Matches in SemOpenAlex for { <https://semopenalex.org/work/W2620346917> ?p ?o ?g. }
- W2620346917 endingPage "44" @default.
- W2620346917 startingPage "1" @default.
- W2620346917 abstract "Multisplit is a broadly useful parallel primitive that permutes its input data into contiguous buckets or bins, where the function that categorizes an element into a bucket is provided by the programmer. Due to the lack of an efficient multisplit on Graphics Processing Units (GPUs), programmers often choose to implement multisplit with a sort. One way is to first generate an auxiliary array of bucket IDs and then sort input data based on it. In case smaller indexed buckets possess smaller valued keys, another way for multisplit is to directly sort input data. Both methods are inefficient and require more work than necessary: The former requires more expensive data movements while the latter spends unnecessary effort in sorting elements within each bucket. In this work, we provide a parallel model and multiple implementations for the multisplit problem. Our principal focus is multisplit for a small (up to 256) number of buckets. We use warp-synchronous programming models and emphasize warpwide communications to avoid branch divergence and reduce memory usage. We also hierarchically reorder input elements to achieve better coalescing of global memory accesses. On a GeForce GTX 1080 GPU, we can reach a peak throughput of 18.93Gkeys/s (or 11.68Gpairs/s) for a key-only (or key-value) multisplit. Finally, we demonstrate how multisplit can be used as a building block for radix sort. In our multisplit-based sort implementation, we achieve comparable performance to the fastest GPU sort routines, sorting 32-bit keys (and key-value pairs) with a throughput of 3.0Gkeys/s (and 2.1Gpair/s)." @default.
- W2620346917 created "2017-06-05" @default.
- W2620346917 creator A5012494631 @default.
- W2620346917 creator A5025222722 @default.
- W2620346917 creator A5028662746 @default.
- W2620346917 creator A5075796801 @default.
- W2620346917 date "2017-08-23" @default.
- W2620346917 modified "2023-09-26" @default.
- W2620346917 title "GPU Multisplit: An Extended Study of a Parallel Algorithm" @default.
- W2620346917 cites W1480958225 @default.
- W2620346917 cites W1482680420 @default.
- W2620346917 cites W1548164611 @default.
- W2620346917 cites W1981585303 @default.
- W2620346917 cites W2007742815 @default.
- W2620346917 cites W2017086619 @default.
- W2620346917 cites W2024794876 @default.
- W2620346917 cites W2035080386 @default.
- W2620346917 cites W2041470524 @default.
- W2620346917 cites W2050182684 @default.
- W2620346917 cites W2050277572 @default.
- W2620346917 cites W2057112598 @default.
- W2620346917 cites W2072731885 @default.
- W2620346917 cites W2074982700 @default.
- W2620346917 cites W2087507944 @default.
- W2620346917 cites W2093012449 @default.
- W2620346917 cites W2107173440 @default.
- W2620346917 cites W2111194344 @default.
- W2620346917 cites W2124298085 @default.
- W2620346917 cites W2134427337 @default.
- W2620346917 cites W2145455679 @default.
- W2620346917 cites W2155503253 @default.
- W2620346917 cites W2161061943 @default.
- W2620346917 cites W2169528473 @default.
- W2620346917 cites W2207292641 @default.
- W2620346917 cites W2257258878 @default.
- W2620346917 cites W2336892223 @default.
- W2620346917 cites W3138798301 @default.
- W2620346917 hasPublicationYear "2017" @default.
- W2620346917 type Work @default.
- W2620346917 sameAs 2620346917 @default.
- W2620346917 citedByCount "2" @default.
- W2620346917 countsByYear W26203469172017 @default.
- W2620346917 countsByYear W26203469172021 @default.
- W2620346917 crossrefType "journal-article" @default.
- W2620346917 hasAuthorship W2620346917A5012494631 @default.
- W2620346917 hasAuthorship W2620346917A5025222722 @default.
- W2620346917 hasAuthorship W2620346917A5028662746 @default.
- W2620346917 hasAuthorship W2620346917A5075796801 @default.
- W2620346917 hasBestOaLocation W26203469171 @default.
- W2620346917 hasConcept C108094655 @default.
- W2620346917 hasConcept C111696304 @default.
- W2620346917 hasConcept C111919701 @default.
- W2620346917 hasConcept C11413529 @default.
- W2620346917 hasConcept C120665830 @default.
- W2620346917 hasConcept C121332964 @default.
- W2620346917 hasConcept C121684516 @default.
- W2620346917 hasConcept C149635348 @default.
- W2620346917 hasConcept C157764524 @default.
- W2620346917 hasConcept C162319229 @default.
- W2620346917 hasConcept C173608175 @default.
- W2620346917 hasConcept C192209626 @default.
- W2620346917 hasConcept C199360897 @default.
- W2620346917 hasConcept C21442007 @default.
- W2620346917 hasConcept C2524010 @default.
- W2620346917 hasConcept C26517878 @default.
- W2620346917 hasConcept C26713055 @default.
- W2620346917 hasConcept C2777210771 @default.
- W2620346917 hasConcept C2778514511 @default.
- W2620346917 hasConcept C33923547 @default.
- W2620346917 hasConcept C41008148 @default.
- W2620346917 hasConcept C555944384 @default.
- W2620346917 hasConcept C77088390 @default.
- W2620346917 hasConcept C80444323 @default.
- W2620346917 hasConcept C88548561 @default.
- W2620346917 hasConceptScore W2620346917C108094655 @default.
- W2620346917 hasConceptScore W2620346917C111696304 @default.
- W2620346917 hasConceptScore W2620346917C111919701 @default.
- W2620346917 hasConceptScore W2620346917C11413529 @default.
- W2620346917 hasConceptScore W2620346917C120665830 @default.
- W2620346917 hasConceptScore W2620346917C121332964 @default.
- W2620346917 hasConceptScore W2620346917C121684516 @default.
- W2620346917 hasConceptScore W2620346917C149635348 @default.
- W2620346917 hasConceptScore W2620346917C157764524 @default.
- W2620346917 hasConceptScore W2620346917C162319229 @default.
- W2620346917 hasConceptScore W2620346917C173608175 @default.
- W2620346917 hasConceptScore W2620346917C192209626 @default.
- W2620346917 hasConceptScore W2620346917C199360897 @default.
- W2620346917 hasConceptScore W2620346917C21442007 @default.
- W2620346917 hasConceptScore W2620346917C2524010 @default.
- W2620346917 hasConceptScore W2620346917C26517878 @default.
- W2620346917 hasConceptScore W2620346917C26713055 @default.
- W2620346917 hasConceptScore W2620346917C2777210771 @default.
- W2620346917 hasConceptScore W2620346917C2778514511 @default.
- W2620346917 hasConceptScore W2620346917C33923547 @default.
- W2620346917 hasConceptScore W2620346917C41008148 @default.
- W2620346917 hasConceptScore W2620346917C555944384 @default.
- W2620346917 hasConceptScore W2620346917C77088390 @default.
- W2620346917 hasConceptScore W2620346917C80444323 @default.