Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285394996> ?p ?o ?g. }
- W4285394996 endingPage "7073" @default.
- W4285394996 startingPage "7073" @default.
- W4285394996 abstract "The sparse matrix–vector product (SpMV), considered one of the seven dwarfs (numerical methods of significance), is essential in high-performance real-world scientific and analytical applications requiring solution of large sparse linear equation systems, where SpMV is a key computing operation. As the sparsity patterns of sparse matrices are unknown before runtime, we used machine learning-based performance optimization of the SpMV kernel by exploiting the structure of the sparse matrices using the Block Compressed Sparse Row (BCSR) storage format. As the structure of sparse matrices varies across application domains, optimizing the block size is important for reducing the overall execution time. Manual allocation of block sizes is error prone and time consuming. Thus, we propose AAQAL, a data-driven, machine learning-based tool that automates the process of data distribution and selection of near-optimal block sizes based on the structure of the matrix. We trained and tested the tool using different machine learning methods—decision tree, random forest, gradient boosting, ridge regressor, and AdaBoost—and nearly 700 real-world matrices from 43 application domains, including computer vision, robotics, and computational fluid dynamics. AAQAL achieved 93.47% of the maximum attainable performance with a substantial difference compared to in practice manual or random selection of block sizes. This is the first attempt at exploiting matrix structure using BCSR, to select optimal block sizes for the SpMV computations using machine learning techniques." @default.
- W4285394996 created "2022-07-14" @default.
- W4285394996 creator A5032172706 @default.
- W4285394996 creator A5036614024 @default.
- W4285394996 creator A5042659148 @default.
- W4285394996 creator A5045031436 @default.
- W4285394996 creator A5078037189 @default.
- W4285394996 creator A5079802006 @default.
- W4285394996 creator A5081272298 @default.
- W4285394996 date "2022-07-13" @default.
- W4285394996 modified "2023-10-01" @default.
- W4285394996 title "AAQAL: A Machine Learning-Based Tool for Performance Optimization of Parallel SPMV Computations Using Block CSR" @default.
- W4285394996 cites W1965551736 @default.
- W4285394996 cites W1988311079 @default.
- W4285394996 cites W1996274599 @default.
- W4285394996 cites W2035080386 @default.
- W4285394996 cites W2039417226 @default.
- W4285394996 cites W2056297204 @default.
- W4285394996 cites W2072806558 @default.
- W4285394996 cites W2089908605 @default.
- W4285394996 cites W2091843288 @default.
- W4285394996 cites W2120768584 @default.
- W4285394996 cites W2126004407 @default.
- W4285394996 cites W2146530035 @default.
- W4285394996 cites W2163027735 @default.
- W4285394996 cites W2566666375 @default.
- W4285394996 cites W2570707890 @default.
- W4285394996 cites W2622833445 @default.
- W4285394996 cites W2796567256 @default.
- W4285394996 cites W2923126305 @default.
- W4285394996 cites W2952347618 @default.
- W4285394996 cites W2964515976 @default.
- W4285394996 cites W3008122584 @default.
- W4285394996 cites W3047429833 @default.
- W4285394996 cites W3080796709 @default.
- W4285394996 cites W3094096727 @default.
- W4285394996 cites W3105121197 @default.
- W4285394996 cites W3125884253 @default.
- W4285394996 cites W3126637267 @default.
- W4285394996 cites W3156548268 @default.
- W4285394996 cites W3157568166 @default.
- W4285394996 cites W3163858611 @default.
- W4285394996 cites W3194108047 @default.
- W4285394996 cites W4247712932 @default.
- W4285394996 doi "https://doi.org/10.3390/app12147073" @default.
- W4285394996 hasPublicationYear "2022" @default.
- W4285394996 type Work @default.
- W4285394996 citedByCount "2" @default.
- W4285394996 countsByYear W42853949962022 @default.
- W4285394996 countsByYear W42853949962023 @default.
- W4285394996 crossrefType "journal-article" @default.
- W4285394996 hasAuthorship W4285394996A5032172706 @default.
- W4285394996 hasAuthorship W4285394996A5036614024 @default.
- W4285394996 hasAuthorship W4285394996A5042659148 @default.
- W4285394996 hasAuthorship W4285394996A5045031436 @default.
- W4285394996 hasAuthorship W4285394996A5078037189 @default.
- W4285394996 hasAuthorship W4285394996A5079802006 @default.
- W4285394996 hasAuthorship W4285394996A5081272298 @default.
- W4285394996 hasBestOaLocation W42853949961 @default.
- W4285394996 hasConcept C11413529 @default.
- W4285394996 hasConcept C114614502 @default.
- W4285394996 hasConcept C119857082 @default.
- W4285394996 hasConcept C121332964 @default.
- W4285394996 hasConcept C12267149 @default.
- W4285394996 hasConcept C154945302 @default.
- W4285394996 hasConcept C163716315 @default.
- W4285394996 hasConcept C2524010 @default.
- W4285394996 hasConcept C2777210771 @default.
- W4285394996 hasConcept C33923547 @default.
- W4285394996 hasConcept C41008148 @default.
- W4285394996 hasConcept C45374587 @default.
- W4285394996 hasConcept C56372850 @default.
- W4285394996 hasConcept C62520636 @default.
- W4285394996 hasConcept C74193536 @default.
- W4285394996 hasConceptScore W4285394996C11413529 @default.
- W4285394996 hasConceptScore W4285394996C114614502 @default.
- W4285394996 hasConceptScore W4285394996C119857082 @default.
- W4285394996 hasConceptScore W4285394996C121332964 @default.
- W4285394996 hasConceptScore W4285394996C12267149 @default.
- W4285394996 hasConceptScore W4285394996C154945302 @default.
- W4285394996 hasConceptScore W4285394996C163716315 @default.
- W4285394996 hasConceptScore W4285394996C2524010 @default.
- W4285394996 hasConceptScore W4285394996C2777210771 @default.
- W4285394996 hasConceptScore W4285394996C33923547 @default.
- W4285394996 hasConceptScore W4285394996C41008148 @default.
- W4285394996 hasConceptScore W4285394996C45374587 @default.
- W4285394996 hasConceptScore W4285394996C56372850 @default.
- W4285394996 hasConceptScore W4285394996C62520636 @default.
- W4285394996 hasConceptScore W4285394996C74193536 @default.
- W4285394996 hasFunder F4320322322 @default.
- W4285394996 hasIssue "14" @default.
- W4285394996 hasLocation W42853949961 @default.
- W4285394996 hasOpenAccess W4285394996 @default.
- W4285394996 hasPrimaryLocation W42853949961 @default.
- W4285394996 hasRelatedWork W1996541855 @default.
- W4285394996 hasRelatedWork W2135063202 @default.
- W4285394996 hasRelatedWork W2355927362 @default.
- W4285394996 hasRelatedWork W2584735684 @default.