Dynamic Optimization of On-Chip Memories for HLS Targeting Many-Accelerator Platforms
- 12 July 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Computer Architecture Letters
- Vol. 21 (2) , 41-44
Abstract
Many-accelerator platforms have been introduced for maximizing FPGA's throughput. However, as the high saturation rate of the FPGA's on-chip memories limits the number of synthesized accelerators, frameworks for Dynamic Memory Management (DMM) that allow the synthesized designs to allocate/de-allocate on-chip memory resources during run-time have been suggested. Although, those frameworks manage to increase the accelerators’ density by minimizing the utilized memory resources, the parallel execution of many-accelerators may cause severe memory fragmentation and thus memory allocation failures. In this work, a framework that optimizes the memory usage by performing memory defragmentation operations in HLS many-accelerator architectures that share on-chip memories is proposed. Experimental results highlight the effectiveness of the proposed solution to eliminate memory allocation failures due to memory fragmentation, reduce memory allocation failures up to 32% on average and decrease the memory size requirements up to 5% with controllable latency and resource utilization overhead.Keywords
Funding Information
- E.C. funded program SERRANO (101017168)
This publication has 11 references indexed in Scilit:
- Towards Automatic High-Level Code Deployment on Reconfigurable Platforms: A Survey of High-Level Synthesis Tools and ToolchainsIEEE Access, 2020
- A Dynamic Memory Allocation Library for High-Level Synthesis2019
- Modular FPGA Acceleration of Data Analytics in Heterogenous Computing2019
- Hi-DMM: High-Performance Dynamic Memory Management in High-Level SynthesisIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2018
- Unleashing Fine-Grained Parallelism on Embedded Many-Core Accelerators with Lightweight OpenMP TaskingIEEE Transactions on Parallel and Distributed Systems, 2018
- Mitigating Memory-Induced Dark Silicon in Many-Accelerator ArchitecturesIEEE Computer Architecture Letters, 2015
- Adaptive Dynamic On-chip Memory Management for FPGA-based reconfigurable architectures2014
- LegUp2011
- Dynamic storage allocation: A survey and critical review1995
- Buddy systemsCommunications of the ACM, 1977