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:








































































































































What are you
shopping for?



































































































































































LOSTCIRCUITS

SHORTCUTS:
A Darwin Award
Prelude to a Bug
Virtualization and TLBs
A Band Aid and a Patch
Phenom Specs
The Spider Platform
Test Configurations
ASUS M3A32-MVP and AOD
Memory subsystem
CPU Power Consumption
TrueSpace and Power Efficiency
Cinebench
DVD-Shrink, MainConcept
VirtualDub/DivX
3DMark'06
FarCry
F.E.A.R.
World In Conflict
Crysis
UnrealTournament3
NB Frequency: Does it Matter?
The Secret of AOD
Final Analysis

Give Us Some Feedback on this Review

 AMD's Phenom Processor - Beyond Erratum 298
(Author: Michael Schuette, January 1, 2008)

The Final Analysis

It took about 5 weeks of trying things out, reading up on other things, trying more things, and throwing away the results to finally figure out to at least a limited degree what is going on with Phenom. And the Spider platform. There was beta hardware, beta firmware, and beta software, there were different motherboards and whenever things started to make sense, there was that one or the other little tidbit that did not fit into the grand picture causing us to go back and recheck our data. By the end of the day --- no it was way more than a day and a lot more midnight oil, too --- we consumed over 10 grams of thermal grease just for changing CPUs back and forth. And we did not even measure the average hard disk transfer rate. But then, you see, a hard disc has a specific platter geometry and the average read performance of any drive is solely defined by the area density of data, depth of the platter and rpm and completely independent of the platform unless the methodology is incorrect. Nor did we apply Hook’s spring constant to figure out force-dependent displacement of the motherboard depending on the weight of the heatsink… well, I digress, those numbers would be off-topic anyway.

What we did was to try to get an idea of where AMD’s Phenom CPU could be placed in the current CPU landscape. Initially, we didn’t have very high hopes, especially after reading some of the early reviews. Then we started digging and, to be sure, Phenom is not a diamond in the rough, but it turned out to be better than what we anticipated.

The 9600 Black Edition is most certainly the better choice, even though it caps out at about 2.6 GHz, the performance is identical to the Phenom 9900 and the power consumption and heat dissipation are considerably lower.

Arguably, there is that thing called legacy support and legacy applications are still prevailing in today’s computing environment. On the other hand, there are truly multithreaded applications and as it turned out, the more thread level parallelism is used in any application, the better fared the Phenom processor. There is a bit more to this. Multicore processing is fine and dandy as long as the access to the data is warranted. Otherwise, there is starvation of the cores. One way of dealing with this situation is the use of FBDIMMs and independent channels with full duplex configuration to allow independent access of data with simultaneous Reads and Writes on separate channels.

Another way to go, and probably a more elegant solution is the use of dual independent DRAM controllers in “unganged” mode. Naturally, there is a potential drawback in that the 128 bit “ÜberDIMM” as we have come to know most currently existing “dual channel” in “dynamic mode” solutions no longer exists. Realistically, however, this is not a problem at all and never has been because aside from doubling the data width on every access, this type of dual channel mode has never proven to add much in terms of performance.

What it boils down to is that there is a tremendous potential embedded in Phenom that does not come into play with the existing software infrastructure. Particularly single threaded games are a lost cause and unfortunately, this is still the standard of the industry. UnrealTournament3 in this respect is a milestone also for the gaming industry and there are other games to follow in the same footsteps that employ more artificial intelligence and PhysX effects, which will cause most dual core processors to choke. But then, there is also the problem of the GPU limitations. Well… as long as nVidia still has high end cards ….


(AMD Phenom 9600 2.3GHz
(HD9600WCGDBO))

next page: => More =>

All advice and educational articles on LostCircuits are free, but if you feel you can, please make a small donation to us!
Thank you!

General disclaimer: This page only reflects the author's personal opinion and assumes no responsibility whatsoever regarding any of the contents or any damages that may occur explicitly or implicitly from reading the contents of this site. All names and trademarks mentioned in this review are the exclusive property of the respective parent companies.
All contents of this site are protected by international copyright laws. Reproduction of the contents even in parts is not allowed except after written permission by the author and referral to this site.
Copyright 2002 - 2008 LostCircuits