Internet Archive Scholar
Filters
























127 Hits in 3.6 sec

SimNet: Accurate and High-Performance Computer Architecture Simulation using Deep Learning [article]

Lingda Li, Santosh Pandey, Thomas Flynn, Hang Liu, Noel Wheeler, Adolfy Hoisie
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.0 MB)
https://web.archive.org/web/20211117004318/https://arxiv.org/pdf/2105.05821v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

2021 pre-print arXiv:2105.05821v2 fatcat:437sb3g675fq5iiz6qirppogtm

Other Versions

2021 pre-print
arXiv:2105.05821v1 fatcat:jhsgxocwufaktdm6tetvnkt4ji
This work describes a concerted effort, where machine learning (ML) is used to accelerate discrete-event simulation.  ...  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  ...  Conclusions This work proposes a new computer architecture simulation paradigm using ML.  ... 
arXiv:2105.05821v3 fatcat:7jvppv6oojhfzhxc7cvlkvlzkq
Multiple Versions
Citation

Lingda Li, Santosh Pandey, Thomas Flynn, Hang Liu, Noel Wheeler, Adolfy Hoisie. "SimNet: Accurate and High-Performance Computer Architecture Simulation using Deep Learning." arXiv (2022)

SimNet

Lingda Li, Santosh Pandey, Thomas Flynn, Hang Liu, Noel Wheeler, Adolfy Hoisie
2022 Abstract Proceedings of the 2022 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (878.2 kB)
https://web.archive.org/web/20220609005700/https://dl.acm.org/doi/pdf/10.1145/3489048.3530958

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

This work describes a concerted effort, where machine learning (ML) is used to accelerate microarchitecture simulation.  ...  Leveraging modern GPUs, the ML-based simulator outperforms traditional CPU-based simulators significantly. CCS CONCEPTS • Computing methodologies → Discrete-event simulation; Neural networks.  ...  In the meantime, machine learning (ML) advances have led to remarkable achievements in many domains, and using ML for analytical performance modeling is significant and growing.  ... 
doi:10.1145/3489048.3530958 fatcat:jr3bopidjrbx3bhjizejxaufwe
Citation

Lingda Li, Santosh Pandey, Thomas Flynn, Hang Liu, Noel Wheeler, Adolfy Hoisie. "SimNet." Abstract Proceedings of the 2022 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems (2022)

SimNet

Lingda Li, Santosh Pandey, Thomas Flynn, Hang Liu, Noel Wheeler, Adolfy Hoisie
2022 Proceedings of the ACM on Measurement and Analysis of Computing Systems  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (3.2 MB)
https://web.archive.org/web/20220617090842/https://dl.acm.org/doi/pdf/10.1145/3530891

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

This work describes a concerted effort, where machine learning (ML) is used to accelerate microarchitecture simulation.  ...  While cycle-accurate 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  ...  As a result, a sequential implementation of SimNet runs at a throughput of ∼ 1k SimNet: Accurate and High-Performance Computer Architecture Simulation using Deep Learning 25:13 Sub-Trace0 Instruction  ... 
doi:10.1145/3530891 fatcat:mt2d46khojgllgmva6ajgvdnri
Citation

Lingda Li, Santosh Pandey, Thomas Flynn, Hang Liu, Noel Wheeler, Adolfy Hoisie. "SimNet." Proceedings of the ACM on Measurement and Analysis of Computing Systems 6.2 (2022) 1-24

SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo [article]

Thomas Kollar, Michael Laskey, Kevin Stone, Brijen Thananjeyan, Mark Tjersland
2021 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (17.4 MB)
https://web.archive.org/web/20210702020635/https://arxiv.org/pdf/2106.16118v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

The underlying model, SimNet, is trained as a single multi-headed neural network using simulated stereo data as input and simulated object segmentation masks, 3D oriented bounding boxes (OBBs), object  ...  A key component of SimNet is the incorporation of a learned stereo sub-network that predicts disparity.  ...  Finally, we like to thank the Machine Learning Research team at TRI for their feedback and guidance.  ... 
arXiv:2106.16118v1 fatcat:7rofj6dpfnbunpibndqvkhf5be
Open Access
Citation

