[ale] Hyperthreading

[James P. Kinney III]

On Wed, 2004-04-14 at 10:40, Dow Hurst wrote:
> Yes, I run two minimizations simultaneously on my single P4 and until the 
> second one starts the machine is very responsive.  It is truly like having a 
> dual CPU from my user perspective.  Run times are doubled on the minimizations.
> 
> 25m37.821s   Single run
> 
> 49m54.143s
> 44m10.795s   Dual runs (The second is the shorter due to different start 
> times, so this is general datapoints)

That looks confusing. To me it seems that using the HT technology made
the same operation take nearly twice as long as with the HT turned off.

This would indicate to me that the  quasi-dual mode of the HT P4 is a
serious performance blow to this type of calculation. Since there is a
significant portion of the CPU core that it still shared in the P4HT
chips, I expect that the apparent poor performance of your test run is
due to excessive task swapping of that common core region and/or cache
starvation due to an un-tuned app. A test I did several years ago of a
real dual processor machine found that the maximum speed up occurred
when the looping code would just fit into L2 cache. At that point the
entire system was purely IO bound by the memory bus rate. DDR RAM was
the next kick to the process. As the system was not having to cache swap
every cycle and the RAM access was now basically in duplex mode, the
same task as before now took just a bit of half the prior time.

I have yet to test this on the dual opteron box as the code is not 64
bit so why bother :)
> 
> 
> These are GPCR receptor minimizations with delta 9 THC bound inside the 
> receptor.  About ~2700 atoms in vacuum using molecular mechanics and a lot of 
> torsional restraints applied.  Not a difficult calculation but is pure FPU on 
> C and Fortran code.  But, my point is the machine was acting like a dual CPU 
> machine in a very efficient manner.
> Dow
> 
> 
> Christopher Fowler wrote:
> > How is the performance? Is there a real gain?
> > 
> > On Wed, 2004-04-14 at 10:03, Jonathan Glass wrote:
> > 
> >>On Wed, 2004-04-14 at 10:02, Mike Millson wrote:
> >>
> >>>I have a box with a P4 processor running Slackware 9.1. What do I need
> >>>to do to enable hyperthreading support? Do I just have to compile a
> >>>kernel with SMP support? Are there any other kernel options or config
> >>>changes I need to make? Does anyone know of any good articles or howtos
> >>>on configuring linux for hyperthreading?
> >>>
> >>>Thank you,
> >>>Mike
> >>>
> >>>_______________________________________________
> >>>Ale mailing list
> >>>Ale at ale.org
> >>>http://www.ale.org/mailman/listinfo/ale
> >>
> >>You win the prize on the first toss.  Just recompile with SMP support,
> >>and enable HT in your BIOS, and voila!  Instant SMP machine.
> > 
> > 
> > _______________________________________________
> > Ale mailing list
> > Ale at ale.org
> > http://www.ale.org/mailman/listinfo/ale
> > 
-- 
James P. Kinney III          \Changing the mobile computing world/
CEO & Director of Engineering \          one Linux user         /
Local Net Solutions,LLC        \           at a time.          /
770-493-8244                    \.___________________________./
http://www.localnetsolutions.com

GPG ID: 829C6CA7 James P. Kinney III (M.S. Physics)
<jkinney at localnetsolutions.com>
Fingerprint = 3C9E 6366 54FC A3FE BA4D 0659 6190 ADC3 829C 6CA7
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: This is a digitally signed message part