logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Domain-Specific Optimization and Generation of High-Performance GPU Code for Stencil Computations

delete2018-11-01
delete41
delete
OA
AI
P
Prashant Singh Rawat
M
Miheer Vaidya
A
Aravind Sukumaran-Rajam
M
M. Ravishankar
V
Vinod Grover
A
Atanas Rountev
L
Louis-Noël Pouchet
P
P. Sadayappan *
DOI：10.1109/JPROC.2018.2862896delete
deleteOriginal
deleteShare
deleteSave
View PDF
Abstract

Abstract

En 中文
Stencil computations arise in a number of computational domains. They exhibit significant data parallelism and are thus well suited for execution on graphical processing units (GPUs), but can be memory-bandwidth limited unless temporal locality is utilized via tiling. This paper describes how effective tiled code can be generated for GPUs from a domain-specific language (DSL) for stencils. Experimental results demonstrate the benefits of such a domain-specific optimization approach over state-of-the-art general-purpose compiler optimizations.
Keywords:
General-purpose graphical processing unit (GPGPU)
resource optimization
stencil computations
streaming
tiling
AI Summary

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.

Journal

Proceedings of the IEEE cover
Proceedings of the IEEE
IF:
25.9
Papers:
9.9K
Citations:
4.5W

Organization

U
University System of Ohio
Scholars:
15.4W
Papers: 13.0W
Citations: 200
N
nvidia corporation
Scholars:
767
Papers: 439
Citations: 1
O
Ohio State University
Scholars:
4.1W
Papers: 3.2W
Citations: 80
researcher View more organizations