Achieving high-performance with a sparse direct solver on Intel KNL

Abstract : The need for energy-efficient high-end systems has led hardware vendors to design new types of chips for general purpose computing. However, designing or porting a code tailored for these new types of processing units is often considered as a major hurdle for their broad adoption. In this paper, we consider a modern Intel Xeon Phi processor, namely the Intel Knights Landing (KNL) and a numerical code initially designed for a classical multi-core system. More precisely, we consider the qr_mumps scientific library implementing a sparse direct method on top of the StarPU runtime system. We show that with a portable programming model (task-based programming), a good software support (a robust runtime system coupled with an efficient scheduler) and some well defined hardware and software settings, we are able to transparently run the exact same numerical code. This code not only achieves very high performance (up to 1 TFlop/s) on the KNL but also significantly outperforms a modern Intel Xeon multi-core processor both in terms of time to solution and energy efficiency up to a factor of 2.0.
Complete list of metadatas

Cited literature [25 references]  Display  Hide  Download

https://hal.inria.fr/hal-01473475
Contributor : Emmanuel Agullo <>
Submitted on : Tuesday, February 21, 2017 - 8:49:05 PM
Last modification on : Thursday, October 17, 2019 - 8:54:09 AM
Long-term archiving on : Monday, May 22, 2017 - 4:28:51 PM

File

RR-9035.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01473475, version 1

Citation

Emmanuel Agullo, Alfredo Buttari, Mikko Byckling, Abdou Guermouche, Ian Masliah. Achieving high-performance with a sparse direct solver on Intel KNL. [Research Report] RR-9035, Inria Bordeaux Sud-Ouest; CNRS-IRIT; Intel corporation; Université Bordeaux. 2017, pp.15. ⟨hal-01473475⟩

Share

Metrics

Record views

1079

Files downloads

487