Matches in SemOpenAlex for { <https://semopenalex.org/work/W2067555400> ?p ?o ?g. }
Showing items 1 to 58 of
58
with 100 items per page.
- W2067555400 abstract "Soft vector processors can accelerate data parallel algorithms on FPGAs while retaining software programmability. To handle divergent control flow, vector processors typically use mask registers and predicated instructions. These work by executing all branches and finally selecting the correct one. Our work improves FPGA based vector processors by adding wavefront skipping, where wavefronts that are completely masked off are skipped. This accelerates conditional algorithms, particularly useful where elements terminate early if simple tests fail but require extensive processing in the worst case. The difference in logic speed and RAM area for FPGA based circuits versus ASICs led us to a different implementation than used in fixed vector processors, storing wavefront offsets in on-chip BRAM rather than computing wavefronts skipped dynamically. Additionally, we allow for partitioning the wavefronts so that partial wavefronts can skip independently of one another. We show that" @default.
- W2067555400 created "2016-06-24" @default.
- W2067555400 creator A5038077890 @default.
- W2067555400 creator A5057087978 @default.
- W2067555400 creator A5071113717 @default.
- W2067555400 date "2015-02-22" @default.
- W2067555400 modified "2023-09-23" @default.
- W2067555400 title "Wavefront Skipping using BRAMs for Conditional Algorithms on Vector Processors" @default.
- W2067555400 cites W1485904170 @default.
- W2067555400 cites W1973012690 @default.
- W2067555400 cites W2001984859 @default.
- W2067555400 cites W2016889342 @default.
- W2067555400 cites W2023203414 @default.
- W2067555400 cites W2079621909 @default.
- W2067555400 cites W2097959379 @default.
- W2067555400 cites W2164215436 @default.
- W2067555400 cites W2167897136 @default.
- W2067555400 cites W4234211448 @default.
- W2067555400 doi "https://doi.org/10.1145/2684746.2689072" @default.
- W2067555400 hasPublicationYear "2015" @default.
- W2067555400 type Work @default.
- W2067555400 sameAs 2067555400 @default.
- W2067555400 citedByCount "5" @default.
- W2067555400 countsByYear W20675554002015 @default.
- W2067555400 countsByYear W20675554002017 @default.
- W2067555400 countsByYear W20675554002018 @default.
- W2067555400 countsByYear W20675554002019 @default.
- W2067555400 crossrefType "proceedings-article" @default.
- W2067555400 hasAuthorship W2067555400A5038077890 @default.
- W2067555400 hasAuthorship W2067555400A5057087978 @default.
- W2067555400 hasAuthorship W2067555400A5071113717 @default.
- W2067555400 hasConcept C11413529 @default.
- W2067555400 hasConcept C120665830 @default.
- W2067555400 hasConcept C121332964 @default.
- W2067555400 hasConcept C165699331 @default.
- W2067555400 hasConcept C41008148 @default.
- W2067555400 hasConceptScore W2067555400C11413529 @default.
- W2067555400 hasConceptScore W2067555400C120665830 @default.
- W2067555400 hasConceptScore W2067555400C121332964 @default.
- W2067555400 hasConceptScore W2067555400C165699331 @default.
- W2067555400 hasConceptScore W2067555400C41008148 @default.
- W2067555400 hasLocation W20675554001 @default.
- W2067555400 hasOpenAccess W2067555400 @default.
- W2067555400 hasPrimaryLocation W20675554001 @default.
- W2067555400 hasRelatedWork W1977949648 @default.
- W2067555400 hasRelatedWork W1986607661 @default.
- W2067555400 hasRelatedWork W2199339534 @default.
- W2067555400 hasRelatedWork W2315828665 @default.
- W2067555400 hasRelatedWork W2333698505 @default.
- W2067555400 hasRelatedWork W2351491280 @default.
- W2067555400 hasRelatedWork W2371447506 @default.
- W2067555400 hasRelatedWork W2386767533 @default.
- W2067555400 hasRelatedWork W2937161056 @default.
- W2067555400 hasRelatedWork W303980170 @default.
- W2067555400 isParatext "false" @default.
- W2067555400 isRetracted "false" @default.
- W2067555400 magId "2067555400" @default.
- W2067555400 workType "article" @default.