Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Near-threshold computing (NTC) (3)
- Tensor processing unit (TPU) (3)
- Deep neural network (DNN) (2)
- Timing error resilience (2)
- AI (1)
-
- Accelerators (1)
- Autoregressive model estimation (1)
- Clock gating (1)
- Computer security (1)
- Correctness (1)
- Deep neural-network (DNN) (1)
- Energy efficiency (1)
- Fault diagnosis (1)
- Fault tolerance (1)
- Ion sources (1)
- Ionospheric plasmas (1)
- Multiply and accumulate (MAC) (1)
- Neural network (1)
- Performance (1)
- Physical quantities (1)
- Plasma properties and parameters (1)
- Precision (1)
- Predictive (1)
- Probabilistic models (1)
- Quantatative verification (1)
- RLS algorithm (1)
- Road vehicle control (1)
- Road vehicle power systems (1)
- Shaping filters (1)
- Spacecrafts (1)
Articles 1 - 8 of 8
Full-Text Articles in Engineering
On Correctness, Precision, And Performance In Quantitative Verification: Qcomp 2020 Competition Report, Carlos E. Budde, Arnd Hartmanns, Michaela Klauck, Jan Křetínský, David Parker, Tim Quatmann, Andrea Turrini, Zhen Zhang
On Correctness, Precision, And Performance In Quantitative Verification: Qcomp 2020 Competition Report, Carlos E. Budde, Arnd Hartmanns, Michaela Klauck, Jan Křetínský, David Parker, Tim Quatmann, Andrea Turrini, Zhen Zhang
Electrical and Computer Engineering Faculty Publications
Quantitative verification tools compute probabilities, expected rewards, or steady-state values for formal models of stochastic and timed systems. Exact results often cannot be obtained efficiently, so most tools use floating-point arithmetic in iterative algorithms that approximate the quantity of interest. Correctness is thus defined by the desired precision and determines performance. In this paper, we report on the experimental evaluation of these trade-offs performed in QComp 2020: the second friendly competition of tools for the analysis of quantitative formal models. We survey the precision guarantees - ranging from exact rational results to statistical confidence statements - offered by the nine …
Challenges And Opportunities In Near-Threshold Dnn Accelerators Around Timing Errors, Pramesh Pandey, Noel Daniel Gundi, Prabal Basu, Tahmoures Shabanian, Mitchell Craig Patrick, Koushik Chakraborty, Sanghamitra Roy
Challenges And Opportunities In Near-Threshold Dnn Accelerators Around Timing Errors, Pramesh Pandey, Noel Daniel Gundi, Prabal Basu, Tahmoures Shabanian, Mitchell Craig Patrick, Koushik Chakraborty, Sanghamitra Roy
Electrical and Computer Engineering Faculty Publications
AI evolution is accelerating and Deep Neural Network (DNN) inference accelerators are at the forefront of ad hoc architectures that are evolving to support the immense throughput required for AI computation. However, much more energy efficient design paradigms are inevitable to realize the complete potential of AI evolution and curtail energy consumption. The Near-Threshold Computing (NTC) design paradigm can serve as the best candidate for providing the required energy efficiency. However, NTC operation is plagued with ample performance and reliability concerns arising from the timing errors. In this paper, we dive deep into DNN architecture to uncover some unique challenges …
Titan: Uncovering The Paradigm Shift In Security Vulnerability At Near-Threshold Computing, Prabal Basu, Pramesh Pandey, Aatreyi Bal, Chidhambaranathan Rajamanikkam, Koushik Chakraborty, Sanghamitra Roy
Titan: Uncovering The Paradigm Shift In Security Vulnerability At Near-Threshold Computing, Prabal Basu, Pramesh Pandey, Aatreyi Bal, Chidhambaranathan Rajamanikkam, Koushik Chakraborty, Sanghamitra Roy
Electrical and Computer Engineering Faculty Publications
In this paper, we investigate the emerging security threats at Near-Threshold Computing (NTC) that are poised to jeopardize the trustworthy operation of future low-power electronic devices. A substantial research effort over the last decade has bolstered energy efficient operation in low-power computing. However, innovation in low-power security has received only marginal attention, thwarting a ubiquitous adoption of critical Internet of Things applications, such as wearable gadgets. Using a cross-layer methodology, we demonstrate that the timing fault vulnerability of a circuit rapidly increases as the operating conditions of the transistor devices shift from super-threshold to near-threshold values. Exploiting this vulnerability, we …
Greentpu: Predictive Design Paradigm For Improving Timing Error Resilience Of A Near-Threshold Tensor Processing Unit, Pramesh Pandey, Prabal Basu, Koushik Chakraborty, Sanghamitra Roy
Greentpu: Predictive Design Paradigm For Improving Timing Error Resilience Of A Near-Threshold Tensor Processing Unit, Pramesh Pandey, Prabal Basu, Koushik Chakraborty, Sanghamitra Roy
Electrical and Computer Engineering Faculty Publications
