Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Engineering
Single-Rail Adiabatic Logic For Energy-Efficient And Cpa-Resistant Cryptographic Circuit In Low-Frequency Medical Devices, Amit Degada, Himanshu Thapliyal
Single-Rail Adiabatic Logic For Energy-Efficient And Cpa-Resistant Cryptographic Circuit In Low-Frequency Medical Devices, Amit Degada, Himanshu Thapliyal
Electrical and Computer Engineering Graduate Research
Designing energy-efficient and secure cryptographic circuits in low-frequency medical devices are challenging due to low-energy requirements. Also, the conventional CMOS logic-based cryptographic circuits solutions in medical devices can be vulnerable to side-channel attacks (e.g. correlation power analysis (CPA)). In this article, we explored single-rail Clocked CMOS Adiabatic Logic (CCAL) to design an energy-efficient and secure cryptographic circuit for low-frequency medical devices. The performance of the CCAL logic-based circuits was checked with a power clock generator (2N2P-PCG) integrated into the design for the frequency range of 50 kHz to 250 kHz. The CCAL logic gates show an average of approximately 48% …
Uptpu: Improving Energy Efficiency Of A Tensor Processing Unit Through Underutilization Based Power-Gating, Pramesh Pandey, Noel Daniel Gundi, Koushik Chakraborty, Sanghamitra Roy
Uptpu: Improving Energy Efficiency Of A Tensor Processing Unit Through Underutilization Based Power-Gating, Pramesh Pandey, Noel Daniel Gundi, Koushik Chakraborty, Sanghamitra Roy
Electrical and Computer Engineering Faculty Publications
The AI boom is bringing a plethora of domain-specific architectures for Neural Network computations. Google's Tensor Processing Unit (TPU), a Deep Neural Network (DNN) accelerator, has replaced the CPUs/GPUs in its data centers, claiming more than 15 × rate of inference. However, the unprecedented growth in DNN workloads with the widespread use of AI services projects an increasing energy consumption of TPU based data centers. In this work, we parametrize the extreme hardware underutilization in TPU systolic array and propose UPTPU: an intelligent, dataflow adaptive power-gating paradigm to provide a staggering 3.5 ×-6.5× energy efficiency to TPU for different input …
Energy And Greenhouse Gas Savings For Leed-Certified U.S. Office Buildings, John H. Scofield, Susannah Brodnitz, Jakob Cornell, Tian Liang, Thomas Scofield
Energy And Greenhouse Gas Savings For Leed-Certified U.S. Office Buildings, John H. Scofield, Susannah Brodnitz, Jakob Cornell, Tian Liang, Thomas Scofield
University Faculty Publications and Creative Works
In this work, we present results from the largest study of measured, whole-building energy performance for commercial LEED-certified buildings, using 2016 energy use data that were obtained for 4417 commercial office buildings (114 million m2 ) from municipal energy benchmarking disclosures for 10 major U.S. cities. The properties included 551 buildings (31 million m2 ) that we identified as LEED-certified. Annual energy use and greenhouse gas (GHG) emission were compared between LEED and non-LEED offices on a city-by-city basis and in aggregate. In aggregate, LEED offices demonstrated 11% site energy savings but only 7% savings in source energy and GHG …