Related papers: PANDA: Architecture-Level Power Evaluation by Unif…
Characterizing and predicting the training performance of modern machine learning (ML) workloads on compute systems with compute and communication spread between CPUs, GPUs, and network devices is not only the key to optimization and…
Understanding and predicting the performance of big data applications running in the cloud or on-premises could help minimise the overall cost of operations and provide opportunities in efforts to identify performance bottlenecks. The…
Video anomaly detection (VAD) is a critical yet challenging task due to the complex and diverse nature of real-world scenarios. Previous methods typically rely on domain-specific training data and manual adjustments when applying to new…
Neural networks are powerful models that have a remarkable ability to extract patterns that are too complex to be noticed by humans or other machine learning models. Neural networks are the first class of models that can train end-to-end…
In neural architecture search, the structure of the neural network to best model a given dataset is determined by an automated search process. Efficient Neural Architecture Search (ENAS), proposed by Pham et al. (2018), has recently…
Architecture-based heat dissipation analyses allow us to reveal fundamental sources of inefficiency in a given processor and thereby provide us with road-maps to design less dissipative computing schemes independent of technology-base used…
Due to the high computational demands executing a rigorous comparison between hyperparameter optimization (HPO) methods is often cumbersome. The goal of this paper is to facilitate a better empirical evaluation of HPO methods by providing…
Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep…
The reliability of machine learning (ML) software systems is heavily influenced by changes in data over time. For that reason, ML systems require regular maintenance, typically based on model retraining. However, retraining requires…
Management and efficient operations in critical infrastructure such as Smart Grids take huge advantage of accurate power load forecasting which, due to its nonlinear nature, remains a challenging task. Recently, deep learning has emerged in…
Different machine learning (ML) models are trained on SCADA and meteorological data collected at an onshore wind farm and then assessed in terms of fidelity and accuracy for predictions of wind speed, turbulence intensity, and power capture…
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…
Given their increasing size and complexity, the need for efficient execution of deep neural networks has become increasingly pressing in the design of heterogeneous High-Performance Computing (HPC) and edge platforms, leading to a wide…
Designing effective architectures is one of the key factors behind the success of deep neural networks. Existing deep architectures are either manually designed or automatically searched by some Neural Architecture Search (NAS) methods.…
The rapid scaling of Large Language Models (LLMs) has pushed training workloads far beyond the limits of single-node analysis, demanding a deeper understanding of how these models behave across large-scale, multi-GPU systems. In this paper,…
Today's scientific challenges, from climate modeling to Inertial Confinement Fusion design to novel material design, require exploring huge design spaces. In order to enable high-impact scientific discovery, we need to scale up our ability…
Graphics Processing Units (GPUs) have become an integral part of High-Performance Computing to achieve an Exascale performance. The main goal of application developers of GPU is to tune their code extensively to obtain optimal performance,…
We introduce a new function-preserving transformation for efficient neural architecture search. This network transformation allows reusing previously trained networks and existing successful architectures that improves sample efficiency. We…
Deep learning models have revolutionized various fields, from image recognition to natural language processing, by achieving unprecedented levels of accuracy. However, their increasing energy consumption has raised concerns about their…
While discrete-event simulators are essential tools for architecture research, design, and development, their practicality is limited by an extremely long time-to-solution for realistic applications under investigation. This work describes…