Replace invalid characters with HTML entities
— with — ’ with ’ + with + × with x ç with ç “ with “ ” with ” ‘ with ‘ • with • – with - µ with µ † with † Fix C++ θ with θ Yen symbol instead of times Fix broken apos Bullet again E-circumflex
This commit is contained in:
James Gregory
parent
9e52de9586
commit
500e7f5654
353 changed files with 5091 additions and 5091 deletions
56
08-04.html
56
08-04.html
|
|
@ -36,7 +36,7 @@
|
|||
</TABLE>
|
||||
</CENTER>
|
||||
<P><BR></P>
|
||||
<P>It’s hard to squeeze much more performance from this code by tweaking it, as exemplified by Listing 8.3, a fine-tuned assembly version of <B>FindIDAverage</B> that was produced by looking at the assembly output of MS C/C<SMALL>++</SMALL> and tightening it. Listing 8.3 eliminates all stack frame access in the inner loop, but that’s about all the tightening there is to do. The result, as shown in Table 8.1, is that Listing 8.3 runs a modest 11 percent faster than Listing 8.1 on a 386. The results could vary considerably, depending on the nature of the data set searched through (average block size and frequency of matches). But, then, understanding the typical and worst case conditions is part of optimization, isn’t it?</P>
|
||||
<P>It’s hard to squeeze much more performance from this code by tweaking it, as exemplified by Listing 8.3, a fine-tuned assembly version of <B>FindIDAverage</B> that was produced by looking at the assembly output of MS C/C<SMALL>++</SMALL> and tightening it. Listing 8.3 eliminates all stack frame access in the inner loop, but that’s about all the tightening there is to do. The result, as shown in Table 8.1, is that Listing 8.3 runs a modest 11 percent faster than Listing 8.1 on a 386. The results could vary considerably, depending on the nature of the data set searched through (average block size and frequency of matches). But, then, understanding the typical and worst case conditions is part of optimization, isn’t it?</P>
|
||||
<P><B>LISTING 8.3 L8-3.ASM</B></P>
|
||||
<!-- CODE //-->
|
||||
<PRE>
|
||||
|
|
@ -107,51 +107,51 @@ DATA_ELEMENT_SIZE equ 4 ;Number of bytes in struct DataElement
|
|||
<!-- CODE //-->
|
||||
<PRE>
|
||||
_FindIDAverage proc near
|
||||
push bp ;Save caller’s stack frame
|
||||
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
|
||||
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]
|
||||
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]
|
||||
mov cx,[si+BlockCount]
|
||||
jcxz DoNextBlock ;No data in this block
|
||||
IntraBlockLoop:
|
||||
cmp [di+ID],ax ;Do we have an ID match?
|
||||
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;
|
||||
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.
|
||||
; Point to the next block and continue if that pointer isn’t NULL.
|
||||
DoNextBlock:
|
||||
mov si,[si+NextBlock] ;Get pointer to the next block
|
||||
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
|
||||
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
|
||||
pop bp ;Restore caller’s stack frame
|
||||
ret
|
||||
_FindIDAverage ENDP
|
||||
end
|
||||
</PRE>
|
||||
<!-- END CODE //-->
|
||||
<P>Listing 8.4 tosses some sophisticated optimization techniques into the mix. The loop is unrolled eight times, eliminating a good deal of branching, and <B>SCASW</B> is used instead of <B>CMP [DI],AX.</B> (Note, however, that <B>SCASW</B> is in fact slower than <B>CMP [DI],AX</B> on the 386 and 486, and is sometimes faster on the 286 and 8088 only because it’s shorter and therefore may prefetch faster.) This advanced tweaking produces a 39 percent improvement over the original C code—substantial, but not a tremendous return for the optimization effort invested.</P>
|
||||
<P>Listing 8.4 tosses some sophisticated optimization techniques into the mix. The loop is unrolled eight times, eliminating a good deal of branching, and <B>SCASW</B> is used instead of <B>CMP [DI],AX.</B> (Note, however, that <B>SCASW</B> is in fact slower than <B>CMP [DI],AX</B> on the 386 and 486, and is sometimes faster on the 286 and 8088 only because it’s shorter and therefore may prefetch faster.) This advanced tweaking produces a 39 percent improvement over the original C code—substantial, but not a tremendous return for the optimization effort invested.</P>
|
||||
<P><B>LISTING 8.4 L8-4.ASM</B></P>
|
||||
<!-- CODE //-->
|
||||
<PRE>
|
||||
|
|
@ -170,7 +170,7 @@ DATA_ELEMENT_SIZE equ 4 ;Number of bytes in struct DataElement
|
|||
.code
|
||||
public _FindIDAverage
|
||||
_FindIDAverage proc near
|
||||
push bp ;Save caller’s stack frame
|
||||
push bp ;Save caller’s stack frame
|
||||
mov bp,sp ;Point to our stack frame
|
||||
push di ;Preserve C register variables
|
||||
push si
|
||||
|
|
@ -179,25 +179,25 @@ _FindIDAverage proc near
|
|||
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
|
||||
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]
|
||||
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 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 ; 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
|
||||
jmp cs:[LoopEntryTable+bp] ; the unrolled loop and
|
||||
; vector to that entry point
|
||||
align 2
|
||||
LoopEntryTable label word
|
||||
|
|
@ -209,8 +209,8 @@ 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;
|
||||
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)
|
||||
|
|
@ -226,20 +226,20 @@ IntraBlockLoop:
|
|||
M_IBL 2
|
||||
M_IBL 1
|
||||
loop IntraBlockLoop
|
||||
; Point to the next block and continue if that pointer isn’t NULL.
|
||||
; Point to the next block and continue if that pointer isn’t NULL.
|
||||
DoNextBlock:
|
||||
mov si,[si+NextBlock] ;Get pointer to the next block
|
||||
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
|
||||
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
|
||||
pop bp ;Restore caller’s stack frame
|
||||
ret
|
||||
_FindIDAverage ENDP
|
||||
end
|
||||
|
|
|
|||
Loading…
Reference in a new issue