robert wrote:
> --------------
> 0040101F mov eax,3B9ACA00h
> 13: for (i = 0; i < count; ++i) {
> 14: __asm lock inc x;
> 00401024 lock inc dword ptr [_x (00408a00)]
> 15: sum += x;
> 0040102B mov edx,dword ptr [_x (00408a00)]
> 00401031 add esi,edx
> 00401033 dec eax
> 00401034 jne main+24h (00401024)
> 16: }
> ---------------
>
> results on a UP PIII :
>
> INC version:
> clocks: 7520
> secs: 7
>
> LOCK INC version:
> clocks: 36632
> secs: 36
>
>
> Its probably not much...
The Intels I checked, have all about this factor of ~5 in that simple example.
AMDs were typically faster. less than ~3.
-robert
PS:
the asm for x86 linux/gcc:
-------------------
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
volatile int x=0;
clock_t c0,c1;
time_t t0,t1;
int main (int argc, char **argv) {
int sum = 0, i, count = 100000000;
t0=time(&t0);
c0=clock();
for (i = 0; i < count; ++i) {
asm ("incl %0;" : "=m"(x) );
sum += x;
}
c1=clock();
t1=time(&t1);
// printf("%d\n", sum);
printf("clocks: %d\n", c1-c0);
printf("secs: %d\n", t1-t0);
return sum;
}
--
http://mail.python.org/mailman/listinfo/python-list
