Matches in SemOpenAlex for { <https://semopenalex.org/work/W4321636675> ?p ?o ?g. }
- W4321636675 abstract "Sparse Matrix-Vector multiplication (SpMV) is an essential computational kernel in many application scenarios. Tens of sparse matrix formats and implementations have been proposed to compress the memory storage and speed up SpMV performance. We develop AlphaSparse, a superset of all existing works that goes beyond the scope of human-designed format(s) and implementation(s). AlphaSparse automatically creates novel machine-designed formats and SpMV kernel implementations en-tirely from the knowledge of input sparsity patterns and hard-ware architectures. Based on our proposed Operator Graph that expresses the path of SpMV format and kernel design, AlphaS-parse consists of three main components: Designer, Format & Kernel Generator, and Search Engine. It takes an arbitrary sparse matrix as input while outputs the performance machine-designed format and SpMV implementation. By extensively evaluating 843 matrices from SuiteSparse Matrix Collection, AlphaSparse achieves significant performance improvement by 3.2 × on average compared to five state-of-the-art artificial formats and 1.5 × on average (up to 2.7×) over the up-to-date implementation of traditional auto-tuning philosophy." @default.
- W4321636675 created "2023-02-24" @default.
- W4321636675 creator A5033926742 @default.
- W4321636675 creator A5049685964 @default.
- W4321636675 creator A5056459929 @default.
- W4321636675 creator A5067345513 @default.
- W4321636675 creator A5085309607 @default.
- W4321636675 creator A5085399047 @default.
- W4321636675 date "2022-11-01" @default.
- W4321636675 modified "2023-10-16" @default.
- W4321636675 title "AlphaSparse: Generating High Performance SpMV Codes Directly from Sparse Matrices" @default.
- W4321636675 cites W1508286210 @default.
- W4321636675 cites W1965034778 @default.
- W4321636675 cites W1986453598 @default.
- W4321636675 cites W1987840949 @default.
- W4321636675 cites W1988888548 @default.
- W4321636675 cites W1993704253 @default.
- W4321636675 cites W1995649289 @default.
- W4321636675 cites W1996274599 @default.
- W4321636675 cites W1996761530 @default.
- W4321636675 cites W1997465075 @default.
- W4321636675 cites W2001258868 @default.
- W4321636675 cites W2002555321 @default.
- W4321636675 cites W2003117296 @default.
- W4321636675 cites W2007441708 @default.
- W4321636675 cites W2008091782 @default.
- W4321636675 cites W2009654791 @default.
- W4321636675 cites W2022219663 @default.
- W4321636675 cites W2023930909 @default.
- W4321636675 cites W2027718011 @default.
- W4321636675 cites W2031460602 @default.
- W4321636675 cites W2034258707 @default.
- W4321636675 cites W2035080386 @default.
- W4321636675 cites W2036856982 @default.
- W4321636675 cites W2044850230 @default.
- W4321636675 cites W2083056254 @default.
- W4321636675 cites W2087507944 @default.
- W4321636675 cites W2088866486 @default.
- W4321636675 cites W2091883426 @default.
- W4321636675 cites W2093804518 @default.
- W4321636675 cites W2099625934 @default.
- W4321636675 cites W2100218206 @default.
- W4321636675 cites W2101511474 @default.
- W4321636675 cites W2102182691 @default.
- W4321636675 cites W2104512032 @default.
- W4321636675 cites W2126004407 @default.
- W4321636675 cites W2130289795 @default.
- W4321636675 cites W2136952590 @default.
- W4321636675 cites W2151764765 @default.
- W4321636675 cites W2157146993 @default.
- W4321636675 cites W2158626113 @default.
- W4321636675 cites W2263374743 @default.
- W4321636675 cites W2340076492 @default.
- W4321636675 cites W2570841452 @default.
- W4321636675 cites W2590246587 @default.
- W4321636675 cites W2594491068 @default.
- W4321636675 cites W2725757310 @default.
- W4321636675 cites W2783772867 @default.
- W4321636675 cites W2788264912 @default.
- W4321636675 cites W2791258966 @default.
- W4321636675 cites W2886632348 @default.
- W4321636675 cites W2898123186 @default.
- W4321636675 cites W2923126305 @default.
- W4321636675 cites W2949676527 @default.
- W4321636675 cites W2952598959 @default.
- W4321636675 cites W2953944188 @default.
- W4321636675 cites W2969583281 @default.
- W4321636675 cites W2999521721 @default.
- W4321636675 cites W3099744258 @default.
- W4321636675 cites W3102476541 @default.
- W4321636675 cites W3103983137 @default.
- W4321636675 cites W3130024571 @default.
- W4321636675 cites W3175189837 @default.
- W4321636675 cites W3177828909 @default.
- W4321636675 cites W4233661064 @default.
- W4321636675 cites W4238995617 @default.
- W4321636675 cites W4240168186 @default.
- W4321636675 cites W4243261006 @default.
- W4321636675 cites W4247712932 @default.
- W4321636675 cites W4247828381 @default.
- W4321636675 cites W4248445937 @default.
- W4321636675 cites W4250981202 @default.
- W4321636675 cites W4251637954 @default.
- W4321636675 cites W60686164 @default.
- W4321636675 doi "https://doi.org/10.1109/sc41404.2022.00071" @default.
- W4321636675 hasPublicationYear "2022" @default.
- W4321636675 type Work @default.
- W4321636675 citedByCount "2" @default.
- W4321636675 countsByYear W43216366752023 @default.
- W4321636675 crossrefType "proceedings-article" @default.
- W4321636675 hasAuthorship W4321636675A5033926742 @default.
- W4321636675 hasAuthorship W4321636675A5049685964 @default.
- W4321636675 hasAuthorship W4321636675A5056459929 @default.
- W4321636675 hasAuthorship W4321636675A5067345513 @default.
- W4321636675 hasAuthorship W4321636675A5085309607 @default.
- W4321636675 hasAuthorship W4321636675A5085399047 @default.
- W4321636675 hasBestOaLocation W43216366752 @default.
- W4321636675 hasConcept C114614502 @default.
- W4321636675 hasConcept C121332964 @default.
- W4321636675 hasConcept C163716315 @default.