Loop transformations leveraging hardware prefetching

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

2 Citaten (Scopus)
5 Downloads (Pure)

Samenvatting

Memory-bound applications heavily depend on the bandwidth of the system in order to achieve high performance. Improving temporal and/or spatial locality through loop transformations is a common way of mitigating this dependency. However, choosing the right combination of optimizations is not a trivial task, due to the fact that most of them alter the memory access pattern of the application and as a result interfere with the efficiency of the hardware prefetching mechanisms present in modern architectures. We propose an optimization algorithm that analytically classifies an algorithmic description of a loop nest in order to decide whether it should be optimized stressing its temporal or spatial locality, while also taking hardware prefetching into account. We implement our technique as a tool to be used with the Halide compiler and test it on a variety of benchmarks. We find an average performance improvement of over 40% compared to previous analytical models targeting the Halide language and compiler.

Originele taal-2Engels
TitelCGO 2018 - Proceedings of the 2018 International Symposium on Code Generation and Optimization
UitgeverijAssociation for Computing Machinery, Inc
Pagina's254-264
Aantal pagina's11
ISBN van elektronische versie9781450356176
DOI's
StatusGepubliceerd - 24 feb 2018
Evenement16th International Symposium on Code Generation and Optimization, (CGO2018) - Vienna, Oostenrijk
Duur: 24 feb 201828 feb 2018
http://cgo.org/cgo2018

Congres

Congres16th International Symposium on Code Generation and Optimization, (CGO2018)
Verkorte titelCGO2018
LandOostenrijk
StadVienna
Periode24/02/1828/02/18
Internet adres

    Vingerafdruk

Citeer dit

Sioutas, S., Stuijk, S., Corporaal, H., Basten, T., & Somers, L. (2018). Loop transformations leveraging hardware prefetching. In CGO 2018 - Proceedings of the 2018 International Symposium on Code Generation and Optimization (blz. 254-264). Association for Computing Machinery, Inc. https://doi.org/10.1145/3168823