Matches in SemOpenAlex for { <https://semopenalex.org/work/W2474844316> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2474844316 abstract "GPUs have been widely used to accelerate computations exhibiting simple patterns of parallelism -- such as flat or two-level parallelism -- and a degree of parallelism that can be statically determined based on the size of the input dataset. However, the effective use of GPUs for algorithms exhibiting complex patterns of parallelism, possibly known only at runtime, is still an open problem. Recently, Nvidia has introduced Dynamic Parallelism (DP) in its GPUs. By making it possible to launch kernels directly from GPU threads, this feature enables nested parallelism at runtime. However, the effective use of DP must still be understood: a naïve use of this feature may suffer from significant runtime overhead and lead to GPU underutilization, resulting in poor performance. In this work, we target this problem. First, we demonstrate how a naïve use of DP can result in poor performance. Second, we propose three workload consolidation schemes to improve performance and hardware utilization of DP-based codes, and we implement these code transformations in a directive-based compiler. Finally, we evaluate our framework on two categories of applications: algorithms including irregular loops and algorithms exhibiting parallel recursion. Our experiments show that our approach significantly reduces runtime overhead and improves GPU utilization, leading to speedup factors from 90x to 3300x over basic DP-based solutions and speedups from 2x to 6x over flat implementations." @default.
- W2474844316 created "2016-07-22" @default.
- W2474844316 creator A5041520129 @default.
- W2474844316 creator A5041600358 @default.
- W2474844316 creator A5042170464 @default.
- W2474844316 date "2016-05-01" @default.
- W2474844316 modified "2023-10-17" @default.
- W2474844316 title "Compiler-Assisted Workload Consolidation for Efficient Dynamic Parallelism on GPU" @default.
- W2474844316 cites W1504291959 @default.
- W2474844316 cites W1896298204 @default.
- W2474844316 cites W1971367716 @default.
- W2474844316 cites W1985291160 @default.
- W2474844316 cites W1985807728 @default.
- W2474844316 cites W1993239831 @default.
- W2474844316 cites W1996541179 @default.
- W2474844316 cites W1997162567 @default.
- W2474844316 cites W2011389593 @default.
- W2474844316 cites W2029940394 @default.
- W2474844316 cites W2058692170 @default.
- W2474844316 cites W2064446724 @default.
- W2474844316 cites W2088866486 @default.
- W2474844316 cites W2094722168 @default.
- W2474844316 cites W2109473404 @default.
- W2474844316 cites W2123440268 @default.
- W2474844316 cites W2134373412 @default.
- W2474844316 cites W2134427337 @default.
- W2474844316 cites W2143114052 @default.
- W2474844316 cites W2156519507 @default.
- W2474844316 cites W2167383108 @default.
- W2474844316 cites W2238700765 @default.
- W2474844316 cites W2260499435 @default.
- W2474844316 cites W3006138624 @default.
- W2474844316 doi "https://doi.org/10.1109/ipdps.2016.98" @default.
- W2474844316 hasPublicationYear "2016" @default.
- W2474844316 type Work @default.
- W2474844316 sameAs 2474844316 @default.
- W2474844316 citedByCount "13" @default.
- W2474844316 countsByYear W24748443162016 @default.
- W2474844316 countsByYear W24748443162017 @default.
- W2474844316 countsByYear W24748443162018 @default.
- W2474844316 countsByYear W24748443162020 @default.
- W2474844316 countsByYear W24748443162021 @default.
- W2474844316 countsByYear W24748443162022 @default.
- W2474844316 countsByYear W24748443162023 @default.
- W2474844316 crossrefType "proceedings-article" @default.
- W2474844316 hasAuthorship W2474844316A5041520129 @default.
- W2474844316 hasAuthorship W2474844316A5041600358 @default.
- W2474844316 hasAuthorship W2474844316A5042170464 @default.
- W2474844316 hasBestOaLocation W24748443162 @default.
- W2474844316 hasConcept C140763907 @default.
- W2474844316 hasConcept C169590947 @default.
- W2474844316 hasConcept C173608175 @default.
- W2474844316 hasConcept C199360897 @default.
- W2474844316 hasConcept C2778119891 @default.
- W2474844316 hasConcept C2779960059 @default.
- W2474844316 hasConcept C2781172179 @default.
- W2474844316 hasConcept C41008148 @default.
- W2474844316 hasConcept C42992933 @default.
- W2474844316 hasConcept C61483411 @default.
- W2474844316 hasConcept C68339613 @default.
- W2474844316 hasConceptScore W2474844316C140763907 @default.
- W2474844316 hasConceptScore W2474844316C169590947 @default.
- W2474844316 hasConceptScore W2474844316C173608175 @default.
- W2474844316 hasConceptScore W2474844316C199360897 @default.
- W2474844316 hasConceptScore W2474844316C2778119891 @default.
- W2474844316 hasConceptScore W2474844316C2779960059 @default.
- W2474844316 hasConceptScore W2474844316C2781172179 @default.
- W2474844316 hasConceptScore W2474844316C41008148 @default.
- W2474844316 hasConceptScore W2474844316C42992933 @default.
- W2474844316 hasConceptScore W2474844316C61483411 @default.
- W2474844316 hasConceptScore W2474844316C68339613 @default.
- W2474844316 hasLocation W24748443161 @default.
- W2474844316 hasLocation W24748443162 @default.
- W2474844316 hasLocation W24748443163 @default.
- W2474844316 hasOpenAccess W2474844316 @default.
- W2474844316 hasPrimaryLocation W24748443161 @default.
- W2474844316 hasRelatedWork W1493795614 @default.
- W2474844316 hasRelatedWork W1594526132 @default.
- W2474844316 hasRelatedWork W1608806855 @default.
- W2474844316 hasRelatedWork W1685698149 @default.
- W2474844316 hasRelatedWork W2023505575 @default.
- W2474844316 hasRelatedWork W2065621939 @default.
- W2474844316 hasRelatedWork W2161363915 @default.
- W2474844316 hasRelatedWork W2313503008 @default.
- W2474844316 hasRelatedWork W2366027386 @default.
- W2474844316 hasRelatedWork W2378666660 @default.
- W2474844316 isParatext "false" @default.
- W2474844316 isRetracted "false" @default.
- W2474844316 magId "2474844316" @default.
- W2474844316 workType "article" @default.