arXiv subjects

Sadasivan Shankar

Publications and source records attributed to Sadasivan Shankar.

6 recordsLinked to original sources

arXiv2024

ON-OFF Neuromorphic ISING Machines using Fowler-Nordheim Annealers

We introduce NeuroSA, a neuromorphic architecture specifically designed to ensure asymptotic convergence to the ground state of an Ising problem using a Fowler-Nordheim quantum mechanical tunneling based threshold-annealing process. The core component of NeuroSA consists of a pair of asynchronous ON-OFF neurons, which effectively map classical simulated annealing dynamics onto a network of integrate-and-fire neurons. The threshold of each ON-OFF neuron pair is adaptively adjusted by an FN annealer and the resulting spiking dynamics replicates the optimal escape mechanism and convergence of SA, particularly at low-temperatures. To validate the effectiveness of our neuromorphic Ising machine, we systematically solved benchmark combinatorial optimization problems such as MAX-CUT and Max Independent Set. Across multiple runs, NeuroSA consistently generates distribution of solutions that are concentrated around the state-of-the-art results (within 99%) or surpass the current state-of-the-art solutions for Max Independent Set benchmarks. Furthermore, NeuroSA is able to achieve these superior distributions without any graph-specific hyperparameter tuning. For practical illustration, we present results from an implementation of NeuroSA on the SpiNNaker2 platform, highlighting the feasibility of mapping our proposed architecture onto a standard neuromorphic accelerator platform.

cs.NE↗

arXiv2023

Neuromorphic Intermediate Representation: A Unified Instruction Set for Interoperable Brain-Inspired Computing

Spiking neural networks and neuromorphic hardware platforms that simulate neuronal dynamics are getting wide attention and are being applied to many relevant problems using Machine Learning. Despite a well-established mathematical foundation for neural dynamics, there exists numerous software and hardware solutions and stacks whose variability makes it difficult to reproduce findings. Here, we establish a common reference frame for computations in digital neuromorphic systems, titled Neuromorphic Intermediate Representation (NIR). NIR defines a set of computational and composable model primitives as hybrid systems combining continuous-time dynamics and discrete events. By abstracting away assumptions around discretization and hardware constraints, NIR faithfully captures the computational model, while bridging differences between the evaluated implementation and the underlying mathematical formalism. NIR supports an unprecedented number of neuromorphic systems, which we demonstrate by reproducing three spiking neural network models of different complexity across 7 neuromorphic simulators and 4 digital hardware platforms. NIR decouples the development of neuromorphic hardware and software, enabling interoperability between platforms and improving accessibility to multiple neuromorphic technologies. We believe that NIR is a key next step in brain-inspired hardware-software co-evolution, enabling research towards the implementation of energy efficient computational principles of nervous systems. NIR is available at neuroir.org

cs.NE↗

arXiv2023

Energy Estimates Across Layers of Computing: From Devices to Large-Scale Applications in Machine Learning for Natural Language Processing, Scientific Computing, and Cryptocurrency Mining

Estimates of energy usage in layers of computing from devices to algorithms have been determined and analyzed. Building on the previous analysis [3], energy needed from single devices and systems including three large-scale computing applications such as Artificial Intelligence (AI)/Machine Learning for Natural Language Processing, Scientific Simulations, and Cryptocurrency Mining have been estimated. In contrast to the bit-level switching, in which transistors achieved energy efficiency due to geometrical scaling, higher energy is expended both at the at the instructions and simulations levels of an application. Additionally, the analysis based on AI/ML Accelerators indicate that changes in architectures using an older semiconductor technology node have comparable energy efficiency with a different architecture using a newer technology. Further comparisons of the energy in computing systems with the thermodynamic and biological limits, indicate that there is a 27-36 orders of magnitude higher energy requirements for total simulation of an application. These energy estimates underscore the need for serious considerations of energy efficiency in computing by including energy as a design parameter, enabling growing needs of compute-intensive applications in a digital world.

cs.CY↗

arXiv2022

Trends in Energy Estimates for Computing in AI/Machine Learning Accelerators, Supercomputers, and Compute-Intensive Applications

We examine the computational energy requirements of different systems driven by the geometrical scaling law, and increasing use of Artificial Intelligence or Machine Learning (AI-ML) over the last decade. With more scientific and technology applications based on data-driven discovery, machine learning methods, especially deep neural networks, have become widely used. In order to enable such applications, both hardware accelerators and advanced AI-ML methods have led to the introduction of new architectures, system designs, algorithms, and software. Our analysis of energy trends indicates three important observations: 1) Energy efficiency due to geometrical scaling is slowing down; 2) The energy efficiency at the bit-level does not translate into efficiency at the instruction-level, or at the system-level for a variety of systems, especially for large-scale AI-ML accelerators or supercomputers; 3) At the application level, general-purpose AI-ML methods can be computationally energy intensive, off-setting the gains in energy from geometrical scaling and special purpose accelerators. Further, our analysis provides specific pointers for integrating energy efficiency with performance analysis for enabling high-performance and sustainable computing in the future.

cs.AR↗

arXiv2013

First Principle-based Analysis of Single-Walled Carbon Nanotube and Silicon Nanowire Junctionless Transistors

Junctionless transistors made of silicon have previously been demonstrated experimentally and by simulations. Junctionless devices do not require fabricating an abrupt source-drain junction and thus can be easier to implement in aggressive geometries. In this paper, we explore a similar architecture for aggressively scaled devices with the channel consisting of doped carbon nanotubes (CNTs). Gate all around (GAA) field effect transistor (FET) structures are investigated for n- and p-type doping. Current-voltage characteristics and sub-threshold characteristics for a CNTbased junctionless FET is compared with a junctionless silicon nanowire (SiNW) FET with comparable dimensions. Despite the higher on-current of the CNT channels, the device characteristics are poorer compared to the silicon devices due to the smaller CNT band gap.

cond-mat.mes-hall↗

arXiv2010

Grain boundary effects on electronic transport in metals

We present quantum-based simulations of single grain boundary reflectivity of electrons in metals, Cu and Ag. We examine twin and non-twin grain boundaries using non-equilibrium Green's function and first principles methods. We also investigate the mechanism of reflectivity in grain boundaries by modeling atomic vacancies, disorder, and orientation and find that the change in grain orientation and disorder in the boundary itself both contribute significantly to reflectivity. We find that grain boundary reflectivity may vary widely depending on the grain boundary structure consistent with experimental results. Finally, we examine the reflectivity from multiple grain boundaries and find that grain boundary reflectivity may depend on neighboring grain boundaries. This study based on detailed numerical techniques reveals some potential limitations in the independent grain boundary assumptions of the Mayadas-Shatzkes model.

cond-mat.mes-hall↗