Results 41 to 50 of about 31,720 (268)
Hardware acceleration of number theoretic transform for zk‐SNARK
Engineering Reports, EarlyView., 2023 An FPGA‐based hardware accelerator with a multi‐level pipeline is designed to support the large‐bitwidth and large‐scale NTT tasks in zk‐SNARK. It can be flexibly scaled to different scales of FPGAs and has been equipped in the heterogeneous acceleration system with the help of HLS and OpenCL.
Haixu Zhao +6 more
wiley +1 more source
Quality of mechanical peanut sowing and digging using autopilot
Revista Brasileira de Engenharia Agrícola e AmbientalOver the past decade, automatic guidance of agricultural machinery via Global Navigation Satellite System (GNSS) signals has been increasingly adopted by the farming community.
Cristiano Zerbato +5 more
doaj +1 more source
Heterogeneous Implementation of a Voronoi Cell-Based SVP Solver
IEEE Access, 2019 This paper presents a new, heterogeneous CPU+GPU attacks against lattice-based (postquantum) cryptosystems based on the Shortest Vector Problem (SVP), a central problem in lattice-based cryptanalysis.
Gabriel Falcao +3 more
doaj +1 more source
A Parallel Meta-Heuristic Approach to Reduce Vehicle Travel Time in Smart Cities
Applied Sciences, 2021 The development of the smart city concept and inhabitants’ need to reduce travel time, in addition to society’s awareness of the importance of reducing fuel consumption and respecting the environment, have led to a new approach to the classic travelling ...
Hector Rico-Garcia +3 more
doaj +1 more source
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 +7 more
wiley +1 more source
Memory-Efficient Deep Learning on a SpiNNaker 2 Prototype
Frontiers in Neuroscience, 2018 The memory requirement of deep learning algorithms is considered incompatible with the memory restriction of energy-efficient hardware. A low memory footprint can be achieved by pruning obsolete connections or reducing the precision of connection ...
Chen Liu +12 more
doaj +1 more source
Tesseract: Parallelize the Tensor Parallelism Efficiently
Proceedings of the 51st International Conference on Parallel Processing, 2022 Together with the improvements in state-of-the-art accuracies of various tasks, deep learning models are getting significantly larger. However, it is extremely difficult to implement these large models because limited GPU memory makes it impossible to fit large models into a single GPU or even a GPU server. Besides, it is highly necessary to reduce the
Boxiang Wang +3 more
openaire +2 more sources
Advanced Science, EarlyView.Comparative genomics of Gondwana‐diverged Pila and Pomacea reveals parallel evolution of aerial oviposition. Convergent chromosomal rearrangements reshape regulatory landscapes within topologically associating domains. Lineage‐specific gene family expansions and viral‐derived perivitelline proteins (PV1) underpin desiccation resistance.
Yufei Zhou +10 more
wiley +1 more source
Parallelism Efficiency in Convolutional Turbo Decoding
EURASIP Journal on Advances in Signal Processing, 2010 Parallel turbo decoding is becoming mandatory in order to achieve high throughput and to reduce latency, both crucial in emerging digital communication applications. This paper explores and analyzes parallelism techniques in convolutional turbo decoding
Baghdadi Amer +2 more
doaj
Energies, 2018 The electromagnetic transient simulation of a power system with nonlinear characteristics is very time-consuming due to numerous inversion calculations of the admittance matrix.
Ji Han +6 more
doaj +1 more source