Thomas Kollar, Michael Laskey, Kevin Stone, Brijen Thananjeyan, Mark Tjersland. "SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo." arXiv (2021)

Distributed Simulation [chapter]

Margaret L. Loper
2015 Modeling and Simulation in the Systems Engineering Life Cycle  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.1 MB)
https://web.archive.org/web/20200320065930/http://www.msc-les.org/proceedings/dhss/2011/DHSS2011_83.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Computing technology has advanced dramatically over the last twenty years, enabling new applications for networked simulation.  ...  Along with these applications are architectures and standards that support the interoperability of heterogeneous simulations.  ...  Using these characteristics, the paper describes the modern distributed simulation architectures in use today.  ... 
doi:10.1007/978-1-4471-5634-5_20 fatcat:kxdbeixjnzdozhj4wk7a7vex54
Citation

Margaret L. Loper. "Distributed Simulation." Modeling and Simulation in the Systems Engineering Life Cycle (2015) 241-253

7.2.3 VIRTUAL PROTOTYPING: RESULTS ILLUSTRATE UTILITY IN DEVELOPING WEAPON SYSTEM REQUIREMENTS

Phillip J. Brown, Jack K. Lavender
1995 INCOSE International Symposium  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (207.7 kB)
https://web.archive.org/web/20170922235116/http://seconcepts.com/papers/virtual.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL. The file type is application/pdf.

The Department of Defense, in response to excruciating budget pressures, recurring system integration problems, and the continuing remarkable growth in computer capability and high resolution graphics,  ...  has seized on the promise of advanced distributed simulation technologies (including virtual prototyping) as a means for improving efficiency in developing integrated defense system products.  ...  LOSAT's SIMNET testbed simulates the LOSAT integrated FCS on a Bradley chassis. Figure 3 shows the LOSAT SIMNET simulator in use.  ... 
doi:10.1002/j.2334-5837.1995.tb01875.x fatcat:noubpkwia5erhedyi3xvpj4zri
Citation

Phillip J. Brown, Jack K. Lavender. "7.2.3 VIRTUAL PROTOTYPING: RESULTS ILLUSTRATE UTILITY IN DEVELOPING WEAPON SYSTEM REQUIREMENTS." INCOSE International Symposium 5.1 (1995) 297-305

Unsupervised Domain Adaptation with Similarity Learning [article]

Pedro O. Pinheiro
2018 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (3.0 MB)
https://web.archive.org/web/20191019025146/https://arxiv.org/pdf/1711.08995v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL. The file type is application/pdf.

Other Versions

2017 pre-print
arXiv:1711.08995v1 fatcat:3vcuolv5ejhvvkrp2b55mjaaxy
In this paper, we propose a different way to do the classification, using similarity learning.  ...  The proposed method learns a pairwise similarity function in which classification can be performed by computing similarity between prototype representations of each category.  ...  I thank Negar Rostamzadeh, Thomas Bosquet and Ishmael Belghazi for helpful discussions and encouragement and Philippe Mathieu and Jean Raby for help with computational infrastructure.  ... 
arXiv:1711.08995v2 fatcat:zmnpnryzzbhyxfqbmojh6bf7ai
Multiple Versions
Citation

Pedro O. Pinheiro. "Unsupervised Domain Adaptation with Similarity Learning." arXiv (2018)

Unsupervised Domain Adaptation with Similarity Learning

Pedro O. Pinheiro
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (7.5 MB)
https://web.archive.org/web/20180920144523/http://openaccess.thecvf.com:80/content_cvpr_2018/papers/Pinheiro_Unsupervised_Domain_Adaptation_CVPR_2018_paper.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL. The file type is application/pdf.

