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

294
08-04.md
View file

@ -24,19 +24,21 @@ optimization, isn't it?
**LISTING 8.3 L8-3.ASM**
; Typically optimized assembly language version of FindIDAverage.
SearchedForID equ 4 ;Passed parameter offsets in the
BlockPointer equ 6 ; stack frame (skip over pushed BP
; and the return address)
NextBlock equ 0 ;Field offsets in struct BlockHeader
BlockCount equ 2
BLOCK_HEADER_SIZE equ 4 ;Number of bytes in struct BlockHeader
ID equ 0 ;struct DataElement field offsets
Value equ 2
DATA_ELEMENT_SIZE equ 4 ;Number of bytes in struct DataElement
.model small
.code
public _FindIDAverage
```nasm
; Typically optimized assembly language version of FindIDAverage.
SearchedForID equ 4 ;Passed parameter offsets in the
BlockPointer equ 6 ; stack frame (skip over pushed BP
; and the return address)
NextBlock equ 0 ;Field offsets in struct BlockHeader
BlockCount equ 2
BLOCK_HEADER_SIZE equ 4 ;Number of bytes in struct BlockHeader
ID equ 0 ;struct DataElement field offsets
Value equ 2
DATA_ELEMENT_SIZE equ 4 ;Number of bytes in struct DataElement
.model small
.code
public _FindIDAverage
```
| | On 20 MHz 386 | On 10 MHz 286 |
|------------------------------------------------------------|------------------|------------------|
@ -47,49 +49,51 @@ optimization, isn't it?
Table: Table 8.1 Execution Times of FindIDAverage.
_FindIDAverage proc near
push bp ;Save caller's stack frame
mov bp,sp ;Point to our stack frame
push di ;Preserve C register variables
push si
sub dx,dx ;IDMatchSum = 0
mov bx,dx ;IDMatchCount = 0
mov si,[bp+BlockPointer] ;Pointer to first block
mov ax,[bp+SearchedForID] ;ID we're looking for
; Search through all the linked blocks until the last block
; (marked with a NULL pointer to the next block) has been searched.
BlockLoop:
; Point to the first DataElement entry within this block.
lea di,[si+BLOCK_HEADER_SIZE]
; Search through all the DataElement entries within this block
; and accumulate data from all that match the desired ID.
mov cx,[si+BlockCount]
jcxz DoNextBlock ;No data in this block
IntraBlockLoop:
cmp [di+ID],ax ;Do we have an ID match?
jnz NoMatch ;No match
inc bx ;We have a match; IDMatchCount++;
add dx,[di+Value] ;IDMatchSum += DataPointer->Value;
NoMatch:
add di,DATA_ELEMENT_SIZE ;point to the next element
loop IntraBlockLoop
; Point to the next block and continue if that pointer isn't NULL.
DoNextBlock:
mov si,[si+NextBlock] ;Get pointer to the next block
and si,si ;Is it a NULL pointer?
jnz BlockLoop ;No, continue
; Calculate the average of all matches.
sub ax,ax ;Assume we found no matches
and bx,bx
jz Done ;We didn't find any matches, return 0
xchg ax,dx ;Prepare for division
div bx ;Return IDMatchSum / IDMatchCount
Done: pop si ;Restore C register variables
pop di
pop bp ;Restore caller's stack frame
ret
_FindIDAverage ENDP
end
```nasm
_FindIDAverage proc near
push bp ;Save caller's stack frame
mov bp,sp ;Point to our stack frame
push di ;Preserve C register variables
push si
sub dx,dx ;IDMatchSum = 0
mov bx,dx ;IDMatchCount = 0
mov si,[bp+BlockPointer] ;Pointer to first block
mov ax,[bp+SearchedForID] ;ID we're looking for
; Search through all the linked blocks until the last block
; (marked with a NULL pointer to the next block) has been searched.
