FPGA Fastfood - A High Speed Systolic Implementation of a Large Scale Online Kernel Method

被引：2

作者：

Fox, Sean ^{[1
]}

Boland, David ^{[1
]}

Leong, Philip ^{[1
]}

机构：

[1] Univ Sydney, Sydney, NSW, Australia

来源：

PROCEEDINGS OF THE 2018 ACM/SIGDA INTERNATIONAL SYMPOSIUM ON FIELD-PROGRAMMABLE GATE ARRAYS (FPGA'18) | 2018年

基金：

澳大利亚研究理事会;

关键词：

D O I：

10.1145/3174243.3174271

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In this paper, we describe a systolic Field Programmable Gate Array (FPGA) implementation of the Fastfood algorithm that is optimised to run at a high frequency. The Fastfood algorithm supports online learning for large scale kernel methods. Empirical results show that 500 MHz clock rates can be sustained for an architecture that can solve problems with input dimensions that are 10(3) times larger than previously reported. Unlike many recent deep learning publications, this design implements both training and prediction. This enables the use of kernel methods in applications requiring a rare combination of capacity, adaption and speed.

引用

页码：279 / 284

页数：6

共 50 条

[41] An efficient high speed AES implementation using Traditional FPGA and LabVIEW FPGA platforms
Rao, Muzaffar
Kaknjo, Admir
Omerdic, Edin
Toal, Daniel
Newe, Thomas
2018 INTERNATIONAL CONFERENCE ON CYBER-ENABLED DISTRIBUTED COMPUTING AND KNOWLEDGE DISCOVERY (CYBERC 2018), 2018, : 93 - 100
[42] FFTRL: A Sparse Online Kernel Classification Algorithm for Large Scale Data
Su, Changzhi
Zhang, Li
Zhao, Lei
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2023, PT I, 2023, 14254 : 195 - 206
[43] Large-scale Online Kernel Learning with Random Feature Reparameterization
Tu Dinh Nguyen
Le, Trung
Bui, Hung
Phung, Dinh
PROCEEDINGS OF THE TWENTY-SIXTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 2543 - 2549
[44] Application of FPGA for High-Speed Dynamic Response Simulator for Large-Scale MDOF Systems
Igarashi, Akira
Matshima, Jun-ichi
PROCEEDINGS OF THE 8TH INTERNATIONAL CONFERENCE ON STRUCTURAL DYNAMICS, EURODYN 2011, 2011, : 2103 - 2109
[45] High-Speed Path Probing Method for Large-Scale Network
Luo, Zhihao
Liu, Jingju
Yang, Guozheng
Zhang, Yongheng
Hang, Zijun
SENSORS, 2022, 22 (15)
[46] FPGA implementation of the high-speed floating-point operation
Ji, XS
Wang, SR
ICEMI 2005: Conference Proceedings of the Seventh International Conference on Electronic Measurement & Instruments, Vol 3, 2005, : 626 - 629
[47] Hardware Implementation of a High Speed Floating Point Multiplier Based on FPGA
Gong Renxi
Zhang Shangjun
Zhang Hainan
Meng Xiaobi
Gong Wenying
Xie Lingling
Huang Yang
ICCSSE 2009: PROCEEDINGS OF 2009 4TH INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE & EDUCATION, 2009, : 1902 - +
[48] FPGA Implementation of High Speed Scalar Multiplication for ECC in GF(p)
Shylashree, N.
Sridhar, V.
TENCON 2015 - 2015 IEEE REGION 10 CONFERENCE, 2015,
[49] The Implementation of High Speed Parallel Timing Synchronization Algorithm Based on FPGA
Hu, Jiao
Zhu, Lichen
Wang, Jianpeng
2018 10TH INTERNATIONAL CONFERENCE ON COMMUNICATION SOFTWARE AND NETWORKS (ICCSN), 2018, : 484 - 487
[50] FPGA Implementation of Low Power High Speed Square Root Circuits
Vijeyakumar, K. N.
Sumathy, V.
Vasakipriya, P.
Babu, A. Dinesh
2012 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND COMPUTING RESEARCH (ICCIC), 2012, : 468 - 472

← 1 2 3 4 5 →