Daisy-Chained Systolic Array and Reconfigurable Memory Space for Narrow Memory Bandwidth

Jun IWAMOTO  Yuma KIKUTANI  Renyuan ZHANG  Yasuhiko NAKASHIMA  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E103-D   No.3   pp.578-589
Publication Date: 2020/03/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2019EDP7144
Type of Manuscript: PAPER
Category: Computer System
Keyword: 
systolic array,  reconfigurable memory space,  memory bandwidth,  

Full Text: PDF(1.7MB)>>
Buy this Article




Summary: 
A paradigm shift toward edge computing infrastructures that prioritize small footprint and scalable/easy-to-estimate performance is increasing. In this paper, we propose the following to improve the footprint and the scalability of systolic arrays: (1) column multithreading for reducing the number of physical units and maintaining the performance even for back-to-back floating-point accumulations; (2) a cascaded peer-to-peer AXI bus for a scalable multichip structure and an intra-chip parallel local memory bus for low latency; (3) multilevel loop control in any unit for reducing the startup overhead and adaptive operation shifting for efficient reuse of local memories. We designed a systolic array with a single column × 64 row configuration with Verilog HDL, evaluated the frequency and the performance on an FPGA attached to a ZYNQ system as an AXI slave device, and evaluated the area with a TSMC 28nm library and memory generator and identified the following: (1) the execution speed of a matrix multiplication/a convolution operation/a light-field depth extraction, whose size larger than the capacity of the local memory, is 6.3× / 9.2× / 6.6× compared with a similar systolic array (EMAX); (2) the estimated speed with a 4-chip configuration is 19.6× / 16.0× / 8.5×; (3) the size of a single-chip is 8.4 mm2 (0.31× of EMAX) and the basic performance per area is 2.4×.