BlockLoop:
; Point to the first DataElement entry within this block.
lea di,[si+BLOCK_HEADER_SIZE]
; Search through all the DataElement entries within this block
; and accumulate data from all that match the desired ID.
mov cx,[si+BlockCount]
jcxz DoNextBlock ;No data in this block
IntraBlockLoop:
cmp [di+ID],ax ;Do we have an ID match?
jnz NoMatch ;No match
inc bx ;We have a match; IDMatchCount++;
add dx,[di+Value] ;IDMatchSum += DataPointer->Value;
NoMatch:
add di,DATA_ELEMENT_SIZE ;point to the next element
loop IntraBlockLoop
; Point to the next block and continue if that pointer isn't NULL.
DoNextBlock:
mov si,[si+NextBlock] ;Get pointer to the next block
and si,si ;Is it a NULL pointer?
jnz BlockLoop ;No, continue
; Calculate the average of all matches.
sub ax,ax ;Assume we found no matches
and bx,bx
jz Done ;We didn't find any matches, return 0
xchg ax,dx ;Prepare for division
div bx ;Return IDMatchSum / IDMatchCount
Done: pop si ;Restore C register variables
pop di
pop bp ;Restore caller's stack frame
ret
_FindIDAverage ENDP
end
```
Listing 8.4 tosses some sophisticated optimization techniques into the
mix. The loop is unrolled eight times, eliminating a good deal of
@ -102,91 +106,93 @@ but not a tremendous return for the optimization effort invested.
**LISTING 8.4 L8-4.ASM**
; Heavily optimized assembly language version of FindIDAverage.
; Features an unrolled loop and more efficient pointer use.
SearchedForID equ 4 ;Passed parameter offsets in the
BlockPointer equ 6 ; stack frame (skip over pushed BP
; and the return address)
NextBlock equ 0 ;Field offsets in struct BlockHeader
BlockCount equ 2
BLOCK_HEADER_SIZE equ 4 ;Number of bytes in struct BlockHeader
ID equ 0 ;struct DataElement field offsets
Value equ 2
DATA_ELEMENT_SIZE equ 4 ;Number of bytes in struct DataElement
.model small
.code
public _FindIDAverage
_FindIDAverage proc near
push bp ;Save caller's stack frame
mov bp,sp ;Point to our stack frame
push di ;Preserve C register variables
push si
mov di,ds ;Prepare for SCASW
mov es,di
cld
sub dx,dx ;IDMatchSum = 0
mov bx,dx ;IDMatchCount = 0
mov si,[bp+BlockPointer] ;Pointer to first block
mov ax,[bp+SearchedForID] ;ID we're looking for
; Search through all of the linked blocks until the last block
; (marked with a NULL pointer to the next block) has been searched.
BlockLoop:
; Point to the first DataElement entry within this block.
lea di,[si+BLOCK_HEADER_SIZE]
; Search through all the DataElement entries within this block
; and accumulate data from all that match the desired ID.
mov cx,[si+BlockCount] ;Number of elements in this block
jcxz DoNextBlock ;Skip this block if it's empty
mov bp,cx ;***stack frame no longer available***
add cx,7
shr cx,1 ;Number of repetitions of the unrolled
shr cx,1 ; loop = (BlockCount + 7) / 8
shr cx,1
and bp,7 ;Generate the entry point for the
shl bp,1 ; first, possibly partial pass through
jmp cs:[LoopEntryTable+bp] ; the unrolled loop and
; vector to that entry point
align 2
LoopEntryTable label word
dw LoopEntry8,LoopEntry1,LoopEntry2,LoopEntry3
dw LoopEntry4,LoopEntry5,LoopEntry6,LoopEntry7
M_IBL macro P1
local NoMatch
LoopEntry&P1&:
scasw ;Do we have an ID match?
jnz NoMatch ;No match
;We have a match
inc bx ;IDMatchCount++;
add dx,[di] ;IDMatchSum += DataPointer->Value;
NoMatch:
add di,DATA_ELEMENT_SIZE-2 ;point to the next element
; (SCASW advanced 2 bytes already)
endm
align 2
IntraBlockLoop:
M_IBL 8
M_IBL 7
M_IBL 6
M_IBL 5
M_IBL 4
M_IBL 3
M_IBL 2
M_IBL 1
loop IntraBlockLoop
; Point to the next block and continue if that pointer isn't NULL.
