FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4236651103> ?p ?o ?g. }

• W4236651103 abstract "FPGAs are a popular target for application-specific accelerators because they lead to a good balance between flexibility and energy efficiency. However, FPGA lookup tables introduce significant area and power overheads, making it difficult to use FPGA devices in environments with tight cost and power constraints. This is the case for datacenter servers, where a modestly-sized FPGA cannot accommodate the large number of diverse accelerators that datacenter applications need. This paper introduces DRAF, an architecture for bit-level reconfigurable logic that uses DRAM subarrays to implement dense lookup tables. DRAF overlaps DRAM operations like bitline precharge and charge restoration with routing within the reconfigurable routing fabric to minimize the impact of DRAM latency. It also supports multiple configuration contexts that can be used to quickly switch between different accelerators with minimal latency. Overall, DRAF trades off some of the performance of FPGAs for significant gains in area and power. DRAF improves area density by 10x over FPGAs and power consumption by more than 3x, enabling DRAF to satisfy demanding applications within strict power and cost constraints. While accelerators mapped to DRAF are 2-3x slower than those in FPGAs, they still deliver a 13x speedup and an 11x reduction in power consumption over a Xeon core for a wide range of datacenter tasks, including analytics and interactive services like speech recognition." @default.
• W4236651103 created "2022-05-12" @default.
• W4236651103 creator A5001498296 @default.
• W4236651103 creator A5026297396 @default.
• W4236651103 creator A5032065701 @default.
• W4236651103 creator A5042148531 @default.
• W4236651103 creator A5046896624 @default.
• W4236651103 creator A5054003129 @default.
• W4236651103 creator A5068606980 @default.
• W4236651103 date "2016-06-01" @default.
• W4236651103 modified "2023-10-16" @default.
• W4236651103 title "DRAF: A Low-Power DRAM-Based Reconfigurable Acceleration Fabric" @default.
• W4236651103 cites W105298322 @default.
• W4236651103 cites W1523051745 @default.
• W4236651103 cites W1963998358 @default.
• W4236651103 cites W1981943579 @default.
• W4236651103 cites W1997979052 @default.
• W4236651103 cites W1999085092 @default.
• W4236651103 cites W2002436356 @default.
• W4236651103 cites W2003313945 @default.
• W4236651103 cites W2005602803 @default.
• W4236651103 cites W2012114780 @default.
• W4236651103 cites W2025787141 @default.
• W4236651103 cites W2047128179 @default.
• W4236651103 cites W2048466306 @default.
• W4236651103 cites W2059706055 @default.
• W4236651103 cites W2062949766 @default.
• W4236651103 cites W2072240626 @default.
• W4236651103 cites W2092324191 @default.
• W4236651103 cites W2099517310 @default.
• W4236651103 cites W2105993646 @default.
• W4236651103 cites W2112980698 @default.
• W4236651103 cites W2114440330 @default.
• W4236651103 cites W2124402195 @default.
• W4236651103 cites W2125662502 @default.
• W4236651103 cites W2130408605 @default.
• W4236651103 cites W2133027790 @default.
• W4236651103 cites W2134890772 @default.
• W4236651103 cites W2138661001 @default.
• W4236651103 cites W2155814884 @default.
• W4236651103 cites W2155876789 @default.
• W4236651103 cites W2158565219 @default.
• W4236651103 cites W2164431468 @default.
• W4236651103 cites W2164586147 @default.
• W4236651103 cites W2170116489 @default.
• W4236651103 cites W2171768221 @default.
• W4236651103 cites W2335240678 @default.
• W4236651103 cites W2545376626 @default.
• W4236651103 cites W3103757032 @default.
• W4236651103 cites W3147974890 @default.
• W4236651103 cites W4206412226 @default.
• W4236651103 cites W4231523356 @default.
• W4236651103 cites W4233030175 @default.
• W4236651103 cites W4251693568 @default.
• W4236651103 cites W4256629673 @default.
• W4236651103 doi "https://doi.org/10.1109/isca.2016.51" @default.
• W4236651103 hasPublicationYear "2016" @default.
• W4236651103 type Work @default.
• W4236651103 citedByCount "5" @default.
• W4236651103 countsByYear W42366511032017 @default.
• W4236651103 countsByYear W42366511032018 @default.
• W4236651103 countsByYear W42366511032019 @default.
• W4236651103 crossrefType "proceedings-article" @default.
• W4236651103 hasAuthorship W4236651103A5001498296 @default.
• W4236651103 hasAuthorship W4236651103A5026297396 @default.
• W4236651103 hasAuthorship W4236651103A5032065701 @default.
• W4236651103 hasAuthorship W4236651103A5042148531 @default.
• W4236651103 hasAuthorship W4236651103A5046896624 @default.
• W4236651103 hasAuthorship W4236651103A5054003129 @default.
• W4236651103 hasAuthorship W4236651103A5068606980 @default.
• W4236651103 hasConcept C142962650 @default.
• W4236651103 hasConcept C149635348 @default.
• W4236651103 hasConcept C173608175 @default.
• W4236651103 hasConcept C41008148 @default.
• W4236651103 hasConcept C42935608 @default.
• W4236651103 hasConcept C68339613 @default.
• W4236651103 hasConcept C7366592 @default.
• W4236651103 hasConcept C76155785 @default.
• W4236651103 hasConcept C82876162 @default.
• W4236651103 hasConcept C9390403 @default.
• W4236651103 hasConceptScore W4236651103C142962650 @default.
• W4236651103 hasConceptScore W4236651103C149635348 @default.
• W4236651103 hasConceptScore W4236651103C173608175 @default.
• W4236651103 hasConceptScore W4236651103C41008148 @default.
• W4236651103 hasConceptScore W4236651103C42935608 @default.
• W4236651103 hasConceptScore W4236651103C68339613 @default.
• W4236651103 hasConceptScore W4236651103C7366592 @default.
• W4236651103 hasConceptScore W4236651103C76155785 @default.
• W4236651103 hasConceptScore W4236651103C82876162 @default.
• W4236651103 hasConceptScore W4236651103C9390403 @default.
• W4236651103 hasLocation W42366511031 @default.
• W4236651103 hasOpenAccess W4236651103 @default.
• W4236651103 hasPrimaryLocation W42366511031 @default.
• W4236651103 hasRelatedWork W1508811950 @default.
• W4236651103 hasRelatedWork W1509211761 @default.
• W4236651103 hasRelatedWork W2102773950 @default.
• W4236651103 hasRelatedWork W2141458065 @default.
• W4236651103 hasRelatedWork W2375326151 @default.
• W4236651103 hasRelatedWork W2379863404 @default.
• W4236651103 hasRelatedWork W2987062793 @default.

• next