From: Beman Dawes (bdawes_at_[hidden])
Date: 2003-05-08 12:07:08
At 11:11 AM 5/8/2003, Darin Adler wrote:
>On Thursday, May 8, 2003, at 07:04 AM, Beman Dawes wrote:
>> A 2-3% timing difference probably isn't reliably repeatable in real
>> How code and data happens to land in hardware caches can easily swamp
>> out such a small difference. The version-to-version or step-to-step
>> differences in CPU's, memory, compilers, or operating systems can
>> cause that much difference in a given program. Differences need to get
>> up into the 20-30% range before they are likely to be reliably
>> repeatable across different systems.
>> At least that's been my experience.
>That has not been my recent experience. While working on my current
>project (the Safari web browser), we have routinely made 1% speedups
>that are measurable and have an effect across multiple machines and
>compilers (same basic CPU type and operating system), and we have also
>detected 1% slowdowns when we inadvertently introduced them.
machine is written mostly in C, IIRC. I wonder if C++ is more sensitive to
For example, some C++ compilers are a lot more aggressive about inlining
than others. For some of the code I've timed, a change slowed results for a
compiler that failed to inline it, but ran quicker for the compiler that
was good at inlining.
>I'm not sure, though, if this negates your point, Beman. Something that
>gives a 2-3% speedup for one Boost user might not be worth any level of
>obfuscation unless we can prove it provides a similar speedup for other
Yes, that's a key point. And of course the 70% gain from a better sort
algorithm is the kind of win Boost needs to be alert to.
Boost list run by bdawes at acm.org, gregod at cs.rpi.edu, cpdaniel at pacbell.net, john at johnmaddock.co.uk