My Turn

SETI@home and the Megahertz Myth

Roberto Perez - 2002.04.15

My Turn is Low End Mac's column for reader-submitted articles. It's your turn to share your thoughts on all things Mac (or iPhone, iPod, etc.) and write for the Mac web. Email your submission to Dan Knight .

It's funny, but I really have no clue why people constantly argue about the differences between the Mac and PC platforms and their speeds!

I have a home network currently consisting of five computers:

I have a Power Mac G4/450 w/384 MB RAM, an IBM 300PL PII/400 w/288 MB RAM, a Dell Dimension Celeron 800 MHz w/192 MB RAM, a Power Mac 6500 w/G3 accelerator @ 300 MHz w/128 MB RAM, and a Dell Inspiron 4100 PIII/866 w/192 MB RAM.

All five computers are networked and have access to the Internet via Verizon DSL; all five five computers share documents, music, and games. I recently installed SETI@home and decided to install the program on all five computers. It did not begin as a benchmark, but I could not help but notice that the PCs were lagging in number crunching performance.

I initially installed SETI@home on my Dell PIII/866 laptop and began running the program. I then decided to do it to the rest. I installed and ran the program on my IBM PC about 25 minutes after starting it on my laptop. 5 minutes after that I installed it on my Power Mac G4, 15 minutes after that I installed and ran the program on my Dell Dimension, then 5 minutes later installed and ran the program on the Power Mac 6500.

To my surprise when making the rounds and checking on all 5 computers, I found that the 450 MHz Power Mac G4 crunched data more quickly than the 866 MHz Pentium III laptop - and that was after starting the PowerMac G4 30 minutes after starting the laptop!

I continued to check on all the computers and found that the Macintosh computers were crunching data much more quickly than their PC counterparts. The Power Mac G4 was leading all other computer even though it was started 30 minutes after the fastest (by MHz) computer I have! Even the slowest Mac I have, the Power Mac 6500/G3-300 was creaming the heck out of my 400 MHz IBM PC and was just slightly behind the 800 MHz Dell Dimension!

I don't know a lot about benchmarking, but this seems like a real world benchmark. All the computers were running the same program with no other programs running, all had 128 MB of RAM or more, and yet even though I started the Macs 30 minutes or more after the PCs, they were winning the number crunching.

If the PC is so much faster in performance than the Mac, why was my three year old Power Mac G4/450 able to surpass a three month old PIII 866 MHz laptop?

After witnessing this, I know for certain that there is a Megahertz Myth!

Further Reading

  • SETI@home platform comparison. Pentium/Windows currently averages 21:06:49.6 per work unit vs. 17:41:29.8 for the Macintosh.
  • SETI@home club teams. Team MacAddict #3 among clubs, averaging 15:38:07.7 per work unit. Faster teams tend to be running Linux, not Windows.
  • Team Mac Observer stats. "Low End Dan" has contributed 1,817 units averaging 14:59:51.2 using various Macs and the classic Mac OS, "Low End Mac" has contributed 46 units @ 24:20:36.1 per unit under OS X, and Team 6100 keeps plugging away - 533 units at 108 hours, 52 minutes, 57.4 seconds per unit, every single one done on a 60 or 66 MHz Power Mac 6100.

Share your perspective on the Mac by emailing with "My Turn" as your subject.

Join us on Facebook, follow us on Twitter or Google+, or subscribe to our RSS news feed

Today's Links

Recent Content

About LEM Support Usage Privacy Contact

Custom Search

Follow Low End Mac on Twitter
Join Low End Mac on Facebook

Favorite Sites

Cult of Mac
Shrine of Apple
The Mac Observer
Accelerate Your Mac
The Vintage Mac Museum
Deal Brothers
Mac Driver Museum
JAG's House
System 6 Heaven
System 7 Today
the pickle's Low-End Mac FAQ

The iTunes Store
PC Connection Express
Macgo Blu-ray Player
Parallels Desktop for Mac

Low End Mac's store


Open Link