8 - Programming Techniques for Supercomputers/ClipID:32019 previous clip next clip

Recording date 2021-04-28

Language

English

Organisational Unit

Friedrich-Alexander-Universität Erlangen-Nürnberg

Producer

Friedrich-Alexander-Universität Erlangen-Nürnberg

This lecture first adresses the problem of calculating the maximum performance of simple kernels if limited by instruction throughput. In a second stept it starts with the chapter on architecture of memory hierarchy. Here the basic structures, Hockney's law and the basic concept of cachelines and latency hiding through non-blocking memory transfers are discussed.

Up next

Wellein, Gerhard
Prof. Dr. Gerhard Wellein
2021-05-03
IdM-login
Wellein, Gerhard
Prof. Dr. Gerhard Wellein
2021-05-04
IdM-login
Wellein, Gerhard
Prof. Dr. Gerhard Wellein
2021-05-05
IdM-login
Wellein, Gerhard
Prof. Dr. Gerhard Wellein
2021-05-10
IdM-login

More clips in this category "Friedrich-Alexander-Universität Erlangen-Nürnberg"

2021-06-22
Studon
protected  
2021-06-22
Studon
protected  
2021-06-22
IdM-login
protected  
2021-06-22
IdM-login
protected  
2021-06-22
IdM-login
protected