Results 21 to 30 of about 260,838 (285)

Fuzzy memoization for floating-point multimedia applications [PDF]

, 2005
Instruction memoization is a promising technique to reduce the power consumption and increase the performance of future low-end/mobile multimedia systems.
Corbal San Adrián, Jesús, Valero Cortés, Mateo, Álvarez Martínez, Carlos   +2 more
core   +2 more sources

BitFlow-Net: Toward Fully Binarized Convolutional Neural Networks

IEEE Access, 2019
Binarization can greatly compress and accelerate deep convolutional neural networks (CNNs) for real-time industrial applications. However, existing binarized CNNs (BCNNs) rely on scaling factor (SF) and batch normalization (BatchNorm) that still involve ...
Lijun Wu, Peiqing Jiang, Zhicong Chen, Xu Lin, Yunfeng Lai, Peijie Lin, Shuying Cheng   +6 more
doaj   +1 more source

Numerical behavior of NVIDIA tensor cores [PDF]

PeerJ Computer Science, 2021
We explore the floating-point arithmetic implemented in the NVIDIA tensor cores, which are hardware accelerators for mixed-precision matrix multiplication available on the Volta, Turing, and Ampere microarchitectures.
Massimiliano Fasi, Nicholas J. Higham, Mantas Mikaitis, Srikara Pranesh   +3 more
doaj   +2 more sources

Unbiased Rounding for HUB Floating-point Addition [PDF]

, 2018
Copyright (c) 2018 IEEE doi:10.1109/TC.2018.2807429Half-Unit-Biased (HUB) is an emerging format based on shifting the represented numbers by half Unit in the Last Place.
Gonzalez-Navarro, Sonia, Hormigo-Aguilar, Javier, Villalba-Moreno, Julio   +2 more
core   +1 more source

Arithmetic operations beyond floating point number precision [PDF]

International Journal of Computational Science and Engineering, 2011
5 figures, accepted for publication in International Journal of Computational Science and ...
Chih-Yueh Wang, Chen-Yang Yin, Hong-Yu Chen, Yung-Ko Chen   +3 more
openaire   +2 more sources

Parallel Algorithms for Summing Floating-Point Numbers

, 2016
The problem of exactly summing n floating-point numbers is a fundamental problem that has many applications in large-scale simulations and computational geometry.
Eldawy, Ahmed, Goodrich, Michael T.
core   +1 more source

FPGA-based floating-point datapath design for geometry processing [PDF]

, 1998
Geometry processing comprises of a great many computationally intensive floating-point operations. Real- time graphics systems generally use application-specific custom designed parallel hardware to provide the high performance computation power.
Xing, S, Yu, WWH
core   +1 more source

Hybrid Precision Floating-Point (HPFP) Selection to Optimize Hardware-Constrained Accelerator for CNN Training

Sensors
The rapid advancement in AI requires efficient accelerators for training on edge devices, which often face challenges related to the high hardware costs of floating-point arithmetic operations.
Muhammad Junaid, Hayotjon Aliev, SangBo Park, HyungWon Kim, Hoyoung Yoo, Sanghoon Sim   +5 more
doaj   +1 more source

DESIGN AND PERFORMANCE ANALYSIS OF TERNARY LOGIC BASED ALU USING DOUBLE PRECISION FLOATING POINT [PDF]

Proceedings on Engineering Sciences
In digital circuits, particularly space signal applications, the detection/estimation of phase (angle) like milli degree is challenging and involves many complex operations.
Nagarathna R , A R Aswatha
doaj   +1 more source

An Efficient Implementation of the Sign LMS Algorithm Using Block Floating Point Format

EURASIP Journal on Advances in Signal Processing, 2007
An efficient scheme is presented for implementing the sign LMS algorithm in block floating point format, which permits processing of data over a wide dynamic range at a processor complexity and cost as low as that of a fixed point processor.
Lee Moon Ho, Chakraborty Mrityunjoy, Shaik Rafiahamed   +2 more
doaj   +2 more sources