Toward Automated Detection of Portability Bugs in Kokkos Parallel Programs

Vivek Kale; Hanru Yan; Shyamali Mukherjee; Jackson Mayo; Keita Teranishi; Richard Rutledge; Alessandro Orso

doi:10.1109/SCW63240.2024.00029

Toward Automated Detection of Portability Bugs in Kokkos Parallel Programs

Vivek Kale
, Hanru Yan
, Shyamali Mukherjee
, Jackson Mayo
, Keita Teranishi
, Richard Rutledge
, Alessandro Orso

Programming Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Performance-portable programming frameworks provide abstractions for parallel execution to allow easily porting an application to multiple backend programming models, such as CUDA, HIP, and OpenMP. However, programs may still have portability bugs that manifest only on specific backends. Traditional testing is ineffective in discovering these bugs, as it would require concrete execution on all supported hardware configurations for a potentially infinite set of inputs. To mitigate this issue, we focused on a specific programming framework, Kokkos, and identified several categories of common portability bugs. We then developed Klokkos, a static analysis approach based on symbolic execution that can run on commodity hardware, before execution on supercomputers. As a proof-of-concept, we ran Klokkos on examples encoding the identified bugs. Our results show that Klokkos is effective, efficient, and precise: it detected all the considered bugs, quickly, and without any false positives. Although preliminary, our results motivate further research and development in this direction.

Original language	English
Title of host publication	Proceedings of SC 2024-W
Subtitle of host publication	Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	180-188
Number of pages	9
ISBN (Electronic)	9798350355543
DOIs	https://doi.org/10.1109/SCW63240.2024.00029
State	Published - 2024
Event	2024 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC Workshops 2024 - Atlanta, United States Duration: Nov 17 2024 → Nov 22 2024

Publication series

Name	Proceedings of SC 2024-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis

Conference

Conference	2024 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC Workshops 2024
Country/Territory	United States
City	Atlanta
Period	11/17/24 → 11/22/24

Funding

This material is based upon work supported by the U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research under Award Number DEFOA- 0002460: X-Stack: Programming Environments for Scientific Computing. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy's National Nuclear Security Administration under contract DENA0003525. This paper (SAND2024-12483C) describes objective technical results and analysis. Any subjective views or opinions that might be expressed in the paper do not necessarily represent the views of the U.S. Department of Energy or the United States Government. This manuscript has been authored by UT-Battelle LLC under contract DE-AC05-00OR22725 with the US Department of Energy (DOE).

Keywords

bug detection
c++
data race
kokkos
mock testing
parallel programming
symbolic execution

Access to Document

10.1109/SCW63240.2024.00029

Cite this

Kale, V., Yan, H., Mukherjee, S., Mayo, J., Teranishi, K., Rutledge, R., & Orso, A. (2024). Toward Automated Detection of Portability Bugs in Kokkos Parallel Programs. In Proceedings of SC 2024-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis (pp. 180-188). (Proceedings of SC 2024-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SCW63240.2024.00029

Kale, Vivek ; Yan, Hanru ; Mukherjee, Shyamali et al. / Toward Automated Detection of Portability Bugs in Kokkos Parallel Programs. Proceedings of SC 2024-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2024. pp. 180-188 (Proceedings of SC 2024-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis).

@inproceedings{d444cc6c5f9d449f90aa0efcf77b9263,

title = "Toward Automated Detection of Portability Bugs in Kokkos Parallel Programs",

abstract = "Performance-portable programming frameworks provide abstractions for parallel execution to allow easily porting an application to multiple backend programming models, such as CUDA, HIP, and OpenMP. However, programs may still have portability bugs that manifest only on specific backends. Traditional testing is ineffective in discovering these bugs, as it would require concrete execution on all supported hardware configurations for a potentially infinite set of inputs. To mitigate this issue, we focused on a specific programming framework, Kokkos, and identified several categories of common portability bugs. We then developed Klokkos, a static analysis approach based on symbolic execution that can run on commodity hardware, before execution on supercomputers. As a proof-of-concept, we ran Klokkos on examples encoding the identified bugs. Our results show that Klokkos is effective, efficient, and precise: it detected all the considered bugs, quickly, and without any false positives. Although preliminary, our results motivate further research and development in this direction.",

