On the Transformation Optimization for Stencil Computation

Autor:	Huayou Su, Kaifang Zhang, Songzhu Mei
Jazyk:	angličtina
Rok vydání:	2021
Předmět:	loop fusion loop unroll TK7800-8360 Computer Networks and Communications performance optimization loop transformation stencil computation HPC Hardware and Architecture Control and Systems Engineering Signal Processing Electrical and Electronic Engineering Electronics
Zdroj:	Electronics; Volume 11; Issue 1; Pages: 38 Electronics, Vol 11, Iss 38, p 38 (2022)
ISSN:	2079-9292
DOI:	10.3390/electronics11010038
Popis:	Stencil computation optimizations have been investigated quite a lot, and various approaches have been proposed. Loop transformation is a vital kind of optimization in modern production compilers and has proved successful employment within compilers. In this paper, we combine the two aspects to study the potential benefits some common transformation recipes may have for stencils. The recipes consist of loop unrolling, loop fusion, address precalculation, redundancy elimination, instruction reordering, load balance, and a forward and backward update algorithm named semi-stencil. Experimental evaluations of diverse stencil kernels, including 1D, 2D, and 3D computation patterns, on two typical ARM and Intel platforms, demonstrate the respective effects of the transformation recipes. An average speedup of 1.65× is obtained, and the best is 1.88× for the single transformation recipes we analyze. The compound recipes demonstrate a maximum speedup of 1.92×.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5cc42a0a5730498edc6c50454708c95e Zobrazit plný text záznamu