LAUSR

A note on Dekker’s FastTwoSum algorithm

Sign Up to like & get
recommendations!
1 Published in 2020 at "Numerische Mathematik"

DOI: 10.1007/s00211-020-01114-2

Abstract: More than 45 years ago, Dekker proved that it is possible to evaluate the exact error of a floating-point sum with only two additional floating-point operations, provided certain conditions are met. Today the respective algorithm… read more here.

Keywords: fasttwosum algorithm; fasttwosum fasttwosum; mathrm fasttwosum; floating point ... See more keywords

Scaling up and down of 3-D floating-point data in quantum computation

Sign Up to like & get
recommendations!
3 Published in 2022 at "Scientific Reports"

DOI: 10.1038/s41598-022-06756-w

Abstract: In the past few decades, quantum computation has become increasingly attractive due to its remarkable performance. Quantum image scaling is considered a common geometric transformation in quantum image processing, however, the quantum floating-point data version… read more here.

Keywords: point; quantum computation; floating point; scaling floating ... See more keywords

An Architecture of Area-Effective High Radix Floating-Point Divider With Low-Power Consumption

Sign Up to like & get
recommendations!
0 Published in 2021 at "IEEE Access"

DOI: 10.1109/access.2021.3065063

Abstract: In this paper, a novel architecture of area-effective high-radix floating-point divider with low power consumption is proposed. By extending the principle of the standard SRT algorithm, the divider can estimate the partial quotient digits by… read more here.

Keywords: area; point divider; floating point; divider ... See more keywords

Development of Floating-Point MAC Engine for 2-D Convolution of Image

Sign Up to like & get
recommendations!
1 Published in 2021 at "IEEE Access"

DOI: 10.1109/access.2021.3117335

Abstract: In the emerging trend of Graphics Processing Architecture, IEEE 754-2008 Floating point numbers are being widely used. Convolution is one of the standard operations in image processing applications, and because of its computationally intensive nature,… read more here.

Keywords: point mac; floating point; convolution; image ... See more keywords

Exact Versus Inexact Decimal Floating-Point Numbers and Arithmetic

Sign Up to like & get
recommendations!
2 Published in 2023 at "IEEE Access"

DOI: 10.1109/access.2023.3244891

Abstract: The IEEE 754 standard does not distinguish between exact and inexact floating-point numbers. There is no bit or field in the binary encoding that indicates whether a floating-point number is exact or not. This is… read more here.

Keywords: inexact decimal; inexact; point numbers; floating point ... See more keywords

FloatSD: A New Weight Representation and Associated Update Method for Efficient Convolutional Neural Network Training

Sign Up to like & get
recommendations!
1 Published in 2019 at "IEEE Journal on Emerging and Selected Topics in Circuits and Systems"

DOI: 10.1109/jetcas.2019.2911999

Abstract: In this paper, we propose a floating-point signed digit (FloatSD) format for convolutional neural network (CNN) weight representation and its update method during CNN training. The number of non-zero digits in a weight can be… read more here.

Keywords: floating point; method; weight representation; point ... See more keywords

A Neural Network Training Processor With 8-Bit Shared Exponent Bias Floating Point and Multiple-Way Fused Multiply-Add Trees

Sign Up to like & get
recommendations!
2 Published in 2022 at "IEEE Journal of Solid-State Circuits"

DOI: 10.1109/jssc.2021.3103603

Abstract: Recent advances in deep neural networks (DNNs) and machine learning algorithms have induced the demand for services based on machine learning algorithms that require a large number of computations, and specialized hardware ranging from accelerators… read more here.

Keywords: training; neural network; floating point; way ... See more keywords

Clock Skew Compensation Algorithm Immune to Floating-Point Precision Loss

Sign Up to like & get
recommendations!
3 Published in 2022 at "IEEE Communications Letters"

DOI: 10.1109/lcomm.2022.3142904

Abstract: We propose a novel clock skew compensation algorithm based on Bresenham’s line drawing algorithm. The proposed algorithm can avoid the effect of limited floating-point precision (e.g., 32-bit single precision) on clock skew compensation and thereby… read more here.

Keywords: skew compensation; floating point; compensation algorithm; clock skew ... See more keywords

Pod-racing: bulk-bitwise to floating-point compute in racetrack memory for machine learning at the edge

Sign Up to like & get
recommendations!
2 Published in 2022 at "IEEE Micro"

DOI: 10.1109/mm.2022.3195761

Abstract: Convolutional neural networks (CNNs) have become a ubiquitous algorithm with growing applications in mobile and edge settings. We describe a compute-in-memory (CIM) technique called POD-RACING using Racetrack memory (RM) to accelerate CNNs for edge systems.… read more here.

Keywords: bulk bitwise; racetrack memory; pod; pod racing ... See more keywords

Real-Time LiDAR Point Cloud Compression Using Bi-Directional Prediction and Range-Adaptive Floating-Point Coding

Sign Up to like & get
recommendations!
1 Published in 2022 at "IEEE Transactions on Broadcasting"

DOI: 10.1109/tbc.2022.3162406

Abstract: Due to the large amount of data involved in the three-dimensional (3D) LiDAR point clouds, point cloud compression (PCC) becomes indispensable to many real-time applications. In autonomous driving of connected vehicles for example, point clouds… read more here.

Keywords: time; point cloud; floating point; prediction ... See more keywords

High-Precision Anchored Accumulators for Reproducible Floating-Point Summation

Sign Up to like & get
recommendations!
0 Published in 2019 at "IEEE Transactions on Computers"

DOI: 10.1109/tc.2018.2855729

Abstract: This paper introduces a new datatype, the High-Precision Anchored (HPA) number, that allows reproducible accumulation of floating-point (FP) numbers in a programmer-selectable range. The new datatype has a larger significand and a smaller range than… read more here.

Keywords: precision anchored; high precision; summation; floating point ... See more keywords