Towards 3D Acceleration for low-power Mixture-of-Experts and Multi-Head Attention Spiking Transformers

Spiking Neural Networks(SNNs) provide a brain-inspired and event-driven mechanism that is believed to be critical to unlock energy-efficient deep learning. The mixture-of-experts approach mirrors the parallel distributed processing of nervous systems, introducing conditional computation policies and expanding model capacity without scaling up the number of computational operations. Additionally, spiking mixture-of-experts self-attention mechanisms enhance representation capacity, effectively capturing diverse patterns of entities and dependencies between visual or linguistic tokens. However, there is currently a lack of hardware support for highly parallel distributed processing needed by spiking transformers, which embody a brain-inspired computation. This paper introduces the first 3D hardware architecture and design methodology for Mixture-of-Experts and Multi-Head Attention spiking transformers. By leveraging 3D integration with memory-on-logic and logic-on-logic stacking, we explore such brain-inspired accelerators with spatially stackable circuitry, demonstrating significant optimization of energy efficiency and latency compared to conventional 2D CMOS integration.

Trimming Down Large Spiking Vision Transformers via Heterogeneous Quantization Search

Spiking Neural Networks (SNNs) are amenable to deployment on edge devices and neuromorphic hardware due to their lower dissipation. Recently, SNN-based transformers have garnered significant interest, incorporating attention mechanisms akin to their counterparts in Artificial Neural Networks (ANNs) while demonstrating excellent performance. However, deploying large spiking transformer models on resource-constrained edge devices such as mobile phones, still poses significant challenges resulted from the high computational demands of large uncompressed high-precision models. In this work, we introduce a novel heterogeneous quantization method for compressing spiking transformers through layer-wise quantization. Our approach optimizes the quantization of each layer using one of two distinct quantization schemes, i.e., uniform or power-of-two quantification, with mixed bit resolutions. Our heterogeneous quantization demonstrates the feasibility of maintaining high performance for spiking transformers while utilizing an average effective resolution of 3.14-3.67 bits with less than a 1% accuracy drop on DVS Gesture and CIFAR10-DVS datasets. It attains a model compression rate of 8.71x-10.19x for standard floating-point spiking transformers. Moreover, the proposed approach achieves a significant energy reduction of 5.69x, 8.72x, and 10.2x while maintaining high accuracy levels of 85.3%, 97.57%, and 80.4% on N-Caltech101, DVS-Gesture, and CIFAR10-DVS datasets, respectively.

Spiking Transformer Hardware Accelerators in 3D Integration

Spiking neural networks (SNNs) are powerful models of spatiotemporal computation and are well suited for deployment on resource-constrained edge devices and neuromorphic hardware due to their low power consumption. Leveraging attention mechanisms similar to those found in their artificial neural network counterparts, recently emerged spiking transformers have showcased promising performance and efficiency by capitalizing on the binary nature of spiking operations. Recognizing the current lack of dedicated hardware support for spiking transformers, this paper presents the first work on 3D spiking transformer hardware architecture and design methodology. We present an architecture and physical design co-optimization approach tailored specifically for spiking transformers. Through memory-on-logic and logic-on-logic stacking enabled by 3D integration, we demonstrate significant energy and delay improvements compared to conventional 2D CMOS integration.

ADO-LLM: Analog Design Bayesian Optimization with In-Context Learning of Large Language Models

Analog circuit design requires substantial human expertise and involvement, which is a significant roadblock to design productivity. Bayesian Optimization (BO), a popular machine learning based optimization strategy, has been leveraged to automate analog design given its applicability across various circuit topologies and technologies. Traditional BO methods employ black box Gaussian Process surrogate models and optimized labeled data queries to find optimization solutions by trading off between exploration and exploitation. However, the search for the optimal design solution in BO can be expensive from both a computational and data usage point of view, particularly for high dimensional optimization problems. This paper presents ADO-LLM, the first work integrating large language models (LLMs) with Bayesian Optimization for analog design optimization. ADO-LLM leverages the LLM's ability to infuse domain knowledge to rapidly generate viable design points to remedy BO's inefficiency in finding high value design areas specifically under the limited design space coverage of the BO's probabilistic surrogate model. In the meantime, sampling of design points evaluated in the iterative BO process provides quality demonstrations for the LLM to generate high quality design points while leveraging infused broad design knowledge. Furthermore, the diversity brought by BO's exploration enriches the contextual understanding of the LLM and allows it to more broadly search in the design space and prevent repetitive and redundant suggestions. We evaluate the proposed framework on two different types of analog circuits and demonstrate notable improvements in design efficiency and effectiveness.

DISTA: Denoising Spiking Transformer with intrinsic plasticity and spatiotemporal attention

Among the array of neural network architectures, the Vision Transformer (ViT) stands out as a prominent choice, acclaimed for its exceptional expressiveness and consistent high performance in various vision applications. Recently, the emerging Spiking ViT approach has endeavored to harness spiking neurons, paving the way for a more brain-inspired transformer architecture that thrives in ultra-low power operations on dedicated neuromorphic hardware. Nevertheless, this approach remains confined to spatial self-attention and doesn't fully unlock the potential of spiking neural networks. We introduce DISTA, a Denoising Spiking Transformer with Intrinsic Plasticity and SpatioTemporal Attention, designed to maximize the spatiotemporal computational prowess of spiking neurons, particularly for vision applications. DISTA explores two types of spatiotemporal attentions: intrinsic neuron-level attention and network-level attention with explicit memory. Additionally, DISTA incorporates an efficient nonlinear denoising mechanism to quell the noise inherent in computed spatiotemporal attention maps, thereby resulting in further performance gains. Our DISTA transformer undergoes joint training involving synaptic plasticity (i.e., weight tuning) and intrinsic plasticity (i.e., membrane time constant tuning) and delivers state-of-the-art performances across several static image and dynamic neuromorphic datasets. With only 6 time steps, DISTA achieves remarkable top-1 accuracy on CIFAR10 (96.26%) and CIFAR100 (79.15%), as well as 79.1% on CIFAR10-DVS using 10 time steps.

UPAR: A Kantian-Inspired Prompting Framework for Enhancing Large Language Model Capabilities

Large Language Models (LLMs) have demonstrated impressive inferential capabilities, with numerous research endeavors devoted to enhancing this capacity through prompting. Despite these efforts, a unified epistemological foundation is still conspicuously absent. Drawing inspiration from Kant's a priori philosophy, we propose the UPAR prompting framework, designed to emulate the structure of human cognition within LLMs. The UPAR framework is delineated into four phases: "Understand", "Plan", "Act", and "Reflect", enabling the extraction of structured information from complex contexts, prior planning of solutions, execution according to plan, and self-reflection. This structure significantly augments the explainability and accuracy of LLM inference, producing a human-understandable and inspectable inferential trajectory. Furthermore, our work offers an epistemological foundation for existing prompting techniques, allowing for a possible systematic integration of these methods. With GPT-4, our approach elevates the accuracy from COT baseline of 22.92% to 58.33% in a challenging subset of GSM8K, and from 67.91% to 75.40% in the causal judgment task.