|
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 |
LOSTCIRCUITS |
SHORTCUTS:
The Multiplier Legacy Validating the New, Supporting the Old Apples to Apples and Clocks to Clocks System Disclosure, SiSoft Sandra Memory PCMark2002, A Different Perspective Benchmarks that won't: CodeCreatures, Comanche4 SPEC ViewPERF and diminishing returns Fraggin the Quake3 Arena Scores Expendable and the Chipset Frequency, 3DMark2001SE 3DMark2001SE: Behind the Looking Glass Profiling Performance, Will Barton Challenge Hammer? AMD Processor Steals |
| 333 MHz FSB for the Athlon The Unkept Promises | |
| (Review by MS, September 2, 2002) |
3D Benchmarks
Many 3D applications are hampered by the bottleneck of the AGP card, rather than by memory or CPU performance that can provide the icing on the cake but not really change the fundamental performance characteristics within the given application / graphics card combination / confrontation. Suffice it to say that this kind of application is not appropriate to evaluate sub-system performance of individual components.
CodeCreatures
CodeCreatures 1024x768. There is a minor and reproducable difference between the different settings but it is nothing to write home about since the margins between the fastest and the slowest configuration is less than 1%
It is really important here to stress the fact that only a minority of application uses streaming data transfer mode, the rest are a mixture of random and "interrupted" in page access, where interrupted means that cache accesses may negate in page accesses and / or eventually lead to page expiration.
NovaLogic Comanche4
Comanche4 depends on raw CPU speed as well as memory bandwidth but only to a lesser degree to the latter. Roughly 2-2.5% performance increases from one setting to another are somewhat negligible in view of some 63 fps we achieved on a higher clocked P4 platform. Keep in mind though that the benchmark appears to favor the P4 (in this case running at 3.15 GHz) and that further the Athlon was underclocked to allow comparable clock speed at variable bus frequency settings.
If there are hardly any differences in these applications, is it even worth going the extra mile to validate the new platforms? There is a very simple answer to that, bottlenecks are bottlenecks that cannot be overthrown by anything in front or back of them, however, there are other applications that will reveal the advantages / drawbacks of the different configurations.
next page: => ViewPerf 6.1.2 =>
