[ale] Hyperthreading

[Jonathan Glass]

Test it anyway, but in 32-bit only.  You'll be amazed at the difference.
At least, according to Open-Mag.com, there is a nice performance diff.

Thanks

Jonathan


> 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
> _______________________________________________
> Ale mailing list
> Ale at ale.org
> http://www.ale.org/mailman/listinfo/ale
>


-- 
Jonathan Glass
Systems Support Specialist II
IBB/GTEC
Office: 404-385-0127
Cell: 404-444-4086