Exploiting historical data: pruning autotuning spaces and estimating the number of tuning steps

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14610%2F19%3A00115100" target="_blank" >RIV/00216224:14610/19:00115100 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-030-48340-1_23" target="_blank" >http://dx.doi.org/10.1007/978-3-030-48340-1_23</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-48340-1_23" target="_blank" >10.1007/978-3-030-48340-1_23</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Exploiting historical data: pruning autotuning spaces and estimating the number of tuning steps

Popis výsledku v původním jazyce

Autotuning, the practice of automatic tuning of code to provide performance portability, has received increased attention in the research community, especially in high performance computing. Ensuring high performance on a variety of hardware usually means modifications to the code, often via different values of a selected set of parameters, such as tiling size, loop unrolling factor or data layout. However, the search space of all possible combinations of these parameters can be enormous. Traditional search methods often fail to find a well-performing set of parameter values quickly. We have found that certain properties of tuning spaces do not vary much when hardware is changed. In this paper, we demonstrate that it is possible to use historical data to reliably predict the number of tuning steps necessary to find a well-performing configuration, and to reduce the size of the tuning space. We evaluate our hypotheses on a number of GPU-accelerated benchmarks written in CUDA and OpenCL.

Název v anglickém jazyce

Exploiting historical data: pruning autotuning spaces and estimating the number of tuning steps

Popis výsledku anglicky

Autotuning, the practice of automatic tuning of code to provide performance portability, has received increased attention in the research community, especially in high performance computing. Ensuring high performance on a variety of hardware usually means modifications to the code, often via different values of a selected set of parameters, such as tiling size, loop unrolling factor or data layout. However, the search space of all possible combinations of these parameters can be enormous. Traditional search methods often fail to find a well-performing set of parameter values quickly. We have found that certain properties of tuning spaces do not vary much when hardware is changed. In this paper, we demonstrate that it is possible to use historical data to reliably predict the number of tuning steps necessary to find a well-performing configuration, and to reduce the size of the tuning space. We evaluate our hypotheses on a number of GPU-accelerated benchmarks written in CUDA and OpenCL.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EF16_013%2F0001802" target="_blank" >EF16_013/0001802: CERIT Scientific Cloud</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Lecture Notes in Computer Science

ISBN

9783030483395

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

13

Strana od-do

295-307

Název nakladatele

Springer, Cham

Místo vydání

Cham, Switzerland

Místo konání akce

Göttingen

Datum konání akce

1. 1. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000557422400001