Title :
Triangular Matrix Inversion on Heterogeneous Multicore Systems
Author :
Ries, Florian ; De Marco, Tommaso ; Guerrieri, Roberto
Author_Institution :
Adv. Res. Center on Electron. Syst. for Inf. & Commun. Technol., E. De Castro (ARCES), Bologna, Italy
Abstract :
Dense matrix inversion is a basic procedure in many linear algebra algorithms. Any factorization-based dense matrix inversion algorithm involves the inversion of one or two triangular matrices. In this work, we present an improved implementation of a parallel triangular matrix inversion for heterogeneous multicore CPU/dual-GPU systems.
Keywords :
computer graphic equipment; coprocessors; linear algebra; matrix inversion; multiprocessing systems; parallel processing; factorization-based dense matrix inversion algorithm; heterogeneous dual-GPU system; heterogeneous multicore CPU system; linear algebra algorithm; parallel triangular matrix inversion; Graphics processing unit; Indexes; Instruction sets; Kernel; Parallel processing; Random access memory; Table lookup; Matrix inversion; parallel processing.;
Journal_Title :
Parallel and Distributed Systems, IEEE Transactions on
DOI :
10.1109/TPDS.2011.103
