Use backtick code blocks for syntax highlighting
This commit is contained in:
James Gregory
parent
8ed9dea394
commit
f658bfbb40
203 changed files with 26546 additions and 25801 deletions
134
21-04.md
134
21-04.md
|
|
@ -27,32 +27,34 @@ same cache data bank, as discussed in the last chapter).
|
|||
|
||||
**LISTING 21.2 L21-2.ASM**
|
||||
|
||||
; Calculates TCP/IP (16-bit carry-wrapping) checksum for buffer
|
||||
; starting at ESI, of length ECX words.
|
||||
; Returns checksum in AX.
|
||||
; High word of EAX, DX, ECX and ESI destroyed.
|
||||
; All cycle counts assume 32-bit protected mode.
|
||||
; Assumes buffer length > 0.
|
||||
```nasm
|
||||
; Calculates TCP/IP (16-bit carry-wrapping) checksum for buffer
|
||||
; starting at ESI, of length ECX words.
|
||||
; Returns checksum in AX.
|
||||
; High word of EAX, DX, ECX and ESI destroyed.
|
||||
; All cycle counts assume 32-bit protected mode.
|
||||
; Assumes buffer length > 0.
|
||||
|
||||
sub eax,eax ;initialize the checksum
|
||||
mov dx,[esi] ;first word to checksum
|
||||
dec ecx ;we'll do 1 checksum outside the loop
|
||||
jz short ckloopend ;only 1 checksum to do
|
||||
add esi,2 ;point to the next word to checksum
|
||||
sub eax,eax ;initialize the checksum
|
||||
mov dx,[esi] ;first word to checksum
|
||||
dec ecx ;we'll do 1 checksum outside the loop
|
||||
jz short ckloopend ;only 1 checksum to do
|
||||
add esi,2 ;point to the next word to checksum
|
||||
|
||||
ckloop:
|
||||
add al,dl ;cycle 1 U-pipe
|
||||
mov dl,[esi] ;cycle 1 V-pipe
|
||||
adc ah,dh ;cycle 2 U-pipe
|
||||
mov dh,[esi+1] ;cycle 2 V-pipe
|
||||
adc eax,0 ;cycle 3 U-pipe
|
||||
add esi,2 ;cycle 3 V-pipe
|
||||
dec ecx ;cycle 4 U-pipe
|
||||
jnz ckloop ;cycle 4 V-pipe
|
||||
ckloop:
|
||||
add al,dl ;cycle 1 U-pipe
|
||||
mov dl,[esi] ;cycle 1 V-pipe
|
||||
adc ah,dh ;cycle 2 U-pipe
|
||||
mov dh,[esi+1] ;cycle 2 V-pipe
|
||||
adc eax,0 ;cycle 3 U-pipe
|
||||
add esi,2 ;cycle 3 V-pipe
|
||||
dec ecx ;cycle 4 U-pipe
|
||||
jnz ckloop ;cycle 4 V-pipe
|
||||
|
||||
ckloopend:
|
||||
add ax,dx ;checksum the last word
|
||||
adc eax,0
|
||||
ckloopend:
|
||||
add ax,dx ;checksum the last word
|
||||
adc eax,0
|
||||
```
|
||||
|
||||
Listing 21.3 is a more sophisticated attempt to speed up the checksum
|
||||
calculation. Here we see a hallmark of Pentium optimization: two
|
||||
|
|
@ -68,52 +70,54 @@ placement of **ADD ESI,4** to avoid an AGI.
|
|||
|
||||
**LISTING 21.3 L21-3.ASM**
|
||||
|
||||
; Calculates TCP/IP (16-bit carry-wrapping) checksum for buffer
|
||||
; starting at ESI, of length ECX words.
|
||||
; Returns checksum in AX.
|
||||
; High word of EAX, BX, EDX, ECX and ESI destroyed.
|
||||
; All cycle counts assume 32-bit protected mode.
|
||||
; Assumes buffer length > 0.
|
||||
```nasm
|
||||
; Calculates TCP/IP (16-bit carry-wrapping) checksum for buffer
|
||||
; starting at ESI, of length ECX words.
|
||||
; Returns checksum in AX.
|
||||
; High word of EAX, BX, EDX, ECX and ESI destroyed.
|
||||
; All cycle counts assume 32-bit protected mode.
