Related papers: S4: a High-sparsity, High-performance AI Accelerat…

For time-critical IoT applications using deep learning, inference acceleration through distributed computing is a promising approach to meet a stringent deadline. In this paper, we implement a working prototype of a new distributed…

Machine learning, particularly deep neural network inference, has become a vital workload for many computing systems, from data centers and HPC systems to edge-based computing. As advances in sparsity have helped improve the efficiency of…

The rapid development and application of foundation models have revolutionized the field of artificial intelligence. Large diffusion models have gained significant attention for their ability to generate photorealistic images and support…

Transformer-based diffusion models offer superior scalability and performance but suffer from high computational overhead due to the iterative nature and quadratic complexity of self-attention at high resolutions. In this paper, we propose…

Pruning aims to accelerate and compress models by removing redundant parameters, identified by specifically designed importance scores which are usually imperfect. This removal is irreversible, often leading to subpar performance in pruned…

While CNNs naturally lend themselves to densely sampled data, and sophisticated implementations are available, they lack the ability to efficiently process sparse data. In this work we introduce a suite of tools that exploit sparsity in…

Remarkable achievements have been attained by deep neural networks in various applications. However, the increasing depth and width of such models also lead to explosive growth in both storage and computation, which has restricted the…

Large language models (LLMs) have grown beyond the memory capacity of single GPU devices, necessitating quantization techniques for practical deployment. While NF4 (4-bit NormalFloat) quantization enables 4$\times$ memory reduction,…

Spiking neural networks (SNNs) communicate via discrete spikes in time rather than continuous activations. Their event-driven nature offers advantages for temporal processing and energy efficiency on resource-constrained hardware, but…

Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. However, prevailing SR models suffer from prohibitive memory footprint and intensive computations, which limits further…

As a foundational architecture of artificial intelligence models, Transformer has been recently adapted to spiking neural networks with promising performance across various tasks. However, existing spiking Transformer(ST)-based models…

Low power deep learning accelerators on the speech processing enable real-time applications on edge devices. However, most of the existing accelerators suffer from high power consumption and focus on image applications only. This paper…

In recent years, the fervent demand for computational power across various domains has prompted hardware manufacturers to introduce specialized computing hardware aimed at enhancing computational capabilities. Particularly, the utilization…

Conventional deep convolutional neural networks (CNNs) apply convolution operators uniformly in space across all feature maps for hundreds of layers - this incurs a high computational cost for real-time applications. For many problems such…

NVIDIA's 2:4 Sparse Tensor Cores deliver 2x throughput but demand strict 50% pruning -- a ratio that collapses LLM reasoning accuracy (Qwen3: 54% to 15%). Milder $(2N-2):2N$ patterns (e.g., 6:8, 25% pruning) preserve accuracy yet receive no…

The MIT/IEEE/Amazon GraphChallenge.org encourages community approaches to developing new solutions for analyzing graphs and sparse data. Sparse AI analytics present unique scalability difficulties. The proposed Sparse Deep Neural Network…

The customizability of RISC-V makes it an attractive choice for accelerating deep neural networks (DNNs). It can be achieved through instruction set extensions and corresponding custom functional units. Yet, efficiently exploiting these…

Weight pruning is a technique to make Deep Neural Network (DNN) inference more computationally efficient by reducing the number of model parameters over the course of training. However, most weight pruning techniques generally does not…

Brain-inspired Spiking neural networks (SNNs) promise energy-efficient intelligence via event-driven, sparse computation, but deeper architectures inflate parameters and computational cost, hindering their edge deployment. Recent progress…

With the fast growth of parameter size, it becomes increasingly challenging to deploy large generative models as they typically require large GPU memory consumption and massive computation. Unstructured model pruning has been a common…