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

[Joshua D Boyd]

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 
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
32 registers.  Except that isn't really correct.  You can use 32 registers at a
time, but it really has more registers and it just uses a register windowing 
scheme to allow you access to 32 registers at a time.  The other registers 
still hold the data in them at the time that the current function was called.

On a related note, I hear that the SS2 has more hardware contexts than the IPX?
What does that mean at a hardware level?  Does this relate to the register 
windowing?

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. 

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.

-- 
Joshua D. Boyd