Misc/abrash-black-book
Watch
1
0
Fork
You've already forked abrash-black-book
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Use backtick code blocks for syntax highlighting

Browse source
This commit is contained in:
James Gregory 2013-12-31 11:38:48 +11:00
commit f658bfbb40
203 changed files with 26546 additions and 25801 deletions
Download patch file Download diff file Expand all files Collapse all files

132
21-05.md
View file

@ -12,36 +12,38 @@ pages: 409-411
**LISTING 21.4 L21-4.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, ECX, EDX, and ESI destroyed.
; All cycle counts assume 32-bit protected mode.
; Assumes buffer starts on a dword boundary, is a dword multiple
; in length, and 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, ECX, EDX, and ESI destroyed.
; All cycle counts assume 32-bit protected mode.
; Assumes buffer starts on a dword boundary, is a dword multiple
; in length, and length > 0.
sub eax,eax ;initialize the checksum
shr ecx,1 ;we'll do two words per loop
mov edx,[esi] ;preload the first dword
add esi,4 ;point to the next dword
dec ecx ;we'll do 1 checksum outside the loop
jz short ckloopend ;only 1 checksum to do
sub eax,eax ;initialize the checksum
shr ecx,1 ;we'll do two words per loop
mov edx,[esi] ;preload the first dword
add esi,4 ;point to the next dword
dec ecx ;we'll do 1 checksum outside the loop
jz short ckloopend ;only 1 checksum to do
ckloop:
add eax,edx ;cycle 1 U-pipe
mov edx,[esi] ;cycle 1 V-pipe
adc eax,0 ;cycle 2 U-pipe
add esi,4 ;cycle 2 V-pipe
dec ecx ;cycle 3 U-pipe
jnz ckloop ;cycle 3 V-pipe
ckloop:
add eax,edx ;cycle 1 U-pipe
mov edx,[esi] ;cycle 1 V-pipe
adc eax,0 ;cycle 2 U-pipe
add esi,4 ;cycle 2 V-pipe
dec ecx ;cycle 3 U-pipe
jnz ckloop ;cycle 3 V-pipe
ckloopend:
add eax,edx ;checksum the last dword
adc eax,0
mov edx,eax ;compress the 32-bit checksum
shr edx,16 ; into a 16-bit checksum
add ax,dx
adc eax,0
ckloopend:
add eax,edx ;checksum the last dword
adc eax,0
mov edx,eax ;compress the 32-bit checksum
shr edx,16 ; into a 16-bit checksum
add ax,dx
adc eax,0
```
Listing 21.5 improves upon Listing 21.4 by processing 2 dwords per loop,
thereby bringing the time per checksummed word down to exactly 1 cycle.
@ -53,46 +55,48 @@ more registers.
**LISTING 21.5 L21-5.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, EBX, ECX, EDX, and ESI destroyed.
; All cycle counts assume 32-bit protected mode.
; Assumes buffer starts on a dword boundary, is a dword multiple
; in length, and 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, EBX, ECX, EDX, and ESI destroyed.
; All cycle counts assume 32-bit protected mode.
; Assumes buffer starts on a dword boundary, is a dword multiple
; in length, and length > 0.
sub eax,eax ;initialize the checksum
shr ecx,2 ;we'll do two dwords per loop
jnc short noodddword ;is there an odd dword in buffer?
mov eax,[esi] ;checksum the odd dword
jz short ckloopdone ;no, done
add esi,4 ;point to the next dword
noodddword:
mov edx,[esi] ;preload the first dword
mov ebx,[esi+4] ;preload the second dword
dec ecx ;we'll do 1 checksum outside the loop
jz short ckloopend ;only 1 checksum to do
add esi,8 ;point to the next dword
sub eax,eax ;initialize the checksum
shr ecx,2 ;we'll do two dwords per loop
jnc short noodddword ;is there an odd dword in buffer?
mov eax,[esi] ;checksum the odd dword
jz short ckloopdone ;no, done
add esi,4 ;point to the next dword
noodddword:
mov edx,[esi] ;preload the first dword
mov ebx,[esi+4] ;preload the second dword
dec ecx ;we'll do 1 checksum outside the loop
jz short ckloopend ;only 1 checksum to do
add esi,8 ;point to the next dword
ckloop:
add eax,edx ;cycle 1 U-pipe
mov edx,[esi] ;cycle 1 V-pipe
adc eax,ebx ;cycle 2 U-pipe
mov ebx,[esi+4] ;cycle 2 V-pipe
adc eax,0 ;cycle 3 U-pipe
add esi,8 ;cycle 3 V-pipe
dec ecx ;cycle 4 U-pipe
jnz ckloop ;cycle 4 V-pipe
ckloop:
add eax,edx ;cycle 1 U-pipe
mov edx,[esi] ;cycle 1 V-pipe
adc eax,ebx ;cycle 2 U-pipe
mov ebx,[esi+4] ;cycle 2 V-pipe
adc eax,0 ;cycle 3 U-pipe
add esi,8 ;cycle 3 V-pipe
dec ecx ;cycle 4 U-pipe
jnz ckloop ;cycle 4 V-pipe
ckloopend:
add eax,edx ;checksum the last two dwords
adc eax,ebx
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
ckloopend:
add eax,edx ;checksum the last two dwords
adc eax,ebx
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
```
Listing 21.5 is undeniably intricate code, and not the sort of thing one
would choose to write as a matter of course. On the other hand, it's