|
||||
; Assumes buffer length > 0.
|
||||
|
||||
sub eax,eax ;initialize the checksum
|
||||
sub edx,edx ;prepare for later ORing
|
||||
shr ecx,1 ;we'll do two words per loop
|
||||
jnc short ckloopsetup ;even number of words
|
||||
mov ax,[esi] ;do the odd word
|
||||
jz short ckloopdone ;no more words to checksum
|
||||
add esi,2 ;point to the next word
|
||||
ckloopsetup:
|
||||
mov dx,[esi] ;load most of 1st word to
|
||||
mov bl,[esi+2] ; checksum (last byte loaded in loop)
|
||||
dec ecx ;any more dwords to checksum?
|
||||
jz short ckloopend ;no
|
||||
sub eax,eax ;initialize the checksum
|
||||
sub edx,edx ;prepare for later ORing
|
||||
shr ecx,1 ;we'll do two words per loop
|
||||
jnc short ckloopsetup ;even number of words
|
||||
mov ax,[esi] ;do the odd word
|
||||
jz short ckloopdone ;no more words to checksum
|
||||
add esi,2 ;point to the next word
|
||||
ckloopsetup:
|
||||
mov dx,[esi] ;load most of 1st word to
|
||||
mov bl,[esi+2] ; checksum (last byte loaded in loop)
|
||||
dec ecx ;any more dwords to checksum?
|
||||
jz short ckloopend ;no
|
||||
|
||||
ckloop:
|
||||
mov bh,[esi+3] ;cycle 1 U-pipe
|
||||
add esi,4 ;cycle 1 V-pipe
|
||||
shl ebx,16 ;cycle 2 U-pipe
|
||||
;cycle 2 V-pipe idle
|
||||
; (register contention)
|
||||
or ebx,edx ;cycle 3 U-pipe
|
||||
mov dl,[esi] ;cycle 3 V-pipe
|
||||
add eax,ebx ;cycle 4 U-pipe
|
||||
mov bl,[esi+2] ;cycle 4 V-pipe
|
||||
adc eax,0 ;cycle 5 U-pipe
|
||||
mov dh,[esi+1] ;cycle 5 V-pipe
|
||||
dec ecx ;cycle 6 U-pipe
|
||||
jnz ckloop ;cycle 6 V-pipe
|
||||
ckloop:
|
||||
mov bh,[esi+3] ;cycle 1 U-pipe
|
||||
add esi,4 ;cycle 1 V-pipe
|
||||
shl ebx,16 ;cycle 2 U-pipe
|
||||
;cycle 2 V-pipe idle
|
||||
; (register contention)
|
||||
or ebx,edx ;cycle 3 U-pipe
|
||||
mov dl,[esi] ;cycle 3 V-pipe
|
||||
add eax,ebx ;cycle 4 U-pipe
|
||||
mov bl,[esi+2] ;cycle 4 V-pipe
|
||||
adc eax,0 ;cycle 5 U-pipe
|
||||
mov dh,[esi+1] ;cycle 5 V-pipe
|
||||
dec ecx ;cycle 6 U-pipe
|
||||
jnz ckloop ;cycle 6 V-pipe
|
||||
|
||||
ckloopend:
|
||||
mov bh,[esi+3] ;checksum the last dword
|
||||
add ax,dx
|
||||
adc ax,bx
|
||||
adc ax,0
|
||||
ckloopend:
|
||||
mov bh,[esi+3] ;checksum the last dword
|
||||
add ax,dx
|
||||
adc ax,bx
|
||||
adc ax,0
|
||||
|
||||
mov edx,eax ;compress the 32-bit checksum
|
||||
shr edx,16 ; into a 16-bit checksum
|
||||
add ax,dx
|
||||
adc eax,0
|
||||
ckloopdone:
|
||||
mov edx,eax ;compress the 32-bit checksum
|
||||
shr edx,16 ; into a 16-bit checksum
|
||||
add ax,dx
|
||||
adc eax,0
|
||||
ckloopdone:
|
||||
```
|
||||
|
||||
The checksum loop in Listing 21.3 takes longer than the loop in Listing
|
||||
21.2, at 6 cycles versus 4 cycles for Listing 21.2—but Listing 21.3 does
|
||||
|
|
|
|||
Loading…
Reference in a new issue