Err, so my question would be, if a p m is slower than p 4, why take the p m? Because its cooler? Whats the difference if neither melts down (I wont exchange hardware nor will i overclock anything) Thx
OK, Master Axe, it seems that you are stuck behind the "MHz myth," the (arguably) mistaken idea that more MHz=performance. I will be blunt and simple.
More MHz does not equal better porformance. Let me back this up with some numbers:
Sisoft Memory Bandwidth (Integer Buffered): This is a test of the amount of data that a given processsor (in a platform identical setup) can move through the RAM channels. Results given in index (NOT a true measurement of actual data, but of the capability to move such data)
Athlon FX-53 (2.4GHZ): 5844
P4 3.4EE(2MB Cache): 5726
Funny how a full 1000MHZ difference can actually give reduced bandwidth measurements. Again:
Athlon FX-51 (2.2GHz): 4986
P4 3.2EE (2MB Cache): 4870
Again, a 1GHz 'faster' processor turning in slower scores
Now, when intel takes the SAME processor, and drops the on-die cache to 1MB, the results are interesting (prior results repeated for reference):
Athlon FX-51 (2.2GHz): 4986
P4 3.2EE (2MB Cache): 4870
P4 3.2E (1MB Cache): 4918
Less cache on the P4 equals better memory banwidth, per these results. Again, the processer that runs a full 1000MHz slower wins.
Now, lets look at this in terms of gaming:
3Dmark2001SE
Athlon FX-53 (2.4GHz): 21469
Athlon FX-51 (2.2GHZ): 21309
P4 3.4EE (2MB cache): 21048
P4 3.2EE (2MB cache): 20714
P4 3.2E (1MB cache): 19153
The two procesors with the lowest "speed" trounced the processors with the higher MHz numbers
Again in real life gaming situations (performed at lower resolution and with eye candy tuirned off to be processor indicative of performance):
Unreal 2003(fps@1024x768, low details)
Athlon FX-53 (2.4GHz): 94.61
Athlon FX-51 (2.2GHZ): 89.79
P4 3.4EE (2MB cache): 76.86
P4 3.2EE (2MB cache): 74.03
P4 3.2E (1MB cache): 65.51
The two procesors with the lowest "speed" trounced the processors with the higher MHz numbers (it's great that I can just copy and paste this )
I took a Pentium M 2.0GHz processor that several have reccommended to you and you have turned down as a "huge speed loss," and tested it in an Aopen desktop Pent-M board, using the same video card and RAM as the other two test setups.
Now, if we take those previous numbers, and compare them to the Pentium M, things get interesting:
Sandra Memory: 5814 (the only one higher is the Athlon FX-53)
3dMark: 21355 (the only one higher is the Athlon FX-53)
Unreal 2003: 79.54 (this one gets beat by both Athlon processors, but still holds its own against the P4s)
My point is is that using MHz to be an indicator of spped is a bad idea. You need to consider other things such as cache, ipc (instructions per cycle), available bandwidth, and of course if you can find real-world data in a gaming situation, even better. Now, these numbers are about from a test that I did about six months ago, so the processors are now considered "last-generation" technology, however, the premise holds true today. AMD now has their flagship FX-55, which sped things up by no longer requiring redistered RAM. Intel's P4 line has moved up to the 3.6GHz chip, and the Pentium M line has moved to 2.13GHz.
Again, keep in mind that the FX and Pentium 4 chips can all easily use 100+ watts of power (and conversely, produce 100+ watts of heat) under full load, while the Pentium M, even in its latest 2.13GHz iteration, the Pentium M 770 that JourneyMan speaks of, produces around 30 watts max.
I hope this helps to enlighten you and to assist in your computer shopping adventures.
Test Setup (for reference):
AthlonFX-53, AthlonFX-51 - Asus SK8V (VIA K8T800 w/ 4.51 Hyperion Drivers ), 1GB (2x512MB) Muskin DDR400 ECC Registered DDR400 (2,3,2,5), ATI 9800XT (ATI Catalyst 3.8 drivers), 40GB Maxtor ATA133 HDD, Windows XP w/SP1 and DX9B.
Athlon64 3400+, A64 3000+ - MSI K8T Neo (VIA K8T800 w/ 4.51 Hyperion Drivers), 1GB (2x512MB) Kingston PC3500 HyperX DDR400 (2,3,2,5), ATI 9800XT (ATI Catalyst 3.8 drivers), 40GB Maxtor ATA133 HDD, Windows XP w/SP1 and DX9B.
Pentium 4 Extreme Edition 3.2GHz & 3.4GHz, Pentium 4 3.2C & 3.2E - Intel D875PBZ (i875P w/ .1012 Intel Inf Drivers ), 1GB (2x512MB) Kingston PC3500 HyperX DDR400 (2,2,2,5), ATI 9800XT (ATI Catalyst 3.8 drivers), 40GB Maxtor ATA133 HDD, Windows XP w/SP1 and DX9B.
Pentium M 2.0GHz - AOpen i855GMEm-LFS (Intel 855GME w/ .1012 Intel Inf Drivers), 1GB (2x512MB) Kingston PC3500 HyperX DDR400 (2,2,2,5), ATI 9800XT (ATI Catalyst 3.8 drivers), 40GB Maxtor ATA133 HDD, Windows XP w/SP1 and DX9B.