3 Search Results for "Spear, Michael"


Document
Brief Announcement
Brief Announcement: BatchBoost: Universal Batching for Concurrent Data Structures

Authors: Vitaly Aksenov, Michael Anoprenko, Alexander Fedorov, and Michael Spear

Published in: LIPIcs, Volume 281, 37th International Symposium on Distributed Computing (DISC 2023)


Abstract
Batching is a technique that stores multiple keys/values in each node of a data structure. In sequential search data structures, batching reduces latency by reducing the number of cache misses and shortening the chain of pointers to dereference. Applying batching to concurrent data structures is challenging, because it is difficult to maintain the search property and keep contention low in the presence of batching. In this paper, we present a general methodology for leveraging batching in concurrent search data structures, called BatchBoost. BatchBoost builds a search data structure from distinct "data" and "index" layers. The data layer’s purpose is to store a batch of key/value pairs in each of its nodes. The index layer uses an unmodified concurrent search data structure to route operations to a position in the data layer that is "close" to where the corresponding key should exist. The requirements on the index and data layers are low: with minimal effort, we were able to compose three highly scalable concurrent search data structures based on three original data structures as the index layers with a batched version of the Lazy List as the data layer. The resulting BatchBoost data structures provide significant performance improvements over their original counterparts.

Cite as

Vitaly Aksenov, Michael Anoprenko, Alexander Fedorov, and Michael Spear. Brief Announcement: BatchBoost: Universal Batching for Concurrent Data Structures. In 37th International Symposium on Distributed Computing (DISC 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 281, pp. 35:1-35:7, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)


Copy BibTex To Clipboard

@InProceedings{aksenov_et_al:LIPIcs.DISC.2023.35,
  author =	{Aksenov, Vitaly and Anoprenko, Michael and Fedorov, Alexander and Spear, Michael},
  title =	{{Brief Announcement: BatchBoost: Universal Batching for Concurrent Data Structures}},
  booktitle =	{37th International Symposium on Distributed Computing (DISC 2023)},
  pages =	{35:1--35:7},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-301-0},
  ISSN =	{1868-8969},
  year =	{2023},
  volume =	{281},
  editor =	{Oshman, Rotem},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.DISC.2023.35},
  URN =		{urn:nbn:de:0030-drops-191612},
  doi =		{10.4230/LIPIcs.DISC.2023.35},
  annote =	{Keywords: Concurrency, Synchronization, Locality}
}
Document
NUMASK: High Performance Scalable Skip List for NUMA

Authors: Henry Daly, Ahmed Hassan, Michael F. Spear, and Roberto Palmieri

Published in: LIPIcs, Volume 121, 32nd International Symposium on Distributed Computing (DISC 2018)


Abstract
This paper presents NUMASK, a skip list data structure specifically designed to exploit the characteristics of Non-Uniform Memory Access (NUMA) architectures to improve performance. NUMASK deploys an architecture around a concurrent skip list so that all metadata accesses (e.g., traversals of the skip list index levels) read and write memory blocks allocated in the NUMA zone where the thread is executing. To the best of our knowledge, NUMASK is the first NUMA-aware skip list design that goes beyond merely limiting the performance penalties introduced by NUMA, and leverages the NUMA architecture to outperform state-of-the-art concurrent high-performance implementations. We tested NUMASK on a four-socket server. Its performance scales for both read-intensive and write-intensive workloads (tested up to 160 threads). In write-intensive workload, NUMASK shows speedups over competitors in the range of 2x to 16x.

Cite as

Henry Daly, Ahmed Hassan, Michael F. Spear, and Roberto Palmieri. NUMASK: High Performance Scalable Skip List for NUMA. In 32nd International Symposium on Distributed Computing (DISC 2018). Leibniz International Proceedings in Informatics (LIPIcs), Volume 121, pp. 18:1-18:19, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2018)


Copy BibTex To Clipboard

@InProceedings{daly_et_al:LIPIcs.DISC.2018.18,
  author =	{Daly, Henry and Hassan, Ahmed and Spear, Michael F. and Palmieri, Roberto},
  title =	{{NUMASK: High Performance Scalable Skip List for NUMA}},
  booktitle =	{32nd International Symposium on Distributed Computing (DISC 2018)},
  pages =	{18:1--18:19},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-092-7},
  ISSN =	{1868-8969},
  year =	{2018},
  volume =	{121},
  editor =	{Schmid, Ulrich and Widder, Josef},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.DISC.2018.18},
  URN =		{urn:nbn:de:0030-drops-98076},
  doi =		{10.4230/LIPIcs.DISC.2018.18},
  annote =	{Keywords: Skip list, NUMA, Concurrent Data Structure}
}
Document
Extending Transactional Memory with Atomic Deferral

Authors: Tingzhe Zhou, Victor Luchangco, and Michael Spear

Published in: LIPIcs, Volume 95, 21st International Conference on Principles of Distributed Systems (OPODIS 2017)


Abstract
This paper introduces atomic deferral, an extension to TM that allows programmers to move long-running or irrevocable operations out of a transaction while maintaining serializability: the transaction and its de- ferred operation appear to execute atomically from the perspective of other transactions. Thus, program- mers can adapt lock-based programs to exploit TM with relatively little effort and without sacrificing scalability by atomically deferring the problematic operations. We demonstrate this with several use cases for atomic deferral, as well as an in-depth analysis of its use on the PARSEC dedup benchmark, where we show that atomic deferral enables TM to be competitive with well-designed lock-based code.

Cite as

Tingzhe Zhou, Victor Luchangco, and Michael Spear. Extending Transactional Memory with Atomic Deferral. In 21st International Conference on Principles of Distributed Systems (OPODIS 2017). Leibniz International Proceedings in Informatics (LIPIcs), Volume 95, pp. 7:1-7:17, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2018)


Copy BibTex To Clipboard

@InProceedings{zhou_et_al:LIPIcs.OPODIS.2017.7,
  author =	{Zhou, Tingzhe and Luchangco, Victor and Spear, Michael},
  title =	{{Extending Transactional Memory with Atomic Deferral}},
  booktitle =	{21st International Conference on Principles of Distributed Systems (OPODIS 2017)},
  pages =	{7:1--7:17},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-061-3},
  ISSN =	{1868-8969},
  year =	{2018},
  volume =	{95},
  editor =	{Aspnes, James and Bessani, Alysson and Felber, Pascal and Leit\~{a}o, Jo\~{a}o},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.OPODIS.2017.7},
  URN =		{urn:nbn:de:0030-drops-86275},
  doi =		{10.4230/LIPIcs.OPODIS.2017.7},
  annote =	{Keywords: Transactional Memory, Concurrency, Synchronization, I/O}
}
  • Refine by Author
  • 2 Spear, Michael
  • 1 Aksenov, Vitaly
  • 1 Anoprenko, Michael
  • 1 Daly, Henry
  • 1 Fedorov, Alexander
  • Show More...

  • Refine by Classification
  • 1 Computing methodologies → Concurrent algorithms
  • 1 Information systems → Data structures

  • Refine by Keyword
  • 2 Concurrency
  • 2 Synchronization
  • 1 Concurrent Data Structure
  • 1 I/O
  • 1 Locality
  • Show More...

  • Refine by Type
  • 3 document

  • Refine by Publication Year
  • 2 2018
  • 1 2023

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