arXiv subjects

Chunguang Wang

Publications and source records attributed to Chunguang Wang.

9 recordsLinked to original sources

arXiv2024

WAGONN: Weight Bit Agglomeration in Crossbar Arrays for Reduced Impact of Interconnect Resistance on DNN Inference Accuracy

Deep neural network (DNN) accelerators employing crossbar arrays capable of in-memory computing (IMC) are highly promising for neural computing platforms. However, in deeply scaled technologies, interconnect resistance severely impairs IMC robustness, leading to a drop in the system accuracy. To address this problem, we propose SWANN - a technique based on shuffling weights in crossbar arrays which alleviates the detrimental effect of wire resistance on IMC. For 8T-SRAM-based 128x128 crossbar arrays in 7nm technology, SWANN enhances the accuracy from 47.78% to 83.5% for ResNet-20/CIFAR-10. We also show that SWANN can be used synergistically with Partial-Word-LineActivation, further boosting the accuracy. Moreover, we evaluate the implications of SWANN for compact ferroelectric-transistorbased crossbar arrays. SWANN incurs minimal hardware overhead, with less than a 1% increase in energy consumption. Additionally, the latency and area overheads of SWANN are ~1% and ~16%, respectively when 1 ADC is utilized per crossbar array.

cs.ET↗

arXiv2024

Comparative Evaluation of Memory Technologies for Synaptic Crossbar Arrays -- Part I: Robustness-driven Device-Circuit Co-Design and System Implications

In-memory computing (IMC) utilizing synaptic crossbar arrays is promising for energy-efficient deep neural network (DNN) accelerators. Various technologies (CMOS and post-CMOS) have been explored as synaptic device candidates, each with its own pros and cons. In this work, we perform a design space exploration and comparative evaluation of four technologies viz. 8T SRAMs, ferroelectric transistors (FeFETs), resistive RAMs (ReRAMs) and spin-orbit torque magnetic RAMs (SOT-MRAMs) in the context of IMC robustness and DNN accuracy. For a fair comparison, we carefully optimize each technology specifically for synaptic crossbar design accounting for device and circuit non-idealities. By integrating different technologies into a cross-layer simulation flow based on physical models of synaptic devices and interconnects, we present insights into various device-circuit interactions. Based on the optimized designs, we obtain inference results for ResNet-20 on CIFAR-10 dataset. Among the four technologies, we show that FeFETs-based DNNs achieve the highest accuracy (followed closely by ReRAMs) and the largest resilience to process variations due to the compactness and high ON/OFF current ratio of FeFET bit-cells. In Part II of this paper, we expand the technology evaluation considering various device-circuit design knobs used for crossbar arrays.

cs.ET↗

arXiv2024

Comparative Evaluation of Memory Technologies for Synaptic Crossbar Arrays- Part 2: Design Knobs and DNN Accuracy Trends

Crossbar memory arrays have been touted as the workhorse of in-memory computing (IMC)-based acceleration of Deep Neural Networks (DNNs), but the associated hardware non-idealities limit their efficacy. To address this, cross-layer design solutions that reduce the impact of hardware non-idealities on DNN accuracy are needed. In Part 1 of this paper, we established the co-optimization strategies for various memory technologies and their crossbar arrays, and conducted a comparative technology evaluation in the context of IMC robustness. In this part, we analyze various design knobs such as array size and bit-slice (number of bits per device) and their impact on the performance of 8T SRAM, ferroelectric transistor (FeFET), Resistive RAM (ReRAM) and spin-orbit-torque magnetic RAM (SOT-MRAM) in the context of inference accuracy at 7nm technology node. Further, we study the effect of circuit design solutions such as Partial Wordline Activation (PWA) and custom ADC reference levels that reduce the hardware non-idealities and comparatively analyze the response of each technology to such accuracy enhancing techniques. Our results on ResNet-20 (with CIFAR-10) show that PWA increases accuracy by up to 32.56% while custom ADC reference levels yield up to 31.62% accuracy enhancement. We observe that compared to the other technologies, FeFET, by virtue of its small layout height and high distinguishability of its memory states, is best suited for large arrays. For higher bit-slices and a more complex dataset (ResNet-50 with Cifar-100) we found that ReRAM matches the performance of FeFET.

