Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385890147> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4385890147 abstract "High-level synthesis (HLS) is a process that automatically translates a software program in a high-level language into a low-level hardware description. However, the hardware designs produced by HLS tools still suffer from a significant performance gap compared to manual implementations. This is because the input HLS programs must still be written using hardware design principles. Existing techniques either leave the program source unchanged or perform a fixed sequence of source transformation passes, potentially missing opportunities to find the optimal design. We propose a super-optimization approach for HLS that automatically rewrites an arbitrary software program into efficient HLS code that can be used to generate an optimized hardware design. We developed a toolflow named SEER, based on the e-graph data structure, to efficiently explore equivalent implementations of a program at scale. SEER provides an extensible framework, orchestrating existing software compiler passes and hardware synthesis optimizers. Our work is the first attempt to exploit e-graph rewriting for large software compiler frameworks, such as MLIR. Across a set of open-source benchmarks, we show that SEER achieves up to 38x the performance within 1.4x the area of the original program. Via an Intel-provided case study, SEER demonstrates the potential to outperform manually optimized designs produced by hardware experts." @default.
- W4385890147 created "2023-08-17" @default.
- W4385890147 creator A5047560439 @default.
- W4385890147 creator A5051728690 @default.
- W4385890147 creator A5060302344 @default.
- W4385890147 creator A5081902675 @default.
- W4385890147 creator A5092652533 @default.
- W4385890147 date "2023-08-15" @default.
- W4385890147 modified "2023-09-25" @default.
- W4385890147 title "SEER: Super-Optimization Explorer for HLS using E-graph Rewriting with MLIR" @default.
- W4385890147 doi "https://doi.org/10.48550/arxiv.2308.07654" @default.
- W4385890147 hasPublicationYear "2023" @default.
- W4385890147 type Work @default.
- W4385890147 citedByCount "0" @default.
- W4385890147 crossrefType "posted-content" @default.
- W4385890147 hasAuthorship W4385890147A5047560439 @default.
- W4385890147 hasAuthorship W4385890147A5051728690 @default.
- W4385890147 hasAuthorship W4385890147A5060302344 @default.
- W4385890147 hasAuthorship W4385890147A5081902675 @default.
- W4385890147 hasAuthorship W4385890147A5092652533 @default.
- W4385890147 hasBestOaLocation W43858901471 @default.
- W4385890147 hasConcept C118524514 @default.
- W4385890147 hasConcept C132525143 @default.
- W4385890147 hasConcept C139571649 @default.
- W4385890147 hasConcept C149635348 @default.
- W4385890147 hasConcept C154690210 @default.
- W4385890147 hasConcept C165696696 @default.
- W4385890147 hasConcept C169590947 @default.
- W4385890147 hasConcept C173608175 @default.
- W4385890147 hasConcept C190902152 @default.
- W4385890147 hasConcept C199360897 @default.
- W4385890147 hasConcept C26713055 @default.
- W4385890147 hasConcept C2777904410 @default.
- W4385890147 hasConcept C38652104 @default.
- W4385890147 hasConcept C41008148 @default.
- W4385890147 hasConcept C42935608 @default.
- W4385890147 hasConcept C43126263 @default.
- W4385890147 hasConcept C558772884 @default.
- W4385890147 hasConcept C58013763 @default.
- W4385890147 hasConcept C80444323 @default.
- W4385890147 hasConceptScore W4385890147C118524514 @default.
- W4385890147 hasConceptScore W4385890147C132525143 @default.
- W4385890147 hasConceptScore W4385890147C139571649 @default.
- W4385890147 hasConceptScore W4385890147C149635348 @default.
- W4385890147 hasConceptScore W4385890147C154690210 @default.
- W4385890147 hasConceptScore W4385890147C165696696 @default.
- W4385890147 hasConceptScore W4385890147C169590947 @default.
- W4385890147 hasConceptScore W4385890147C173608175 @default.
- W4385890147 hasConceptScore W4385890147C190902152 @default.
- W4385890147 hasConceptScore W4385890147C199360897 @default.
- W4385890147 hasConceptScore W4385890147C26713055 @default.
- W4385890147 hasConceptScore W4385890147C2777904410 @default.
- W4385890147 hasConceptScore W4385890147C38652104 @default.
- W4385890147 hasConceptScore W4385890147C41008148 @default.
- W4385890147 hasConceptScore W4385890147C42935608 @default.
- W4385890147 hasConceptScore W4385890147C43126263 @default.
- W4385890147 hasConceptScore W4385890147C558772884 @default.
- W4385890147 hasConceptScore W4385890147C58013763 @default.
- W4385890147 hasConceptScore W4385890147C80444323 @default.
- W4385890147 hasLocation W43858901471 @default.
- W4385890147 hasOpenAccess W4385890147 @default.
- W4385890147 hasPrimaryLocation W43858901471 @default.
- W4385890147 hasRelatedWork W1497385637 @default.
- W4385890147 hasRelatedWork W1541585229 @default.
- W4385890147 hasRelatedWork W1583465708 @default.
- W4385890147 hasRelatedWork W1601646354 @default.
- W4385890147 hasRelatedWork W1606851719 @default.
- W4385890147 hasRelatedWork W1827234896 @default.
- W4385890147 hasRelatedWork W1853049011 @default.
- W4385890147 hasRelatedWork W2150815772 @default.
- W4385890147 hasRelatedWork W2192862863 @default.
- W4385890147 hasRelatedWork W2479014312 @default.
- W4385890147 isParatext "false" @default.
- W4385890147 isRetracted "false" @default.
- W4385890147 workType "article" @default.