2.8 Ghz or 3.0 Ghz

elektrotek1 · 06-28-2004, 04:52 AM

I'm looking to build a couple of computers that will be made for number crunching. (Prime factoring numbers hundreds of digits long.) Since it will take months to complete, should I go with a 2.8 Ghz P4, or a 3.0 Ghz P4? Will it really make THAT much of a time difference? Also, would a 800Mhz FSB make the calculating go alot faster than the 533Mhz FSB?

A friend and I are going to be doing some serious number crunching for encryption research. We will be using about six to seven dedicated computers of our own, plus others that want to help out. If you are interested, please e-mail me at joel@elektrotek.biz. My friend is developing software that can be used on dedicated machines and used on machines that are being used. (The program will take over when your screensaver comes on.) Right now he's trying to find an efficient alogrithm that can really speed the calculations up. If you have any ideas, please pass them on to me. Thanks alot.

joel@elektrotek.biz

blacktop89 · 07-01-2004, 06:00 PM

the FSB will make a difference, but the 200mhz jump from 2.8ghz to 3ghz will not have a significant increase in the time it takes to crunch numbers.

**Praetor** · 07-07-2004, 05:24 AM

blacktop89 has it dead on: the antiquated NortwoodB (533) processors were officially "left out in the cold" by Intel in favor of the new Canterwood/Springdale based, 800Mhz processors. The actual clock speed of the 533's is 133Mhz while the actual clock speed of the 800's is 200Mhz -- a big difference.

As for processors, the price jump from 2.8Ghz to 3.0Ghz is not worth the performance jump: you're probably better off with the P4C-2.8 and if you desire the extra performance, getting some fancy cooling and then overclocking it

06-28-2004, 04:52 AM	#1 (permalink)
elektrotek1 New Member Join Date: Jun 2004 Posts: 16	2.8 Ghz or 3.0 Ghz I'm looking to build a couple of computers that will be made for number crunching. (Prime factoring numbers hundreds of digits long.) Since it will take months to complete, should I go with a 2.8 Ghz P4, or a 3.0 Ghz P4? Will it really make THAT much of a time difference? Also, would a 800Mhz FSB make the calculating go alot faster than the 533Mhz FSB? A friend and I are going to be doing some serious number crunching for encryption research. We will be using about six to seven dedicated computers of our own, plus others that want to help out. If you are interested, please e-mail me at joel@elektrotek.biz. My friend is developing software that can be used on dedicated machines and used on machines that are being used. (The program will take over when your screensaver comes on.) Right now he's trying to find an efficient alogrithm that can really speed the calculations up. If you have any ideas, please pass them on to me. Thanks alot. joel@elektrotek.biz

07-07-2004, 05:24 AM	#3 (permalink)
Praetor Administrator Join Date: Jul 2004 Location: Canada Age: 24 Posts: 19,900	blacktop89 has it dead on: the antiquated NortwoodB (533) processors were officially "left out in the cold" by Intel in favor of the new Canterwood/Springdale based, 800Mhz processors. The actual clock speed of the 533's is 133Mhz while the actual clock speed of the 800's is 200Mhz -- a big difference. As for processors, the price jump from 2.8Ghz to 3.0Ghz is not worth the performance jump: you're probably better off with the P4C-2.8 and if you desire the extra performance, getting some fancy cooling and then overclocking it __________________ ASUS P5K Premium WiFi-AP, Q6600@3.7 / ASUS P5ND, E6400@3.8 4GB OCz Platinum XTC 8500 / 4GB CorsairXMS2 6400 5x500GB Seagate 7200.10 / 2x500 Seagate 7200.10 OCz 8800GTX 768MB @ 630/800 / 2x Galaxy 8800GT SLI

Thread Tools
Show Printable Version Email this Page
Display Modes
Linear Mode Switch to Hybrid Mode Switch to Threaded Mode

07-01-2004, 06:00 PM	#2 (permalink)
blacktop89 New Member Join Date: Jul 2004 Location: Albany, Ga Posts: 19	the FSB will make a difference, but the 200mhz jump from 2.8ghz to 3ghz will not have a significant increase in the time it takes to crunch numbers.