Matches in SemOpenAlex for { <https://semopenalex.org/work/W2928320209> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2928320209 abstract "Probabilistic models (PMs) are ubiquitously used across a variety of machine learning applications. They have been shown to successfully integrate structural prior information about data and effectively quantify uncertainty to enable the development of more powerful, interpretable, and efficient learning algorithms. This paper presents AcMC2, a compiler that transforms PMs into optimized hardware accelerators (for use in FPGAs or ASICs) that utilize Markov chain Monte Carlo methods to infer and query a distribution of posterior samples from the model. The compiler analyzes statistical dependencies in the PM to drive several optimizations to maximally exploit the parallelism and data locality available in the problem. We demonstrate the use of AcMC2 to implement several learning and inference tasks on a Xilinx Virtex-7 FPGA. AcMC2-generated accelerators provide a 47-100× improvement in runtime performance over a 6-core IBM Power8 CPU and a 8-18× improvement over an NVIDIA K80 GPU. This corresponds to a 753-1600× improvement over the CPU and 248-463× over the GPU in performance-per-watt terms." @default.
- W2928320209 created "2019-04-11" @default.
- W2928320209 creator A5032073929 @default.
- W2928320209 creator A5043860236 @default.
- W2928320209 creator A5067802693 @default.
- W2928320209 date "2019-04-04" @default.
- W2928320209 modified "2023-09-26" @default.
- W2928320209 title "AcMC <sup>2</sup>" @default.
- W2928320209 cites W1516506771 @default.
- W2928320209 cites W1963818584 @default.
- W2928320209 cites W1965573563 @default.
- W2928320209 cites W1980452149 @default.
- W2928320209 cites W1983394510 @default.
- W2928320209 cites W1997113918 @default.
- W2928320209 cites W2006384093 @default.
- W2928320209 cites W2012117576 @default.
- W2928320209 cites W2024859348 @default.
- W2928320209 cites W2056760934 @default.
- W2928320209 cites W2090934172 @default.
- W2928320209 cites W2094998159 @default.
- W2928320209 cites W2096544401 @default.
- W2928320209 cites W2110401950 @default.
- W2928320209 cites W2126540423 @default.
- W2928320209 cites W2133309656 @default.
- W2928320209 cites W2137813581 @default.
- W2928320209 cites W2138309709 @default.
- W2928320209 cites W2151439684 @default.
- W2928320209 cites W2295266283 @default.
- W2928320209 cites W2345615132 @default.
- W2928320209 cites W2551841786 @default.
- W2928320209 cites W2577537660 @default.
- W2928320209 cites W2584732844 @default.
- W2928320209 cites W2606722458 @default.
- W2928320209 cites W2624999081 @default.
- W2928320209 cites W2626211758 @default.
- W2928320209 cites W2752488889 @default.
- W2928320209 cites W2785369415 @default.
- W2928320209 cites W4240267682 @default.
- W2928320209 cites W4245440340 @default.
- W2928320209 doi "https://doi.org/10.1145/3297858.3304019" @default.
- W2928320209 hasPublicationYear "2019" @default.
- W2928320209 type Work @default.
- W2928320209 sameAs 2928320209 @default.
- W2928320209 citedByCount "14" @default.
- W2928320209 countsByYear W29283202092019 @default.
- W2928320209 countsByYear W29283202092020 @default.
- W2928320209 countsByYear W29283202092021 @default.
- W2928320209 countsByYear W29283202092022 @default.
- W2928320209 countsByYear W29283202092023 @default.
- W2928320209 crossrefType "proceedings-article" @default.
- W2928320209 hasAuthorship W2928320209A5032073929 @default.
- W2928320209 hasAuthorship W2928320209A5043860236 @default.
- W2928320209 hasAuthorship W2928320209A5067802693 @default.
- W2928320209 hasBestOaLocation W29283202091 @default.
- W2928320209 hasConcept C118524514 @default.
- W2928320209 hasConcept C149635348 @default.
- W2928320209 hasConcept C165696696 @default.
- W2928320209 hasConcept C169590947 @default.
- W2928320209 hasConcept C173608175 @default.
- W2928320209 hasConcept C199360897 @default.
- W2928320209 hasConcept C38652104 @default.
- W2928320209 hasConcept C41008148 @default.
- W2928320209 hasConcept C42935608 @default.
- W2928320209 hasConcept C78766204 @default.
- W2928320209 hasConceptScore W2928320209C118524514 @default.
- W2928320209 hasConceptScore W2928320209C149635348 @default.
- W2928320209 hasConceptScore W2928320209C165696696 @default.
- W2928320209 hasConceptScore W2928320209C169590947 @default.
- W2928320209 hasConceptScore W2928320209C173608175 @default.
- W2928320209 hasConceptScore W2928320209C199360897 @default.
- W2928320209 hasConceptScore W2928320209C38652104 @default.
- W2928320209 hasConceptScore W2928320209C41008148 @default.
- W2928320209 hasConceptScore W2928320209C42935608 @default.
- W2928320209 hasConceptScore W2928320209C78766204 @default.
- W2928320209 hasFunder F4320306076 @default.
- W2928320209 hasLocation W29283202091 @default.
- W2928320209 hasOpenAccess W2928320209 @default.
- W2928320209 hasPrimaryLocation W29283202091 @default.
- W2928320209 hasRelatedWork W1508811940 @default.
- W2928320209 hasRelatedWork W1529511812 @default.
- W2928320209 hasRelatedWork W1545342238 @default.
- W2928320209 hasRelatedWork W1582485370 @default.
- W2928320209 hasRelatedWork W2032980190 @default.
- W2928320209 hasRelatedWork W2081281748 @default.
- W2928320209 hasRelatedWork W2372170743 @default.
- W2928320209 hasRelatedWork W2980373281 @default.
- W2928320209 hasRelatedWork W3004176791 @default.
- W2928320209 hasRelatedWork W93419836 @default.
- W2928320209 isParatext "false" @default.
- W2928320209 isRetracted "false" @default.
- W2928320209 magId "2928320209" @default.
- W2928320209 workType "article" @default.