SI
SI
discoversearch

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor.  We ask that you disable ad blocking while on Silicon Investor in the best interests of our community.  If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.
Politics : Formerly About Advanced Micro Devices -- Ignore unavailable to you. Want to Upgrade?

To: fyo who wrote (66554)7/23/1999 8:09:00 PM
From: Scumbria  Read Replies (1) | Respond to of 1574006
 
Fyo,

I strongly suspect that this is good example of an instance where a dual PIII would thrash a dual Celeron system. Since the data set for an FFT in SETI is 128kB, this would only fit in the Celeron's L2 cache in theory.

Has anyone tried running SETI on a K6-III system versus a Celeron? If the theory is correct and the cache is too small on Celeron, the K6 system should have an advantage.

Scumbria



To: fyo who wrote (66554)7/23/1999 8:36:00 PM
From: Ali Chen  Read Replies (2) | Respond to of 1574006
 
Fyo, <the data set for an FFT in SETI is 128kB>
According to SETI technical papers, it is
actually 128k of data POINTS, which are most
likely at least single-precision 4-bytes floats.
Take it into account.

More, as I understand them, each work unit
contains about 2M points, or about 8MBytes
to work with. These data are also processed for
different doppler shifts which does not improve
the data locality either.

Take care,
- Ali


HomeMailHotSubjectMarksPeopleMarksKeepersSettings
Terms Of UseContact UsCopyright/IP PolicyPrivacy PolicyAbout UsFAQAdvertise on SI
© 2025 Knight Sac Media.  Data provided by Twelve Data, Alpha Vantage, and CityFALCON News