81.6 GOPS Object Recognition Processor Based on a Memory-Centric NoC

Author

Kim, Donghyun ; Kim, Kwanho ; Kim, Joo-Young ; Lee, Seungjin ; Lee, Se-Joong ; Yoo, Hoi-Jun

Author_Institution

Sch. of Electr. Eng. & Comput. Sci., Korea Adv. Inst. of Sci. & Technol. (KAIST), Daejon

Volume

17

Issue

3

fYear

2009

fDate

3/1/2009 12:00:00 AM

Firstpage

370

Lastpage

383

Abstract

For mobile intelligent robot applications, an 81.6 GOPS object recognition processor is implemented. Based on an analysis of the target application, the chip architecture and hardware features are decided. The proposed processor aims to support both task-level and data-level parallelism. Ten processing elements are integrated for the task-level parallelism and single instruction multiple data (SIMD) instruction is added to exploit the data-level parallelism. The memory-centric network-on-chip (NoC) is proposed to support efficient pipelined task execution using the ten processing elements. It also provides coherence and consistency schemes tailored for 1-to-N and M-to-1 data transactions in a task-level pipeline. For further performance gain, the visual image processing memory is also implemented. The chip is fabricated in a 0.18-mum CMOS technology and computes the key-point localization stage of the SIFT object recognition twice faster than the 2.3 GHz Core 2 Duo processor.

Keywords

intelligent robots; mobile robots; network-on-chip; object recognition; robot vision; SIFT object recognition; chip architecture; data-level parallelism; frequency 2.3 GHz; key-point localization stage; memory-centric NoC; memory-centric network-on-chip; mobile intelligent robot applications; object recognition processor; pipelined task execution; single instruction multiple data instruction; task-level parallelism; visual image processing memory; Multiprocessing; VLSI; network-on-chip (NoC); object recognition;

fLanguage

English

Journal_Title

Very Large Scale Integration (VLSI) Systems, IEEE Transactions on

Publisher

ieee

ISSN

1063-8210

Type

jour

DOI

10.1109/TVLSI.2008.2011226

Filename

4773146