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: Names and Confusion Benchmarking Issues Test Configurations Content Creation Office Productivity 3D Rendering Cinebench 2003 FutureMarks Gaming A-D Gaming M-X NX bit Tales More NX bit Tales Surprises and Conclusions Give Us Some Feedback to Help Us Improve our Reviews
AMD Athlon64 4000+
(Review by MS and Jerry Coffin, October 19, 2004)

3ds max 5.1

3ds max is currently at 6.0, however, changes don't influence the performance in the given benchmarks, rather they add features that, for this particular purpose, we are not concerned about. We ran three of the "classic" rendering benchmarks, that is "Underwater Environment", "cballs" and "Single Pipe". In all cases we are looking at runtime in seconds, that is lower scores are better.

Single Pipe

.

Underwater Environment

The difference between the 3800+ and the 4000+ is in the noise and the P4 phalanx takes the undisputed lead

cballs

With a granularity of 1 sec, there was no detectable difference in score between the 3800+ and the 4000+.

3ds max does not discriminate between the two AMD CPUs. We are far from saying that cache does not matter for this application, however, keep in mind that a line-by-line rendering uses non-recurrent data streams and, therefore, the usefulness of the cache is restricted to instructions --- which in turn should fit into the 512kB cache of the Newcastle core with ease.

Amorphium3

Amorphium is a different story altogether in that the entire scene is split into much larger blocks that are rendered "in layers" meaning that the blocks (in this case 1/3 of the total image) is processed through the different procedures. This means that the same data are accessed much more than in 3ds max and consequenty, cache size seems to matter somewhat. However, the bad performance of the Prescott also shows that access latencies, particularly those of the cache make a big difference in the overall picture.

At 2640 MHz, the 4000+ finished in unheard of 511 seconds.

Whereas there was no performance increase for the A64-4000+ over the 3800+ in 3ds max, there was some increase in Amorphium3.

next page: => Cinebench =>