Results 71 to 80 of about 186,522 (338)

Massively-Parallel Lossless Data Decompression

, 2016
Today's exponentially increasing data volumes and the high cost of storage make compression essential for the Big Data industry. Although research has concentrated on efficient compression, fast decompression is critical for analytics queries that ...
Kaldewey, Tim, Lohman, Guy, Mueller, Rene, Ross, Kenneth, Sitaridi, Evangelia   +4 more
core   +1 more source

Harnessing Time‐Dependent Magnetic Texture Dynamics via Spin‐Orbit Torque for Physics‐Enhanced Neuromorphic Computing

Advanced Science, EarlyView.
A neuromorphic computing platform using spin‐orbit torque‐controlled magnetic textures is reported. The device implements bio‐inspired synaptic functions and achieves high performance in both pattern recognition (>93%) and combinatorial optimization (>95%), enabling unified processing of cognitive and optimization tasks.
Yifan Zhang, Yu Li, Huai Lin, Xinying Wang, Long Liu, Guoliang Xing, Di Wang, Zhihao Zhao, Zhipeng Guo, Junbo Yang, Jiebin Niu, Yan Sun, Tom Wu, Guozhong Xing   +13 more
wiley   +1 more source

Distributed training of large language models: A survey

Natural Language Processing Journal
The emergence of large language models (LLMs) such as ChatGPT has opened up groundbreaking possibilities, enabling a wide range of applications in diverse fields, including healthcare, law, and education.
Fanlong Zeng, Wensheng Gan, Yongheng Wang, Philip S. Yu   +3 more
doaj   +1 more source

Exploring Various Levels of Parallelism in High-Performance CRC Algorithms

IEEE Access, 2019
Modern processors have increased the capabilities of instruction-level parallelism (ILP) and thread-level parallelism (TLP). These resources, however, typically exhibit poor utilization on conventional cyclic redundancy check (CRC) algorithms.
Mucong Chi, Dazhong He, Jun Liu
doaj   +1 more source

Efficient electro-magnetic analysis of a GPU bitsliced AES implementation

Cybersecurity, 2020
The advent of CUDA-enabled GPU makes it possible to provide cloud applications with high-performance data security services. Unfortunately, recent studies have shown that GPU-based applications are also susceptible to side-channel attacks.
Yiwen Gao, Yongbin Zhou, Wei Cheng
doaj   +1 more source

Microscale Mapping of Fiber Strain and Damage in Composite Wrinkled Laminates Using Computed Tomography Assisted Wide‐Angle X‐Ray Scattering

Advanced Science, EarlyView.
This study combines full‐field tomography with diffraction mapping to quantify radial (ε002$\varepsilon _{002}$) and axial (ε100$\varepsilon _{100}$) lattice strain in wrinkled carbon‐fiber specimens for the first time. Radial microstrain gradients (−14.5 µεMPa$\varepsilon \mathrm{MPa}$−1) are found to signal damage‐prone zones ahead of failure, which ...
Hoang Minh Luong, James Trevarthen, Igor Dolbnya, Wadwan Singhapong, Nicholas Pilato, Richard Butler, Jiraphant Srisuriyachot, Alexander J. G. Lunt   +7 more
wiley   +1 more source

Partial Parallelism Plots

Applied Sciences
Demonstrating parallelism in quantitative laboratory tests is crucial to ensure accurate reporting of data and minimise risks to patients. Regulatory authorities make the demonstration of parallelism before clinical use approval mandate.
Axel Petzold
doaj   +1 more source

BISMO: A Scalable Bit-Serial Matrix Multiplication Overlay for Reconfigurable Computing

, 2018
Matrix-matrix multiplication is a key computational kernel for numerous applications in science and engineering, with ample parallelism and data locality that lends itself well to high-performance implementations.
Rasnayake, Lahiru, Sjalander, Magnus, Umuroglu, Yaman   +2 more
core   +1 more source

Ultrafast Multilevel Switching and Synaptic Behavior in a Planar Quantum Topological Memristor

Advanced Science, EarlyView.
Dry‐transferred Bi2Te3 layers enable a planar quantum topological memristor framework. In‐plane topological surface states facilitate ultrafast & low‐power operations. Coexisting analog and digital modes support current‐controlled multilevel states. PQTM exhibits 105 s retention, 103 cycles endurance, and reproducibility across 24 devices.
Mamoon Ur Rashid, Usman Safder, Sobia Ali Khan, Anh‐Tuan Pham, Muhammad Sheeraz, Nguyen‐Hoang Dang, Duy Le Thanh, Zeeshan Tahir, Faisal Maqbool, Koo‐Hyun Chung, Sunglae Cho, Jungdae Kim, Yong Soo Kim   +12 more
wiley   +1 more source

Strategies and Principles of Distributed Machine Learning on Big Data

Engineering, 2016
The rise of big data has led to new demands for machine learning (ML) systems to learn complex models, with millions to billions of parameters, that promise adequate capacity to digest massive datasets and offer powerful predictive analytics (such as ...
Eric P. Xing, Qirong Ho, Pengtao Xie, Dai Wei   +3 more
doaj   +1 more source