arXiv subjects

Yingmin Li

Publications and source records attributed to Yingmin Li.

6 recordsLinked to original sources

arXiv2020

Software-defined Design Space Exploration for an Efficient DNN Accelerator Architecture

Deep neural networks (DNNs) have been shown to outperform conventional machine learning algorithms across a wide range of applications, e.g., image recognition, object detection, robotics, and natural language processing. However, the high computational complexity of DNNs often necessitates extremely fast and efficient hardware. The problem gets worse as the size of neural networks grows exponentially. As a result, customized hardware accelerators have been developed to accelerate DNN processing without sacrificing model accuracy. However, previous accelerator design studies have not fully considered the characteristics of the target applications, which may lead to sub-optimal architecture designs. On the other hand, new DNN models have been developed for better accuracy, but their compatibility with the underlying hardware accelerator is often overlooked. In this article, we propose an application-driven framework for architectural design space exploration of DNN accelerators. This framework is based on a hardware analytical model of individual DNN operations. It models the accelerator design task as a multi-dimensional optimization problem. We demonstrate that it can be efficaciously used in application-driven accelerator architecture design. Given a target DNN, the framework can generate efficient accelerator design solutions with optimized performance and area. Furthermore, we explore the opportunity to use the framework for accelerator configuration optimization under simultaneous diverse DNN applications. The framework is also capable of improving neural network models to best fit the underlying hardware resources.

cs.DC↗

arXiv2019

Manipulating Optical Nonlinearities of Molecular Polaritons by Delocalization

Optical nonlinearities - how light-matter interactions are influenced by previous interactions with photons, are key resources in the contemporary photonics toolbox, relevant to quantum gate operations and all-optical switches. Optical nonlinearities of materials are often controlled at the microscopic level by chemical modification, which makes on-the-fly manipulation of such response challenging. Tunability of optical nonlinearities in the mid-IR is even less developed, hindering its applications in chemical sensing or IR photonic circuitry. Here, we report control of vibrational polariton coherent nonlinearities by manipulation of macroscopic parameters such as cavity longitudinal length or molecular concentration. These emergent nonlinearities last for the lifetime of the cavity mode, and subsequently evolve into the response determined by an incoherent population of dark reservoir modes. The observed phenomena arise due to the nonlinear macroscopic polarization stemming from strong coupling between microscopic molecular excitations and a macroscopic photonic cavity mode.

cond-mat.mtrl-sci↗

arXiv2019

Modeling spontaneous charge transfer at metal/organic hybrid heterostructures

Hybrid materials are crucial in photovoltaics where the overall efficiency of the heterostructure is closely related to the level of charge transfer at the interface. Here, using various metal / poly(3-hexylthiophene)(P3HT) heterostructure models, we reveal that the level of spontaneous charge transfer and electronic coupling at these interfaces depend on the conformational regularity of the organic polymer deposited on the metal substrate. Using ab-initio quantum chemical calculations based on density functional theory (DFT) and heterodyne vibrational sum frequency generation (HD-VSFG) measurements, we show that inducing regio-randomness into the organic polymer modifies the intensity of interfacial electronic states, level of hybridization, density of interfacial charge transfer and the electronic wave function of the material. We present the HD-VSFG responses of the metal/P3HT heterojunctions containing both regio-regular and regio-random P3HT structures and show that the amount of non-resonant signal is closely related to the level of the spontaneous charge transfer at the interface. Thus, by measuring the non-resonant response of the metal/P3HT heterojunctions, the level of spontaneous charge transfer at the interface can be determined.

cond-mat.mtrl-sci↗

arXiv2019

Hardware-Guided Symbiotic Training for Compact, Accurate, yet Execution-Efficient LSTM

Many long short-term memory (LSTM) applications need fast yet compact models. Neural network compression approaches, such as the grow-and-prune paradigm, have proved to be promising for cutting down network complexity by skipping insignificant weights. However, current compression strategies are mostly hardware-agnostic and network complexity reduction does not always translate into execution efficiency. In this work, we propose a hardware-guided symbiotic training methodology for compact, accurate, yet execution-efficient inference models. It is based on our observation that hardware may introduce substantial non-monotonic behavior, which we call the latency hysteresis effect, when evaluating network size vs. inference latency. This observation raises question about the mainstream smaller-dimension-is-better compression strategy, which often leads to a sub-optimal model architecture. By leveraging the hardware-impacted hysteresis effect and sparsity, we are able to achieve the symbiosis of model compactness and accuracy with execution efficiency, thus reducing LSTM latency while increasing its accuracy. We have evaluated our algorithms on language modeling and speech recognition applications. Relative to the traditional stacked LSTM architecture obtained for the Penn Treebank dataset, we reduce the number of parameters by 18.0x (30.5x) and measured run-time latency by up to 2.4x (5.2x) on Nvidia GPUs (Intel Xeon CPUs) without any accuracy degradation. For the DeepSpeech2 architecture obtained for the AN4 dataset, we reduce the number of parameters by 7.0x (19.4x), word error rate from 12.9% to 9.9% (10.4%), and measured run-time latency by up to 1.7x (2.4x) on Nvidia GPUs (Intel Xeon CPUs). Thus, our method yields compact, accurate, yet execution-efficient inference models.

cs.NE↗

arXiv2017

Revealing Hidden Vibration Polariton Interactions by 2D IR Spectroscopy

We report the first experimental two-dimensional infrared (2D IR) spectra of novel molecular photonic excitations - vibrational-polaritons. The application of advanced 2D IR spectroscopy onto novel vibrational-polariton challenges and advances our understanding in both fields. From spectroscopy aspect, 2D IR spectra of polaritons differ drastically from free uncoupled molecules; from vibrational-polariton aspects, 2D IR uniquely resolves hybrid light-matter polariton excitations and unexpected dark states in a state-selective manner and revealed hidden interactions between them. Moreover, 2D IR signals highlight the role of vibrational anharmonicities in generating non-linear signals. To further advance our knowledge on 2D IR of vibrational polaritons, we develop a new quantum-mechanical model incorporating the effects of both nuclear and electrical anharmonicities on vibrational-polaritons and their 2D IR signals. This work reveals polariton physics that is difficult or impossible to probe with traditional linear spectroscopy and lays the foundation for investigating new non-linear optics and chemistry of molecular vibrational-polaritons.

quant-ph↗

arXiv2016

Solving the "Magic Angle" Challenge in Determining Molecular Orientation at Interfaces

We introduce a novel method to determine the orientation heterogeneity (mean tilt angle and orientational distribution) of molecules at interfaces using heterodyne two-dimensional sum frequency generation spectroscopy. By doing so, we not only have solved the long-standing "magic angle" challenge, i.e. the measurement of molecular orientation by assuming a narrow orientational distribution results in ambiguities, but we also are able to determine the orientational distribution, which is otherwise difficult to measure. We applied our new method to a CO2 reduction catalyst/gold interface and found that the catalysts formed a monolayer with a mean tilt angle between the quasi-C3 symmetric axis of the catalysts and the surface normal of 53 deg, with 5 deg orientational distribution. Although applied to a specific system, this method is a general way to determine the orientation heterogeneity of an ensemble-averaged molecular interface, which can potentially be applied to a wide-range of energy material, catalytic and biological interfaces.

physics.chem-ph↗