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)

NXTest

According to the recommendations made by AMD we used Robert Schlabbach's NX test (Version 1 March 5th 2004) to test the functionality of the No eXecution bit. We installed Windows XP with Service pack 2 and ran the 32-bit version of NXTest also known as Data Execution Prevention (DEP) test.

The result was somewhat surprising to say the least and we will have to take it to AMD for further discussion and, hopefully, an update of the situation. Suffice it to say that the system met all requirements listed.

Update

According to the information we gathered over the last day, one of the differences between the first release candidates of SP2 and the final version is that DEP needs to be enabled in the Control Panel:

Aftter that the system needs to reboot (which makes sense since there is a fundamental change in the memory management as performed by the operating system.

If NX Test is run subsequently, several loops of the following error messages appear:

We can only speculate about the reasoning behind the decision for not enabling DEP by default any more with the "retail version" of SP2, however, suffice it to say that we experienced spontaneous reboots of the system during the test and that may happen under other circumstances as well.

Conclusions

Another day, another processor and finally a new name suggesting yet another performance bump for AMD, thereby extending their leadership. If we summarize everything, we end up a bit short of our own expectations since in reality there was hardly any increase in performance of the 4000+ over the 3800+. Suffice it to say that the mere requirement of having to clear the CMOS on the test board offers a bit of an explanation. On the other hand, we do feel quite comfortable about the benchmark results since they fell right where we expected them. Not every application will take advantage of increased cache size and that is where the performance has to stem from increased clock speed. In the case of the Athlon64 3800+ vs. 4000+ this difference does not exist.

In so far, one might question whether the 4000+ moniker is justified compared to the 3800+. If we look at the different application types, we find three distinct categories:

• System applications like Sysmark2004 -- Hardly any difference in overall performance
• 3D Rendering like 3ds max: -- the difference is practically non-existent
• Gaming applications: -- a small increase in performance that is mostly negated by the GPU limitations.

next page: => To Be Continued =>