Matches in SemOpenAlex for { <https://semopenalex.org/work/W2554400228> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2554400228 abstract "This paper proposes a performance model for general matrix multiplication (GEMM) on decoupled access/execute (DAE) architecture platforms, in order to guide improvements of the GEMM performance in the Godson-3B1500. This model focuses on the features of access processors (APs) and execute processors (EPs). To reduce the synchronization overhead between APs and EPs, a synchronization module selection mechanism (SMSM) is presented. Furthermore, two optimized algorithms of GEMM for DAE platforms based on the performance model are proposed for ideal performance. In the proposed algorithms, the kernel functions are optimized with single instruction multiple data (SIMD) vector instructions, and the overhead of AP is almost overlapped with EP by taking full advantage of the features of the architecture. Moreover, the synchronization overhead can be reduced according to the SMSM. In the end, the proposed algorithms are tested on the Godson-3B1500. The experimental results demonstrate that the computing performance of dGEMM reaches 91.9% of the theoretical peak performance and that zGEMM can reach 93% of the theoretical peak performance." @default.
- W2554400228 created "2016-11-30" @default.
- W2554400228 creator A5060087983 @default.
- W2554400228 creator A5080733133 @default.
- W2554400228 creator A5084538628 @default.
- W2554400228 date "2016-11-25" @default.
- W2554400228 modified "2023-09-22" @default.
- W2554400228 title "BLAS3 optimization for the Godson-3B1500" @default.
- W2554400228 cites W1969648707 @default.
- W2554400228 cites W1992228230 @default.
- W2554400228 cites W2020277913 @default.
- W2554400228 cites W2064872546 @default.
- W2554400228 cites W2070225380 @default.
- W2554400228 cites W2073061372 @default.
- W2554400228 cites W2084379367 @default.
- W2554400228 cites W2154790323 @default.
- W2554400228 cites W2559013348 @default.
- W2554400228 doi "https://doi.org/10.1186/s40064-016-3690-3" @default.
- W2554400228 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/5122567" @default.
- W2554400228 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/27933269" @default.
- W2554400228 hasPublicationYear "2016" @default.
- W2554400228 type Work @default.
- W2554400228 sameAs 2554400228 @default.
- W2554400228 citedByCount "0" @default.
- W2554400228 crossrefType "journal-article" @default.
- W2554400228 hasAuthorship W2554400228A5060087983 @default.
- W2554400228 hasAuthorship W2554400228A5080733133 @default.
- W2554400228 hasAuthorship W2554400228A5084538628 @default.
- W2554400228 hasBestOaLocation W25544002281 @default.
- W2554400228 hasConcept C111919701 @default.
- W2554400228 hasConcept C114614502 @default.
- W2554400228 hasConcept C118524514 @default.
- W2554400228 hasConcept C127162648 @default.
- W2554400228 hasConcept C150552126 @default.
- W2554400228 hasConcept C173608175 @default.
- W2554400228 hasConcept C2778562939 @default.
- W2554400228 hasConcept C2779960059 @default.
- W2554400228 hasConcept C31258907 @default.
- W2554400228 hasConcept C33923547 @default.
- W2554400228 hasConcept C3826847 @default.
- W2554400228 hasConcept C41008148 @default.
- W2554400228 hasConcept C74193536 @default.
- W2554400228 hasConceptScore W2554400228C111919701 @default.
- W2554400228 hasConceptScore W2554400228C114614502 @default.
- W2554400228 hasConceptScore W2554400228C118524514 @default.
- W2554400228 hasConceptScore W2554400228C127162648 @default.
- W2554400228 hasConceptScore W2554400228C150552126 @default.
- W2554400228 hasConceptScore W2554400228C173608175 @default.
- W2554400228 hasConceptScore W2554400228C2778562939 @default.
- W2554400228 hasConceptScore W2554400228C2779960059 @default.
- W2554400228 hasConceptScore W2554400228C31258907 @default.
- W2554400228 hasConceptScore W2554400228C33923547 @default.
- W2554400228 hasConceptScore W2554400228C3826847 @default.
- W2554400228 hasConceptScore W2554400228C41008148 @default.
- W2554400228 hasConceptScore W2554400228C74193536 @default.
- W2554400228 hasFunder F4320334897 @default.
- W2554400228 hasLocation W25544002281 @default.
- W2554400228 hasLocation W25544002282 @default.
- W2554400228 hasLocation W25544002283 @default.
- W2554400228 hasLocation W25544002284 @default.
- W2554400228 hasOpenAccess W2554400228 @default.
- W2554400228 hasPrimaryLocation W25544002281 @default.
- W2554400228 hasRelatedWork W1489917148 @default.
- W2554400228 hasRelatedWork W1496930465 @default.
- W2554400228 hasRelatedWork W1513152622 @default.
- W2554400228 hasRelatedWork W1589200278 @default.
- W2554400228 hasRelatedWork W1989747681 @default.
- W2554400228 hasRelatedWork W2052129173 @default.
- W2554400228 hasRelatedWork W2060923576 @default.
- W2554400228 hasRelatedWork W2088907061 @default.
- W2554400228 hasRelatedWork W2106405002 @default.
- W2554400228 hasRelatedWork W2127373103 @default.
- W2554400228 hasRelatedWork W2155801019 @default.
- W2554400228 hasRelatedWork W2162451809 @default.
- W2554400228 hasRelatedWork W2171047111 @default.
- W2554400228 hasRelatedWork W2251532325 @default.
- W2554400228 hasRelatedWork W2313437200 @default.
- W2554400228 hasRelatedWork W2590058526 @default.
- W2554400228 hasRelatedWork W3013281160 @default.
- W2554400228 hasRelatedWork W3092849330 @default.
- W2554400228 hasRelatedWork W3153543698 @default.
- W2554400228 hasRelatedWork W2144650967 @default.
- W2554400228 isParatext "false" @default.
- W2554400228 isRetracted "false" @default.
- W2554400228 magId "2554400228" @default.
- W2554400228 workType "article" @default.