[mythtv-users] Compiler optimizations

[Henk Poley]

> Van: Michael McConnell <mmcconnell at uniserve.com>
> 
> Hello Joseph,
> 
>     The reason I'm surprised, and suspect that it can't be true, is
> "generally" compiler optimizations of this nature only yield very minimal
> improvement; improvements in the range of 1% - 3% would generally be
gained
> on some trivial operation calls via compiler optimization. It's very,
very
> rare to see an improvement of 15% - 20% just through compiler
optimization,
> however I clearly, and continually see the optimizations made a
significant
> different. I'm trying to track down where, and what operation call could
be
> used so heavily in MythTV that a PentiumPro to Pentium3 + FastMath
compile
> could yield such an improvement.

Isn't it that from the P-Pro to the PIII (even) more 'speculative' code got
into the CPU, together with OP-codes to hint the CPU what is expected ahead
(pre-loading data, branch predection, etc.). And the addition of some more
pipelines might have influence on the optimization model, wasn't it that
the P-Pro 'only' has 2 pipelines?

> Ultimately until I can track the point, which result in such different,
I'm
> still a bit of a sceptic and I see it with my own eyes! (-; Clearly it
will
> require a "some what trivial" rewrite of whatever is causing this. It
must
> be bad code.

Intel's and AMD's PR consortia have said such a speedup could be true. So
MythTV might as well hit one of the rare occasions where this 'rule' holds
;-)

But indeed, it is probably 'bad code' that when written in another way will
work about as speedy on both optimization models.

	Henk Poley <><