一种可重构的单精度近似浮点乘法器设计.pdfVIP

计算机研究与发展

Journal

of

Computer

Research

and

Development62（6）：1581−1593，2025

一种可重构的单精度近似浮点乘法器设计

1,21,231,21,21,21,21,2

李鹏程黄立波陈刚赖明澈邓林刘威杨乾明王永文

1

（国防科技大学计算机学院长沙410073）

2

（先进微处理器芯片与系统重点实验室（国防科技大学）长沙410073）

3

（中山大学计算机学院广州510275）

（lipengcheng@）

AReconfigurableSingle-PrecisionApproximateFloating-PointMultiplierDesign

1,2

1,2

3

1,2

1,2

1,2

1,2

Li

Pengcheng,

Huang

Libo,

Chen

Gang,

Lai

Mingche,

Deng

Lin,

Liu

Wei,

Yang

Qianming,

and

Wang

Yongwen1,2

1

（CollegeofComputerScienceandTechnology,NationalUniversityofDefenseTechnology,Changsha410073）

2

（KeyLaboratoryofAdvancedMicroprocessorChipsandSystems(NationalUniversityofDefenseTechnology),Changsha410073）

3

（SchoolofComputerScienceandEngineering,SunYat-senUniversity,Guangzhou510275）

AbstractThe

rapid

development

of

artificial

intelligence

(AI)

and

Internet

of

things

(IoT)

technologies

has

increased

demands

for

the

computing

energy

efficiency,

and

terminal

devices

are

also

facing

great

challenges

in

terms

of

hardware

resource

overhead.

In

order

to

solve

the

problem

of

energy

efficiency,

new

designs

of

approximate

computing

units

with

low

power

have

been

widely

studied.

In

application

scenarios

such

as

digital

signal

processing

and

image

processing,

there

are

a

large

number

of

floating-point

operations.

These

applications

consume

a

lot

of

hardware

resources.

However,

they

have

certain

fault

tolerance

characteristics

and

do