skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: LUsim: A Framework for Simulation-Based Performance Modelingand Prediction of Parallel Sparse LU Factorization

Conference ·
OSTI ID:928005

Sparse parallel factorization is among the most complicated and irregular algorithms to analyze and optimize. Performance depends both on system characteristics such as the floating point rate, the memory hierarchy, and the interconnect performance, as well as input matrix characteristics such as such as the number and location of nonzeros. We present LUsim, a simulation framework for modeling the performance of sparse LU factorization. Our framework uses micro-benchmarks to calibrate the parameters of machine characteristics and additional tools to facilitate real-time performance modeling. We are using LUsim to analyze an existing parallel sparse LU factorization code, and to explore a latency tolerant variant. We developed and validated a model of the factorization in SuperLU_DIST, then we modeled and implemented a new variant of slud, replacing a blocking collective communication phase with a non-blocking asynchronous point-to-point one. Our strategy realized a mean improvement of 11percent over a suite of test matrices.

Research Organization:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Organization:
Computational Research Division
DOE Contract Number:
DE-AC02-05CH11231
OSTI ID:
928005
Report Number(s):
LBNL-196E; TRN: US200816%%714
Resource Relation:
Conference: SC2008, Austin, TX, Nov. 15-21, 2008
Country of Publication:
United States
Language:
English