑战。超维计算（HDC）提供了一种轻量级、类脑替代方案，具备高并行性，但在复杂视觉任务上准确率常偏低。为此，学者提出结合HDC与卷积神经网络（CNN）的混合加速器，但其应用受限于泛化性和可编程性差。开源RISC-V架构的兴起为领域专用GPU设计带来新机遇。与传统专有GPU不同，新兴的RISC-V GPU提供灵活可编程平台，适用于HDC等定制计算模型。本研究设计并实现了针对HDC操作优化的自定义GPU指令，支持混合HDC-CNN工作负载的高效处理。使用四类自定义HDC指令的实验表明，微基准测试中性能最高提升56.2倍，验证了RISC-V GPU在节能、高性能计算方面的潜力。
原文摘要 · Abstract (English)
Machine learning based on neural networks has advanced rapidly, but the high energy consumption required for training and inference remains a major challenge. Hyperdimensional Computing (HDC) offers a lightweight, brain-inspired alternative that enables high parallelism but often suffers from lower accuracy on complex visual tasks. To overcome this, hybrid accelerators combining HDC and Convolutional Neural Networks (CNNs) have been proposed, though their adoption is limited by poor generalizability and programmability. The rise of open-source RISC-V architectures has created new opportunities for domain-specific GPU design. Unlike traditional proprietary GPUs, emerging RISC-V-based GPUs provide flexible, programmable platforms suitable for custom computation models such as HDC. In this study, we design and implement custom GPU instructions optimized for HDC operations, enabling efficient processing for hybrid HDC-CNN workloads. Experimental results using four types of custom HDC instructions show a performance improvement of up to 56.2 times in microbenchmark tests, demonstrating the potential of RISC-V GPUs for energy-efficient, high-performance computing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。