Matches in SemOpenAlex for { <https://semopenalex.org/work/W2165087681> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2165087681 endingPage "1615" @default.
- W2165087681 startingPage "1604" @default.
- W2165087681 abstract "<para xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> The partial fast Fourier transform (PFFT) is an extended fast Fourier transformation (FFT) where only part of the input or output bins are used. By pruning useless data flow, it is possible to achieve a significant speedup in many important applications. Although theoretical aspects of the PFFT have been thoroughly studied in the past three decades, efficient and generic implementations were rarely reported. The most important obstacle for the optimization of the PFFT is the highly irregular data flow and the associated control flow. In addition, a size-<formula formulatype=inline><tex Notation=TeX>$N$</tex> </formula> PFFT has <formula formulatype=inline><tex Notation=TeX>$2^{N}$</tex> </formula> possibilities of data flow patterns, so finding a flexible but efficient implementation is very challenging. Our contribution is a generic method to map the highly irregular data flow of an arbitrary PFFT onto instruction level parallel architectures using software pipelining. By leveraging the algorithmic level flexibilities in a FFT, we select an appropriate data flow variant that enables aggressive optimizations in implementation schemes. Then, we apply a divide and conquer strategy, partitioning the PFFT into three phases. For each phase, we introduce specialized control structures, loop structures, address generation schemes and memory operations. This reduces cycle count, number of executed instructions and memory accesses. By studying ten representative benchmarks from wireless baseband applications, we are able to produce repeatable and successful results on the TMS320C6000. When comparing to two optimized FFT implementations, our work reduces the cycle count by 20.5% to 87.5%, executed instructions by 11.2% to 86.5% and L1D and L1P cache accesses by 16.1% to 79.4% and 19.5% to 87.1% respectively. To the best of our knowledge, this is the first reported work about a generic software pipelined PFFT for instruction level parallel architectures. </para>" @default.
- W2165087681 created "2016-06-24" @default.
- W2165087681 creator A5008838372 @default.
- W2165087681 creator A5016605260 @default.
- W2165087681 creator A5033235745 @default.
- W2165087681 creator A5087295309 @default.
- W2165087681 creator A5089231704 @default.
- W2165087681 creator A5069683581 @default.
- W2165087681 date "2009-04-01" @default.
- W2165087681 modified "2023-10-03" @default.
- W2165087681 title "Generic Multiphase Software Pipelined Partial FFT on Instruction Level Parallel Architectures" @default.
- W2165087681 cites W1960995591 @default.
- W2165087681 cites W1984936209 @default.
- W2165087681 cites W1998152234 @default.
- W2165087681 cites W2021267552 @default.
- W2165087681 cites W2034971312 @default.
- W2165087681 cites W2048272888 @default.
- W2165087681 cites W2050778442 @default.
- W2165087681 cites W2059925342 @default.
- W2165087681 cites W2090690379 @default.
- W2165087681 cites W2102030243 @default.
- W2165087681 cites W2102182691 @default.
- W2165087681 cites W2103310688 @default.
- W2165087681 cites W2111062328 @default.
- W2165087681 cites W2113951268 @default.
- W2165087681 cites W2118924536 @default.
- W2165087681 cites W2136537144 @default.
- W2165087681 cites W2136952590 @default.
- W2165087681 cites W2142891960 @default.
- W2165087681 cites W2143284537 @default.
- W2165087681 cites W2146586535 @default.
- W2165087681 cites W2151978417 @default.
- W2165087681 cites W2154345268 @default.
- W2165087681 cites W2154543331 @default.
- W2165087681 cites W2157976505 @default.
- W2165087681 cites W2163102431 @default.
- W2165087681 cites W2296520333 @default.
- W2165087681 cites W2296760900 @default.
- W2165087681 cites W4232404745 @default.
- W2165087681 cites W4254944975 @default.
- W2165087681 doi "https://doi.org/10.1109/tsp.2008.2010422" @default.
- W2165087681 hasPublicationYear "2009" @default.
- W2165087681 type Work @default.
- W2165087681 sameAs 2165087681 @default.
- W2165087681 citedByCount "6" @default.
- W2165087681 countsByYear W21650876812012 @default.
- W2165087681 countsByYear W21650876812014 @default.
- W2165087681 countsByYear W21650876812023 @default.
- W2165087681 crossrefType "journal-article" @default.
- W2165087681 hasAuthorship W2165087681A5008838372 @default.
- W2165087681 hasAuthorship W2165087681A5016605260 @default.
- W2165087681 hasAuthorship W2165087681A5033235745 @default.
- W2165087681 hasAuthorship W2165087681A5069683581 @default.
- W2165087681 hasAuthorship W2165087681A5087295309 @default.
- W2165087681 hasAuthorship W2165087681A5089231704 @default.
- W2165087681 hasConcept C11413529 @default.
- W2165087681 hasConcept C160191386 @default.
- W2165087681 hasConcept C173608175 @default.
- W2165087681 hasConcept C188854837 @default.
- W2165087681 hasConcept C199360897 @default.
- W2165087681 hasConcept C2777904410 @default.
- W2165087681 hasConcept C41008148 @default.
- W2165087681 hasConcept C489000 @default.
- W2165087681 hasConcept C68339613 @default.
- W2165087681 hasConcept C75172450 @default.
- W2165087681 hasConcept C77088390 @default.
- W2165087681 hasConceptScore W2165087681C11413529 @default.
- W2165087681 hasConceptScore W2165087681C160191386 @default.
- W2165087681 hasConceptScore W2165087681C173608175 @default.
- W2165087681 hasConceptScore W2165087681C188854837 @default.
- W2165087681 hasConceptScore W2165087681C199360897 @default.
- W2165087681 hasConceptScore W2165087681C2777904410 @default.
- W2165087681 hasConceptScore W2165087681C41008148 @default.
- W2165087681 hasConceptScore W2165087681C489000 @default.
- W2165087681 hasConceptScore W2165087681C68339613 @default.
- W2165087681 hasConceptScore W2165087681C75172450 @default.
- W2165087681 hasConceptScore W2165087681C77088390 @default.
- W2165087681 hasIssue "4" @default.
- W2165087681 hasLocation W21650876811 @default.
- W2165087681 hasOpenAccess W2165087681 @default.
- W2165087681 hasPrimaryLocation W21650876811 @default.
- W2165087681 hasRelatedWork W1602521801 @default.
- W2165087681 hasRelatedWork W1644404237 @default.
- W2165087681 hasRelatedWork W1967627035 @default.
- W2165087681 hasRelatedWork W2004775621 @default.
- W2165087681 hasRelatedWork W2111984394 @default.
- W2165087681 hasRelatedWork W2165087681 @default.
- W2165087681 hasRelatedWork W2389666628 @default.
- W2165087681 hasRelatedWork W3142504699 @default.
- W2165087681 hasRelatedWork W4242837953 @default.
- W2165087681 hasRelatedWork W2109400628 @default.
- W2165087681 hasVolume "57" @default.
- W2165087681 isParatext "false" @default.
- W2165087681 isRetracted "false" @default.
- W2165087681 magId "2165087681" @default.
- W2165087681 workType "article" @default.