arXiv subjects

Yixin Xu

Publications and source records attributed to Yixin Xu.

35 records · Page 2Linked to original sources

arXiv2023

Multi-Scale Attention for Audio Question Answering

Audio question answering (AQA), acting as a widely used proxy task to explore scene understanding, has got more attention. The AQA is challenging for it requires comprehensive temporal reasoning from different scales' events of an audio scene. However, existing methods mostly extend the structures of visual question answering task to audio ones in a simple pattern but may not perform well when perceiving a fine-grained audio scene. To this end, we present a Multi-scale Window Attention Fusion Model (MWAFM) consisting of an asynchronous hybrid attention module and a multi-scale window attention module. The former is designed to aggregate unimodal and cross-modal temporal contexts, while the latter captures sound events of varying lengths and their temporal dependencies for a more comprehensive understanding. Extensive experiments are conducted to demonstrate that the proposed MWAFM can effectively explore temporal information to facilitate AQA in the fine-grained scene.Code: https://github.com/GeWu-Lab/MWAFM

cs.SD↗

arXiv2023

Powering Disturb-Free Reconfigurable Computing and Tunable Analog Electronics with Dual-Port Ferroelectric FET

Single-port ferroelectric FET (FeFET) that performs write and read operations on the same electrical gate prevents its wide application in tunable analog electronics and suffers from read disturb, especially to the high-threshold voltage (VTH) state as the retention energy barrier is reduced by the applied read bias. To address both issues, we propose to adopt a read disturb-free dual-port FeFET where write is performed on the gate featuring a ferroelectric layer and the read is done on a separate gate featuring a non-ferroelectric dielectric. Combining the unique structure and the separate read gate, read disturb is eliminated as the applied field is aligned with polarization in the high-VTH state and thus improving its stability, while it is screened by the channel inversion charge and exerts no negative impact on the low-VTH state stability. Comprehensive theoretical and experimental validation have been performed on fully-depleted silicon-on-insulator (FDSOI) FeFETs integrated on 22 nm platform, which intrinsically has dual ports with its buried oxide layer acting as the non-ferroelectric dielectric. Novel applications that can exploit the proposed dual-port FeFET are proposed and experimentally demonstrated for the first time, including FPGA that harnesses its read disturb-free feature and tunable analog electronics (e.g., frequency tunable ring oscillator in this work) leveraging the separated write and read paths.

cs.ET↗

arXiv2023

ASMCap: An Approximate String Matching Accelerator for Genome Sequence Analysis Based on Capacitive Content Addressable Memory

Genome sequence analysis is a powerful tool in medical and scientific research. Considering the inevitable sequencing errors and genetic variations, approximate string matching (ASM) has been adopted in practice for genome sequencing. However, with exponentially increasing bio-data, ASM hardware acceleration is facing severe challenges in improving the throughput and energy efficiency with the accuracy constraint. This paper presents ASMCap, an ASM acceleration approach for genome sequence analysis with hardware-algorithm co-optimization. At the circuit level, ASMCap adopts charge-domain computing based on the capacitive multi-level content addressable memories (ML-CAMs), and outperforms the state-of-the-art ML-CAM-based ASM accelerators EDAM with higher accuracy and energy efficiency. ASMCap also has misjudgment correction capability with two proposed hardware-friendly strategies, namely the Hamming-Distance Aid Correction (HDAC) for the substitution-dominant edits and the Threshold-Aware Sequence Rotation (TASR) for the consecutive indels. Evaluation results show that ASMCap can achieve an average of 1.2x (from 74.7% to 87.6%) and up to 1.8x (from 46.3% to 81.2%) higher F1 score (the key metric of accuracy), 1.4x speedup, and 10.8x energy efficiency improvement compared with EDAM. Compared with the other ASM accelerators, including ResMA based on the comparison matrix, and SaVI based on the seeding strategy, ASMCap achieves an average improvement of 174x and 61x speedup, and 8.7e3x and 943x higher energy efficiency, respectively.

