Sökning: onr:"swepub:oai:DiVA.org:mdh-63673" >
Special Session :
Special Session : Approximation and Fault Resiliency of DNN Accelerators
-
- Ahmadilivani, Mohammed. H. (författare)
- Tallinn University of Technology, Estonia
-
- Barbareschi, Mario (författare)
- University of Naples Federico II, Italy
-
- Barone, Salvatore (författare)
- University of Naples Federico II, Italy
-
visa fler...
-
- Bosio, Alberto (författare)
- Ecole Centrale de Lyon, France
-
- Daneshtalab, Masoud (författare)
- Mälardalens universitet,Inbyggda system,Tallinn University of Technology, Estonia
-
- Torca, Salvatore. D. (författare)
- University of Naples Federico II, Italy
-
- Gavarini, Gabriele (författare)
- Politecnico di Torino, Italy
-
- Jenihhin, Maksim (författare)
- Tallinn University of Technology, Estonia
-
- Raik, Jaan (författare)
- Tallinn University of Technology, Estonia
-
- Ruospo, Annachiara (författare)
- Politecnico di Torino, Italy
-
- Sanchez, Ernesto (författare)
- Politecnico di Torino, Italy
-
- Taheri, Mahdi (författare)
- Tallinn University of Technology, Estonia
-
visa färre...
-
(creator_code:org_t)
- IEEE Computer Society, 2023
- 2023
- Engelska.
-
Ingår i: Proceedings of the IEEE VLSI Test Symposium. - : IEEE Computer Society. - 9798350346305
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Deep Learning, and in particular, Deep Neural Network (DNN) is nowadays widely used in many scenarios, including safety-critical applications such as autonomous driving. In this context, besides energy efficiency and performance, reliability plays a crucial role since a system failure can jeopardize human life. As with any other device, the reliability of hardware architectures running DNNs has to be evaluated, usually through costly fault injection campaigns. This paper explores approximation and fault resiliency of DNN accelerators. We propose to use approximate (AxC) arithmetic circuits to agilely emulate errors in hardware without performing fault injection on the DNN. To allow fast evaluation of AxC DNN, we developed an efficient GPU-based simulation framework. Further, we propose a fine-grain analysis of fault resiliency by examining fault propagation and masking in networks.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Datorsystem (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Computer Systems (hsv//eng)
Nyckelord
- approximate computing
- deep neural networks
- fault emulation
- reliability
- resiliency assessment
- Backpropagation
- Energy efficiency
- Safety engineering
- Software testing
- Autonomous driving
- Efficiency and performance
- Fault emulations
- Fault injection
- Human lives
- Performance reliability
- Safety critical applications
- System failures
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas
- Av författaren/redakt...
-
Ahmadilivani, Mo ...
-
Barbareschi, Mar ...
-
Barone, Salvator ...
-
Bosio, Alberto
-
Daneshtalab, Mas ...
-
Torca, Salvatore ...
-
visa fler...
-
Gavarini, Gabrie ...
-
Jenihhin, Maksim
-
Raik, Jaan
-
Ruospo, Annachia ...
-
Sanchez, Ernesto
-
Taheri, Mahdi
-
visa färre...
- Om ämnet
-
- TEKNIK OCH TEKNOLOGIER
-
TEKNIK OCH TEKNO ...
-
och Elektroteknik oc ...
-
och Datorsystem
- Artiklar i publikationen
-
Proceedings of t ...
- Av lärosätet
-
Mälardalens universitet