Matches in SemOpenAlex for { <https://semopenalex.org/work/W4327852053> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4327852053 endingPage "389" @default.
- W4327852053 startingPage "375" @default.
- W4327852053 abstract "Model-Based Iterative Reconstruction (MBIR) algorithms iteratively use expensive computational operators of forward and backward projections. The irregular memory access pattern of these operators makes them a memory-bound application. Their computation time must be reduced to meet clinical routine constraints. This article proposes a hardware accelerator architecture based on Field Programmable Gate Arrays (FPGAs) through high-level language, as an alternative to GPU architecture. This acceleration is based on an offline memory access analysis to address the main bottleneck of the algorithm and maximize the data reuse rate. The offline analysis allows for the tuning of the architecture parameters so that they converge to an optimal solution. Then, the Berkeley Roofline model guides our optimization steps by iteratively analyzing the design performance. Our design flow significantly improved the algorithm's computational intensity and overcame the memory bottleneck. Thus, our architecture takes advantage of the FPGA local memory to achieve significant memory bandwidth and efficiently harness the pipeline without stalling the computation. Furthermore, we present the scaling-up strategy from mid-range FPGA to high-end FPGA and any concerns of portability. We used two Intel FPGA devices to implement the algorithm, and then we compared the results with our GPU implementation in terms of speedup and energy efficiency. Our experimental results show that our design has achieved better computational throughput than the works on FPGA architectures reported in the literature." @default.
- W4327852053 created "2023-03-20" @default.
- W4327852053 creator A5000664485 @default.
- W4327852053 creator A5082573179 @default.
- W4327852053 date "2023-04-01" @default.
- W4327852053 modified "2023-09-30" @default.
- W4327852053 title "X-Ray Tomography Reconstruction Accelerated on FPGA Through High-Level Synthesis Tools" @default.
- W4327852053 cites W1998277304 @default.
- W4327852053 cites W2002555321 @default.
- W4327852053 cites W2003624223 @default.
- W4327852053 cites W2053958583 @default.
- W4327852053 cites W2067830498 @default.
- W4327852053 cites W2081395699 @default.
- W4327852053 cites W2130097981 @default.
- W4327852053 cites W2157812230 @default.
- W4327852053 cites W2159269332 @default.
- W4327852053 cites W2159940799 @default.
- W4327852053 cites W2294171759 @default.
- W4327852053 cites W2583383421 @default.
- W4327852053 cites W2589329959 @default.
- W4327852053 cites W2890624533 @default.
- W4327852053 cites W2912291740 @default.
- W4327852053 cites W2961292910 @default.
- W4327852053 cites W2965136699 @default.
- W4327852053 cites W2980171969 @default.
- W4327852053 cites W3034467352 @default.
- W4327852053 cites W3034508728 @default.
- W4327852053 cites W3038517061 @default.
- W4327852053 cites W3166405244 @default.
- W4327852053 cites W3170007692 @default.
- W4327852053 cites W4252821989 @default.
- W4327852053 doi "https://doi.org/10.1109/tbcas.2023.3258879" @default.
- W4327852053 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37030851" @default.
- W4327852053 hasPublicationYear "2023" @default.
- W4327852053 type Work @default.
- W4327852053 citedByCount "0" @default.
- W4327852053 crossrefType "journal-article" @default.
- W4327852053 hasAuthorship W4327852053A5000664485 @default.
- W4327852053 hasAuthorship W4327852053A5082573179 @default.
- W4327852053 hasConcept C113775141 @default.
- W4327852053 hasConcept C11413529 @default.
- W4327852053 hasConcept C142962650 @default.
- W4327852053 hasConcept C149635348 @default.
- W4327852053 hasConcept C173608175 @default.
- W4327852053 hasConcept C188045654 @default.
- W4327852053 hasConcept C199360897 @default.
- W4327852053 hasConcept C2780513914 @default.
- W4327852053 hasConcept C41008148 @default.
- W4327852053 hasConcept C42935608 @default.
- W4327852053 hasConcept C43521106 @default.
- W4327852053 hasConcept C45374587 @default.
- W4327852053 hasConcept C63000827 @default.
- W4327852053 hasConcept C68339613 @default.
- W4327852053 hasConceptScore W4327852053C113775141 @default.
- W4327852053 hasConceptScore W4327852053C11413529 @default.
- W4327852053 hasConceptScore W4327852053C142962650 @default.
- W4327852053 hasConceptScore W4327852053C149635348 @default.
- W4327852053 hasConceptScore W4327852053C173608175 @default.
- W4327852053 hasConceptScore W4327852053C188045654 @default.
- W4327852053 hasConceptScore W4327852053C199360897 @default.
- W4327852053 hasConceptScore W4327852053C2780513914 @default.
- W4327852053 hasConceptScore W4327852053C41008148 @default.
- W4327852053 hasConceptScore W4327852053C42935608 @default.
- W4327852053 hasConceptScore W4327852053C43521106 @default.
- W4327852053 hasConceptScore W4327852053C45374587 @default.
- W4327852053 hasConceptScore W4327852053C63000827 @default.
- W4327852053 hasConceptScore W4327852053C68339613 @default.
- W4327852053 hasIssue "2" @default.
- W4327852053 hasLocation W43278520531 @default.
- W4327852053 hasLocation W43278520532 @default.
- W4327852053 hasOpenAccess W4327852053 @default.
- W4327852053 hasPrimaryLocation W43278520531 @default.
- W4327852053 hasRelatedWork W1572523360 @default.
- W4327852053 hasRelatedWork W2063532530 @default.
- W4327852053 hasRelatedWork W2071214559 @default.
- W4327852053 hasRelatedWork W2116951845 @default.
- W4327852053 hasRelatedWork W2388140273 @default.
- W4327852053 hasRelatedWork W2946227552 @default.
- W4327852053 hasRelatedWork W3034872807 @default.
- W4327852053 hasRelatedWork W4327911812 @default.
- W4327852053 hasRelatedWork W2582864838 @default.
- W4327852053 hasRelatedWork W2599858257 @default.
- W4327852053 hasVolume "17" @default.
- W4327852053 isParatext "false" @default.
- W4327852053 isRetracted "false" @default.
- W4327852053 workType "article" @default.