Abstractions for C++ code optimizations in parallel high-performance applications

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10483259" target="_blank" >RIV/00216208:11320/24:10483259 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=rRwBU-W6J4" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=rRwBU-W6J4</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.parco.2024.103096" target="_blank" >10.1016/j.parco.2024.103096</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Abstractions for C++ code optimizations in parallel high-performance applications

Popis výsledku v původním jazyce

Many computational problems consider memory throughput a performance bottleneck, especially in the domain of parallel computing. Software needs to be attuned to hardware features like cache architectures or concurrent memory banks to reach a decent level of performance efficiency. This can be achieved by selecting the right memory layouts for data structures or changing the order of data structure traversal. In this work, we present an abstraction for traversing a set of regular data structures (e.g., multidimensional arrays) that allows the design of traversal-agnostic algorithms. Such algorithms can easily optimize for memory performance and employ semi-automated parallelization or autotuning without altering their internal code. We also add an abstraction for autotuning that allows defining tuning parameters in one place and removes boilerplate code. The proposed solution was implemented as an extension of the Noarr library that simplifies a layout-agnostic design of regular data structures. It is implemented entirely using C++ template meta-programming without any nonstandard dependencies, so it is fully compatible with existing compilers, including CUDA NVCC or Intel DPC++. We evaluate the performance and expressiveness of our approach on the Polybench-C benchmarks.

Název v anglickém jazyce

Abstractions for C++ code optimizations in parallel high-performance applications

Popis výsledku anglicky

Many computational problems consider memory throughput a performance bottleneck, especially in the domain of parallel computing. Software needs to be attuned to hardware features like cache architectures or concurrent memory banks to reach a decent level of performance efficiency. This can be achieved by selecting the right memory layouts for data structures or changing the order of data structure traversal. In this work, we present an abstraction for traversing a set of regular data structures (e.g., multidimensional arrays) that allows the design of traversal-agnostic algorithms. Such algorithms can easily optimize for memory performance and employ semi-automated parallelization or autotuning without altering their internal code. We also add an abstraction for autotuning that allows defining tuning parameters in one place and removes boilerplate code. The proposed solution was implemented as an extension of the Noarr library that simplifies a layout-agnostic design of regular data structures. It is implemented entirely using C++ template meta-programming without any nonstandard dependencies, so it is fully compatible with existing compilers, including CUDA NVCC or Intel DPC++. We evaluate the performance and expressiveness of our approach on the Polybench-C benchmarks.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

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

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název periodika

Parallel Computing

ISSN

0167-8191

e-ISSN

1872-7336

Svazek periodika

121

Číslo periodika v rámci svazku

September 2024

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

13

Strana od-do

103096

Kód UT WoS článku

001299241000001

EID výsledku v databázi Scopus

2-s2.0-85201453256