Please use this identifier to cite or link to this item:
Title: GraphMMU: Memory Management Unit for Sparse Graph Accelerators
Authors: Han, Jianglei
Kapre, Nachiket
Bean, Andrew
Moorthy, Pradeep
Keywords: Computer Science and Engineering
Issue Date: 2015
Source: Kapre, N., Jianglei, H., Bean, A., Moorthy, P., & Siddhartha (2015). GraphMMU: Memory Management Unit for Sparse Graph Accelerators. 2015 IEEE International Parallel and Distributed Processing Symposium Workshop, 113-120.
Conference: 2015 IEEE International Parallel and Distributed Processing Symposium Workshop (IPDPSW)
Abstract: Memory management units that use low-level AXI descriptor chains to hold irregular graph-oriented access sequences can help improve DRAM memory throughput of graph algorithms by almost an order of magnitude. For the Xilinx Zed board, we explore and compare the memory throughputs achievable when using (1) cache-enabled CPUs with an OS, (2) cache-enabled CPUs running bare metal code, (2) CPU-based control of FPGA-based AXI DMAs, and finally (3) local FPGA-based control of AXI DMA transfers. For short-burst irregular traffic generated from sparse graph access patterns, we observe a performance penalty of almost 10× due to DRAM row activations when compared to cache-friendly sequential access. When using an AXI DMA engine configured in FPGA logic and programmed in AXI register mode from the CPU, we can improve DRAM performance by as much as 2.4× over naïve random access on the CPU. In this mode, we use the host CPU to trigger DMA transfer by writing appropriate control information in the internal register of the DMA engine. We also encode the sparse graph access patterns as locally-stored BRAM-hosted AXI descriptor chains to drive the AXI DMA engines with minimal CPU involvement under Scatter Gather mode. In this configuration, we deliver an additional 3× speedup, for a cumulative throughput improvement of 7× over a CPU-based approach using caches while running an OS to manage irregular access.
DOI: 10.1109/IPDPSW.2015.101
Schools: School of Computer Engineering 
Rights: © 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: [].
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Conference Papers

Files in This Item:
File Description SizeFormat 
GraphMMU_Memory Management Unit for Sparse Graph Accelerators.pdf422.8 kBAdobe PDFThumbnail

Citations 50

Updated on Jun 5, 2024

Web of ScienceTM
Citations 50

Updated on Oct 30, 2023

Page view(s)

Updated on Jun 13, 2024

Download(s) 20

Updated on Jun 13, 2024

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.