Mail Archives: djgpp/2000/03/11/08:44:40
On Fri, 10 Mar 2000 GAMMELJL AT SLU DOT EDU wrote:
> I did get work on the machine with an AMD processor and found
> (as several had pointed out) that the problem I was having had nothing
> to with the AMD chip but rather had to do with the new version of djgpp
> (not the latest but the one before the latest) being used on that machine.
Yes this was the problem, and its great that you've sorted it out.
> Everything works fine after that. What one learns is that the
> AMD processor is faster than what one would expect from the clock speed
> (megahertz)
Certainly true. AFAIK My K7 athlon running at 500 mhz certainly thrashes
any Wintel 500 mhz chip. Actually I bet that it even outperforms the
Wintel 600 mhz chips even. And even better I can overclock the 500 up to
800 mhz IIRC..
>provided one does not optimizing and does not use assembly
> language.
I am a bit confused here. Certainly assembly code will run slower than c
code if it is badly written. As there is no way that good hand optimized
assembly can be slooow, except if they are written for a diferrent CPU
etc.
on a side note, I find that there is less reason to write assembly as most
of the modern day compilers do a superb job in producing effecient C code
which can inturn be compiler optimized for specific architectures (386
,686 etc).
So a good way is to write as much of the code as possible in C profile it,
identify the bottlenecks and _then_ decide to rewrite the slow code in
assembly.
>The executables run much faster when one uses assembly language
> and optimization -O2.
Now you say that the exes run faster when using assembly???? Could you
please clarify this.
> in line with what the clock speed suggests, with the Intel processor
> a little faster.
No way that this is possible :-) K7 athlons outperform wintel chips on
most aspects especially on the floating point handling.
Hi, I'm a signature virus. plz set me as your signature and help me spread
:)
- Raw text -