This work describes some first efforts to design a new Linpack-like benchmark useful to evaluate the performance of Heterogeneous Computing Resources. The benchmark is based on the Schur Complement reformulation of the solution of a linear equation system. Details about its implementation and evaluation, mainly in terms of performance scalability, are presented for a computing environment based on multi NVIDIA GP-GPUs nodes connected by an Infiniband network.
Toward a new linpack‐like benchmark for heterogeneous computing resources / Carracciuolo, Luisa; Mele, Valeria; Sabella, Gianluca. - In: CONCURRENCY AND COMPUTATION. - ISSN 1532-0626. - 36:10(2024). [10.1002/cpe.7962]
Toward a new linpack‐like benchmark for heterogeneous computing resources
Carracciuolo, Luisa;Mele, Valeria;Sabella, Gianluca
2024
Abstract
This work describes some first efforts to design a new Linpack-like benchmark useful to evaluate the performance of Heterogeneous Computing Resources. The benchmark is based on the Schur Complement reformulation of the solution of a linear equation system. Details about its implementation and evaluation, mainly in terms of performance scalability, are presented for a computing environment based on multi NVIDIA GP-GPUs nodes connected by an Infiniband network.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


