Linear Systems Solvers for Distributed-Memory Machines with GPU Accelerators
| Autor: | Jakub Kurzak, Jack Dongarra, Mark Gates, Asim YarKhan, Ali Charara, Ichitaro Yamazaki |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
020203 distributed computing
Computer science ScaLAPACK Linear system 010103 numerical & computational mathematics 02 engineering and technology Parallel computing 01 natural sciences LU decomposition law.invention law Linear algebra 0202 electrical engineering electronic engineering information engineering Distributed memory 0101 mathematics Pivot element Cholesky decomposition |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783030293994 Euro-Par |
| Popis: | This work presents two implementations of linear solvers for distributed-memory machines with GPU accelerators—one based on the Cholesky factorization and one based on the LU factorization with partial pivoting. The routines are developed as part of the Software for Linear Algebra Targeting Exascale (SLATE) package, which represents a sharp departure from the traditional conventions established by legacy packages, such as LAPACK and ScaLAPACK. The article lays out the principles of the new approach, discusses the implementation details, and presents the performance results. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|