Implementation of the conjugate gradient algorithm for heterogeneous systems

28 Jul 2021, 14:15
15m
Oral presentation Software development and Machines Software development and Machines

Speaker

Dr Salvatore Cali (MIT)

Description

Lattice QCD calculations require a relevant computational effort and most of the computer time is typically spent in the numerical inversion of the Dirac-Wilson operator. One of the simplest methods to solve large and sparse linear systems is the conjugate gradient (CG). In this work we present an implementation of the CG that can be executed on different devices, including CPUs, GPUs and FPGAs. This is achieved by using SYCL/DPC++ framework, that allows the execution of the same source code on heterogeneous systems.

Authors

Dr Salvatore Cali (MIT) Prof. William Detmold (Massachusetts Institute of Technology) Dr Grzegorz Korcyl (Jagiellonian University) Prof. Piotr Korcyl (Jagiellonian University) Prof. Phiala Shanahan (Massachusetts Institute of Technology)

Presentation materials