The emergence of hardware accelerators has brought about several orders of magnitude improvement in the speed of the deep neural-network (DNN) inference. Among such DNN accelerators, the Google tensor processing unit (TPU) has transpired to be the best-in-class, offering more than 15\times speedup over the contemporary GPUs. However, the rapid growth in several DNN workloads conspires to escalate the energy consumptions of the TPU-based data-centers. In order to restrict the energy consumption of TPUs, we propose GreenTPU - a low-power near-threshold (NTC) TPU design paradigm. To ensure a high inference accuracy at a low-voltage operation, GreenTPU identifies the patterns in …
The Gridded Retarding Ion Drift Sensor For The Petitsat Cubesat Mission, Ryan L. Davidson, B. Oborn, E. F. Robertson, S. Noel, G. D. Earle, J. Green, J. Kramer
The Gridded Retarding Ion Drift Sensor For The Petitsat Cubesat Mission, Ryan L. Davidson, B. Oborn, E. F. Robertson, S. Noel, G. D. Earle, J. Green, J. Kramer
Electrical and Computer Engineering Faculty Publications
The Gridded Retarding Ion Drift Sensor (GRIDS) is a small sensor that will fly on the 6 U petitSat CubeSat. It is designed to measure the three-dimensional plasma drift velocity vector in the Earth’s ionosphere. The GRIDS also supplies information about the ion temperature, ion density, and the ratio of light to heavy ions present in the ionospheric plasma. It utilizes well-proven techniques that have been successfully validated by similar instruments on larger satellite missions while meeting CubeSat-compatible requirements for low mass, size, and power consumption. GRIDS performs the functions of a Retarding Potential Analyzer (RPA) and an Ion Drift …
Estimation Of Autoregressive Parameters From Noisy Observations Using Iterated Covariance Updates, Todd K. Moon, Jacob H. Gunther
Estimation Of Autoregressive Parameters From Noisy Observations Using Iterated Covariance Updates, Todd K. Moon, Jacob H. Gunther
Electrical and Computer Engineering Faculty Publications
Estimating the parameters of the autoregressive (AR) random process is a problem that has been well-studied. In many applications, only noisy measurements of AR process are available. The effect of the additive noise is that the system can be modeled as an AR model with colored noise, even when the measurement noise is white, where the correlation matrix depends on the AR parameters. Because of the correlation, it is expedient to compute using multiple stacked observations. Performing a weighted least-squares estimation of the AR parameters using an inverse covariance weighting can provide significantly better parameter estimates, with improvement increasing with …
Reducing Road Wear While Ensuring Comfort And Charging Constraints For Dynamically Charged Passenger Vehicles Through Noise-Shaped Path Variations, Clint Jay Ferrin, Randall Christensen
Reducing Road Wear While Ensuring Comfort And Charging Constraints For Dynamically Charged Passenger Vehicles Through Noise-Shaped Path Variations, Clint Jay Ferrin, Randall Christensen
Electrical and Computer Engineering Faculty Publications
Dynamically charged vehicles suffer from power loss during wireless power transfer due to receiver and transmitter coil misalignment while driving. Autonomous, dynamically charged vehicles can maximize wireless power transfer by minimizing the misalignment, but the repeated high-precision driving increases road wear. To avoid unnecessary road wear and rutting, a noise shaping filter is proposed that adds variability to a vehicle's trajectory that complies with passenger acceleration and position constraints. However, introducing variability into an optimal charging path also risks depleting battery life prior to destination arrival. Therefore, a path planner is proposed that guarantees average charge within a specified probability …
Effort: Enhancing Energy Efficiency And Error Resilience Of A Near-Threshold Tensor Processing Unit, Noel Daniel Gundi, Tahmoures Shabanian, Prabal Basu, Pramesh Pandey, Sanghamitra Roy, Koushik Chakraborty, Zhen Zhang
Effort: Enhancing Energy Efficiency And Error Resilience Of A Near-Threshold Tensor Processing Unit, Noel Daniel Gundi, Tahmoures Shabanian, Prabal Basu, Pramesh Pandey, Sanghamitra Roy, Koushik Chakraborty, Zhen Zhang
Electrical and Computer Engineering Faculty Publications
Modern deep neural network (DNN) applications demand a remarkable processing throughput usually unmet by traditional Von Neumann architectures. Consequently, hardware accelerators, comprising a sea of multiplier and accumulate (MAC) units, have recently gained prominence in accelerating DNN inference engine. For example, Tensor Processing Units (TPU) account for a lion's share of Google's datacenter inference operations. The proliferation of real-time DNN predictions is accompanied with a tremendous energy budget. In quest of trimming the energy footprint of DNN accelerators, we propose EFFORT-an energy optimized, yet high performance TPU architecture, operating at the Near-Threshold Computing (NTC) region. EFFORT promotes a better-than-worst-case design …