cs.AR↗

arXiv2022

Ferroelectric FET based Context-Switching FPGA Enabling Dynamic Reconfiguration for Adaptive Deep Learning Machines

Field Programmable Gate Array (FPGA) is widely used in acceleration of deep learning applications because of its reconfigurability, flexibility, and fast time-to-market. However, conventional FPGA suffers from the tradeoff between chip area and reconfiguration latency, making efficient FPGA accelerations that require switching between multiple configurations still elusive. In this paper, we perform technology-circuit-architecture co-design to break this tradeoff with no additional area cost and lower power consumption compared with conventional designs while providing dynamic reconfiguration, which can hide the reconfiguration time behind the execution time. Leveraging the intrinsic transistor structure and non-volatility of ferroelectric FET (FeFET), compact FPGA primitives are proposed and experimentally verified, including 1FeFET look-up table (LUT) cell, 1FeFET routing cell for connection blocks (CBs) and switch boxes (SBs). To support dynamic reconfiguration, two local copies of primitives are placed in parallel, which enables loading of arbitrary configuration without interrupting the active configuration execution. A comprehensive evaluation shows that compared with the SRAM-based FPGA, our dynamic reconfiguration design shows 63.0%/71.1% reduction in LUT/CB area and 82.7%/53.6% reduction in CB/SB power consumption with minimal penalty in the critical path delay (9.6%). We further implement a Super-Sub network model to show the benefit from the context-switching capability of our design. We also evaluate the timing performance of our design over conventional FPGA in various application scenarios. In one scenario that users switch between two preloaded configurations, our design yields significant time saving by 78.7% on average. In the other scenario of implementing multiple configurations with dynamic reconfiguration, our design offers time saving of 20.3% on average.

cs.AR↗

arXiv2022

A Nonlinear Sum of Squares Search for CAZAC Sequences

We report on a search for CAZAC sequences by using nonlinear sum of squares optimization. Up to equivalence, we found all length 7 CAZAC sequences. We obtained evidence suggesting there are finitely many length 10 CAZAC sequences with a total of 3040 sequences. Last, we compute longer sequences and compare their aperiodic autocorrelation properties to known sequences. The code and results of this search are publicly available through GitHub.

cs.IT↗

arXiv2022

Itemset Utility Maximization with Correlation Measure

As an important data mining technology, high utility itemset mining (HUIM) is used to find out interesting but hidden information (e.g., profit and risk). HUIM has been widely applied in many application scenarios, such as market analysis, medical detection, and web click stream analysis. However, most previous HUIM approaches often ignore the relationship between items in an itemset. Therefore, many irrelevant combinations (e.g., \{gold, apple\} and \{notebook, book\}) are discovered in HUIM. To address this limitation, many algorithms have been proposed to mine correlated high utility itemsets (CoHUIs). In this paper, we propose a novel algorithm called the Itemset Utility Maximization with Correlation Measure (CoIUM), which considers both a strong correlation and the profitable values of the items. Besides, the novel algorithm adopts a database projection mechanism to reduce the cost of database scanning. Moreover, two upper bounds and four pruning strategies are utilized to effectively prune the search space. And a concise array-based structure named utility-bin is used to calculate and store the adopted upper bounds in linear time and space. Finally, extensive experimental results on dense and sparse datasets demonstrate that CoIUM significantly outperforms the state-of-the-art algorithms in terms of runtime and memory consumption.

cs.AI↗

arXiv2022

ALL-MASK: A Reconfigurable Logic Locking Method for Multicore Architecture with Sequential-Instruction-Oriented Key

