Search Results

Documents authored by Kharal, Rosina F.


Document
Performance Anomalies in Concurrent Data Structure Microbenchmarks

Authors: Rosina F. Kharal and Trevor Brown

Published in: LIPIcs, Volume 253, 26th International Conference on Principles of Distributed Systems (OPODIS 2022)


Abstract
Recent decades have witnessed a surge in the development of concurrent data structures with an increasing interest in data structures implementing concurrent sets (CSets). Microbenchmarking tools are frequently utilized to evaluate and compare the performance differences across concurrent data structures. The underlying structure and design of the microbenchmarks themselves can play a hidden but influential role in performance results. However, the impact of microbenchmark design has not been well investigated. In this work, we illustrate instances where concurrent data structure performance results reported by a microbenchmark can vary 10-100x depending on the microbenchmark implementation details. We investigate factors leading to performance variance across three popular microbenchmarks and outline cases in which flawed microbenchmark design can lead to an inversion of performance results between two concurrent data structure implementations. We further derive a set of recommendations for best practices in the design and usage of concurrent data structure microbenchmarks and explore advanced features in the Setbench microbenchmark.

Cite as

Rosina F. Kharal and Trevor Brown. Performance Anomalies in Concurrent Data Structure Microbenchmarks. In 26th International Conference on Principles of Distributed Systems (OPODIS 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 253, pp. 7:1-7:24, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)


Copy BibTex To Clipboard

@InProceedings{kharal_et_al:LIPIcs.OPODIS.2022.7,
  author =	{Kharal, Rosina F. and Brown, Trevor},
  title =	{{Performance Anomalies in Concurrent Data Structure Microbenchmarks}},
  booktitle =	{26th International Conference on Principles of Distributed Systems (OPODIS 2022)},
  pages =	{7:1--7:24},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-265-5},
  ISSN =	{1868-8969},
  year =	{2023},
  volume =	{253},
  editor =	{Hillel, Eshcar and Palmieri, Roberto and Rivi\`{e}re, Etienne},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.OPODIS.2022.7},
  URN =		{urn:nbn:de:0030-drops-176273},
  doi =		{10.4230/LIPIcs.OPODIS.2022.7},
  annote =	{Keywords: concurrent microbenchmarks, concurrent data structures, concurrent performance evaluation, PRNGs, parallel computing}
}
Document
Brief Announcement
Brief Announcement: Performance Anomalies in Concurrent Data Structure Microbenchmarks

Authors: Rosina F. Kharal and Trevor Brown

Published in: LIPIcs, Volume 246, 36th International Symposium on Distributed Computing (DISC 2022)


Abstract
Recent decades have witnessed a surge in the development of concurrent data structures with an increasing interest in data structures implementing concurrent sets (CSets). Microbenchmarking tools are frequently utilized to evaluate and compare performance differences across concurrent data structures. The underlying structure and design of the microbenchmarks themselves can play a hidden but influential role in performance results. However, the impact of microbenchmark design has not been well investigated. In this work, we illustrate instances where concurrent data structure performance results reported by a microbenchmark can vary 10-100x depending on the microbenchmark implementation details. We investigate factors leading to performance variance across three popular microbenchmarks and outline cases in which flawed microbenchmark design can lead to an inversion of performance results between two concurrent data structure implementations. We further derive a prescriptive approach for best practices in the design and utilization of concurrent data structure microbenchmarks.

Cite as

Rosina F. Kharal and Trevor Brown. Brief Announcement: Performance Anomalies in Concurrent Data Structure Microbenchmarks. In 36th International Symposium on Distributed Computing (DISC 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 246, pp. 45:1-45:3, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)


Copy BibTex To Clipboard

@InProceedings{kharal_et_al:LIPIcs.DISC.2022.45,
  author =	{Kharal, Rosina F. and Brown, Trevor},
  title =	{{Brief Announcement: Performance Anomalies in Concurrent Data Structure Microbenchmarks}},
  booktitle =	{36th International Symposium on Distributed Computing (DISC 2022)},
  pages =	{45:1--45:3},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-255-6},
  ISSN =	{1868-8969},
  year =	{2022},
  volume =	{246},
  editor =	{Scheideler, Christian},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.DISC.2022.45},
  URN =		{urn:nbn:de:0030-drops-172363},
  doi =		{10.4230/LIPIcs.DISC.2022.45},
  annote =	{Keywords: concurrent microbenchmarks, concurrent data structures, high performance simulations, PRNGs}
}
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail