https://github.com/sss-lehigh/numask

NUMASK is skip list designed to exploit the characteristics of Non-Uniform Memory Access (NUMA) architectures to improve performance
https://github.com/sss-lehigh/numask

Last synced: 3 months ago
JSON representation

NUMASK is skip list designed to exploit the characteristics of Non-Uniform Memory Access (NUMA) architectures to improve performance

• Host: GitHub
• URL: https://github.com/sss-lehigh/numask
• Owner: sss-lehigh
• Created: 2020-08-18T14:52:25.000Z (about 4 years ago)
• Default Branch: master
• Last Pushed: 2020-08-21T20:38:21.000Z (about 4 years ago)
• Last Synced: 2024-05-03T06:23:13.388Z (6 months ago)
• Language: C
• Size: 60.5 KB
• Stars: 4
• Watchers: 1
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-numa - NUMASK - A skip list designed to exploit the characteristics of NUMA architectures to improve performance (NUMA-aware memory placement and scheduling)

README

        
# numask

NUMASK is skip list designed to exploit the characteristics of Non-Uniform Memory Access (NUMA) architectures to improve performance.

The design of numask is detaled in the paper:

- H. Daly, A. Hassan, M. Spear, R. Palmieri. NUMASK: High Performance Scalable Skip List for NUMA. In DISC, 2018.

Numask is included in synchrobench. This repository allows for the compilation and use of a static and shared version of numask as it is implemented in synchrobench.

Compilation using CMake has currently been tested with CMake version 3.17 although it should work for CMake versions as early as 3.0. It has been tested using clang++ 9 and g++ 8. This implementation of numask requires libnuma, POSIX thread support, and unistd.h.