Intellectual property (IP) piracy has become a non-negligible problem as the integrated circuit (IC) production supply chain is becoming increasingly globalized and separated that enables attacks by potentially untrusted attackers. Logic locking is a widely adopted method to lock the circuit module with a key and prevent hackers from cracking it. The key is the critical aspect of logic locking, but the existing works have overlooked three possible challenges of the key: safety of key storage, easy key-attempt from interface and key-related overheads, bringing the further challenges of low error rate and small state space. In this work, the key is dynamically generated by utilizing the huge space of a CPU core, and the unlocking is performed implicitly through the interconnection inside the chip. A novel low-cost logic reconfigurable gate is together proposed with ferroelectric FET (FeFET) to mitigate the reverse engineering and removal attack. Compared to the common logic locking methods, our proposed approach is 19,945 times more time consuming to traverse all the possible combinations in only 9-bit-key condition. Furthermore, our technique let key length increases this complexity exponentially and ensure the logic obfuscation effect.

cs.AR↗

arXiv2022

Interfacial Thermal Conductance Spectrum in Nonequilibrium Molecular Dynamics Simulations Considering Anharmonicity, Non-homogeneity and Quantum Effects

Interfacial thermal transport is critical for many thermal-related applications such as heat dissipation in electronics. While the total interfacial thermal conductance (ITC) can be easily measured or calculated, the ITC spectral mapping has been investigated only recently and is not fully understood. By combining nonequilibrium molecular dynamics simulations and atomistic Green's function method, we systematically investigate the ITC spectrum across an ideal interface, i.e., the argon-heavy argon interface. Our results show that the ITC spectrum increases gradually with temperature as more phonons and anharmonic scattering channels are activated, e.g., the vibrations with frequencies larger than 1 THz can contribute 5% (15%) to the total ITC at 2 K (40 K) through anharmonic phonon scatterings channels. We further find that the ITC spectrum from the left interfacial Hamiltonian is quite different from that of the right interfacial Hamiltonian, which stems from the asymmetry of anharmonic phonon scatterings caused by the dissimilar vibrational property of the two interfacial contacts. While all the phonons are involved in the anharmonic scatterings for the heavy argon interfacial Hamiltonian, these phonons involved in the anharmonic phonon scatterings from the argon interfacial Hamiltonians are mainly these vibrations with frequency smaller than 1 THz (i.e., the cut-off frequency of heavy argon). Finally, we find the quantum effect is important for the ITC spectrum at low temperatures, e.g., below 30 K in our systems. Our results here systematically investigate the influence of anharmonicity, non-homogeneity, and quantum effects on the ITC spectrum, which is critical for designing and optimizing the interfaces with better performance.

cond-mat.mtrl-sci↗

arXiv2022

CMOS-Compatible Ising Machines built using Bistable Latches Coupled through Ferroelectric Transistor Arrays

Realizing compact and scalable Ising machines that are compatible with CMOS-process technology is crucial to the effectiveness and practicality of using such hardware platforms for accelerating computationally intractable problems. Besides the need for realizing compact Ising spins, the implementation of the coupling network, which describes the spin interaction, is also a potential bottleneck in the scalability of such platforms. Therefore, in this work, we propose an Ising machine platform that exploits the novel behavior of compact bi-stable CMOS-latches (cross-coupled inverters) as classical Ising spins interacting through highly scalable and CMOS-process compatible ferroelectric-HfO2-based Ferroelectric FETs (FeFETs) which act as coupling elements. We experimentally demonstrate the prototype building blocks of this system, and evaluate the behavior of the scaled system using simulations. We project that the proposed architecture can compute Ising solutions with an efficiency of ~1.04 x 10^8 solutions/W/second. Our work not only provides a pathway to realizing CMOS-compatible designs but also to overcoming their scaling challenges.

