[图书][B] Why systolic architecture?

HT Kung - 1982 - eecs.harvard.edu
Roughly, the cycle for developing a special-purpose system can be divided into three
phases–task definition, design, and implementation. During task definition, some system …

[图书][B] Models of computation

JE Savage - 1998 - dna.caltech.edu
Models of Computation.ppt [Read-Only] Page 1 Models of Computation John E Savage
Computer Science Brown University CBSSS 2004 July 16, 2004 Page 2 CBSSS: JE Savage …

[PDF][PDF] Gemmini: An agile systolic array generator enabling systematic evaluations of deep-learning architectures

H Genc, A Haj-Ali, V Iyer, A Amid, H Mao… - arXiv preprint arXiv …, 2019 - alonamid.github.io
Advances in deep learning and neural networks have resulted in rapid development of
hardware accelerators that support them. A large majority of ASIC accelerators, however …

A generator of numerically-tailored and high-throughput accelerators for batched GEMMs

L Ledoux, M Casas - 2022 IEEE 30th Annual International …, 2022 - ieeexplore.ieee.org
We propose a hardware generator of GEMM accelerators. Our generator produces vendor-
agnostic HDL describing highly customizable systolic arrays guided by accuracy and energy …

Parallelism in computer vision: A review

V Chaudhary, JK Aggarwal - Parallel algorithms for machine intelligence …, 1990 - Springer
Computer vision tasks require an enormous amount of computation, especially when the
data is in image form, demanding high-performance computers for practical, real-time …

Parallel computer architectures for image processing

AP Reeves - Computer Vision, Graphics, and Image Processing, 1984 - Elsevier
Image processing problems frequently involve large structured arrays of data and a need for
very rapid computation. Special parallel processing schemes have evolved over the last 20 …

Two-level pipelined systolic array for multidimensional convolution

HT Kung, LM Ruane, DWL Yen - Image and Vision Computing, 1983 - Elsevier
This paper describes a systolic array for the computation of n-dimensional (nD) convolutions
for any positive integer n. Systolic systems usually achieve high performance by allowing …

Parallel 2-D convolution on a mesh connected array processor

SY Lee, JK Aggarwal - IEEE Transactions on Pattern Analysis …, 1987 - ieeexplore.ieee.org
In this correspondence, a parallel 2-D convolution scheme is presented. The processing
structure is a mesh connected array processor consisting of the same number of simple …

[图书][B] Multi-computer architectures for artificial intelligence: Toward fast, robust, parallel systems

L Uhr - 1987 - dl.acm.org
Multi-computer architectures for artificial intelligence: toward fast, robust, parallel systems |
Guide books skip to main content ACM Digital Library home ACM home Google, Inc. (search) …

Evolutionary Mapping Techniques for Systolic Computing System

C Bagavathi, O Saraniya - Deep Learning and Parallel Computing …, 2019 - Elsevier
Systolic arrays are hardware structures built for fast and efficient operation of regular
algorithms that perform the same task with different data at different time instants. Systolic …