Messages in this thread |  | | Date | Tue, 05 Sep 2000 13:57:17 +0300 | From | Petko Manolov <> | Subject | Re: [patch] string-486.h modified |
| |
Jamie Lokier wrote: > > Alan Cox wrote: > > > Alan, can you send me again the list of CPUs you think > > > is worth using 486 string routines. > > > Sorry, i lost your previous mail. > > > > I suspect it is > > > > 486 > > K5 > > IDT Winchip > > Rise > > NexGen > > Take a look at > http://now.cs.berkeley.edu/Td/bcopy.html
Nice page, thank you.
> Speed increases by 50% for unrolled string copies on their P5s. Sure > they're old, but so are 486s :-) > > Of course you do _not_ want to inline a long string copy routine. > There should probably be a arch/i386/lib/string-486.c.
These routines are often used and one of the goals was reducing code size. That's why for generic case i used as few instructions as possible, while for optimized one i made some speedups with the cost of few instructions more.
I don't see the point of string-486.c - string-486.h is a replacement of string.h for i[45]86 machines so let stay in include directory.
best, Petkan - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org Please read the FAQ at http://www.tux.org/lkml/
|  |