Related papers: Predict; Do not React for Enabling Efficient Fine …

Network Function Virtualization (NFV) can cost-efficiently provide network services by running different virtual network functions (VNFs) at different virtual machines (VMs) in a correct order. This can result in strong couplings between…

The hardware implementation of deep neural networks (DNNs) has recently received tremendous attention: many applications in fact require high-speed operations that suit a hardware implementation. However, numerous elements and complex…

The last decade has witnessed the proliferation of network function virtualization (NFV) in the telco industry, thanks to its unparalleled flexibility, scalability, and cost-effectiveness. However, as the NFV infrastructure is shared by…

The evaluation of new microprocessor designs is constrained by slow, cycle-accurate simulators that rely on unrepresentative benchmark traces. This paper introduces a novel deep learning framework for high-fidelity, ``in-the-wild''…

We empirically evaluate an undervolting technique, i.e., underscaling the circuit supply voltage below the nominal level, to improve the power-efficiency of Convolutional Neural Network (CNN) accelerators mapped to Field Programmable Gate…

Pre-training & fine-tuning is a prevalent paradigm in computer vision (CV). Recently, parameter-efficient transfer learning (PETL) methods have shown promising performance in adapting to downstream tasks with only a few trainable…

The performance of video prediction has been greatly boosted by advanced deep neural networks. However, most of the current methods suffer from large model sizes and require extra inputs, e.g., semantic/depth maps, for promising…

In this work, we investigate the potential utility of parallelization for meeting real-time constraints and minimizing energy. We consider malleable Gang scheduling of implicit-deadline sporadic tasks upon multiprocessors. We first show the…

Deep Learning Recommendation Models (DLRMs) have become increasingly popular and prevalent in today's datacenters, consuming most of the AI inference cycles. The performance of DLRMs is heavily influenced by available bandwidth due to their…

The deployment of ML models on edge devices is challenged by limited computational resources and energy availability. While split computing enables the decomposition of large neural networks (NNs) and allows partial computation on both edge…

This paper introduces a phase tracking method for planetary radio science research with computational algorithm implemented fo r NVIDIA GPUs. In contrast to the phase-locked loop (PPL) phase counting method used in traditional Doppler data…

Compared to the first generation of deep neural networks, dominated by regular, compute-intensive kernels such as matrix multiplications (MatMuls) and convolutions, modern decoder-based transformers interleave attention, normalization, and…

Thermal-Aware Scheduling (TAS) provides methods to manage the thermal dissipation of a computing chip during task execution. These methods aim to avoid issues such as accelerated aging of the device, premature failure and degraded chip…

Large-scale GPU clusters are widely-used to speed up both latency-critical (online) and best-effort (offline) deep learning (DL) workloads. However, most DL clusters either dedicate each GPU to one workload or share workloads in time,…

Bayesian Neural Networks (BNNs) have been proposed to address the problem of model uncertainty in training and inference. By introducing weights associated with conditioned probability distributions, BNNs are capable of resolving the…

The in-memory computing paradigm with emerging memory devices has been recently shown to be a promising way to accelerate deep learning. Resistive processing unit (RPU) has been proposed to enable the vector-vector outer product in a…

With the increase in the complexity of chip designs, VLSI physical design has become a time-consuming task, which is an iterative design process. Power planning is that part of the floorplanning in VLSI physical design where power grid…

The explosive growth of artificial intelligence has created gigawatt-scale data centers that fundamentally challenge power system operation, exhibiting power fluctuations exceeding 500 MW within seconds and millisecond-scale variations of…

To ensure frequency stability in future low-inertia power grids, fast ancillary services such as fast frequency reserves (FFR) have been proposed. In this work, the coordination of conventional (slow) frequency containment reserves (FCR)…

As large-scale HPC compute clusters increasingly adopt accelerators such as GPUs to meet the voracious demands of modern workloads, these clusters are increasingly becoming power constrained. Unfortunately, modern applications can often…