Messages in this thread | | | Date | Fri, 20 Nov 1998 17:10:50 +0100 | From | Marc Lehmann <> | Subject | Re: Linux-asm (was A patch for linux 2.1.127) |
| |
On Thu, Nov 19, 1998 at 02:19:25AM -0500, Albert D. Cahalan wrote: > > C will never run faster than assembly, since C gets converted to
Wrong logic. Actually, its quite easy in many cases to write faster C than assembly.
This argument is very misleading and wrong. I've seen too many assembly functions written with the i386 in mind to even agree theoretically to that argument.
True, you can always beat a specific algorithm in c by implementing it in assembly (or at least be on par), but that does _not_ imply that C will not run faster then assembly, which, to the contrary, is often the case.
> Remember that a performance advantage worth 1 year of hardware > improvement won't just disappear after a year.
Wrong. The performance improvement of implementing software in assembly in the 386 days has completely vanished, and has even turned into a loss of performance since compilers produce better code for pentium (etc.) then i386 assembly programmers.
(if you are concerned about the timespan, take 486 programmers and pentium compilers)
> 1-year lead, and only lose it slowly as processors change and > compilers improve.
Depends. True, for 386 machines the perfomance gains are still worth it, but we were not talking about using the same cpu in the next year...
-----==- | ----==-- _ | ---==---(_)__ __ ____ __ 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/
| |