> > this option dosen't make sense for pentium because there are no
> > architecture specific instrunctions available for it (but not for
> > pentiumpro). So the valide option for pentium is -mpentium.
Thats what I said, which weas an approximation. There are no useful
instructions (from a compiler perspective).
> Their are alot of pentium specific instructions. Of course gcc/gas make
> not support any of them.
gcc/gas support all of them, of course!
On Tue, Dec 15, 1998 at 01:19:13AM +0000, Jamie Lokier wrote:
>
> That doesn't mean the compiler won't use them in future. Compilers get
> cleverer all the time.
True. But I think the very rare additional instructions that were addedc for
the i486 and the pentium won't get used in the future.
the bswap instruction is quite slow, but might be useful in some occasions.
That _might_ introduce a incompatibility in the future.
But note that using -mpentium & friends might also define additional
preprocessor symbols (like __i586) so include files or other code might
adjust (the kernel will use bswap when configured for !386 for example)
On Mon, Dec 14, 1998 at 07:25:02PM -0500, Anthony Barbachan wrote:
> group's web site and you should find out any other options. Although, if
> I remember correctly, their web site claims to have Cyrix optimization I
> do not know what they are. You may have to ask them.
Yes, that should go to the mailing list beastium-list@desk.nl. At the moment
there are switches for the cyrix6x86 and 6x86mx cpus, but they only change
some scheduling attributes. I don't get enough feedback on them to know
wether they work or not.
-----==- |
----==-- _ |
---==---(_)__ __ ____ __ Marc Lehmann +--
--==---/ / _ \/ // /\ \/ / pcg@goof.com |e|
-=====/_/_//_/\_,_/ /_/\_\ --+
The choice of a GNU generation |
|
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/