In this paper, we propose a different way to do the classification, using similarity learning.  ...  The proposed method learns a pairwise similarity function in which classification can be performed by computing similarity between prototype representations of each category.  ...  In SimNet-152, we show the results using a ResNet-152 (pretrained on ImageNet) as base architecture, which pushes the performance even further.  ... 
doi:10.1109/cvpr.2018.00835 dblp:conf/cvpr/Pinheiro18 fatcat:dvax226dmfgoxfcicdxeyhrxcu
Citation

Pedro O. Pinheiro. "Unsupervised Domain Adaptation with Similarity Learning." 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (2018) 8004-8013

NPSNET:A Network Software Architecture for LargeScale Virtual Environments

Michael R. Macedonia, Michael J. Zyda, David R. Pratt, Paul T. Barham, Steven Zeswitz
1994 Presence - Teleoperators and Virtual Environments  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (104.1 kB)
https://web.archive.org/web/20110331202046/http://gamepipe.usc.edu/~zyda/pubs/Presence.3.4.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2011; you can also visit the original URL. The file type is application/pdf.

our software to exploit parallel computing architectures.  ...  In addition, our own experience and research with previous versions of NPSNET has also caused us to conclude that the development of a software architecture for a real-time distributed environment requires  ...  The good news for those interested in developing distributed virtual environment is that advances in computer architectures and graphics, as well as standards such as the DIS and SIMNET (Simulator Networking  ... 
doi:10.1162/pres.1994.3.4.265 fatcat:6hzvjnobtvdyrhmg45oxe6t2ke
Citation

Michael R. Macedonia, Michael J. Zyda, David R. Pratt, Paul T. Barham, Steven Zeswitz. "NPSNET:A Network Software Architecture for LargeScale Virtual Environments." Presence - Teleoperators and Virtual Environments 3.4 (1994) 265-287

All But War Is Simulation: The Military-Entertainment Complex

Timothy Lenoir
2000 Configurations  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (174.7 kB)
https://web.archive.org/web/20130309213806/http://jenkins.duke.edu/publications/Lenoir_AllButWarIsSimulation.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2013; you can also visit the original URL. The file type is application/pdf.

in which wearable computers, independent computational agent-artifacts, and material objects are all part of the landscape.  ...  The box office smash from spring 1999, The Matrix, projects a vision of a world in which "real" world objects are actually simulations emerging from streams of bits.  ...  Flight and tank simulators are excellent tools for learning and practicing the use of complex, expensive equipment.  ... 
doi:10.1353/con.2000.0022 fatcat:625xpmxyqfhsxhuvua5ctixl3i
Citation

Timothy Lenoir. "All But War Is Simulation: The Military-Entertainment Complex." Configurations 8.3 (2000) 289-335

Reinforcement Learning-based Resource Management Model for Fog Radio Access Network Architectures in 5G

Nosipho N. Khumalo, Olutayo O. Oyerinde, Luzango Mfupe
2021 IEEE Access  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.0 MB)
https://web.archive.org/web/20210429103718/https://ieeexplore.ieee.org/ielx7/6287639/9312710/09323035.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

However, despite the potential, the management of computational resources remains a challenge in F-RAN architectures.  ...  Reinforcement learning (RL) is presented as a method for dynamic and autonomous resource allocation, and an algorithm is proposed based on Q-learning.  ...  By using machine learning techniques to address the resource allocation problem in 5G F-RAN architectures, this paper has contributed to the area of machine learning applications in fog computing and 5G  ... 
doi:10.1109/access.2021.3051695 fatcat:ijiatyzhgnad3jhrmc4qzebrbi
DOAJ
Citation

Nosipho N. Khumalo, Olutayo O. Oyerinde, Luzango Mfupe. "Reinforcement Learning-based Resource Management Model for Fog Radio Access Network Architectures in 5G." IEEE Access (2021) 1-1

Neural networks learn to speed up simulations

Chris Edwards
2022 Communications of the ACM  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.1 MB)
https://web.archive.org/web/20220504121459/https://dl.acm.org/doi/pdf/10.1145/3524015

