Implementing Multifrontal Sparse Solvers for Multicore Architectures with Sequential Task Flow Runtime Systems

• Published in: ACM transactions on mathematical software Vol. 43; no. 2; pp. 1 - 22
• Main Authors: Agullo, Emmanuel, Buttari, Alfredo, Guermouche, Abdou, Lopez, Florent
• Format: Journal Article
• Language: English
• Published: Association for Computing Machinery 01.09.2016
• Subjects: Computer Science; Consumption; Distributed, Parallel, and Cluster Computing; Mathematical models; Programming; Run time (computers); Solvers; Task complexity; Task scheduling; Tasks; Categories and Subject Descriptors: D13 [Programming Techniques]: Concurrent Programming; Performance Additional Key Words and Phrases: Sparse direct solvers; communication-avoiding; multicores; runtime systems; G13 [Numerical Analysis]: Numerical Linear Algebra; G4 [Mathematical Software] General Terms: Algorithms; memory-aware
• ISSN: 0098-3500; 1557-7295; 1557-7295
• DOI: 10.1145/2898348

To face the advent of multicore processors and the ever increasing complexity of hardware architectures, programming models based on DAG parallelism regained popularity in the high performance, scientific computing community. Modern runtime systems offer a programming interface that complies with this paradigm and powerful engines for scheduling the tasks into which the application is decomposed. These tools have already proved their effectiveness on a number of dense linear algebra applications. This article evaluates the usability and effectiveness of runtime systems based on the Sequential Task Flow model for complex applications, namely, sparse matrix multifrontal factorizations that feature extremely irregular workloads, with tasks of different granularities and characteristics and with a variable memory consumption. Most importantly, it shows how this parallel programming model eases the development of complex features that benefit the performance of sparse, direct solvers as well as their memory consumption. We illustrate our discussion with the multifrontal QR factorization running on top of the StarPU runtime system.