FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3042238487> ?p ?o ?g. }

• W3042238487 abstract "Manycore processors such as GPUs and Intel Xeon Phis have become popular due to their massive parallelism and high power-efficiency. To achieve optimal performance, it is necessary to optimize the use of the compute cores and of the memory system available on these devices. Previous work has proposed techniques to improve the use of the GPU resources. While Intel Phi can provide massive parallelism through their x86 cores and vector units, optimization techniques for these platforms have received less consideration.In this work, we study the benefits of thread coarsening and low-cost synchronization on applications running on Intel Xeon Phi processors and encoded in SIMT fashion. Specifically, we explore thread coarsening as a way to remap the work to the available cores and vector lanes. In addition, we propose low- overhead synchronization primitives, such as atomic operations and barriers, which transparently apply to threads mapped to the same or different VPUs and x86 cores. Finally, we consider the combined use of thread coarsening and our proposed synchronization primitives. We evaluate the effect of these techniques on the performance of two kinds of kernels: collaborative and non-collaborative ones, the former using scratchpad memory to explicitly control data sharing among threads. Our evaluation leads to the following results. First, while not always beneficial for non-collaborative kernels, thread coarsening improves the performance of collaborative kernels consistently by reducing the synchronization overhead. Second, our synchronization primitives outperform standard pthread APIs by a factor up to 8x in real-world benchmarks. Last, the combined use of the proposed techniques leads to performance improvements, especially for collaborative kernels." @default.
• W3042238487 created "2020-07-23" @default.
• W3042238487 creator A5041520129 @default.
• W3042238487 creator A5041600358 @default.
• W3042238487 date "2020-05-01" @default.
• W3042238487 modified "2023-09-26" @default.
• W3042238487 title "Evaluating Thread Coarsening and Low-cost Synchronization on Intel Xeon Phi" @default.
• W3042238487 cites W1979607662 @default.
• W3042238487 cites W1989562524 @default.
• W3042238487 cites W2044709030 @default.
• W3042238487 cites W2067479799 @default.
• W3042238487 cites W2080592089 @default.
• W3042238487 cites W2094722168 @default.
• W3042238487 cites W2134427337 @default.
• W3042238487 cites W2140861996 @default.
• W3042238487 cites W2160428323 @default.
• W3042238487 cites W2224946430 @default.
• W3042238487 cites W2289880787 @default.
• W3042238487 cites W2295951005 @default.
• W3042238487 cites W2476946651 @default.
• W3042238487 cites W2751680920 @default.
• W3042238487 cites W2765106570 @default.
• W3042238487 cites W2808709390 @default.
• W3042238487 cites W2885840893 @default.
• W3042238487 cites W2896831700 @default.
• W3042238487 cites W2912735493 @default.
• W3042238487 cites W4242286475 @default.
• W3042238487 cites W4248655967 @default.
• W3042238487 doi "https://doi.org/10.1109/ipdps47924.2020.00108" @default.
• W3042238487 hasPublicationYear "2020" @default.
• W3042238487 type Work @default.
• W3042238487 sameAs 3042238487 @default.
• W3042238487 citedByCount "2" @default.
• W3042238487 countsByYear W30422384872023 @default.
• W3042238487 crossrefType "proceedings-article" @default.
• W3042238487 hasAuthorship W3042238487A5041520129 @default.
• W3042238487 hasAuthorship W3042238487A5041600358 @default.
• W3042238487 hasConcept C111919701 @default.
• W3042238487 hasConcept C127162648 @default.
• W3042238487 hasConcept C138101251 @default.
• W3042238487 hasConcept C145108525 @default.
• W3042238487 hasConcept C149635348 @default.
• W3042238487 hasConcept C170723468 @default.
• W3042238487 hasConcept C173608175 @default.
• W3042238487 hasConcept C201410400 @default.
• W3042238487 hasConcept C2777904410 @default.
• W3042238487 hasConcept C2778562939 @default.
• W3042238487 hasConcept C2779960059 @default.
• W3042238487 hasConcept C31258907 @default.
• W3042238487 hasConcept C41008148 @default.
• W3042238487 hasConcept C96972482 @default.
• W3042238487 hasConceptScore W3042238487C111919701 @default.
• W3042238487 hasConceptScore W3042238487C127162648 @default.
• W3042238487 hasConceptScore W3042238487C138101251 @default.
• W3042238487 hasConceptScore W3042238487C145108525 @default.
• W3042238487 hasConceptScore W3042238487C149635348 @default.
• W3042238487 hasConceptScore W3042238487C170723468 @default.
• W3042238487 hasConceptScore W3042238487C173608175 @default.
• W3042238487 hasConceptScore W3042238487C201410400 @default.
• W3042238487 hasConceptScore W3042238487C2777904410 @default.
• W3042238487 hasConceptScore W3042238487C2778562939 @default.
• W3042238487 hasConceptScore W3042238487C2779960059 @default.
• W3042238487 hasConceptScore W3042238487C31258907 @default.
• W3042238487 hasConceptScore W3042238487C41008148 @default.
• W3042238487 hasConceptScore W3042238487C96972482 @default.
• W3042238487 hasLocation W30422384871 @default.
• W3042238487 hasOpenAccess W3042238487 @default.
• W3042238487 hasPrimaryLocation W30422384871 @default.
• W3042238487 hasRelatedWork W1977871529 @default.
• W3042238487 hasRelatedWork W2047292351 @default.
• W3042238487 hasRelatedWork W2170268965 @default.
• W3042238487 hasRelatedWork W2183138449 @default.
• W3042238487 hasRelatedWork W2624440775 @default.
• W3042238487 hasRelatedWork W2808000164 @default.
• W3042238487 hasRelatedWork W2808198696 @default.
• W3042238487 hasRelatedWork W2890336205 @default.
• W3042238487 hasRelatedWork W2951047939 @default.
• W3042238487 hasRelatedWork W4289916438 @default.
• W3042238487 isParatext "false" @default.
• W3042238487 isRetracted "false" @default.
• W3042238487 magId "3042238487" @default.
• W3042238487 workType "article" @default.