Symbolic mapping and allocation for the Cholesky factorization on NUMA machines-Reference-Cited by-同舟云学术

Symbolic mapping and allocation for the Cholesky factorization on NUMA machines

Published:2013-07-01 Issue:3 Volume:27 Page:283-290
ISSN:1094-3420
Container-title:The International Journal of High Performance Computing Applications
language:en
Short-container-title:The International Journal of High Performance Computing Applications

Author:

Jeannot Emmanuel¹

Affiliation:

1. Inria Bordeaux Sud-Ouest, LaBRI, France

Abstract

We discuss some performance issues of the tiled Cholesky factorization on non-uniform memory access-time (NUMA) shared memory machines. We show how to optimize thread and data placement in order to improve performance. The final result is 50\% faster than PLASMA and 75\% faster than MKL.

Publisher

SAGE Publications

Subject

Hardware and Architecture,Theoretical Computer Science,Software

Link

http://journals.sagepub.com/doi/pdf/10.1177/0734904113492410

Reference9 articles.

1. Agullo E, Dongarra J, Hadri B, (2010) PLASMA users guide. Technical Report, Innovative Computing Laboratory, University of Tennessee , TN.

2. AUTOMATIC TASK GRAPH GENERATION TECHNIQUES

3. A Simple Algorithm for the Generation of Efficient Loop Structures

4. SLC: Symbolic scheduling for executing parameterized task graphs on multiprocessors

Cited by 4 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. READYS: A Reinforcement Learning Based Strategy for Heterogeneous Dynamic Scheduling;2021 IEEE International Conference on Cluster Computing (CLUSTER);2021-09

2. Geometric deep reinforcement learning for dynamic DAG scheduling;2020 IEEE Symposium Series on Computational Intelligence (SSCI);2020-12-01

3. Tuning linear algebra for energy efficiency on multicore machines by adapting the ATLAS library;Future Generation Computer Systems;2018-05

4. Automatic, Abstracted and Portable Topology-Aware Thread Placement;2017 IEEE International Conference on Cluster Computing (CLUSTER);2017-09