Models of artificial intelligence (AI) that have billions of parameters can achieve high accuracy across a range of tasks1,2, but they exacerbate the poor energy efficiency of conventional general-purpose processors, such as graphics processing units or central processing units. Analog in-memory computing (analog-AI)3–7 can provide better energy efficiency by performing matrix–vector multiplications in parallel on ‘memory tiles’. However, analog-AI has yet to demonstrate software-equivalent (SWeq) accuracy on models that require many such tiles and efficient communication of neural-network activations between the tiles. Here we present an analog-AI chip that combines 35 million phase-change memory devices across 34 tiles, massively parallel inter-tile communication and analog, low-power peripheral circuitry that can achieve up to 12.4 tera-operations per second per watt (TOPS/W) chip-sustained performance. We demonstrate fully end-to-end SWeq accuracy for a small keyword-spotting network and near-SWeq accuracy on the much larger MLPerf8 recurrent neural-network transducer (RNNT), with more than 45 million weights mapped onto more than 140 million phase-change memory devices across five chips.
21 November 2022 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
We introduce a highly heterogeneous and programmable compute-in-memory (CIM) accelerator architecture for deep neural network (DNN) inference. This architecture combines spatially distributed CIM memory array “tiles” for weight-stationary, energy-efficient multiply–accumulate (MAC) operations, together with heterogeneous special-function compute cores for auxiliary digital computation. Massively parallel vectors of neuron activation data are exchanged over short distances using a dense and efficient circuit-switched 2-D mesh, offering full end-to-end support for a wide range of DNN workloads, including CNNs, long-short-term-memory (LSTM), and transformers. We discuss the design of the “analog fabric”—the 2-D grid of tiles and compute cores interconnected by the 2-D mesh—and address the efficiency in both mapping of DNNs onto the hardware and in pipelining of various DNN workloads across a range of batch sizes. We show, for the first time, system-level assessments using projected component parameters for a realistic “analog AI” system, based on dense crossbar arrays of low-power nonvolatile analog memory elements, while incorporating a single common analog fabric design that can scale to large networks by introducing data transport between multiple analog AI chips. Our performance estimates for several networks, including large LSTM and bidirectional encoder representations from transformers (BERT), show highly competitive throughput while offering $40\times $ – $140\times $ higher energy efficiency than NVIDIA A100—thus illustrating the strong promise of analog AI and the proposed architecture for DNN inference applications.
We propose a quantum error mitigation strategy for the variational quantum eigensolver (VQE) algorithm. We find, via numerical simulation, that very small amounts of coherent noise in VQE can cause substantially large errors that are difficult to suppress by conventional mitigation methods, and yet our proposed mitigation strategy is able to significantly reduce these errors. The proposed strategy is a combination of previously reported techniques, namely randomized compiling (RC) and zero-noise extrapolation (ZNE). Intuitively, randomized compiling turns coherent errors in the circuit into stochastic Pauli errors, which facilitates extrapolation to the zero-noise limit when evaluating the cost function. Our numerical simulation of VQE for small molecules shows that the proposed strategy can mitigate energy errors induced by various types of coherent noise by up to two orders of magnitude.
A fully silicon‐integrated restricted Boltzmann machine (RBM) with an event‐driven contrastive divergence (eCD) training algorithm is implemented using novel stochastic leaky integrate‐and‐fire (LIF) neuron circuits and six‐transistor/2‐PCM‐resistor (6T2R) synaptic unit cells on 90 nm CMOS technology. To elaborate, designed a bidirectional, asynchronous, and parallel pulse‐signaling scheme over an analog‐weighted phase‐change memory (PCM) synapse array to enable spike‐timing‐dependent plasticity (STDP) as a local weight update rule based on eCD is designed. Building upon the initial version of this work, significantly more experimental details are added, such as the on‐chip characterization results of LIF and backward‐LIF (BLIF) and stochasticity of our random walk circuitry. The experimental characterization of these on‐chip stochastic neuron circuits shows a reasonable symmetricity between LIF and BLIF as well as the necessary stochasticity for spiking RBM operation. Fully hardware‐based image classification recorded 93% on‐chip training accuracy from 100 handwritten MNIST digit images. In addition, we experimentally demonstrated the generative characteristics of the RBM by reconstructing partial patterns on hardware. As each synapse and neuron execute its computations in an asynchronous and fully parallel fashion, the chip can perform data‐intensive machine learning (ML) tasks in a power‐efficient manner and take advantage of the sparseness of spiking.
A Lite Bidirectional Encoder Representations from Transformers model is demonstrated on an analog inference chip fabricated at 14nm node with phase change memory. The 7.1 million unique analog weights shared across 12 layers are mapped to a single chip, accurately programmed into the conductance of 28.3 million devices, for this first analog hardware demonstration of a meaningfully large Transformer model. The implemented model achieved near iso-accuracy on the General Language Understanding Evaluation benchmark of seven tasks, despite the presence of weight-programming errors, hardware imperfections, readout noise, and error propagation. The average hardware accuracy was only 1.8% below that of the floating-point reference, with several tasks at full iso-accuracy. Careful fine-tuning of model weights using hardware-aware techniques contributes an average hardware accuracy improvement of 4.4%. Accuracy loss due to conductance drift – measured to be roughly 5% over 30 days – was reduced to less than 1% with a recalibration-based “drift compensation” technique.
Efficiently solving combinatorial optimization problems (COPs) such as Max‐Cut is challenging because the resources required increase exponentially with the problem size. This study proposes a hardware‐friendly method for solving the Max‐Cut problem by implementing a spiking neural network (SNN)‐based Boltzmann machine (BM) in neuromorphic hardware systems. To implement the hardware‐oriented version of the spiking Boltzmann machine (sBM), the stochastic dynamics of leaky integrate‐and‐fire (LIF) neurons with random walk noise are analyzed, and an innovative algorithm based on overlapping time windows is proposed. The simulation results demonstrate the effective convergence and high accuracy of the proposed method for large‐scale Max‐Cut problems. The proposed method is validated through successful hardware implementation on a 6‐transistor/2‐resistor (6T2R) neuromorphic chip with phase change memory (PCM) synapses. In addition, as an expansion of the algorithm, several annealing techniques and bias split methods are proposed to improve convergence, along with circuit design ideas for efficient evaluation of sampling convergence using cell arrays and spiking systems. Overall, the results of the proposed methods demonstrate the potential of energy‐efficient and hardware‐implementable approaches using SNNs to solve COPs. To the best of the author's knowledge, this is the first study to solve the Max‐Cut problem using an SNN neuromorphic hardware chip.