Mostra el registre d'ítem simple
Optimizing the SpMV kernel on long-vector accelerators
dc.contributor.author | Gómez Crespo, Constantino |
dc.contributor.author | Mantovani, Filippo |
dc.contributor.author | Focht, Erich |
dc.contributor.author | Casas, Marc |
dc.date.accessioned | 2021-05-28T08:43:00Z |
dc.date.available | 2021-05-28T08:43:00Z |
dc.date.issued | 2021-05 |
dc.identifier.citation | Gómez Crespo, C. [et al.]. Optimizing the SpMV kernel on long-vector accelerators. A: . Barcelona Supercomputing Center, 2021, p. 30-31. |
dc.identifier.uri | http://hdl.handle.net/2117/346295 |
dc.description.abstract | Sparse Matrix-Vector multiplication (SpMV) is an essential kernel for parallel numerical applications. SpMV displays sparse and irregular data accesses, which complicate its vectorization. Such difficulties make SpMV to frequently experiment non-optimal results when run on long vector ISAs exploiting SIMD parallelism. In this context, the development of new optimizations becomes fundamental to enable high performance SpMV executions on emerging long vector architectures. In our work, we improve the state-of-the-art SELL-C- sparse matrix format by proposing several new optimizations for SpMV. We target aggressive long vector architectures like the NEC Vector Engine. By combining several optimizations, we obtain an average 12% improvement over SELL-C- considering a heterogeneous set of 24 matrices. Our optimizations boost performance in long vector architectures since they expose a high degree of SIMD parallelism. |
dc.format.extent | 2 p. |
dc.language | en |
dc.language.iso | eng |
dc.publisher | Barcelona Supercomputing Center |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Arquitectura de computadors |
dc.subject.lcsh | High performance computing |
dc.subject.lcsh | Kernel functions |
dc.subject.other | SpMV |
dc.subject.other | Long-Vector Architectures |
dc.subject.other | Performance Optimization |
dc.subject.other | NEC Vector Engine |
dc.title | Optimizing the SpMV kernel on long-vector accelerators |
dc.type | Conference report |
dc.subject.lemac | Càlcul intensiu (Informàtica) |
dc.subject.lemac | Kernel, Funcions de |
dc.rights.access | Open Access |
local.citation.startingPage | 30 |
local.citation.endingPage | 31 |
Fitxers d'aquest items
Aquest ítem apareix a les col·leccions següents
-
8th BSC Doctoral Symposium, 11th-13th May 2021 [33]
Book of abstracts