physics.app-ph↗

arXiv2022

Hardware Functional Obfuscation With Ferroelectric Active Interconnects

Camouflaging gate techniques are typically used in hardware security to prevent reverse engineering. Layout level camouflaging by adding dummy contacts ensures some level of protection against extracting the correct netlist. Threshold voltage manipulation for multi-functional logic with identical layouts has also been introduced for functional obfuscation. All these techniques are implemented at the expense of circuit-complexity and with significant area, energy, and delay penalty. In this paper, we propose an efficient hardware encryption technique with minimal complexity and overheads based on ferroelectric field-effect transistor (FeFET) active interconnects. The active interconnect provides run-time reconfigurable inverter-buffer logic by utilizing the threshold voltage programmability of the FeFETs. Our method utilizes only two FeFETs and an inverter to realize the masking function compared to recent reconfigurable logic gate implementations using several FeFETs and complex differential logic. We fabricate the proposed circuit and demonstrate the functionality. Judicious placement of the proposed logic in the IC makes it acts as a hardware encryption key and enables encoding and decoding of the functional output without affecting the critical path timing delay. Also, we achieve comparable encryption probability with a limited number of encryption units. In addition, we show a peripheral programming scheme for reconfigurable logic by reusing the existing scan chain logic, hence obviating the need for specialized programming logic and circuitry for keybit distribution. Our analysis shows an average encryption probability of 97.43% with an increase of 2.24%/ 3.67% delay for the most critical path/ sum of 100 critical paths delay for ISCAS85 benchmarks.

cs.ET↗

arXiv2021

Supervised multi-specialist topic model with applications on large-scale electronic health record data

Motivation: Electronic health record (EHR) data provides a new venue to elucidate disease comorbidities and latent phenotypes for precision medicine. To fully exploit its potential, a realistic data generative process of the EHR data needs to be modelled. We present MixEHR-S to jointly infer specialist-disease topics from the EHR data. As the key contribution, we model the specialist assignments and ICD-coded diagnoses as the latent topics based on patient's underlying disease topic mixture in a novel unified supervised hierarchical Bayesian topic model. For efficient inference, we developed a closed-form collapsed variational inference algorithm to learn the model distributions of MixEHR-S. We applied MixEHR-S to two independent large-scale EHR databases in Quebec with three targeted applications: (1) Congenital Heart Disease (CHD) diagnostic prediction among 154,775 patients; (2) Chronic obstructive pulmonary disease (COPD) diagnostic prediction among 73,791 patients; (3) future insulin treatment prediction among 78,712 patients diagnosed with diabetes as a mean to assess the disease exacerbation. In all three applications, MixEHR-S conferred clinically meaningful latent topics among the most predictive latent topics and achieved superior target prediction accuracy compared to the existing methods, providing opportunities for prioritizing high-risk patients for healthcare services. MixEHR-S source code and scripts of the experiments are freely available at https://github.com/li-lab-mcgill/mixehrS

cs.LG↗

arXiv2020

Weyl type $f(Q,T)$ gravity, and its cosmological implications

We consider an $f(Q,T)$ type gravity model in which the scalar non-metricity $Q_{αμν}$ of the space-time is expressed in its standard Weyl form, and it is fully determined by a vector field $w_μ$. The field equations of the theory are obtained under the assumption of the vanishing of the total scalar curvature, a condition which is added into the gravitational action via a Lagrange multiplier. The gravitational field equations are obtained from a variational principle, and they explicitly depend on the scalar nonmetricity and on the Lagrange multiplier. The covariant divergence of the matter energy-momentum tensor is also determined, and it follows that the nonmetricity-matter coupling leads to the nonconservation of the energy and momentum. The energy and momentum balance equations are explicitly calculated, and the expressions of the energy source term and of the extra force are found. We investigate the cosmological implications of the theory, and we obtain the cosmological evolution equations for a flat, homogeneous and isotropic geometry, which generalize the Friedmann equations of standard general relativity. We consider several cosmological models by imposing some simple functional forms of the function $f(Q,T)$, and we compare the predictions of the theory with the standard $Λ$CDM model.

gr-qc↗

arXiv2019

GeoPrune: Efficiently Finding Shareable Vehicles Based on Geometric Properties

On-demand ride-sharing is rapidly growing.Matching trip requests to vehicles efficiently is critical for the service quality of ride-sharing. To match trip requests with vehicles, a prune-and-select scheme is commonly used. The pruning stage identifies feasible vehicles that can satisfy the trip constraints (e.g., trip time). The selection stage selects the optimal one(s) from the feasible vehicles. The pruning stage is crucial to reduce the complexity of the selection stage and to achieve efficient matching. We propose an effective and efficient pruning algorithm called GeoPrune. GeoPrune represents the time constraints of trip requests using circles and ellipses, which can be computed and updated efficiently. Experiments on real-world datasets show that GeoPrune reduces the number of vehicle candidates in nearly all cases by an order of magnitude and the update cost by two to three orders of magnitude compared to the state-of-the-art.

