FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897519942> ?p ?o ?g. }

• W2897519942 endingPage "866" @default.
• W2897519942 startingPage "852" @default.
• W2897519942 abstract "The rising use of deep learning and other big-data algorithms has led to an increasing demand for hardware platforms that are computationally powerful, yet energy-efficient. Due to the amount of data parallelism in these algorithms, high-performance 3D manycore platforms that incorporate both CPUs and GPUs present a promising direction. However, as systems use heterogeneity (e.g., a combination of CPUs, GPUs, and accelerators) to improve performance and efficiency, it becomes more pertinent to address the distinct and likely conflicting communication requirements (e.g., CPU memory access latency or GPU network throughput) that arise from such heterogeneity. Unfortunately, it is difficult to quickly explore the hardware design space and choose appropriate tradeoffs between these heterogeneous requirements. To address these challenges, we propose the design of a 3D Network-on-Chip (NoC) for heterogeneous manycore platforms that considers the appropriate design objectives for a 3D heterogeneous system and explores various tradeoffs using an efficient ML-based multi-objective optimization technique. The proposed design space exploration considers the various requirements of its heterogeneous components and generates a set of 3D NoC architectures that efficiently trades off these design objectives. Our findings show that by jointly considering these requirements (latency, throughput, temperature, and energy), we can achieve 9.6% better Energy-Delay Product on average at nearly iso-temperature conditions when compared to a thermally-optimized design for 3D heterogeneous NoCs. More importantly, our results suggest that our 3D NoCs optimized for a few applications can be generalized for unknown applications as well. Our results show that these generalized 3D NoCs only incur a 1.8% (36-tile system) and 1.1% (64-tile system) average performance loss compared to application-specific NoCs." @default.
• W2897519942 created "2018-10-26" @default.
• W2897519942 creator A5033021422 @default.
• W2897519942 creator A5036227385 @default.
• W2897519942 creator A5055445718 @default.
• W2897519942 creator A5065985595 @default.
• W2897519942 creator A5078441163 @default.
• W2897519942 creator A5089540762 @default.
• W2897519942 date "2019-06-01" @default.
• W2897519942 modified "2023-10-15" @default.
• W2897519942 title "Learning-Based Application-Agnostic 3D NoC Design for Heterogeneous Manycore Systems" @default.
• W2897519942 cites W1541633348 @default.
• W2897519942 cites W1564638059 @default.
• W2897519942 cites W1941428696 @default.
• W2897519942 cites W1964978749 @default.
• W2897519942 cites W1980094609 @default.
• W2897519942 cites W1994999558 @default.
• W2897519942 cites W2005532616 @default.
• W2897519942 cites W2023264348 @default.
• W2897519942 cites W2026883296 @default.
• W2897519942 cites W2066985990 @default.
• W2897519942 cites W2079248286 @default.
• W2897519942 cites W2080592089 @default.
• W2897519942 cites W2093043622 @default.
• W2897519942 cites W2104492856 @default.
• W2897519942 cites W2106404421 @default.
• W2897519942 cites W2106562406 @default.
• W2897519942 cites W2109128040 @default.
• W2897519942 cites W2109255166 @default.
• W2897519942 cites W2112796928 @default.
• W2897519942 cites W2122636510 @default.
• W2897519942 cites W2123406209 @default.
• W2897519942 cites W2126105956 @default.
• W2897519942 cites W2130820665 @default.
• W2897519942 cites W2140855716 @default.
• W2897519942 cites W2141973190 @default.
• W2897519942 cites W2147541574 @default.
• W2897519942 cites W2148615815 @default.
• W2897519942 cites W2151338124 @default.
• W2897519942 cites W2153215457 @default.
• W2897519942 cites W2153654820 @default.
• W2897519942 cites W2157225945 @default.
• W2897519942 cites W2159218826 @default.
• W2897519942 cites W2170382128 @default.
• W2897519942 cites W2465608688 @default.
• W2897519942 cites W2618530766 @default.
• W2897519942 cites W2756437767 @default.
• W2897519942 cites W2963565222 @default.
• W2897519942 cites W3101558675 @default.
• W2897519942 cites W3142845206 @default.
• W2897519942 doi "https://doi.org/10.1109/tc.2018.2889053" @default.
• W2897519942 hasPublicationYear "2019" @default.
• W2897519942 type Work @default.
• W2897519942 sameAs 2897519942 @default.
• W2897519942 citedByCount "40" @default.
• W2897519942 countsByYear W28975199422019 @default.
• W2897519942 countsByYear W28975199422020 @default.
• W2897519942 countsByYear W28975199422021 @default.
• W2897519942 countsByYear W28975199422022 @default.
• W2897519942 countsByYear W28975199422023 @default.
• W2897519942 crossrefType "journal-article" @default.
• W2897519942 hasAuthorship W2897519942A5033021422 @default.
• W2897519942 hasAuthorship W2897519942A5036227385 @default.
• W2897519942 hasAuthorship W2897519942A5055445718 @default.
• W2897519942 hasAuthorship W2897519942A5065985595 @default.
• W2897519942 hasAuthorship W2897519942A5078441163 @default.
• W2897519942 hasAuthorship W2897519942A5089540762 @default.
• W2897519942 hasBestOaLocation W28975199422 @default.
• W2897519942 hasConcept C108037233 @default.
• W2897519942 hasConcept C118524514 @default.
• W2897519942 hasConcept C119599485 @default.
• W2897519942 hasConcept C120314980 @default.
• W2897519942 hasConcept C127413603 @default.
• W2897519942 hasConcept C149635348 @default.
• W2897519942 hasConcept C157764524 @default.
• W2897519942 hasConcept C158207573 @default.
• W2897519942 hasConcept C172430144 @default.
• W2897519942 hasConcept C173608175 @default.
• W2897519942 hasConcept C2742236 @default.
• W2897519942 hasConcept C2776221188 @default.
• W2897519942 hasConcept C41008148 @default.
• W2897519942 hasConcept C555944384 @default.
• W2897519942 hasConcept C76155785 @default.
• W2897519942 hasConcept C82876162 @default.
• W2897519942 hasConceptScore W2897519942C108037233 @default.
• W2897519942 hasConceptScore W2897519942C118524514 @default.
• W2897519942 hasConceptScore W2897519942C119599485 @default.
• W2897519942 hasConceptScore W2897519942C120314980 @default.
• W2897519942 hasConceptScore W2897519942C127413603 @default.
• W2897519942 hasConceptScore W2897519942C149635348 @default.
• W2897519942 hasConceptScore W2897519942C157764524 @default.
• W2897519942 hasConceptScore W2897519942C158207573 @default.
• W2897519942 hasConceptScore W2897519942C172430144 @default.
• W2897519942 hasConceptScore W2897519942C173608175 @default.
• W2897519942 hasConceptScore W2897519942C2742236 @default.
• W2897519942 hasConceptScore W2897519942C2776221188 @default.
• W2897519942 hasConceptScore W2897519942C41008148 @default.
• W2897519942 hasConceptScore W2897519942C555944384 @default.

• next