A compilation technique and performance profits for VLIW with heterogeneous vectors

E. Diken, L. Jozwiak

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

In numerous mobile applications involving complex video, image, signal, communication or security processing, massive parallelism is mainly in the form of data-level parallelism (DLP). However, the sorts and amount of DLP parallelism in applications vary due to different computational characteristics of applications. On the contrary, most of the processors today include single-width SIMD (vector) hardware to exploit DLP. However, single-width SIMD architectures may not be optimal to serve applications with varying DLP and they may cause performance and energy inefficiency. We propose the usage of VLIW processors with multiple native vector-widths to better serve applications with changing DLP. This paper focuses on the short SIMD code generation. More specifically, we target generating 32-bit SIMD code for the native 32-bit wide vector units of our example processor. In this way, we improved the performance of compiler generated SIMD code by reducing the number of overhead operations. Experimental results demonstrated that our methodology implemented in the compiler reduces the number of operations of synthetic benchmarks up to 40%.
Original languageEnglish
Title of host publicationProceedings - 2015 4th Mediterranean Conference on Embedded Computing, MECO 2015 - Including ECyPS 2015, BioEMIS 2015, BioICT 2015, MECO-Student Challenge 2015
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Pages9-12
Number of pages4
ISBN (Print)978-1-4799-8999-7
DOIs
Publication statusPublished - 6 Aug 2015
Event4th Mediterranean Conference on Embedded Computing, MECO 2015 - Hotel Slovenska Plaza, Budva, Montenegro
Duration: 14 Jun 201518 Jun 2015
Conference number: 4

Conference

Conference4th Mediterranean Conference on Embedded Computing, MECO 2015
Abbreviated titleMECO 2015
Country/TerritoryMontenegro
CityBudva
Period14/06/1518/06/15
Other4th Mediterranean Conference on Embedded Computing (MECO 2015) - Including ECyPS 2015, BioEMIS 2015, BioICT 2015, MECO-Student Challenge 2015

Fingerprint

Dive into the research topics of 'A compilation technique and performance profits for VLIW with heterogeneous vectors'. Together they form a unique fingerprint.

Cite this