OT Linux (RE: [rescue] OT: Stuffed Proliant?)

[Patrick Giagnocavo]

On Fri, Dec 21, 2001 at 11:38:38PM -0500, Joshua D Boyd wrote:
> On Fri, Dec 21, 2001 at 10:35:38PM -0500, Patrick Giagnocavo wrote:
> > That sounds a bit like flamebait actually.  IMHO it's the software not
> > the hardware that makes x86 look so bad - since most of it ships with
> > Microslop.
> > 
> > OpenBSD on x86 performs quite well in my experience.
> 
> No, it isn't just the MS ware that makes x86 poor.  There are other things.  
> For instance, it needs to spend more time than almost any other chip loading
> variables from memory since it can only handle 6 at a time.  Arguably the
> cache should help this, but if you load the machine too heavily, the cache will
> be swapping out constantly, just like on bigger risc machines.  The sparc is 

You get 512KB L2 cache to begin with.  OpenBSD screams fast enough on
an AMD K6-2 450Mhz.  Will be getting an Athlon 1700XP wDDR RAM in the
near future and will see how that goes.

If you want to get really picky about it, you need to include the fact
that RISC code is generally "bigger" by 20 or 30% due to more
instructions needed (reduce instruction set, remember.)  So 512KB
cache on decent x86 is closer to say 630KB+ on RISC.

> pretty nice in this instance for a few reasons.  First, it is possible to get 
> more cache (up to 2 megs L2, isn't it? If not, then I'm wrong).  Second, it has

Up to 8MB on some chips/systems.

> Another problem with Intel (for some tasks) is floating point performance.  
> When Intel quotes benchmarks saying how fast they are, they are almost always
> using single precision.  However, almost everything uses double, which Intel
> is no where near as good at. 

Slightly less than half the numbers quoted for single-precision.

> Then, there is the general worthlessness of MMX and SSE.  SSE2 might be decent,
> but they crippled the P4 is other ways meaning that you have to rewrite for 
> SSE2 if you want decent performance at all.

The main boost seen from early MMX implementations was the increase in
L2 cache size for the original Pentiums. SSE dunno.  However Intel did
one thing right when they added hw rotate instruction, which is used
in crypto code and makes it faster.

The REAL thing I am seeing in my x86/OpenBSD systems is that the
performance isn't balanced - I/O on stock hw is not that great until
you buy good quality 7200 or 10K drives, good PCI enet cards, etc.

./patrick