WO2023227064A9 - 一种浮点数压缩方法、运算装置及计算器可读取存储媒介 - Google Patents

一种浮点数压缩方法、运算装置及计算器可读取存储媒介 Download PDF

Info

Publication number
WO2023227064A9
WO2023227064A9 PCT/CN2023/096302 CN2023096302W WO2023227064A9 WO 2023227064 A9 WO2023227064 A9 WO 2023227064A9 CN 2023096302 W CN2023096302 W CN 2023096302W WO 2023227064 A9 WO2023227064 A9 WO 2023227064A9
Authority
WO
WIPO (PCT)
Prior art keywords
floating
point number
compression method
storage medium
readable storage
Prior art date
Application number
PCT/CN2023/096302
Other languages
English (en)
French (fr)
Other versions
WO2023227064A1 (zh
Inventor
罗允辰
吕仁硕
Original Assignee
吕仁硕
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 吕仁硕 filed Critical 吕仁硕
Publication of WO2023227064A1 publication Critical patent/WO2023227064A1/zh
Publication of WO2023227064A9 publication Critical patent/WO2023227064A9/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F7/00Methods or arrangements for processing data by operating upon the order or content of the data handled
    • G06F7/38Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation
    • G06F7/48Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation using non-contact-making devices, e.g. tube, solid state device; using unspecified devices
    • G06F7/483Computations with numbers represented by a non-linear combination of denominational numbers, e.g. rational numbers, logarithmic number system or floating-point numbers

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Computing Systems (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Nonlinear Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Complex Calculations (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)

Abstract

一种浮点数压缩方法,包含使用一算术单元进行以下步骤:取得多个浮点数;对该等浮点数产生共同倍率因子;对于该等浮点数中每一者,压缩为多个定点数尾数;输出一压缩结果,该压缩结果包含该等共同倍率因子及该等个定点数尾数。
PCT/CN2023/096302 2022-05-26 2023-05-25 一种浮点数压缩方法、运算装置及计算器可读取存储媒介 WO2023227064A1 (zh)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US202263345918P 2022-05-26 2022-05-26
US63/345,918 2022-05-26
US202263426727P 2022-11-19 2022-11-19
US63/426,727 2022-11-19

Publications (2)

Publication Number Publication Date
WO2023227064A1 WO2023227064A1 (zh) 2023-11-30
WO2023227064A9 true WO2023227064A9 (zh) 2024-01-04

Family

ID=88918577

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/096302 WO2023227064A1 (zh) 2022-05-26 2023-05-25 一种浮点数压缩方法、运算装置及计算器可读取存储媒介

Country Status (1)

Country Link
WO (1) WO2023227064A1 (zh)

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7355603B2 (en) * 2004-08-04 2008-04-08 Nvidia Corporation Filtering unit for floating-point texture data
US9047118B2 (en) * 2011-06-30 2015-06-02 Altera Corporation Computationally efficient compression of floating-point data
US11615301B2 (en) * 2019-09-03 2023-03-28 Microsoft Technology Licensing, Llc Lossless exponent and lossy mantissa weight compression for training deep neural networks

Also Published As

Publication number Publication date
WO2023227064A1 (zh) 2023-11-30
TW202403539A (zh) 2024-01-16

Similar Documents

Publication Publication Date Title
GB2590888A (en) Data representation for dynamic precision in neural network cores
US11797269B2 (en) Apparatus and methods for neural network operations supporting floating point numbers of short bit length
TW200604942A (en) Method and apparatus for compressing and decompressing instructions in a computer system
BR112021016138A2 (pt) Aparelho, método, processador gráfico de propósito geral e sistema de processamento de dados
WO2018224055A3 (zh) 多维数据异常检测方法及装置
EP4224253A3 (en) Process, apparatus and photoswitchable photoinitiators for locally polymerizing a starting material by dual color photopolymerization and method for volumetric printing of a shaped body
WO2007101216A3 (en) Floating-point processor with reduced power requirements for selectable subprecision
MX343564B (es) Aparato y metodo para proveer funciones mejoradas de mezcla guiada para audio 3d.
WO2011050293A3 (en) Block floating point compression of signal data
KR20070065370A (ko) 음향 신호 부호화 장치 및 음향 신호 복호 장치
MX2014001870A (es) Dispositivo y metodo de codificacion, dispositivo y metodo de decodificacion, y programa.
TW200519633A (en) Method and apparatus for multiplying based on booth's algorithm
CN110265002B (zh) 语音识别方法、装置、计算机设备及计算机可读存储介质
WO2008154653A3 (en) Efficient method for forming and sharing impairment covariance matrix
WO2023227064A9 (zh) 一种浮点数压缩方法、运算装置及计算器可读取存储媒介
EP4343670A3 (en) Power trading system and management apparatus
US8498874B2 (en) Audio signal encoding employing interchannel and temporal redundancy reduction
TW200634616A (en) Arithmetic unit of arbitrary precision, operation method for processing data of arbitrary precision and electronic equipment
EP2209251A3 (en) Cryptographic processing apparatus and cryptographic processing method
CN116205244B (zh) 一种数字信号处理结构
EP4064036A4 (en) METHOD AND DEVICE FOR THE MULTIPLICATION CALCULATION OF FLOATING-POINT NUMBERS AND ARITHMETIC LOGIC UNIT
CN113283591B (zh) 基于Winograd算法和近似乘法器的高效卷积实现方法及装置
US9478223B2 (en) Method and apparatus for down-mixing multi-channel audio
MX2022003055A (es) Metodos y aparatos para determinar la entrada de energia a los procesos de soldadura que involucran varias fuentes de energia.
Pereira et al. Evaluating Robustness to Noise and Compression of Deep Neural Networks for Keyword Spotting

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23811134

Country of ref document: EP

Kind code of ref document: A1