Using hardware performance counters to speed up autotuning
convergence on GPUs

J 2022

Using hardware performance counters to speed up autotuning convergence on GPUs

FILIPOVIČ, Jiří, Jana HOZZOVÁ, Amin NEZARAT, Jaroslav OĽHA, Filip PETROVIČ et. al.

Basic information

Original name

Using hardware performance counters to speed up autotuning convergence on GPUs

Authors

FILIPOVIČ, Jiří (203 Czech Republic, guarantor, belonging to the institution), Jana HOZZOVÁ (703 Slovakia, belonging to the institution), Amin NEZARAT (364 Islamic Republic of Iran, belonging to the institution), Jaroslav OĽHA (703 Slovakia, belonging to the institution) and Filip PETROVIČ (703 Slovakia, belonging to the institution)

Edition

Journal of Parallel and Distributed Computing, Elsevier, 2022, 0743-7315

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Netherlands

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 3.800

RIV identification code

RIV/00216224:14610/22:00125022

Organization unit

Institute of Computer Science

DOI

http://dx.doi.org/10.1016/j.jpdc.2021.10.003

UT WoS

000711621300002

Keywords in English

Auto-tuning; Search method; Performance counters; CUDA

Abstract

V originále

Nowadays, GPU accelerators are commonly used to speed up general-purpose computing tasks on a variety of hardware. However, due to the diversity of GPU architectures and processed data, optimization of codes for a particular type of hardware and specific data characteristics can be extremely challenging. The autotuning of performance-relevant source-code parameters allows for automatic optimization of applications and keeps their performance portable. Although the autotuning process typically results in code speed-up, searching the tuning space can bring unacceptable overhead if (i) the tuning space is vast and full of poorly-performing implementations, or (ii) the autotuning process has to be repeated frequently because of changes in processed data or migration to different hardware. In this paper, we introduce a novel method for searching generic tuning spaces. The tuning spaces can contain tuning parameters changing any user-defined property of the source code. The method takes advantage of collecting hardware performance counters (also known as profiling counters) during empirical tuning. Those counters are used to navigate the searching process towards faster implementations. The method requires the tuning space to be sampled on any GPU. It builds a problem-specific model, which can be used during autotuning on various, even previously unseen inputs or GPUs. Using a set of five benchmarks, we experimentally demonstrate that our method can speed up autotuning when an application needs to be ported to different hardware or when it needs to process data with different characteristics. We also compared our method to state of the art and show that our method is superior in terms of the number of searching steps and typically outperforms other searches in terms of convergence time.

Links

EF16_013/0001802, research and development project

Name: CERIT Scientific Cloud

MUNI/A/1145/2021, interní kód MU

Name: Rozsáhlé výpočetní systémy: modely, aplikace a verifikace XI. (Acronym: SV-FI MAV XI.)

Investor: Masaryk University

Citovat

FILIPOVIČ, Jiří, Jana HOZZOVÁ, Amin NEZARAT, Jaroslav OĽHA and Filip PETROVIČ. Using hardware performance counters to speed up autotuning convergence on GPUs. Journal of Parallel and Distributed Computing. Elsevier, 2022, vol. 160, February, p. 16-35. ISSN 0743-7315. Available from: https://dx.doi.org/10.1016/j.jpdc.2021.10.003.

@article{1799520,
   author = {Filipovič, Jiří and Hozzová, Jana and Nezarat, Amin and Oľha, Jaroslav and Petrovič, Filip},
   article_number = {February},
   doi = {http://dx.doi.org/10.1016/j.jpdc.2021.10.003},
   keywords = {Auto-tuning; Search method; Performance counters; CUDA},
   language = {eng},
   issn = {0743-7315},
   journal = {Journal of Parallel and Distributed Computing},
   title = {Using hardware performance counters to speed up autotuning convergence on GPUs},
   url = {https://www.sciencedirect.com/science/article/pii/S0743731521001945?via%3Dihub},
   volume = {160},
   year = {2022}
}

TY  - JOUR
ID  - 1799520
AU  - Filipovič, Jiří - Hozzová, Jana - Nezarat, Amin - Oľha, Jaroslav - Petrovič, Filip
PY  - 2022
TI  - Using hardware performance counters to speed up autotuning convergence on GPUs
JF  - Journal of Parallel and Distributed Computing
VL  - 160
IS  - February
SP  - 16-35
EP  - 16-35
PB  - Elsevier
SN  - 07437315
KW  - Auto-tuning
KW  - Search method
KW  - Performance counters
KW  - CUDA
UR  - https://www.sciencedirect.com/science/article/pii/S0743731521001945?via%3Dihub
N2  - Nowadays, GPU accelerators are commonly used to speed up general-purpose computing tasks on a variety of hardware. However, due to the diversity of GPU architectures and processed data, optimization of codes for a particular type of hardware and specific data characteristics can be extremely challenging. The autotuning of performance-relevant source-code parameters allows for automatic optimization of applications and keeps their performance portable. Although the autotuning process typically results in code speed-up, searching the tuning space can bring unacceptable overhead if (i) the tuning space is vast and full of poorly-performing implementations, or (ii) the autotuning process has to be repeated frequently because of changes in processed data or migration to different hardware. In this paper, we introduce a novel method for searching generic tuning spaces. The tuning spaces can contain tuning parameters changing any user-defined property of the source code. The method takes advantage of collecting hardware performance counters (also known as profiling counters) during empirical tuning. Those counters are used to navigate the searching process towards faster implementations. The method requires the tuning space to be sampled on any GPU. It builds a problem-specific model, which can be used during autotuning on various, even previously unseen inputs or GPUs. Using a set of five benchmarks, we experimentally demonstrate that our method can speed up autotuning when an application needs to be ported to different hardware or when it needs to process data with different characteristics. We also compared our method to state of the art and show that our method is superior in terms of the number of searching steps and typically outperforms other searches in terms of convergence time.
ER  -

FILIPOVIČ, Jiří, Jana HOZZOVÁ, Amin NEZARAT, Jaroslav OĽHA and Filip PETROVIČ. Using hardware performance counters to speed up autotuning convergence on GPUs. \textit{Journal of Parallel and Distributed Computing}. Elsevier, 2022, vol.~160, February, p.~16-35. ISSN~0743-7315. Available from: https://dx.doi.org/10.1016/j.jpdc.2021.10.003.

Detailed Information on Publication Record