Navigate: Advice Beginners BIOS Guide CPUs Links Mainboards Memory Network Storage Video/Sound Cards Contact Forum SiteMap Sponsors WebNews Home	.	.
Prices: Mainboards ABIT ASUS Chaintech Shuttle Soyo Tyan CPU Intel P4 2.4C-800 P4 2.6C-800 P4 2.8C-800 P4 3.0-800 P4 3.2-800 AMD AthlonXP XP 1700+ XP 2000+ XP 2400+ XP 2500+ XP 2700+ XP 3000+ XP 3200+ Athlon64 Athlon64 3200+ Athlon64 FX-51 Opteron Opteron 240 Opteron 242 Opteron 244 Opteron 246 Memory Corsair Crucial Kingston Mushkin OCZ Search Prices:

LOSTCIRCUITS	SHORTCUTS: Top Page Die Shrinks and Leakage Currents Test Setup Amorphium3 Cinebench 2003 I Cinebench 2003 II MDK2 3DMark2001SE Comanche4 Unreal Tournament 2003 X2 Sysmark 2004 Sysmark2004 continued Conclusions Prescott 3.0 Pricing Give Us Some Feedback to Improve our Reviews
Intel Pentium4 "Prescott" To Scale or not to Scale, that is our question.
(Review by MS, May. 23, 2004)

The test platform for all Pentium4 processors was identical in order to avoid any differences caused by either soft or hardware. In short, the identical system configuration was used and only the CPU was changed with the only exception that the same Maxtor DiamondMax9 Plus was used for all Sysmark runs on all testbeds - preceeded by a fresh installation of Windows XP and the necessary chipset drivers.

Benchmarks

There are a number of benchmarks out there that are interesting to look at per se but that are limited primarily by one or the other system bottleneck such as graphics cards or else the I/O performance of the IDE / SATA interface. We ran a number of benchmarks and then decided to show those only that were actually relevant for this report, in that they scale with the CPU frequency as the predominant prerequisite. In other words, it is of no use to show benchmarks that are limited by the one or the other peripheral component and, therefore, will not reflect CPU performance at all. Likewise, some typical system benchmarks like SiSoft Sandra's memory performance don't really add anything when, in reality, we are concerned with CPU performance. One example would be Aquamark3, where, the spread between the fastest and the slowest CPU is in the order of 2 fps - it is not clear where the CPU metric comes from and, therefore, we will leave it out completely.

In short, we focused on CPU-centric benchmarks and threw in one or the other graphics benchmark that does not totally depend on the graphics adapter.

3D Rendering

• Amorphium3
• CineBench 2003

OpenGL Applications**

• Cinebench 2003
• MDK2

D3D Gaming

• 3DMark2001SE
• Comanche4
• UnrealTournament 2003
• X2 Rolling Demo

General Applications

• Sysmark2004

** we decided against using some of the professional OpenGL applications since most of those are solely dependent on the graphics adapter (if done correctly).

next page:    => 3D Rendering =>