SLATE: Design of a Modern Distributed and Accelerated Linear Algebra Library

The SLATE (Software for Linear Algebra Targeting Exascale) library is being developed to provide fundamental dense linear algebra capabilities for current and upcoming distributed high-performance systems, both accelerated CPU-GPU based and CPU based. SLATE will provide coverage of existing ScaLAPAC...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:SC19: International Conference for High Performance Computing, Networking, Storage and Analysis s. 1 - 18
Hlavní autoři: Gates, Mark, Kurzak, Jakub, Charara, Ali, YarKhan, Asim, Dongarra, Jack
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: ACM 17.11.2019
Témata:
C++ languages
dense linear algebra
distributed computing
Eigenvalues and eigenfunctions
GPU computing
Libraries
Linear systems
Parallel processing
Performance evaluation
Processor scheduling
Scheduling
Software
Vectors
ISSN:2167-4337
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The SLATE (Software for Linear Algebra Targeting Exascale) library is being developed to provide fundamental dense linear algebra capabilities for current and upcoming distributed high-performance systems, both accelerated CPU-GPU based and CPU based. SLATE will provide coverage of existing ScaLAPACK functionality, including the parallel BLAS; linear systems using LU and Cholesky; least squares problems using QR; and eigenvalue and singular value problems. In this respect, it will serve as a replacement for Sea-LAPACK, which after two decades of operation, cannot adequately be retrofitted for modern accelerated architectures. SLATE uses modern techniques such as communication-avoiding algorithms, lookahead panels to overlap communication and computation, and task-based scheduling, along with a modern C++ framework. Here we present the design of SLATE and initial reports of several of its components.
ISSN:2167-4337
DOI:10.1145/3295500.3356223