MIPS64寄存器与指令集

 

MIPS64指令集

 

需要注意的与32位的区别(32为的w:word  ----- 64为的d: double)：

运算类：add变成dadd，同理sub/mul/div变成dsub/dmul/ddiv

访存: lw变成ld, sw变成sd

寄存器名： S0/S1…   全部变为r0/r1/… / r31

 

I/O映射表

 

 

在符号区域定义的符号的值是当前符号所对应的内存地址,使用的是字节地址

如:

.data

A :  .word 32

A的值并不是32，而是其所在的内存位置 0

 

在.text定义的变量记录的是当前的字地址

.text

Loop: dadd $s0,$s1,$s2

 

来源：网上资料

64位版本开头以“d”表示，无符号数以“u”结尾，立即数通常以“i”结尾，字节操作以“b”结尾，双字操作以“d”结尾，字操作以“w”结尾

序号

伪指令

功能

1

.data

start of data segment

2

.text

start of code segment

3

.code

start of code segment (same as .text)

4

.org    <n>

start address

5

.space  <n>

leave n empty bytes

6

.asciiz <s>

enters zero terminated ascii string

7

.ascii  <s>

enter ascii string

8

.align  <n>

align to n-byte boundary

9

.word   <n1>,<n2>..

enters word(s) of data (64-bits)

10

.byte   <n1>,<n2>..

enter bytes

11

.word16 <n1>,<n2>..

enters 16 bit number(s)

12

.word32 <n1>,<n2>..

enters 32 bit number(s)

13

.double <n1>,<n2>..

enters floating-point number(s)

 

序号

指令

功能

 

访存

 

 

lb reg,imm(reg)

load byte

 

lbu reg,imm(reg)

load byte unsigned

 

lh reg,imm(reg)

load 16-bit half-word

 

lhu reg,imm(reg)

load 16-bit half word unsigned

 

lw reg,imm(reg)

load 32-bit word

 

lwu reg,imm(reg)

load 32-bit word unsigned

 

ld reg,imm(reg)

load 64-bit double-word

 

l.s freg,imm(reg)

load 32-bit floating-point(single FP )

 

l.d freg,imm(reg)

load 64-bit floating-point(double FP )

 

sb reg,imm(reg)

store byte

 

sh reg,imm(reg)

store 16-bit half-word

 

sw reg,imm(reg)

store 32-bit word

 

sd reg,imm(reg)

store 64-bit double-word

 

s.s freg,imm(reg)

store 32-bit floating-point

 

s.d freg,imm(reg)

store 64-bit floating-point

 

 

 

 

传送

 

 

movz r1，r2,r3

If(r3==0) r1=r2

 

movn reg,reg,reg

move if register not equal to zero

 

 

 

 

mov.s freg,freg

move floating-point(single FP )

 

mov.d freg,freg

move floating-point(double FP )

 

 

 

 

mtc1 reg,freg

move data from integer register to FP register

 

mfc1 reg,freg

move data from FP register to integer register

 

 

 

 

lui  reg,imm

load upper half of register immediate

 

 

 

 

算术

 

 

dadd reg,reg,reg

add integers

 

daddu reg,reg,reg

add integers unsigned

 

daddi reg,reg,imm

add immediate

 

daddui reg,reg,imm

add immediate unsigned( WinMIPS64格式 )

 

daddiu reg,reg,imm

add immediate unsigned( MIPSsim格式 )

 

add.s freg,freg,freg

add floating-point(single FP )

 

add.d freg,freg,freg

add floating-point(double FP )

 

dsub reg,reg,reg

subtract integers

 

dsubu reg,reg,reg

subtract integers unsigned

 

sub.s freg,freg,freg

subtract floating-point(single FP )

 

sub.d freg,freg,freg

subtract floating-point(double FP )

 

dmul reg,reg,reg

signed integer multiplication

 

dmulu reg,reg,reg

unsigned integer multiplication

 

mul.d freg,freg,freg

multiply floating-point

 

ddiv reg,reg,reg

signed integer division

 

ddivu reg,reg,reg

unsigned integer division

 

div.d freg,freg,freg

divide floating-point

 

 

 

 

逻辑

 

 

and reg,reg,reg

logical and

 

andi reg,reg,imm

logical and immediate

 

or reg,reg,reg

logical or

 

ori reg,reg,imm

logical or immediate

 

xor reg,reg,reg

logical xor

 

xori reg,reg,imm

exclusive or immediate

 

 

 

 

dsll reg,reg,imm

shift left logical

 

dsllv reg,reg,reg

shift left logical by variable amount

 

dsrl reg,reg,imm

shift right logical

 

dsra reg,reg,imm

shift right arithmetic

 

dsrlv reg,reg,reg

shift right logical by variable amount

 

dsrav reg,reg,reg

shift right arithmetic by variable amount

 

 

 

 

转换

 

 

cvt.d.l freg,freg

convert 64-bit integer to a double FP format

 

cvt.l.d freg,freg

convert double FP to a 64-bit integer format

 

 

 

 

标志

 

 

slt reg,reg,reg

set if less than

 

dslt reg,reg,reg

set if less than( 教材写错，上条为正确格式 )

 

sltu reg,reg,reg

set if less than unsigned

 

slti reg,reg,imm

set if less than immediate

 

sltiu reg,reg,imm

set if less than immediate unsigned

 

 

 

 

c.lt.d freg,freg

set FP flag if less than

 

c.eq.d freg,freg

set FP flag if equal to

 

c.le.d freg,freg

set FP flag if less than or equal to

 

 

 

 

跳转

 

 

j imm

jump to address                            (不会保存返回地址)

 

jr reg

jump to address in register             （不会保存返回地址）

 

jal imm

跳转到imm地址并且将返回地址记录在寄存器ra中（会保存）

 

jalr reg

jump and link to address in register  （会保存）

 

 

 

 

beqz reg,imm

branch if register is equal to zero

 

bnez reg,imm

branch if register is not equal to zero

 

beq reg,reg,imm

branch if pair of registers are equal

 

bne reg,reg,imm

branch if pair of registers are not equal

 

bc1t imm

branch to address if FP flag is TRUE

 

bc1f imm

branch to address if FP flag is FALSE

 

 

 

 

控制

 

 

nop

no operation

 

halt

stops the program