Related papers: QSync: Quantization-Minimized Synchronous Distribu…

This paper proposes Mandheling, the first system that enables highly resource-efficient on-device training by orchestrating the mixed-precision training with on-chip Digital Signal Processing (DSP) offloading. Mandheling fully explores the…

Deep Neural Networks (DNNs) have gained considerable attention in the past decades due to their astounding performance in different applications, such as natural language modeling, self-driving assistance, and source code understanding.…

Graph Neural Networks (GNNs) have become essential for handling large-scale graph applications. However, the computational demands of GNNs necessitate the development of efficient methods to accelerate inference. Mixed precision…

Deep learning has become a promising programming paradigm in software development, owing to its surprising performance in solving many challenging tasks. Deep neural networks (DNNs) are increasingly being deployed in practice, but are…

Distributed training is a novel approach to accelerate Deep Neural Networks (DNN) training, but common training libraries fall short of addressing the distributed cases with heterogeneous processors or the cases where the processing nodes…

We introduce iQSync, a clock offset recovery method designed for implementation on low-level hardware, such as FPGAs or microcontrollers, for quantum key distribution (QKD). iQSync requires minimal memory, only a simple instruction set…

Recent trends in lower precision, e.g. half-precision floating point, training have shown improved system performance and reduced memory usage for Deep Learning while maintaining accuracy. However, current GNN systems cannot achieve such…

Deep Neural Networks (DNNs) have gained immense success in cognitive applications and greatly pushed today's artificial intelligence forward. The biggest challenge in executing DNNs is their extremely data-extensive computations. The…

The resource requirements of deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mixed-precision quantization, which lead to latency and memory…

Recent breakthroughs in deep neural networks (DNNs) have fueled a tremendous demand for intelligent edge devices featuring on-site learning, while the practical realization of such systems remains a challenge due to the limited resources…

Modern deep neural network (DNN) training jobs use complex and heterogeneous software/hardware stacks. The efficacy of software-level optimizations can vary significantly when used in different deployment configurations. It is onerous and…

Low-bit deep neural networks (DNNs) become critical for embedded applications due to their low storage requirement and computing efficiency. However, they suffer much from the non-negligible accuracy drop. This paper proposes the stochastic…

Spiking neural networks are emerging as a promising energy-efficient alternative to traditional artificial neural networks due to their spike-driven paradigm. However, recent research in the SNN domain has mainly focused on enhancing…

The demand for executing Deep Neural Networks (DNNs) with low latency and minimal power consumption at the edge has led to the development of advanced heterogeneous Systems-on-Chips (SoCs) that incorporate multiple specialized computing…

The proliferation of extensive neural network architectures, particularly deep learning models, presents a challenge in terms of resource-intensive training. GPU memory constraints have become a notable bottleneck in training such sizable…

Systems for serving inference requests on graph neural networks (GNN) must combine low latency with high throughout, but they face irregular computation due to skew in the number of sampled graph nodes and aggregated GNN features. This…

Distributed deep neural networks (DNNs) have become central to modern computer vision, yet their deployment on resource-constrained edge devices remains hindered by substantial parameter counts, computational demands, and the probability of…

As deep learning models scale, their training cost has surged significantly. Due to both hardware advancements and limitations in current software stacks, the need for data efficiency has risen. Data efficiency refers to the effective…

Quantum neural networks (QNNs) and quantum kernels stand as prominent figures in the realm of quantum machine learning, poised to leverage the nascent capabilities of near-term quantum computers to surmount classical machine learning…

Ultra-low-precision inference can sharply reduce memory and latency but often degrades accuracy and relies on specialized hardware. We present SONIQ, a system-optimized, noise-injected quantization framework that learns per-channel mixed…