Special Session : Approximation and Fault Resiliency of DNN Accelerators

• 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.

Subject headings

TEKNIK OCH TEKNOLOGIER  -- Elektroteknik och elektronik -- Datorsystem (hsv//swe)

ENGINEERING AND TECHNOLOGY  -- Electrical Engineering, Electronic Engineering, Information Engineering -- Computer Systems (hsv//eng)

Keyword

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

Publication and Content Type

ref (subject category)

kon (subject category)