Learn · CERN

Talk59 min

Performant programming for GPUs

Daniel Campora · CERN

Watch At CERN

About

Programming for Heterogeneous Architectures - lecture 3

- Data locality, coalesced memory accesses, tiled data processing - GPU streams, pipelined memory transfers - Under the hood: branchless, warps, masked execution - Debugging and profiling a GPU application.

0:00:00 Slide 1

0:05:49 Slide 2

0:11:37 Slide 3

0:17:25 Slide 4

0:23:14 Slide 5

0:29:02 Slide 6

0:34:50 Slide 7

0:40:39 Slide 8

0:46:27 Slide 9

0:52:15 Slide 10

The talk

  1. Performant programming for GPUs 2021-06-17 · 59 min · CERN's player

Credits and licence

Institution
CERN
Department
Thematic CSC
Speaker
Daniel Campora
Year
2021
Language
English
Subjects
Computer science
Source
CERN
Licence
CERN, as CERN states it. CERN's terms
Attribution
© CERN. CERN provides its audiovisual media free of charge for educational and informational use, credited to CERN; this lecture is shown in CERN's own player.
Who can watch
CERN gives no rating. Invisible Network shows it to Tweens profiles and older, judged from what the source says about it. How courses are placed