|
Advice Beginners BIOS Guide CPUs Links Mainboards Memory Network Storage Video/Sound Cards Contact Forum SiteMap Sponsors WebNews Home |
. | . |
|
Prices: 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 |
|
|
| ASUS P4G8X Deluxe The Black Obelisk | ||
| (Review by MS, December 15, 2002) |
3DMark2001SE
3DMark2001SE is not multi threaded and does not take advantage of HyperThreading, therefore, there is no surprise that the scores come out about even for HT enabled/ disabled. There is a small impact of system memory density on performance but overall, the single DIMM and Dual Channel configurations show a bimodal distribution with the individual scores within each group too close to really call the differences.
As expected, the Single DIMM configurations are slower than the Dual Channel mode. For the record, the same processor / graphics card scored 15403 (HT+) and 15506 (HT-) on the Dual Rambus i850E board but we feel that adding all non-related scores to the charts would add confusion and only dilute the important message.
Comanche4
We'll leave out the higher memory density configurations and just go with a total of 512 MB system RAM. Again, we see a strictly bimodal distribution of scores.
UnrealTournament 2003 Asbestos FLyby
Nothing new in UT2003 either. All in all, we are looking at 7.5 - roughly 10% performance increase in gaming applications based on frame rates (not counting 3DMark with its weighing system).
next page: => ViewPerf =>