Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 7 of 7 for “"undervolting"”.
-
Finding and exploiting faults in hardware and software
… operating voltage. We further investigate the undervolting effect and are able to improve the attack to create an out-of-bounds under/overflow. Meanwhile, fault injection attacks (such as our software undervolting one) represent a major threat to Internet-of-Things and embedded devices. As of …
-
Improving Efficiency and Robustness for Neural Networks Inference and Training
… robustness of the network. An importance-aware undervolting technique is proposed in this dissertation to achieve high inference robustness and low training energy consumption at the same time. Furthermore, image super-resolution (SR) which bridges the gap between modern hardware and real-time …
-
Achieving Low-Cost and High-Efficient Robust Inference and Training for Convolutional Neural Networks
… targets on adversarial inputs. It utilizes the undervolting technique and process variation to generate hardware based diverse noise patterns, effectively mitigating the impact of misleading adversarial noises during inference. LP-RFL, on the other hand, is a low-cost weight gradient …
-
Software policies and techniques for improving the energy and cost efficiency of cloud and high-performance computing infrastructures
… and the more aggressive approaches of voltage (undervolting) and frequency (overclocking) overscaling of the processor. We introduce models for estimating the failure rate for each of the aforementioned techniques (VFS, undervolting, overclocking). Our models capture the expected energy …
-
Techniques with Impact of Process Variation in CNN Neuron Computation Output
… examples, using FPGA by overclocking and/or undervolting and attempting to run neuron-like circuits under these conditions. The use of FPGA is a free energy resource with which to introduce noise. With data of possible correlation between baseline and incorrect values, we can from there …
-
Optimization-Driven Techniques for mm-Wave Beamforming and Power Delivery Analysis in Digital SoCs
This dissertation explores optimization-driven techniques to enhance the performance of digital integrated circuits, with three primary contributions: the design and implementation of two baseband processors for optimal mm-Wave beamforming, and the estimation of worst-case supply-voltage (Vdd) …
-
Exploiting intrinsic hardware guardbands and software heterogeneity to improve the energy efficiency of computing systems
A key challenge for both current- and next-generation computing infrastructure deployments is to increase the delivered computational performance within stringent power budget constraints due to power delivery, cooling and cost-related concerns. Techniques such as transistor shrinking, frequency …