FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950973902> ?p ?o ?g. }

• W2950973902 abstract "Most deep neural networks deployed today are trained using GPUs via high-level frameworks such as TensorFlow and PyTorch. This paper describes changes we made to the GPGPU-Sim simulator to enable it to run PyTorch by running PTX kernels included in NVIDIA's cuDNN library. We use the resulting modified simulator, which has been made available publicly with this paper, to study some simple deep learning workloads. With our changes to GPGPU-Sim's functional simulation model, we find GPGPU-Sim performance model running a cuDNN enabled implementation of LeNet for MNIST reports results within 30% of real hardware. Using GPGPU-Sim's AerialVision performance analysis tool we observe that cuDNN API calls contain many varying phases and appear to include potentially inefficient microarchitecture behaviour such as DRAM partition bank camping, at least when executed on GPGPU-Sim's current performance model." @default.
• W2950973902 created "2019-06-27" @default.
• W2950973902 creator A5011399602 @default.
• W2950973902 creator A5011539999 @default.
• W2950973902 creator A5013836260 @default.
• W2950973902 creator A5015196366 @default.
• W2950973902 creator A5015392786 @default.
• W2950973902 creator A5026554402 @default.
• W2950973902 creator A5026788167 @default.
• W2950973902 creator A5038577900 @default.
• W2950973902 creator A5047054160 @default.
• W2950973902 creator A5055071069 @default.
• W2950973902 creator A5086960944 @default.
• W2950973902 date "2018-11-18" @default.
• W2950973902 modified "2023-09-27" @default.
• W2950973902 title "Analyzing Machine Learning Workloads Using a Detailed GPU Simulator" @default.
• W2950973902 cites W137106866 @default.
• W2950973902 cites W1487564550 @default.
• W2950973902 cites W1667652561 @default.
• W2950973902 cites W1686810756 @default.
• W2950973902 cites W1979527452 @default.
• W2950973902 cites W2026883296 @default.
• W2950973902 cites W2064941923 @default.
• W2950973902 cites W2080592089 @default.
• W2950973902 cites W2097117768 @default.
• W2950973902 cites W2112796928 @default.
• W2950973902 cites W2134101883 @default.
• W2950973902 cites W2194775991 @default.
• W2950973902 cites W2233116163 @default.
• W2950973902 cites W2279098554 @default.
• W2950973902 cites W2285660444 @default.
• W2950973902 cites W2541839172 @default.
• W2950973902 cites W2612445135 @default.
• W2950973902 cites W2625457103 @default.
• W2950973902 cites W2763421725 @default.
• W2950973902 cites W2795994638 @default.
• W2950973902 cites W2899771611 @default.
• W2950973902 cites W2962821792 @default.
• W2950973902 cites W2963340555 @default.
• W2950973902 cites W2963446712 @default.
• W2950973902 cites W2964330541 @default.
• W2950973902 hasPublicationYear "2018" @default.
• W2950973902 type Work @default.
• W2950973902 sameAs 2950973902 @default.
• W2950973902 citedByCount "1" @default.
• W2950973902 countsByYear W29509739022020 @default.
• W2950973902 crossrefType "posted-content" @default.
• W2950973902 hasAuthorship W2950973902A5011399602 @default.
• W2950973902 hasAuthorship W2950973902A5011539999 @default.
• W2950973902 hasAuthorship W2950973902A5013836260 @default.
• W2950973902 hasAuthorship W2950973902A5015196366 @default.
• W2950973902 hasAuthorship W2950973902A5015392786 @default.
• W2950973902 hasAuthorship W2950973902A5026554402 @default.
• W2950973902 hasAuthorship W2950973902A5026788167 @default.
• W2950973902 hasAuthorship W2950973902A5038577900 @default.
• W2950973902 hasAuthorship W2950973902A5047054160 @default.
• W2950973902 hasAuthorship W2950973902A5055071069 @default.
• W2950973902 hasAuthorship W2950973902A5086960944 @default.
• W2950973902 hasConcept C107598950 @default.
• W2950973902 hasConcept C108583219 @default.
• W2950973902 hasConcept C111919701 @default.
• W2950973902 hasConcept C114614502 @default.
• W2950973902 hasConcept C118524514 @default.
• W2950973902 hasConcept C154945302 @default.
• W2950973902 hasConcept C173608175 @default.
• W2950973902 hasConcept C190502265 @default.
• W2950973902 hasConcept C21442007 @default.
• W2950973902 hasConcept C2778119891 @default.
• W2950973902 hasConcept C33923547 @default.
• W2950973902 hasConcept C41008148 @default.
• W2950973902 hasConcept C42812 @default.
• W2950973902 hasConcept C50630238 @default.
• W2950973902 hasConcept C68339613 @default.
• W2950973902 hasConcept C7366592 @default.
• W2950973902 hasConcept C9390403 @default.
• W2950973902 hasConceptScore W2950973902C107598950 @default.
• W2950973902 hasConceptScore W2950973902C108583219 @default.
• W2950973902 hasConceptScore W2950973902C111919701 @default.
• W2950973902 hasConceptScore W2950973902C114614502 @default.
• W2950973902 hasConceptScore W2950973902C118524514 @default.
• W2950973902 hasConceptScore W2950973902C154945302 @default.
• W2950973902 hasConceptScore W2950973902C173608175 @default.
• W2950973902 hasConceptScore W2950973902C190502265 @default.
• W2950973902 hasConceptScore W2950973902C21442007 @default.
• W2950973902 hasConceptScore W2950973902C2778119891 @default.
• W2950973902 hasConceptScore W2950973902C33923547 @default.
• W2950973902 hasConceptScore W2950973902C41008148 @default.
• W2950973902 hasConceptScore W2950973902C42812 @default.
• W2950973902 hasConceptScore W2950973902C50630238 @default.
• W2950973902 hasConceptScore W2950973902C68339613 @default.
• W2950973902 hasConceptScore W2950973902C7366592 @default.
• W2950973902 hasConceptScore W2950973902C9390403 @default.
• W2950973902 hasLocation W29509739021 @default.
• W2950973902 hasOpenAccess W2950973902 @default.
• W2950973902 hasPrimaryLocation W29509739021 @default.
• W2950973902 hasRelatedWork W1991056822 @default.
• W2950973902 hasRelatedWork W2005865076 @default.
• W2950973902 hasRelatedWork W2021476856 @default.
• W2950973902 hasRelatedWork W2073616138 @default.
• W2950973902 hasRelatedWork W2086739451 @default.

• next