• Home
  • Search
  • Optimizing SDRAM bandwidth for custom FPGA loop accelerators
  • Cite Icon30
  • https://doi.org/10.1145/2145694.2145727Copy DOI Icon

Optimizing SDRAM bandwidth for custom FPGA loop accelerators

  • Feb 22, 2012
  • Samuel Bayliss +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Memory bandwidth is critical to achieving high performance in many FPGA applications. The bandwidth of SDRAM memories is, however, highly dependent upon the order in which addresses are presented on the SDRAM interface. We present an automated tool for constructing an application specific on-chip memory address sequencer which presents requests to the external memory with an ordering that optimizes off-chip memory bandwidth for fixed on-chip memory resource. Within a class of algorithms described by affine loop nests, this approach can be shown to reduce both the number of requests made to external memory and the overhead associated with those requests. Data presented shows a trade off between the use of on-chip resources and achievable off-chip memory bandwidth where a range of improvements from 3.6x to 4x gain in efficiency on the external memory interface can be gained at a cost of up to a 1.4x increase in the ALUTs dedicated to address generation circuits in an Altera Stratix III device.

Similar Papers
  • Book Chapter
  • Citations7

Application Specific Memory Access, Reuse and Reordering for SDRAM

  • Jan 01, 2011
  • Samuel Bayliss +1
  • Conference Article

Memory Bandwidth Reduction of Video Decoder

  • Apr 06, 2012
  • Zhenqian Shen +2
  • Research Article
  • Citations7

A Reconfigurable Heterogeneous Multimedia Processor for IC-Stacking on Si-Interposer

  • Apr 01, 2012
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Hyo-Eun Kim +5
  • Conference Article
  • Citations12

OpenCL library of stream memory components targeting FPGAs

  • Dec 01, 2015
  • Jasmina Vasiljevic +6
  • Conference Article
  • Citations11

A multilevel data reuse scheme for Motion Estimation and its VLSI design

  • May 01, 2011
  • Mateus Grellert +3
  • Research Article
  • Citations5

Cluster-Based Motion Estimation Algorithm With Low Memory and Bandwidth Requirements for H.264/AVC Scalable Extension

  • Jun 01, 2014
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Ching-Lung Su +2
  • Conference Article
  • Citations4

Design and implementation of a real-time image processing system with modularization and extendibility

  • Jul 01, 2008
  • Jun Wang +1
  • Conference Article

A new method to optimize function verification

  • Apr 01, 2011
  • Feng Xinyu +2
  • Research Article
  • Citations38

Architecture Design for H.264/AVC Integer Motion Estimation with Minimum Memory Bandwidth

  • Aug 01, 2007
  • IEEE Transactions on Consumer Electronics
  • Dong-Xiao Li +2
  • Conference Article
  • Citations11

An on-chip cache design for vector processors

  • Sep 16, 2007
  • Akihiro Musa +5
  • Conference Article
  • Citations400

A dynamically configurable coprocessor for convolutional neural networks

  • Jun 19, 2010
  • Srimat Chakradhar +3
  • Conference Article
  • Citations3

Evaluating the Memory Architecture of Next-Generation FPGA-SoCs for HPC

  • Jul 01, 2019
  • Matthias Goebel +3
  • Conference Article
  • Citations2

Motion estimation method based on efficient memory bandwidth for HEVC real-time algorithm based on graph theoryncoding

  • May 01, 2016
  • Kodai Miyajima +1
  • Conference Article
  • Citations10

Custom-sized caches in application-specific memory hierarchies

  • Dec 01, 2015
  • Felix Winterstein +4
  • Conference Article
  • Citations10

Scheduling algorithms for automated synthesis of pipelined designs on FPGAs for applications described in MATLAB

  • Jan 01, 2000
  • Malay Haldar +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.