arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2104.07776cs.ARcs.DB
收藏

基于FPGA的图形处理加速器的内存访问模式揭秘

Demystifying Memory Access Patterns of FPGA-Based Graph Processing Accelerators

Jonas Dann, Daniel Ritter, Holger Fröning

摘要:

可重编程硬件的最新进展(例如,FPGA)和存储器技术(例如,DDR4,HBM)承诺解决图形处理固有的性能问题,如传统硬件上的不规则存储器访问模式(例如,CPU)。虽然近年来提出了几个这样的图形加速器,但由于很少有开源实现和过多的实现工作,仍然很难评估它们的性能并在常见的图形工作负载和加速器平台上进行比较。在这项工作中,我们建立了一个图形处理加速器的模拟环境,使几个现有的加速器方法可比。这使我们能够研究相关的性能维度,例如分区方案和内存技术等。该评估深入了解了当前图形处理加速器在这些方面的优势和劣势,并进行了新颖的深入比较。

英文摘要:

Recent advances in reprogrammable hardware (e.g., FPGAs) and memory technology (e.g., DDR4, HBM) promise to solve performance problems inherent to graph processing like irregular memory access patterns on traditional hardware (e.g., CPU). While several of these graph accelerators were proposed in recent years, it remains difficult to assess their performance and compare them on common graph workloads and accelerator platforms, due to few open source implementations and excessive implementation effort. In this work, we build on a simulation environment for graph processing accelerators, to make several existing accelerator approaches comparable. This allows us to study relevant performance dimensions such as partitioning schemes and memory technology, among others. The evaluation yields insights into the strengths and weaknesses of current graph processing accelerators along these dimensions, and features a novel in-depth comparison.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