Efficient Hardware Accelerator Based on Medium Granularity Dataflow for SpTRSV

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Qian, Yang, Xiaofeng, Lu, Shengli
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912280889786368
author Chen, Qian
Yang, Xiaofeng
Lu, Shengli
author_facet Chen, Qian
Yang, Xiaofeng
Lu, Shengli
contents Sparse triangular solve (SpTRSV) is widely used in various domains. Numerous studies have been conducted using CPUs, GPUs, and specific hardware accelerators, where dataflows can be categorized into coarse and fine granularity. Coarse dataflows offer good spatial locality but suffer from low parallelism, while fine dataflows provide high parallelism but disrupt the spatial structure, leading to increased nodes and poor data reuse. This paper proposes a novel hardware accelerator for SpTRSV or SpTRSV-like DAGs. The accelerator implements a medium granularity dataflow through hardware-software codesign and achieves both excellent spatial locality and high parallelism. Additionally, a partial sum caching mechanism is introduced to reduce the blocking frequency of processing elements (PEs), and a reordering algorithm of intra-node edges computation is developed to enhance data reuse. Experimental results on 245 benchmarks with node counts reaching up to 85,392 demonstrate that this work achieves average performance improvements of 7.0$\times$ (up to 27.8$\times$) over CPUs and 5.8$\times$ (up to 98.8$\times$) over GPUs. Compared to the state-of-the-art technique (DPU-v2), this work shows a 2.5$\times$ (up to 5.9$\times$) average performance improvement and 1.7$\times$ (up to 4.1$\times$) average energy efficiency enhancement.
format Preprint
id arxiv_https___arxiv_org_abs_2406_10511
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Hardware Accelerator Based on Medium Granularity Dataflow for SpTRSV
Chen, Qian
Yang, Xiaofeng
Lu, Shengli
Distributed, Parallel, and Cluster Computing
Hardware Architecture
Numerical Analysis
Performance
Sparse triangular solve (SpTRSV) is widely used in various domains. Numerous studies have been conducted using CPUs, GPUs, and specific hardware accelerators, where dataflows can be categorized into coarse and fine granularity. Coarse dataflows offer good spatial locality but suffer from low parallelism, while fine dataflows provide high parallelism but disrupt the spatial structure, leading to increased nodes and poor data reuse. This paper proposes a novel hardware accelerator for SpTRSV or SpTRSV-like DAGs. The accelerator implements a medium granularity dataflow through hardware-software codesign and achieves both excellent spatial locality and high parallelism. Additionally, a partial sum caching mechanism is introduced to reduce the blocking frequency of processing elements (PEs), and a reordering algorithm of intra-node edges computation is developed to enhance data reuse. Experimental results on 245 benchmarks with node counts reaching up to 85,392 demonstrate that this work achieves average performance improvements of 7.0$\times$ (up to 27.8$\times$) over CPUs and 5.8$\times$ (up to 98.8$\times$) over GPUs. Compared to the state-of-the-art technique (DPU-v2), this work shows a 2.5$\times$ (up to 5.9$\times$) average performance improvement and 1.7$\times$ (up to 4.1$\times$) average energy efficiency enhancement.
title Efficient Hardware Accelerator Based on Medium Granularity Dataflow for SpTRSV
topic Distributed, Parallel, and Cluster Computing
Hardware Architecture
Numerical Analysis
Performance
url https://arxiv.org/abs/2406.10511