Searching CUDA code autotuning spaces with hardware performance
counters: data from benchmarks running on various GPU
architectures

J 2021

Searching CUDA code autotuning spaces with hardware performance counters: data from benchmarks running on various GPU architectures

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

Basic information

Original name

Searching CUDA code autotuning spaces with hardware performance counters: data from benchmarks running on various GPU architectures

Authors

HOZZOVÁ, Jana (703 Slovakia, belonging to the institution), Jiří FILIPOVIČ (203 Czech Republic, guarantor, 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

Data in Brief, Elsevier, 2021, 2352-3409

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

RIV identification code

RIV/00216224:14610/21:00123013

Organization unit

Institute of Computer Science

DOI

http://dx.doi.org/10.1016/j.dib.2021.107631

UT WoS

000725561900057

Keywords in English

Auto-tuning; Tuning spaces; Performance counters; CUDA

Abstract

V originále

We have developed several autotuning benchmarks in CUDA that take into account performance-relevant source-code parameters and reach near peak-performance on various GPU architectures. We have used them during the development and evaluation of a search method for tuning space proposed in [1]. With our framework Kernel Tuning Toolkit, freely available at Github, we measured computation times and hardware performance counters on several GPUs for the complete tuning spaces of five benchmarks. These data, which we provide here, might benefit research of search algorithms for the tuning spaces of GPU codes or research of relation between applied code optimization, hardware performance counters, and GPU kernels’ performance. Moreover, we describe the scripts we used for robust evaluation of our searcher and comparison to others in detail. In particular, the script that simulates the tuning, i.e., replaces time-demanding compiling and executing the tuned kernels with a quick reading of the computation time from our measured data, makes it possible to inspect the convergence of tuning search over a large number of experiments. These scripts, freely available with our other codes, make it easier to experiment with search algorithms and compare them in a robust and reproducible way. During our research, we generated models for predicting values of performance counters from values of tuning parameters of our benchmarks. Here, we provide the models themselves and describe the scripts we implemented for their training. These data might benefit researchers who want to reproduce or build on our research.

Links

EF16_013/0001802, research and development project

Name: CERIT Scientific Cloud

LM2018140, research and development project

Name: e-Infrastruktura CZ (Acronym: e-INFRA CZ)

Investor: Ministry of Education, Youth and Sports of the CR

Citovat

HOZZOVÁ, Jana, Jiří FILIPOVIČ, Amin NEZARAT, Jaroslav OĽHA and Filip PETROVIČ. Searching CUDA code autotuning spaces with hardware performance counters: data from benchmarks running on various GPU architectures. Data in Brief. Elsevier, 2021, vol. 39, December, p. 1-12. ISSN 2352-3409. Available from: https://dx.doi.org/10.1016/j.dib.2021.107631.

@article{1805266,
   author = {Hozzová, Jana and Filipovič, Jiří and Nezarat, Amin and Oľha, Jaroslav and Petrovič, Filip},
   article_number = {December},
   doi = {http://dx.doi.org/10.1016/j.dib.2021.107631},
   keywords = {Auto-tuning; Tuning spaces; Performance counters; CUDA},
   language = {eng},
   issn = {2352-3409},
   journal = {Data in Brief},
   title = {Searching CUDA code autotuning spaces with hardware performance counters: data from benchmarks running on various GPU architectures},
   url = {https://www.sciencedirect.com/science/article/pii/S2352340921009069},
   volume = {39},
   year = {2021}
}

TY  - JOUR
ID  - 1805266
AU  - Hozzová, Jana - Filipovič, Jiří - Nezarat, Amin - Oľha, Jaroslav - Petrovič, Filip
PY  - 2021
TI  - Searching CUDA code autotuning spaces with hardware performance counters: data from benchmarks running on various GPU architectures
JF  - Data in Brief
VL  - 39
IS  - December
SP  - 1-12
EP  - 1-12
PB  - Elsevier
SN  - 23523409
KW  - Auto-tuning
KW  - Tuning spaces
KW  - Performance counters
KW  - CUDA
UR  - https://www.sciencedirect.com/science/article/pii/S2352340921009069
N2  - We have developed several autotuning benchmarks in CUDA that take into account performance-relevant source-code parameters and reach near peak-performance on various GPU architectures. We have used them during the development and evaluation of a search method for tuning space proposed in [1]. With our framework Kernel Tuning Toolkit, freely available at Github, we measured computation times and hardware performance counters on several GPUs for the complete tuning spaces of five benchmarks. These data, which we provide here, might benefit research of search algorithms for the tuning spaces of GPU codes or research of relation between applied code optimization, hardware performance counters, and GPU kernels’ performance. Moreover, we describe the scripts we used for robust evaluation of our searcher and comparison to others in detail. In particular, the script that simulates the tuning, i.e., replaces time-demanding compiling and executing the tuned kernels with a quick reading of the computation time from our measured data, makes it possible to inspect the convergence of tuning search over a large number of experiments. These scripts, freely available with our other codes, make it easier to experiment with search algorithms and compare them in a robust and reproducible way. During our research, we generated models for predicting values of performance counters from values of tuning parameters of our benchmarks. Here, we provide the models themselves and describe the scripts we implemented for their training. These data might benefit researchers who want to reproduce or build on our research.
ER  -

HOZZOVÁ, Jana, Jiří FILIPOVIČ, Amin NEZARAT, Jaroslav OĽHA and Filip PETROVIČ. Searching CUDA code autotuning spaces with hardware performance counters: data from benchmarks running on various GPU architectures. \textit{Data in Brief}. Elsevier, 2021, vol.~39, December, p.~1-12. ISSN~2352-3409. Available from: https://dx.doi.org/10.1016/j.dib.2021.107631.

Detailed Information on Publication Record