cs.DB↗

arXiv2019

Symmetry breaking and entropy production during the evolution of spinor Bose-Einstein condensate driven by coherent atom beam

The spinor condensate with spin states degenerated in the ground spin-space provides a unique platform for investigating the edge of quantum mechanics and statistical physics. We study the evolution of the condensate under the scattering of a coherent atom beam. The time-dependent magnetization, entanglement entropy, thermal entropy and the entropy production rate are calculated. A novel spontaneous symmetry breaking is found during the evolution, It is shown that the stationary spin distribution can be controlled by the incoming coherent spin state of the incident atom beam, therefore the atom-condensate scattering provides a new way to probe the spin distribution of the condensate

cond-mat.quant-gas↗

arXiv2019

$f(Q,T)$ gravity

We propose an extension of the symmetric teleparallel gravity, in which the gravitational action $L$ is given by an arbitrary function $f$ of the nonmetricity $Q$ and of the trace of the matter energy-momentum tensor $T$, so that $L=f(Q,T)$. The field equations of the theory are obtained by varying the gravitational action with respect to both metric and connection. The covariant divergence of the field equations is obtained, with the geometry-matter coupling leading to the nonconservation of the energy-momentum tensor. We investigate the cosmological implications of the theory, and we obtain the cosmological evolution equations for a flat, homogeneous and isotropic geometry, which generalize the Friedmann equations of general relativity. We consider several cosmological models by imposing some simple functional forms of the function $f(Q,T)$, corresponding to additive expressions of $f(Q,T)$ of the form $f(Q,T)=αQ+βT$, $f(Q,T)=αQ^{n+1}+βT$, and $f(Q,T)=-αQ-βT^2$. The Hubble function, the deceleration parameter, and the matter energy density are obtained as a function of the redshift by using analytical and numerical techniques. For all considered cases the Universe experiences an accelerating expansion, ending with a de Sitter type evolution. The theoretical predictions are also compared with the results of the standard $Λ$CDM model.

gr-qc↗

arXiv2015

Impossibility Theorems and the Universal Algebraic Toolkit

We elucidate a close connection between the Theory of Judgment Aggregation (more generally, Evaluation Aggregation), and a relatively young but rapidly growing field of universal algebra, that was primarily developed to investigate constraint satisfaction problems. Our connection yields a full classification of non-binary evaluations into possibility and impossibility domains both under the idempotent and the supportive conditions. Prior to the current result E. Dokow and R. Holzman nearly classified non-binary evaluations in the supportive case, by combinatorial means. The algebraic approach gives us new insights to the easier binary case as well, which had been fully classified by the above authors. Our algebraic view lets us put forth a suggestion about a strengthening of the Non-dictatorship criterion, that helps us avoid "outliers" like the affine subspace. Finally, we give upper bounds on the complexity of computing if a domain is impossible or not (to our best knowledge no finite time bounds were given earlier).

cs.CC↗

arXiv2013

The Garden Hose Complexity for the Equality Function

The garden hose complexity is a new communication complexity introduced by H. Buhrman, S. Fehr, C. Schaffner and F. Speelman [BFSS13] to analyze position-based cryptography protocols in the quantum setting. We focus on the garden hose complexity of the equality function, and improve on the bounds of O. Margalit and A. Matsliah[MM12] with the help of a new approach and of our handmade simulated annealing based solver. We have also found beautiful symmetries of the solutions that have lead us to develop the notion of garden hose permutation groups. Then, exploiting this new concept, we get even further, although several interesting open problems remain.

quant-ph↗