Page 1 of 1
Processor issue
Posted: Wed Jan 17, 2007 4:06 pm
by pedromsouza
Which one is better?
Pentium M or Pentium 4 M?
Are there any differences?
Posted: Wed Jan 17, 2007 4:15 pm
by pianowizard
Pentium M is much faster and draws less power. See
http://www.systemshootouts.org/processors.html
Posted: Wed Jan 17, 2007 4:29 pm
by pedromsouza
I thought Pentium 4 m was better. But, is it better than a modern Celeron processor?
Posted: Wed Jan 17, 2007 9:53 pm
by kulivontot
Pentium M is a far more efficient and capable processor than a Pentium 4-M. Odds are that you can get equivalent performance out of a Pentium M processor with a lower clock speed than with a Pentium 4-M, and at the same time have a battery life greater than an hour. Both, however, are far superior to any celeron derivative.
Posted: Wed Jan 17, 2007 9:55 pm
by christopher_wolf
kulivontot wrote:Pentium M is a far more efficient and capable processor than a Pentium 4-M. Odds are that you can get equivalent performance out of a Pentium M processor with a lower clock speed than with a Pentium 4-M, and at the same time have a battery life greater than an hour. Both, however, are far superior to any celeron derivative.
That's pretty much it; you will get more not only more performance per watt out of a Pentium M, as opposed to a P4-M, but also significant;y more total performance as compared to a P4-M of the same clock frequency. Also, the site that Pianowizard posted is a pretty good guide to such things.

Posted: Wed Jan 17, 2007 10:06 pm
by pianowizard
christopher_wolf wrote:Also, the site that Pianowizard posted is a pretty good guide to such things.

Of course, it was you who found that site several weeks ago!
Posted: Thu Jan 18, 2007 6:14 am
by tomh009
kulivontot wrote:Pentium M is a far more efficient and capable processor than a Pentium 4-M. Odds are that you can get equivalent performance out of a Pentium M processor with a lower clock speed than with a Pentium 4-M, and at the same time have a battery life greater than an hour. Both, however, are far superior to any celeron derivative.
Exactly. This is basically because Pentium M is based on Pentium III, which was a more effective (but less scalable in the end) design than its successor.
Those of us old enough to remember the Pentium 4 launch back in 2000 will recall that the Pentium 4s were power-hungry but in spite of the 1.5 GHz clock speeds they struggled to match the performance of the older Pentium IIIs.
The P6 architecture (as used in the Pentium Pro and later in Pentium III and Pentium M) was IMHO one of the most effective ever done by the company, and far more impressive in its longevity, too, than the NetBurst architecture of the P4.
It's worthwhile to note that the P6 design team developed the new Core architecture, and while there are NetBurst influences in Core, the new design probably owes more to P6 and Pentium M than to the NetBurst and Pentium 4.
Posted: Thu Jan 18, 2007 10:34 am
by leoblob
tomh009 wrote:This is basically because Pentium M is based on Pentium III, which was a more effective (but less scalable in the end) design than its successor.
Can you explain this a little more?
Posted: Thu Jan 18, 2007 1:53 pm
by tomh009
There is a good explanation on Wikipedia:
http://en.wikipedia.org/wiki/Pentium_M
To wit:
"The Pentium M represents a new and radical departure for Intel, as it is not a low-power version of the desktop-oriented Pentium 4, but instead a heavily modified version of the Pentium III Tualatin design (itself based on the Pentium Pro core design). It is optimised for power efficiency, a vital characteristic for extending notebook computer battery life. Running with very low average power consumption and much lower heat output than desktop processors, the Pentium M runs at a lower clock speed than the laptop version of the Pentium 4 (The Pentium 4-Mobile, or P4-M), but with similar performance - a 1.6 GHz Pentium M can typically attain the performance of a 2.4 GHz Pentium 4-M."
Posted: Thu Jan 18, 2007 2:59 pm
by pedromsouza
P4 - M is better then Sempron? And Turion?
Posted: Thu Jan 18, 2007 3:08 pm
by tomh009
Sempron and Turion are a whole different kettle of fish as these are AMD CPUs rather than Intel ones. In general, Sempron is a low-end desktop CPU comparable to the Intel Celeron, whereas the Turion is a mobile CPU -- and the current Turion X64 is generally comparable to an Intel Core 2 Duo.
Posted: Thu Jan 18, 2007 5:33 pm
by leoblob
Everything I've read about the Tualatin processors is so highly favorable, I can't help but think that the first-generation P4's were a step backward. Why didn't Intel continue to develop the Tualatin processors? I think I read they still had the potential for even higher clock speeds than the 1.4GHz where they stopped making them... ??
Posted: Thu Jan 18, 2007 7:47 pm
by tomh009
At the time I think their clock speeds were limited by the then-current 130 nm manufacturing process. Dothan made it up to 2.1 GHz but that was in 2004 when the 90 nm process was available.
Back in 2000, though, the Athlon was about to speed past the P3, so Intel was forced to switch to the P4 architecture to respond to AMD's performance advantage.
Posted: Thu Jan 18, 2007 8:01 pm
by jdhurst
Forgetting all the tech stuff, side by side a 1.3GHz T41 PM 4200-rpm drive (I still have it) is faster than a 2.0Ghz T30 P4M 5400-rpm drive (I had one). I later put a 1.8Ghz CPU and 7200-rpm drive in the T41, and still service T30's as spec'd above. The difference is very noticeable. ... JD Hurst
Posted: Thu Jan 18, 2007 10:22 pm
by leoblob
tomh009 wrote:At the time I think their clock speeds were limited by the then-current 130 nm manufacturing process.
This is one of the things I don't understand. When Intel came out with the P4 and the P4-based Celeron, they went back to using the 180 nm process again (up to 2GHz for the P4)... then used a both the 180 and 130 nm for a while, with the 130 nm process continuing to be used in some P4s up to 3GHz... ??
Why all this back-and-forth stuff? (and I'm speaking about the desktop side... sorry that this is off-topic)
Posted: Thu Jan 18, 2007 10:30 pm
by tomh009
The first P4s (and P4-based Celerons) were 180 nm, and then switched to 130 nm with Northwood. Prescott (the final P4) was 90 nm.
I don't recall Intel introing new chips at 180 nm after going to 130 nm, but I may have selective memory here.

Posted: Thu Jan 18, 2007 10:48 pm
by leoblob
I just refreshed my own memory over at Intel's site

, and it looks like the 400MHz FSB P4s with 256K cache were done in 180nm and the ones with 512K were done using 130nm. I still wonder why they went back to the 180 nm process at all, after the success of the 130nm Tualatins...?
Posted: Fri Jan 19, 2007 2:38 am
by kulivontot
tomh009 wrote:Sempron and Turion are a whole different kettle of fish as these are AMD CPUs rather than Intel ones. In general, Sempron is a low-end desktop CPU comparable to the Intel Celeron, whereas the Turion is a mobile CPU -- and the current Turion X64 is generally comparable to an Intel Core 2 Duo.
Just so we are clear, there is a Turion 64 chip, which is somewhat older and contains only a single processor and also a Turion 64 X2 chip, which is a low-voltage dual core chip similar to a Core Duo Chip. Just as Pentium M and Pentium 4-M may be confusing to people, I think it would be easy to confuse these two turion chips as well.
Posted: Fri Jan 19, 2007 5:49 am
by tomh009
Right. The older "base" Turion is single-core but still 64-bit capable so it's most closely compared at the technical level to a Core 2 Solo -- though in practice such beasts are rather rare.