Near-Threshold Computing: Reclaiming Moore's Law Through Energy Efficient Integrated Circuits
By Ronald Dreslinski Jr., M. Wieckowski, David T. Blaauw, D. Sylvester, T. Mudge. Proceedings of the IEEE, 2010
884 citations recorded by the source corpus.
Subfields: Electrical and Electronic Engineering
View Paper: https://www.semanticscholar.org/paper/5ebe93c255bab795da0f9b44a095342caf915b37
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Electrical and Electronic Engineering
- Luca Benini
- Igor L. Markov
- Daniele Palossi
- Francesco Conti
- Frank Kagan Gürkaynak
- Michael Bedford Taylor
- Davide Rossi
- Eric Flamand
Citations in the corpus
- The Cost of Application-Class Processing: Energy and Performance Analysis of a Linux-Ready 1.7-GHz 64-Bit RISC-V Core in 22-nm FDSOI Technology (2019, methodology): “technology scaling gains from 40 to 22 nm [25], we compare 10 pJ of the small core to 51.”
- A near-threshold RISC-V core with DSP extensions for scalable IoT Endpoint Devices (2016, background): “ULP-operations can be achieved by exploiting the near-threshold voltage regime where transistors become more energy-efficient[7].”
- Is dark silicon useful? Harnessing the four horsemen of the coming dark silicon apocalypse (2012, background): “One recently emerging approach is the use of near-threshold voltage (NTV) logic [5], which operates in the near-threshold regime, providing more less-extreme tradeoffs between energy and delay than conventional subthreshold circuits.”
- Near-Threshold RISC-V Core With DSP Extensions for Scalable IoT Endpoint Devices (2017, neutral): “ULP operations can be achieved by exploiting the near-threshold (NT) voltage regime where transistors become more energy efficient [7].”
- Enabling the heterogeneous accelerator model on ultra-low power microcontroller platforms (2016, background): “Most of these commercial ULP microcontrollers exploit the fact that CMOS technology is inherently most efficient when driven at near-threshold voltage [13]; the same applies to research microcontrollers.”
- Limits on fundamental limits to computation (2014, background): “Charge recovery [58], power management [47], voltage scaling [57], and near-threshold computing [59] reduce energy waste.”