Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387187832> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4387187832 abstract "High-Level Synthesis (HLS) tools are mature enough to provide efficient code generation for computation kernels on FPGA hardware. For more complex applications, multiple kernels may be connected by a dataflow graph. Although some tools, such as Xilinx Vitis HLS, support dataflow directives, they lack efficient analysis methods to compute the buffer sizes between kernels in a dataflow graph. This paper proposes an original method to safely approximate such buffer sizes. The first contribution computes an initial overestimation of buffer sizes, wihout knowing the memory access patterns of kernels. The second contribution iteratively refines those buffer sizes thanks to cosimulation. Moreover, the paper introduces an open source framework using these methods to facilitate dataflow programming on FPGA using HLS. The proposed methods and framework have been tested on 7 dataflow applications, and outperform Vitis HLS cosimulation in 5 benchmarks, either in terms of BRAM and LUT usage, or in term of exploration time. In the 2 other benchmarks, our best method gets results similar to Vitis HLS. Last but not least, our method admits directed cycles in the application graphs." @default.
- W4387187832 created "2023-09-30" @default.
- W4387187832 creator A5041007136 @default.
- W4387187832 creator A5051748007 @default.
- W4387187832 creator A5059319745 @default.
- W4387187832 creator A5090627469 @default.
- W4387187832 date "2023-09-29" @default.
- W4387187832 modified "2023-10-15" @default.
- W4387187832 title "Automated Buffer Sizing of Dataflow Applications in a High-Level Synthesis Workflow" @default.
- W4387187832 cites W1580368786 @default.
- W4387187832 cites W1989988531 @default.
- W4387187832 cites W2040466547 @default.
- W4387187832 cites W2041935783 @default.
- W4387187832 cites W2051677156 @default.
- W4387187832 cites W2070385897 @default.
- W4387187832 cites W2091158003 @default.
- W4387187832 cites W2100645006 @default.
- W4387187832 cites W2155256384 @default.
- W4387187832 cites W2164084134 @default.
- W4387187832 cites W2891946740 @default.
- W4387187832 cites W2914867373 @default.
- W4387187832 cites W3004310455 @default.
- W4387187832 cites W3007436455 @default.
- W4387187832 cites W3033664232 @default.
- W4387187832 cites W3085407124 @default.
- W4387187832 cites W3169788481 @default.
- W4387187832 cites W4224265992 @default.
- W4387187832 doi "https://doi.org/10.1145/3626103" @default.
- W4387187832 hasPublicationYear "2023" @default.
- W4387187832 type Work @default.
- W4387187832 citedByCount "0" @default.
- W4387187832 crossrefType "journal-article" @default.
- W4387187832 hasAuthorship W4387187832A5041007136 @default.
- W4387187832 hasAuthorship W4387187832A5051748007 @default.
- W4387187832 hasAuthorship W4387187832A5059319745 @default.
- W4387187832 hasAuthorship W4387187832A5090627469 @default.
- W4387187832 hasBestOaLocation W43871878321 @default.
- W4387187832 hasConcept C11413529 @default.
- W4387187832 hasConcept C118524514 @default.
- W4387187832 hasConcept C132525143 @default.
- W4387187832 hasConcept C149635348 @default.
- W4387187832 hasConcept C173608175 @default.
- W4387187832 hasConcept C176727019 @default.
- W4387187832 hasConcept C177212765 @default.
- W4387187832 hasConcept C41008148 @default.
- W4387187832 hasConcept C42935608 @default.
- W4387187832 hasConcept C45374587 @default.
- W4387187832 hasConcept C489000 @default.
- W4387187832 hasConcept C58013763 @default.
- W4387187832 hasConcept C74197172 @default.
- W4387187832 hasConcept C77088390 @default.
- W4387187832 hasConcept C80444323 @default.
- W4387187832 hasConcept C88468194 @default.
- W4387187832 hasConcept C96324660 @default.
- W4387187832 hasConceptScore W4387187832C11413529 @default.
- W4387187832 hasConceptScore W4387187832C118524514 @default.
- W4387187832 hasConceptScore W4387187832C132525143 @default.
- W4387187832 hasConceptScore W4387187832C149635348 @default.
- W4387187832 hasConceptScore W4387187832C173608175 @default.
- W4387187832 hasConceptScore W4387187832C176727019 @default.
- W4387187832 hasConceptScore W4387187832C177212765 @default.
- W4387187832 hasConceptScore W4387187832C41008148 @default.
- W4387187832 hasConceptScore W4387187832C42935608 @default.
- W4387187832 hasConceptScore W4387187832C45374587 @default.
- W4387187832 hasConceptScore W4387187832C489000 @default.
- W4387187832 hasConceptScore W4387187832C58013763 @default.
- W4387187832 hasConceptScore W4387187832C74197172 @default.
- W4387187832 hasConceptScore W4387187832C77088390 @default.
- W4387187832 hasConceptScore W4387187832C80444323 @default.
- W4387187832 hasConceptScore W4387187832C88468194 @default.
- W4387187832 hasConceptScore W4387187832C96324660 @default.
- W4387187832 hasLocation W43871878321 @default.
- W4387187832 hasLocation W43871878322 @default.
- W4387187832 hasOpenAccess W4387187832 @default.
- W4387187832 hasPrimaryLocation W43871878321 @default.
- W4387187832 hasRelatedWork W1488303959 @default.
- W4387187832 hasRelatedWork W1512554843 @default.
- W4387187832 hasRelatedWork W1533244915 @default.
- W4387187832 hasRelatedWork W2032571270 @default.
- W4387187832 hasRelatedWork W2134941280 @default.
- W4387187832 hasRelatedWork W2140468016 @default.
- W4387187832 hasRelatedWork W2243710416 @default.
- W4387187832 hasRelatedWork W2403596187 @default.
- W4387187832 hasRelatedWork W2461217932 @default.
- W4387187832 hasRelatedWork W2471130673 @default.
- W4387187832 isParatext "false" @default.
- W4387187832 isRetracted "false" @default.
- W4387187832 workType "article" @default.