keywords = "bug detection, c++, data race, kokkos, mock testing, parallel programming, symbolic execution",

author = "Vivek Kale and Hanru Yan and Shyamali Mukherjee and Jackson Mayo and Keita Teranishi and Richard Rutledge and Alessandro Orso",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 2024 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC Workshops 2024 ; Conference date: 17-11-2024 Through 22-11-2024",

year = "2024",

doi = "10.1109/SCW63240.2024.00029",

language = "English",

series = "Proceedings of SC 2024-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "180--188",

booktitle = "Proceedings of SC 2024-W",

}

Kale, V, Yan, H, Mukherjee, S, Mayo, J, Teranishi, K, Rutledge, R & Orso, A 2024, Toward Automated Detection of Portability Bugs in Kokkos Parallel Programs. in Proceedings of SC 2024-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis. Proceedings of SC 2024-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, Institute of Electrical and Electronics Engineers Inc., pp. 180-188, 2024 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC Workshops 2024, Atlanta, United States, 11/17/24. https://doi.org/10.1109/SCW63240.2024.00029

Toward Automated Detection of Portability Bugs in Kokkos Parallel Programs. / Kale, Vivek; Yan, Hanru; Mukherjee, Shyamali et al.
Proceedings of SC 2024-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2024. p. 180-188 (Proceedings of SC 2024-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Toward Automated Detection of Portability Bugs in Kokkos Parallel Programs

AU - Kale, Vivek

AU - Yan, Hanru

AU - Mukherjee, Shyamali

AU - Mayo, Jackson

AU - Teranishi, Keita

AU - Rutledge, Richard

AU - Orso, Alessandro

PY - 2024

Y1 - 2024

N2 - Performance-portable programming frameworks provide abstractions for parallel execution to allow easily porting an application to multiple backend programming models, such as CUDA, HIP, and OpenMP. However, programs may still have portability bugs that manifest only on specific backends. Traditional testing is ineffective in discovering these bugs, as it would require concrete execution on all supported hardware configurations for a potentially infinite set of inputs. To mitigate this issue, we focused on a specific programming framework, Kokkos, and identified several categories of common portability bugs. We then developed Klokkos, a static analysis approach based on symbolic execution that can run on commodity hardware, before execution on supercomputers. As a proof-of-concept, we ran Klokkos on examples encoding the identified bugs. Our results show that Klokkos is effective, efficient, and precise: it detected all the considered bugs, quickly, and without any false positives. Although preliminary, our results motivate further research and development in this direction.

AB - Performance-portable programming frameworks provide abstractions for parallel execution to allow easily porting an application to multiple backend programming models, such as CUDA, HIP, and OpenMP. However, programs may still have portability bugs that manifest only on specific backends. Traditional testing is ineffective in discovering these bugs, as it would require concrete execution on all supported hardware configurations for a potentially infinite set of inputs. To mitigate this issue, we focused on a specific programming framework, Kokkos, and identified several categories of common portability bugs. We then developed Klokkos, a static analysis approach based on symbolic execution that can run on commodity hardware, before execution on supercomputers. As a proof-of-concept, we ran Klokkos on examples encoding the identified bugs. Our results show that Klokkos is effective, efficient, and precise: it detected all the considered bugs, quickly, and without any false positives. Although preliminary, our results motivate further research and development in this direction.

KW - bug detection

KW - c++

KW - data race

KW - kokkos

KW - mock testing

KW - parallel programming

KW - symbolic execution

UR - https://www.scopus.com/pages/publications/85217161610

U2 - 10.1109/SCW63240.2024.00029

DO - 10.1109/SCW63240.2024.00029

M3 - Conference contribution

AN - SCOPUS:85217161610

T3 - Proceedings of SC 2024-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis

SP - 180

EP - 188

BT - Proceedings of SC 2024-W

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2024 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC Workshops 2024

Y2 - 17 November 2024 through 22 November 2024

ER -

Kale V, Yan H, Mukherjee S, Mayo J, Teranishi K, Rutledge R et al. Toward Automated Detection of Portability Bugs in Kokkos Parallel Programs. In Proceedings of SC 2024-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc. 2024. p. 180-188. (Proceedings of SC 2024-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis). doi: 10.1109/SCW63240.2024.00029

Toward Automated Detection of Portability Bugs in Kokkos Parallel Programs

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this