Systolic array: Difference between revisions

Revision as of 22:40, 21 June 2021

Revision as of 05:52, 22 June 2021

Line 1:

{{Use dmy dates|date=October 2019}}

In [[parallel computing|parallel]] [[computer architectures]], a '''systolic array''' is a homogeneous [[Graph (discrete mathematics)|network]] of tightly coupled [[data processing unit]]s (DPUs) called cells or [[Node (computer science)|node]]s. Each node or DPU independently computes a partial result as a function of the data received from its upstream neighbors, stores the result within itself and passes it downstream. Systolic arrays were first used in [[Colossus_computerColossus computer|Colossus]], which was an early computer used to break German [[Lorenz_cipherLorenz cipher|Lorenz]] ciphers during [[World War II]].<ref>{{YouTube |id=g2tMcMQqSbA |title=Colossus - The Greatest Secret in the History of Computing |time=41m45s}}</ref> They were invented or rediscovered by [[H. T. Kung]] and [[Charles Leiserson]] who described arrays for many dense linear algebra computations (matrix product, solving systems of [[linear equation]]s, [[LU decomposition]], etc.) for banded matrices. Early applications include computing [[greatest common divisor]]s of integers and polynomials.<ref>http://www.eecs.harvard.edu/~htk/publication/1984-ieeetoc-brent-kung.pdf</ref> They are sometimes classified as [[MISD|multiple-instruction single-data]] (MISD) architectures under [[Flynn's taxonomy]], but this classification is questionable because a strong argument can be made to distinguish systolic arrays from any of Flynn's four categories: [[SISD]], [[SIMD]], [[MISD]], [[MIMD]], as discussed later in this article.

The parallel input [[data]] flows through a network of hard-wired [[Microprocessor|processor]] nodes, which combine, process, [[merge algorithm|merge]] or [[sorting algorithm|sort]] the input data into a derived result. Because the [[wave]]-like propagation of data through a systolic array resembles the [[pulse]] of the human circulatory system, the name ''systolic'' was coined from medical terminology. The name is derived from [[systole]] as an analogy to the regular pumping of blood by the heart.

Line 71:

* Paracel FDF4T TestFinder text search system<ref name="FDF4">{{cite web|title=About Paracel|url=http://brandprosgroup.com/pages/first/websites/paracel/data/html/about_paracel2.html|website=brandprosgroup.com|publisher=Paracel|access-date=4 May 2018}}</ref>

* Paracel FDF4G GeneMatcher Biological (DNA and Protein) search system

* Inferentia chip at [[Amazon Web Services]] <ref>{{cite web|title=Announcing availability of Inf1 instances in Amazon SageMaker for high performance and cost-effective machine learning inference|url=https://aws.amazon.com/blogs/aws/amazon-ecs-now-supports-ec2-inf1-instances/|access-date=15 August 2020}}</ref>

*[[MIT Eyeriss]] is a systolic array accelerator for convolutional neural networks.<ref>{{Cite web|title=Eyeriss Project|url=http://eyeriss.mit.edu/|access-date=2021-02-21|website=eyeriss.mit.edu}}</ref><ref>{{Cite journal|last=Chen|first=Yu-Hsin|last2=Emer|first2=Joel|last3=Sze|first3=Vivienne|date=2016-10-12|title=Eyeriss: a spatial architecture for energy-efficient dataflow for convolutional neural networks|url=https://dl.acm.org/doi/10.1145/3007787.3001177|journal=ACM SIGARCH Computer Architecture News|language=en|volume=44|issue=3|pages=367–379|doi=10.1145/3007787.3001177|issn=0163-5964}}</ref>