Title
Boosting Memory Performance of Many-Core FPGA Device through Dynamic Precedence Graph
Abstract
Emerging FPGA device, integrated with abundant RAM blocks and high-performance processor cores, offers an unprecedented opportunity to effectively implement single-chip distributed logic-memory (DLM) architectures [1]. Being “memory-centric”, the DLM architecture can significantly improve the overall performance and energy efficiency of many memory-intensive embedded applications, especially those that exhibit irregular array data access patterns at algorithmic level. However, implementing DLM architecture poses unique challenges to an FPGA designer in terms of 1) organizing and partitioning diverse on-chip memory resources, and 2) orchestrating effective data transmission between on-chip and off-chip memory. In this paper, we offer our solutions to both of these challenges. Specifically, 1) we propose a stochastic memory partitioning scheme based on the well-known simulated annealing algorithm. It obtains memory partitioning solutions that promote parallelized memory accesses by exploring large solution space; 2) we augment the proposed DLM architecture with a reconfigure hardware graph that can dynamically compute precedence relationship between memory partitions, thus effectively exploiting algorithmic level memory parallelism on a per-application basis. We evaluate the effectiveness of our approach (A3) against two other DLM architecture synthesizing methods: an algorithmic-centric reconfigurable computing architectures with a single monolithic memory (A1) and the heterogeneous distributed architectures synthesized according to [1] (A2). To make our comparison fair, in all three architectures, the data path remains the same while local memory architecture differs. For each of ten benchmark applications from SPEC2006 and MiBench [2], we break down the performance benefit of using A3 into two parts: the portion due to stochastic local memory partitioning and the portion due to the dynamic graph-based memory arbitration. All experiments have been c- nducted with a Virtex-5 (XCV5LX155T-2) FPGA. On average, our experimental results show that our proposed A3 architecture outperforms A2 and A1 by 34% and 250%, respectively. Within the performance improvement of A3 over A2, more than 70% improvement comes from the hardware graph-based memory scheduling.
Year
DOI
Venue
2013
10.1109/FCCM.2013.39
FCCM
Keywords
Field
DocType
processor scheduling,stochastic memory partitioning scheme,overall performance improvement,diverse on-chip memory resource,dlm architecture,diverse on-chip memory resource organization,virtex-5 fpga,memory partition,memory-centric,irregular array data access patterns,xcv5lx155t-2 fpga,simulated annealing algorithm,precedence graph,reconfigurable architectures,diverse on-chip memory resource partition,local memory partitioning,dynamic graph-based memory arbitration,ram blocks,parallelized memory access,dynamic precedence graph,multiprocessing systems,algorithmic level memory parallelism,mibench,parallelized memory accesses,hardware graph-based memory scheduling,logic design,memory performance boosting,single monolithic memory,fpga,high-performance processor cores,off-chip memory,performance evaluation,boosting memory performance,graph theory,many-core fpga device,field programmable gate arrays,heterogeneous distributed architectures,spec2006,parallel memories,simulated annealing,algorithmic-centric reconfigurable computing architectures,energy efficiency improvement,single-chip distributed logic-memory architectures,local memory architecture,hardware,parallel processing,computer architecture
Registered memory,Interleaved memory,Computer architecture,Uniform memory access,Shared memory,Computer science,Parallel computing,Cache-only memory architecture,Real-time computing,Memory map,Distributed shared memory,Memory architecture
Conference
ISBN
Citations 
PageRank 
978-1-4673-6005-0
1
0.38
References 
Authors
4
5
Name
Order
Citations
PageRank
Yu Bai110.38
Abigail Fuentes210.72
Michael Riera310.72
Mohammed Alawad496.80
Mingjie Lin57325.04