DoNextBlock:
mov si,[si+NextBlock] ;Get pointer to the next block
and si,si ;Is it a NULL pointer?
jnz BlockLoop ;No, continue
; Calculate the average of all matches.
sub ax,ax ;Assume we found no matches
and bx,bx
jz Done ;We didn't find any matches, return 0
xchg ax,dx ;Prepare for division
div bx ;Return IDMatchSum / IDMatchCount
Done: pop si ;Restore C register variables
pop di
pop bp ;Restore caller's stack frame
ret
_FindIDAverage ENDP
end
```nasm
; Heavily optimized assembly language version of FindIDAverage.
; Features an unrolled loop and more efficient pointer use.
SearchedForID equ 4 ;Passed parameter offsets in the
BlockPointer equ 6 ; stack frame (skip over pushed BP
; and the return address)
NextBlock equ 0 ;Field offsets in struct BlockHeader
BlockCount equ 2
BLOCK_HEADER_SIZE equ 4 ;Number of bytes in struct BlockHeader
ID equ 0 ;struct DataElement field offsets
Value equ 2
DATA_ELEMENT_SIZE equ 4 ;Number of bytes in struct DataElement
.model small
.code
public _FindIDAverage
_FindIDAverage proc near
push bp ;Save caller's stack frame
mov bp,sp ;Point to our stack frame
push di ;Preserve C register variables
push si
mov di,ds ;Prepare for SCASW
mov es,di
cld
sub dx,dx ;IDMatchSum = 0
mov bx,dx ;IDMatchCount = 0
mov si,[bp+BlockPointer] ;Pointer to first block
mov ax,[bp+SearchedForID] ;ID we're looking for
; Search through all of the linked blocks until the last block
; (marked with a NULL pointer to the next block) has been searched.
BlockLoop:
; Point to the first DataElement entry within this block.
lea di,[si+BLOCK_HEADER_SIZE]
; Search through all the DataElement entries within this block
; and accumulate data from all that match the desired ID.
mov cx,[si+BlockCount] ;Number of elements in this block
jcxz DoNextBlock ;Skip this block if it's empty
mov bp,cx ;***stack frame no longer available***
add cx,7
shr cx,1 ;Number of repetitions of the unrolled
shr cx,1 ; loop = (BlockCount + 7) / 8
shr cx,1
and bp,7 ;Generate the entry point for the
shl bp,1 ; first, possibly partial pass through
jmp cs:[LoopEntryTable+bp] ; the unrolled loop and
; vector to that entry point
align 2
LoopEntryTable label word
dw LoopEntry8,LoopEntry1,LoopEntry2,LoopEntry3
dw LoopEntry4,LoopEntry5,LoopEntry6,LoopEntry7
M_IBL macro P1
local NoMatch
LoopEntry&P1&:
scasw ;Do we have an ID match?
jnz NoMatch ;No match
;We have a match
inc bx ;IDMatchCount++;
add dx,[di] ;IDMatchSum += DataPointer->Value;
NoMatch:
add di,DATA_ELEMENT_SIZE-2 ;point to the next element
; (SCASW advanced 2 bytes already)
endm
align 2
IntraBlockLoop:
M_IBL 8
M_IBL 7
M_IBL 6
M_IBL 5
M_IBL 4
M_IBL 3
M_IBL 2
M_IBL 1
loop IntraBlockLoop
; Point to the next block and continue if that pointer isn't NULL.
DoNextBlock:
mov si,[si+NextBlock] ;Get pointer to the next block
and si,si ;Is it a NULL pointer?
jnz BlockLoop ;No, continue
; Calculate the average of all matches.
sub ax,ax ;Assume we found no matches
and bx,bx
jz Done ;We didn't find any matches, return 0
xchg ax,dx ;Prepare for division
div bx ;Return IDMatchSum / IDMatchCount
Done: pop si ;Restore C register variables
pop di
pop bp ;Restore caller's stack frame
ret
_FindIDAverage ENDP
end
```