Configurable CNN SoC Co-Processor Architecture

被引：2

作者：

Wijaya, Joshua Adiel ^{[1
]}

Adiono, Trio ^{[2
]}

机构：

[1] Inst Teknol Bandung, Sch Elect Engn & Informat, Bandung, Indonesia

[2] Univ Ctr Excellence Microelect, Inst Teknol Bandung, Bandung, Indonesia

来源：

2019 INTERNATIONAL SOC DESIGN CONFERENCE (ISOCC) | 2019年

关键词：

Convolution Neural Network (CNN); System on Chip (SoC); processor;

D O I：

10.1109/isocc47750.2019.9078513

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper we proposed a configurable CNN architecture design for use in a SoC co-processor. The co-processor is configured and generated by the proposed design tools utilizing folding architecture and multiple processing elements working in parallel. The proposed system utilized a configurable system designer that can automatically generate the verilog source file that defines a CNN processor that can process various image and kernel sizes. The system designer also able to generate the program code to be run on the SoC platform. The system design has been verified using a ZYNQ (TM) 7000 SoC platform and shows the processing result is similar to the simulation results. The system can reach the processing speed of 72.727 MHz.

引用

页码：281 / 282

页数：2

共 50 条

[21] Asynchronous ARM processor employing an adaptive pipeline architecture
Lee, Je-Hoon
Lee, Seung-Sook
Cho, Kyoung-Rok
RECONFIGURABLE COMPUTING: ARCHITECTURES, TOOLS AND APPLICATIONS, 2007, 4419 : 39 - +
[22] FPGA Implementation of a Novel Dual - BRAM Processor Architecture
Ignat, Cristian
Farago, Paul
Hintea, Sorin
2020 43RD INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS AND SIGNAL PROCESSING (TSP), 2020, : 124 - 128
[23] Novel Graph Processor Architecture, Prototype System, and Results
Song, William S.
Gleyzer, Vitaliy
Lomakin, Alexei
Kepner, Jeremy
2016 IEEE HIGH PERFORMANCE EXTREME COMPUTING CONFERENCE (HPEC), 2016,
[24] A new processor architecture for real-time systems
Uchiyama, M
Itou, T
Sato, J
Yamasaki, N
Anzai, Y
NEW TECHNOLOGIES FOR COMPUTER CONTROL 2001, 2002, : 365 - 370
[25] Modeling of Processor Datapaths with VLIW Architecture at the System Level
Tarasov, Ilya
Kazantseva, Larisa
Daeva, Sofia
HIGH-PERFORMANCE COMPUTING SYSTEMS AND TECHNOLOGIES IN SCIENTIFIC RESEARCH, AUTOMATION OF CONTROL AND PRODUCTION, 2022, 1526 : 3 - 12
[26] The v2.0+EDR Bluetooth SOC architecture for multimedia
Kim, Jeonghun
Choi, Youngwhan
Jeong, Jungwon
Lee, Suhho
Kim, Suki
IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 2006, 52 (02) : 436 - 444
[27] Nonstop processor field upgrading with layered software architecture
Futagami, S
Nakamura, H
Inamori, H
ELECTRONICS AND COMMUNICATIONS IN JAPAN PART I-COMMUNICATIONS, 2002, 85 (11): : 87 - 96
[28] A 40 nm 16-Core 128-Thread SPARC SoC Processor
Shin, Jinuk Luke
Huang, Dawei
Petrick, Bruce
Hwang, Changku
Tam, Kenway W.
Smith, Alan
Pham, Ha
Li, Hongping
Johnson, Timothy
Schumacher, Francis
Leon, Ana Sonia
Strong, Allan
IEEE JOURNAL OF SOLID-STATE CIRCUITS, 2011, 46 (01) : 131 - 144
[29] SoC Architecture for an Ultrasonic Receiver applied to Local Positioning Systems
Hernandez, Alvaro
Urena, Jesus
Villadangos, Jose M.
Mannay, Khaoula
2018 XXXIII CONFERENCE ON DESIGN OF CIRCUITS AND INTEGRATED SYSTEMS (DCIS), 2018,
[30] Convolutional Neural Network and Maxpooling Architecture on Zynq SoC FPGA
Bachtiar, Y. A.
Adiono, T.
2019 INTERNATIONAL SYMPOSIUM ON ELECTRONICS AND SMART DEVICES (ISESD 2019): FUTURE SMART DEVICES AND NANOTECHNOLOGY FOR MICROELECTRONICS, 2019,

← 1 2 3 4 5 →