Batched Computing

View Sample PDF

Copyright: 2023
Pages: 23
Source title: Developing Linear Algebra Codes on Modern Processors: Emerging Research and Opportunities
Source Author(s)/Editor(s): Sandra Catalán Pallarés (Universidad Complutense de Madrid, Spain), Pedro Valero-Lara (Oak Ridge National Laboratory, USA), Leonel Antonio Toledo Díaz (Barcelona Supercomputing Center, Spain)and Rocío Carratalá Sáez (Universidad de Valladolid, Spain)
DOI: 10.4018/978-1-7998-7082-1.ch005

Keywords: Computer Science & IT / High Performance Computing / Information Science Reference / Programming Languages

Purchase

View Batched Computing on the publisher's website for pricing and purchasing information.

Abstract

This chapter presents the concept of batched computing, which consists of the division of a large problem into smaller portions and can be applied to both dense and sparse linear algebra. Two examples, general matrix-matrix multiplication (GEMM) and general triangular solver (GTSV), are used to present different approaches depending on the problem to solve. The GEMM example focuses on multi-core platforms, and it is also used to introduce the concept of auto-tunning. In the case of GTSV, the targeted device is a GPU. Moreover, given that this is a sparse operation, an analysis of the data layout is presented to see the impact of this aspect.

The IRMA Community

Research IRM

Batched Computing

Purchase

Abstract

Related Content

IRMA Sponsors