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

Physics-informed machine learning is gaining attention, but suffers from training issues.  ...  Nvidia has packaged the machine learning techniques that underpin the weather-forecasting project into the Simnet software package it provides to customers.  ...  At the company's technology conference in November, Animashree Anandkumar, Nvidia's director of machine learning research and Bren Professor of Computing at the California Institute of Technology, pointed  ... 
doi:10.1145/3524015 fatcat:jqmy65scnbgnhihuyusmxjq3am
Citation

Chris Edwards. "Neural networks learn to speed up simulations." Communications of the ACM 65.5 (2022) 27-29

Technology Disruption in the Simulation Industry

Roger Smith
2006 The Journal of Defence Modeling and Simulation: Applications, Methodology, Technology  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (259.9 kB)
https://web.archive.org/web/20170810153233/http://www.simulationfirst.com/papers/TechDisrupt_JDMS06.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL. The file type is application/pdf.

In this paper, we explore the impact that computer game technologies are having on the simulation industry.  ...  This wave will spread cheaper, more powerful and more accessible simulations and simulators across the modern military.  ...  The SIMNET project of the late 1980's was a major innovation that really launched the use of computer-driven, 3D immersive, networked combat simulators [4] .  ... 
doi:10.1177/875647930600300102 fatcat:nlur7eumfzgkfiu6heicxgeiti
Citation

Roger Smith. "Technology Disruption in the Simulation Industry." The Journal of Defence Modeling and Simulation: Applications, Methodology, Technology 3.1 (2006) 3-10

Learning A Physical Long-term Predictor [article]

Sebastien Ehrhardt, Aron Monszpart, Niloy J. Mitra, Andrea Vedaldi
2017 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (851.3 kB)
https://web.archive.org/web/20191012013912/https://arxiv.org/pdf/1703.00247v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL. The file type is application/pdf.

In the context of artificial intelligence, a recent line of work has focused on estimating physical parameters based on sensory data and use them in physical simulators to make long-term predictions.  ...  Based on extensive evaluation, we demonstrate that such networks can outperform alternate approaches having even access to ground-truth physical simulators, especially when some physical parameters are  ...  Our work is closely related to a range of recent works in the machine learning community. Learning intuitive physics.  ... 
arXiv:1703.00247v1 fatcat:xqwjwszjfvbmfopwt422jao4te
Citation

Sebastien Ehrhardt, Aron Monszpart, Niloy J. Mitra, Andrea Vedaldi. "Learning A Physical Long-term Predictor." arXiv (2017)

Solving Partial Differential Equations with Point Source Based on Physics-Informed Neural Networks [article]

Xiang Huang, Hongsheng Liu, Beiji Shi, Zidong Wang, Kang Yang, Yang Li, Bingya Weng, Min Wang, Haotian Chu, Jing Zhou, Fan Yu, Bei Hua (+2 others)
2021 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.0 MB)
https://web.archive.org/web/20211104220915/https://arxiv.org/pdf/2111.01394v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL. The file type is application/pdf.

In recent years, deep learning technology has been used to solve partial differential equations (PDEs), among which the physics-informed neural networks (PINNs) emerges to be a promising method for solving  ...  We evaluate the proposed method with three representative PDEs, and the experimental results show that our method outperforms existing deep learning-based methods with respect to the accuracy, the efficiency  ...  simulation and many other areas [1, 2] , and data-driven deep learning approaches are proposed to alleviate the computational burden.  ... 
arXiv:2111.01394v1 fatcat:ff43titt5fcf7hzojux4yq3gsa
Open Access
Citation

Xiang Huang, Hongsheng Liu, Beiji Shi, Zidong Wang, Kang Yang, Yang Li, Bingya Weng, Min Wang, Haotian Chu, Jing Zhou, Fan Yu, Bei Hua, Lei Chen, Bin Dong. "Solving Partial Differential Equations with Point Source Based on Physics-Informed Neural Networks." arXiv (2021)

« Previous Showing results 1 — 15 out of 127 results