English
Related papers

Related papers: Discovering Multi-Hardware Mobile Models via Archi…

200 papers

In a technological landscape that is quickly moving toward dense multi-CPU and multi-core computer systems, where using multithreading is an increasingly popular application design decision, it is important to choose a proper model for…

Networking and Internet Architecture · Computer Science 2009-09-29 Ivan Voras , Mario Zagar

Computers used for data analytics are often NUMA systems with multiple sockets per machine, multiple cores per socket, and multiple thread contexts per core. To get the peak performance out of these machines requires the correct number of…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-06-16 Daniel Goodman , Roni Haecki , Tim Harris

While neural architecture search methods have been successful in previous years and led to new state-of-the-art performance on various problems, they have also been criticized for being unstable, being highly sensitive with respect to their…

Machine Learning · Computer Science 2021-07-09 Thomas Elsken , Benedikt Staffler , Arber Zela , Jan Hendrik Metzen , Frank Hutter

Differentiable architecture search (DARTS) marks a milestone in Neural Architecture Search (NAS), boasting simplicity and small search costs. However, DARTS still suffers from frequent performance collapse, which happens when some…

Computer Vision and Pattern Recognition · Computer Science 2021-08-19 Pengfei Hou , Ying Jin , Yukang Chen

Recent breakthroughs in Deep Learning (DL) applications have made DL models a key component in almost every modern computing system. The increased popularity of DL applications deployed on a wide-spectrum of platforms have resulted in a…

Machine Learning · Computer Science 2018-09-17 Diana Marculescu , Dimitrios Stamoulis , Ermao Cai

Distributed execution of deep learning training involves a dynamic interplay between hardware accelerator architecture and device placement strategy. This is the first work to explore the co-optimization of determining the optimal…

Machine Learning · Computer Science 2024-07-19 Irene Wang , Jakub Tarnawski , Amar Phanishayee , Divya Mahajan

Cycle-accurate software simulation of multicores with complex microarchitectures is often excruciatingly slow. People use simplified core models to gain simulation speed. However, a persistent question is to what extent the results derived…

Hardware Architecture · Computer Science 2016-10-10 Sizhuo Zhang , Andrew Wright , Daniel Sanchez , Arvind

Once-for-All (OFA) is a Neural Architecture Search (NAS) framework designed to address the problem of searching efficient architectures for devices with different resources constraints by decoupling the training and the searching stages.…

Neural and Evolutionary Computing · Computer Science 2023-03-27 Rafael C. Ito , Fernando J. Von Zuben

Efficient video architecture is the key to deploying video recognition systems on devices with limited computing resources. Unfortunately, existing video architectures are often computationally intensive and not suitable for such…

Computer Vision and Pattern Recognition · Computer Science 2021-12-10 Yifan Jiang , Xinyu Gong , Junru Wu , Humphrey Shi , Zhicheng Yan , Zhangyang Wang

Almost all neural architecture search methods are evaluated in terms of performance (i.e. test accuracy) of the model structures that it finds. Should it be the only metric for a good autoML approach? To examine aspects beyond performance,…

Machine Learning · Computer Science 2020-03-04 Stefano Alletto , Shenyang Huang , Vincent Francois-Lavet , Yohei Nakata , Guillaume Rabusseau

Designing low-latency and high-efficiency hybrid networks for a variety of low-cost commodity edge devices is both costly and tedious, leading to the adoption of hardware-aware neural architecture search (NAS) for finding optimal…

Machine Learning · Computer Science 2024-08-29 Hung-Yueh Chiang , Diana Marculescu

Deep neural networks have recently become a popular solution to keyword spotting systems, which enable the control of smart devices via voice. In this paper, we apply neural architecture search to search for convolutional neural network…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-27 Tong Mo , Yakun Yu , Mohammad Salameh , Di Niu , Shangling Jui

Modern hardware is abundantly parallel and increasingly heterogeneous. The numerous processing cores have non-uniform access latencies to the main memory and to the processor caches, which causes variability in the communication costs.…

Databases · Computer Science 2016-08-14 Danica Porobic , Ippokratis Pandis , Miguel Branco , Pınar Tözün , Anastasia Ailamaki

In the hardware design space exploration process, it is critical to optimize both hardware parameters and algorithm-to-hardware mappings. Previous work has largely approached this simultaneous optimization problem by separately exploring…

Hardware Architecture · Computer Science 2025-09-16 Charles Hong , Qijing Huang , Grace Dinh , Mahesh Subedar , Yakun Sophia Shao

The increasing parallelism of many-core systems demands for efficient strategies for the run-time system management. Due to the large number of cores the management overhead has a rising impact to the overall system performance. This work…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-02-11 Daniel Gregorek , Robert Schmidt , Alberto Garcia-Ortiz

Driven by the tremendous effort in researching novel deep learning (DL) algorithms, the training cost of developing new models increases staggeringly in recent years. We analyze GPU cluster usage statistics from a top research institute for…

Machine Learning · Computer Science 2021-03-30 Shang Wang , Peiming Yang , Yuxuan Zheng , Xin Li , Gennady Pekhimenko

Neural Architecture Search (NAS) is a popular tool for automatically generating Neural Network (NN) architectures. In early NAS works, these tools typically optimized NN architectures for a single metric, such as accuracy. However, in the…

Neural and Evolutionary Computing · Computer Science 2023-04-05 Emil Njor , Jan Madsen , Xenofon Fafoutis

Tremendous success of machine learning (ML) and the unabated growth in ML model complexity motivated many ML-specific designs in both CPU and accelerator architectures to speed up the model inference. While these architectures are diverse,…

We present magneto-hydrodynamic simulation results for heterogeneous systems. Heterogeneous architectures combine high floating point performance many-core units hosted in conventional server nodes. Examples include Graphics Processing…

Performance · Computer Science 2010-11-04 Bijia Pang , Ue-li Pen , Michael Perrone

Increasing complexity of modern multi-processor system on chip (MPSoC) and the decreasing feature size have introduced new challenges. System designers have to consider now aspects which were not part of the design process in past times.…

Other Computer Science · Computer Science 2014-05-14 Aurang Zaib , Prashanth Raju , Thomas Wild , Andreas Herkersdorf
‹ Prev 1 4 5 6 7 8 10 Next ›