An Energy-Efficient Patchable Accelerator and Its Design Methods

被引:1
作者
Yoshida, Hiroaki [1 ]
Wakizaka, Masayuki [2 ]
Yamashita, Shigeru [2 ]
Fujita, Masahiro [3 ]
机构
[1] Fujitsu Labs Amer, Sunnyvale, CA 94085 USA
[2] Ritsumeikan Univ, Grad Sch, Kusatsu Shi 5258577, Japan
[3] Univ Tokyo, VLSI Design & Educ Ctr, Tokyo 1130032, Japan
关键词
engineering change; high-level synthesis; energy efficiency;
D O I
10.1587/transfun.E97.A.2507
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
With the shorter time-to-market and the rising cost in SoC development, the demand for post-silicon programmability has been increasing. Recently, programmable accelerators have attracted more attention as an enabling solution for post-silicon engineering change. However, programmable accelerators suffers from 5 similar to 10X less energy efficiency than fixed-function accelerators mainly due to their extensive use of memories. This paper proposes a highly energy-efficient accelerator which enables post-silicon engineering change by a control patching mechanism. Then, we propose a patch compilation method from a given pair of an original design and a modified design. We also propose a design method to add redundant wires in advance to decrease the necessary amount of patch memory for post-silicon engineering change. Experimental results demonstrate that the proposed accelerators offer high energy efficiency competitive to fixed-function accelerators and can achieve about 5X higher efficiency than the existing programmable accelerators. We also show the trade-off between redundant wires and the necessary amount of patch memory.
引用
收藏
页码:2507 / 2517
页数:11
相关论文
共 15 条
[1]  
[Anonymous], INT TECHN ROADM SEM
[2]   An architecture framework for transparent instruction set customization in embedded processors [J].
Clark, N ;
Blome, J ;
Chu, M ;
Mahlke, S ;
Biles, S ;
Flautner, K .
32ND INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE, PROCEEDINGS, 2005, :272-283
[3]   Efficient embedded computing [J].
Dally, William J. ;
Balfour, James ;
Black-Shaffer, David ;
Chen, James ;
Harting, R. Curtis ;
Parikh, Vishal ;
Park, Jongsoo ;
Sheffield, David .
COMPUTER, 2008, 41 (07) :27-+
[4]  
Fan K, 2009, INT S HIGH PERF COMP, P313, DOI 10.1109/HPCA.2009.4798266
[5]  
Fan K, 2008, INT SYM CODE GENER, P124
[6]  
Hameed R, 2010, CONF PROC INT SYMP C, P37, DOI 10.1145/1816038.1815968
[7]  
Lattner C, 2004, INT SYM CODE GENER, P75, DOI 10.1109/CGO.2004.1281665
[8]   Swing module scheduling: A lifetime-sensitive approach [J].
Llosa, J ;
Gonzalez, A ;
Ayguade, E ;
Valero, M .
PROCEEDINGS OF THE 1996 CONFERENCE ON PARALLEL ARCHITECTURES AND COMPILATION TECHNIQUES (PACT '96), 1996, :80-86
[9]   Design methodology for a tightly coupled VLIW/reconfigurable, matrix architecture: A case study [J].
Mei, BF ;
Vernalde, S ;
Verkest, D ;
Lauwereins, R .
DESIGN, AUTOMATION AND TEST IN EUROPE CONFERENCE AND EXHIBITION, VOLS 1 AND 2, PROCEEDINGS, 2004, :1224-1229
[10]   Improving performance and energy efficiency of embedded processors via post-fabrication instruction set customization [J].
Noori, Hamid ;
Mehdipour, Farhad ;
Inoue, Koji ;
Murakami, Kazuaki .
JOURNAL OF SUPERCOMPUTING, 2012, 60 (02) :196-222