cs.ET↗

arXiv2022

ADRA: Extending Digital Computing-in-Memory with Asymmetric Dual-Row-Activation

Computing in-memory (CiM) has emerged as an attractive technique to mitigate the von-Neumann bottleneck. Current digital CiM approaches for in-memory operands are based on multi-wordline assertion for computing bit-wise Boolean functions and arithmetic functions such as addition. However, most of these techniques, due to the many-to-one mapping of input vectors to bitline voltages, are limited to CiM of commutative functions, leaving out an important class of computations such as subtraction. In this paper, we propose a CiM approach, which solves the mapping problem through an asymmetric wordline biasing scheme, enabling (a) simultaneous single-cycle memory read and CiM of primitive Boolean functions (b) computation of any Boolean function and (c) CiM of non-commutative functions such as subtraction and comparison. While the proposed technique is technology-agnostic, we show its utility for ferroelectric transistor (FeFET)-based non-volatile memory. Compared to the standard near-memory methods (which require two full memory accesses per operation), we show that our method can achieve a full scale two-operand digital CiM using just one memory access, leading to a 23.2% - 72.6% decrease in energy-delay product (EDP).

cs.AR↗

arXiv2020

NMR and NQR studies on transition-metal arsenide superconductors LaRu2As2, KCa2Fe4As4F2, and A2Cr3As3

We report 75As-nuclear magnetic resonance (NMR) and nuclear quadrupole resonance (NQR) measurements on transition-metal arsenides LaRu2As2, KCa2Fe4As4F2, and A2Cr3As3. In the superconducting state of LaRu2As2, a Hebel- Slichter coherence peak is found in the temperature dependence of the spin-lattice relaxation rate-1/T1 just below Tc, which indicates that LaRu2As2 is a full-gap superperconducor. For KCa2Fe4As4F2, antiferromagnetic spin fluctuations are observed in the normal state. We further find that the anisotropy rate RAF = Tc1/Tab1 is small and temperature independent, implying that the low energy spin fluctuations are isotropic in spin space. Our results indicate that KCa2Fe4As4F2 is a moderately overdoped iron-arsenide high-temperature superconductor with a stoichiometric composition. For A2Cr3As3, we calculate the electric field gradient by first-principle method and assign the 75As-NQR peaks with two crystallographically different As sites, paving the way for further NMR investigation.

cond-mat.supr-con↗

arXiv2017

Quantum group symmetries and completeness for A_{2n}^(2) open spin chains

We argue that the Hamiltonians for A_{2n}^(2) open quantum spin chains corresponding to two choices of integrable boundary conditions have the symmetries U_q(B_n) and U_q(C_n), respectively. We find a formula for the Dynkin labels of the Bethe states (which determine the degeneracies of the corresponding eigenvalues) in terms of the numbers of Bethe roots of each type. With the help of this formula, we verify numerically (for a generic value of the anisotropy parameter) that the degeneracies and multiplicities of the spectra implied by the quantum group symmetries are completely described by the Bethe ansatz.

math-ph↗

arXiv2014

Twisting singular solutions of Bethe's equations

The Bethe equations for the periodic XXX and XXZ spin chains admit singular solutions, for which the corresponding eigenvalues and eigenvectors are ill-defined. We use a twist regularization to derive conditions for such singular solutions to be physical, in which case they correspond to genuine eigenvalues and eigenvectors of the Hamiltonian.

math-ph↗

arXiv2014

Boundary energy of the open XXX chain with a non-diagonal boundary term

We analyze the ground state of the open spin-1/2 isotropic quantum spin chain with a non-diagonal boundary term using a recently proposed Bethe ansatz solution. As the coefficient of the non-diagonal boundary term tends to zero, the Bethe roots split evenly into two sets: those that remain finite, and those that become infinite. We argue that the former satisfy conventional Bethe equations, while the latter satisfy a generalization of the Richardson-Gaudin equations. We derive an expression for the leading correction to the boundary energy in terms of the boundary parameters.

math-ph↗

arXiv2013

Algebraic Bethe ansatz for singular solutions

The Bethe equations for the isotropic periodic spin-1/2 Heisenberg chain with N sites have solutions containing i/2, -i/2 that are singular: both the corresponding energy and the algebraic Bethe ansatz vector are divergent. Such solutions must be carefully regularized. We consider a regularization involving a parameter that can be determined using a generalization of the Bethe equations. These generalized Bethe equations provide a practical way of determining which singular solutions correspond to eigenvectors of the model.

hep-th↗