A Synthesis Methodology for Intelligent Memory Interfaces in Accelerator Systems
Open Access
- 20 January 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1016-1022
Abstract
Domain-specific systems improve the performance of specific applications compared to general-purpose processing systems by deploying custom hardware accelerators. These hardware accelerators are generated using high-level synthesis (HLS) tools. The HLS tools enable a comprehensive design space exploration, optimizing the accelerators' compute performance. However, they often ignore the challenges of implementing the accelerators in a system-on-chip, particularly how they access memory. Our work introduces a buffering system design that improves accelerators' memory accesses by intelligently employing burst transactions to prefetch useful data from external memory to on-chip local buffers. Our design is dynamic, parametric, and transparent to the accelerators generated by HLS tools. We derive the buffering system parameters using appropriate compiler-based analysis passes and memory channel latency constraints. The proposed buffering system design results in, on average, 8.8× performance improvements while lowering memory channel utilization by 53.2% for a set of PolyBench kernels.Keywords
This publication has 5 references indexed in Scilit:
- ScaleHLS2022
- Invited: Bambu: an Open-Source Research Framework for the High-Level Synthesis of Complex Applications2021
- Unaligned Burst-Aware Memory SubsystemIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2019
- Managing the FPGA memory wall: Custom computing or vector processing?2013
- When Prefetching Works, When It Doesn’t, and WhyACM Transactions on Architecture and Code Optimization, 2012