[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Re: On linux kernel packaging issue

On Sat, 8 Nov 2003 12:33:15 +0000
Andrew Suffield <asuffield@debian.org> wrote:

> Please provide carefully documented evidence of the performance gains
> that you are claiming, not handwaving. Evidence of a difference is not
> the same thing; anybody who has any experience with low-level
> programming knows that differences are as likely to cause a
> performance loss as they are to cause a gain. More so, in fact; it's
> easier to make code slower than it is to make it faster.
> We're all very interested in *real* evidence here, because there
> hasn't been any in the past. If you don't have any evidence, you can
> expect people to call bullshit on this.

Andrew, i agree with you, its impossible to make programs run faster
just by making them to use different hardware instructions.

We all know its just the MHz number that makes programs run good, all
that RISC, CISC, MMX, 3DNOW stuff, its just marketing.

I want for original i386 instruction set back as well, but all these
hardware engineers and GCC programmers just keep offering these
optimisations, what more can we do to protect our users from these
proofless people ?



Reply to: