Titel

Merkliste
1 Ergebnisse

DeftNN : addressing bottlenecks for DNN execution on GPU..:

, In: Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchitecture,

Hill, Parker ; Jain, Animesh ; Hill, Mason... - p. 786-799 , 2017

Link: https://dl.acm.org/doi/10.1145/3123939.3123970

RT 
T1 <cTitle>Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchitecture</cTitle>: T1 <Title>DeftNN				: addressing bottlenecks for DNN execution on GPUs via synapse vector elimination and near-compute data fission</Title>

UL https://suche.suub.uni-bremen.de/peid=acm-3123970&Exemplar=1&LAN=DE
				
A1 Hill, Parker
A1 Jain, Animesh
A1 Hill, Mason
A1 Zamirai, Babak
A1 Hsu, Chang-Hong
A1 Laurenzano, Michael A.
A1 Mahlke, Scott
A1 Tang, Lingjia
A1 Mars, Jason
PB ACM
YR 2017
K1 GPU architecture
K1 deep neural networks
K1 memory bandwidth
K1 performance optimization
K1 Computing methodologies
K1 Machine learning
K1 Machine learning approaches
K1 Neural networks
K1 General and reference
K1 Cross-computing tools and techniques
K1 Performance
K1 Computer systems organization
K1 Architectures
K1 Parallel architectures
K1 Single instruction, multiple data
SP 786
OP 799
LK http://dx.doi.org/https://dl.acm.org/doi/10.1145/3123939.3123970
DO https://dl.acm.org/doi/10.1145/3123939.3123970
SF ELIB - SuUB Bremen

Export

RefWorks (nur Desktop-Version!)
Flow (Zuerst in Flow einloggen, dann importieren)