Related papers: DNN is not all you need: Parallelizing Non-Neural …

Modern datacenters increasingly rely on low-power, single-slot inference accelerators to balance performance, energy efficiency, and rack density constraints. The NVIDIA T4 GPU has become widely deployed due to strong performance per watt…

Mixture-of-Experts (MoE) models are typically pre-trained with explicit load-balancing constraints to ensure statistically balanced expert routing. Despite this, we observe that even well-trained MoE models exhibit significantly imbalanced…

Scaling Deep Neural Networks (DNNs) requires significant computational resources in terms of GPU quantity and compute capacity. In practice, there usually exists a large number of heterogeneous GPU devices due to the rapid release cycle of…

Deep neural network (DNN) inference is increasingly being executed on mobile and embedded platforms due to low latency and better privacy. However, efficient deployment on these platforms is challenging due to the intensive computation and…

Edge computing and IoT applications are severely constrained by limited hardware resource. This makes memory consuming DNN frameworks not applicable to edge computing. Simple algorithms such as direct convolution are finding their way in…

In recent years, deep neural networks (DNNs), have yielded strong results on a wide range of applications. Graphics Processing Units (GPUs) have been one key enabling factor leading to the current popularity of DNNs. However, despite…

With the growing number of data-intensive workloads, GPU, which is the state-of-the-art single-instruction-multiple-thread (SIMT) processor, is hindered by the memory bandwidth wall. To alleviate this bottleneck, previously proposed…

Recent advancements in quantization and mixed-precision approaches offers substantial opportunities to improve the speed and energy efficiency of Neural Networks (NN). Research has shown that individual parameters with varying low…

Training deep neural networks (DNNs) in large-cluster computing environments is increasingly necessary, as networks grow in size and complexity. Local memory and processing limitations require robust data and model parallelism for crossing…

Neural network (NN) accelerators have been integrated into a wide-spectrum of computer systems to accommodate the rapidly growing demands for artificial intelligence (AI) and machine learning (ML) applications. NN accelerators share the…

Machine learning potentials (MLPs) trained on data from quantum-mechanics based first-principles methods can approach the accuracy of the reference method at a fraction of the computational cost. To facilitate efficient MLP-based molecular…

Recent technological advances have proliferated the available computing power, memory, and speed of modern Central Processing Units (CPUs), Graphics Processing Units (GPUs), and Field Programmable Gate Arrays (FPGAs). Consequently, the…

Increased capabilities such as recognition and self-adaptability are now required from IoT applications. While IoT node power consumption is a major concern for these applications, cloud-based processing is becoming unsustainable due to…

The deployment of Deep Neural Networks (DNNs) on end-nodes at the extreme edge of the Internet-of-Things is a critical enabler to support pervasive Deep Learning-enhanced applications. Low-Cost MCU-based end-nodes have limited on-chip…

We present a library of efficient implementations of deep learning primitives. Deep learning workloads are computationally intensive, and optimizing their kernels is difficult and time-consuming. As parallel architectures evolve, kernels…

The deployment of machine learning (ML) models on microcontrollers (MCUs) is constrained by strict energy, latency, and memory requirements, particularly in battery-operated and real-time edge devices. While software-level optimizations…

In-memory computing (IMC) with non-volatile memories (NVMs) has emerged as a promising approach to address the rapidly growing computational demands of Deep Neural Networks (DNNs). Mapping DNN layers spatially onto NVM-based IMC…

Data movement in memory-intensive workloads, such as deep learning, incurs energy costs that are over three orders of magnitude higher than the cost of computation. Since these workloads involve frequent data transfers between memory and…

Super-TinyML aims to optimize machine learning models for deployment on ultra-low-power application domains such as wearable technologies and implants. Such domains also require conformality, flexibility, and non-toxicity which traditional…

Deep Neural Network (DNN) frameworks use distributed training to enable faster time to convergence and alleviate memory capacity limitations when training large models and/or using high dimension inputs. With the steady increase in datasets…