Navigate:

Advice
Beginners
BIOS Guide
CPUs
Links
Mainboards
Memory
Network
Storage
Video/Sound Cards

Contact
Forum
SiteMap
Sponsors
WebNews
Home

. .


CPU
Intel
P4 840 D
P4 820 D
P4 630
P4 640
P4 650
P4 660
P4 670

AMD
Athlon64
3500+
3700+
3800+
4000+
X2-3800+
X2-4200+
X2-4400+
X2-4600+
X2-4800+

1-Way Opteron
Opteron 144
Opteron 146
Opteron 148
Opteron 150
Opteron 152

2-Way Opteron
Opteron 240
Opteron 242
Opteron 244
Opteron 246
Opteron 248
Opteron 250
Opteron 252

2-Way Dual Core Opteron
Opteron 270
Opteron 275

nVidia
GF 7800GT
GF 6800GT
GF 6600GT

ATI
R X850 XT PE
R X850 XT
R X800 XT PE
R X800 XT
R X800 XL

Memory

Corsair
Crucial
Kingston
Mushkin
OCZ

What are you
shopping for?







































































LOSTCIRCUITS

SHORTCUTS:
Top page
Registers and Buffers
Blueprints, Components
and Modules

Test Setup, Verification
Sandra, Cachemem
First Results
Some Differences
The Big Difference
Conclusions

Please Give Us Some Feedback

Memory Pricing

 Registered ECC DDR400    
for the Athlon64 FX and Opteron
(Review by MS, October 3, 2003)


Different Platforms, Different Latencies

Probably the biggest selling issue of the Athlon64 in its various iterations is the integrated memory controller to allow reduced latencies on the memory controller level. It is, therefore, quite interesting to see the high memory latencies on modules qualified for this particular platform. Keep in mind that if the controller latencies are lower, the memory latencies weigh in much heavier than in a standard system where the bulk of data access latencies can be attributed to the controller. What we are getting at is the fact that if there is any system to show the impact of latencies on actual system performance, the Athlon 64 FX platform is the prime candidate for doing so.

We have taken the four candidates and run them through a number of different synthetic and more real world benchmarks and the numbers are somewhat surprising, at least compared to what we have become used to in the context of conventional platforms.


Test Configuration

  • AMD Athlon 64 FX-51
  • ASUS SK8N, BIOS revision 1002\
  • ATI RADEON 9800 Pro 128MB / ATI FireGL X1
  • 2 x 512 MB Kingston Registered ECC DDR400 DIMMs
  • 2 x 512 MB Samsung Registered ECC DDR400 DIMMs
  • 2 x 512 MB Legacy Registered ECC DDR400 DIMMs
  • 2 x 512 MB Mushkin Registered ECC DDR400 DIMMs
  • 2 x WD Raptor 10k HDDs RAID 0
  • 1 x Sony DVDRW
  • WindowsXP Pro Corporate Ed
  • Service Pack 1
  • DX9a
  • MS Patch 312135
  • MovieMaker2
  • ATI Catalyst 3.7
  • ATI FireGL drivers 78841
  • all chipset drivers as available
  • SiSoft Sandra MAX3!
  • Cachemem 2.65 MMX
  • Comanche4
  • Aquamark3
  • Cinebench 2003
  • SPEC VIEWPerf 7.0
  • FinalFantasy XI B2
  • 3DMark2001SE

Verification of Settings

It is one thing to set latencies and frequencies in the BIOS, it is a totally different story altogether whether these settings are actually executed. In the past, we have often enough encountered some severe mismatches between the BIOS GUI and the actual settings as they were enabled during system initialization and the ASUS SK8N is no exception here. For example, modules with an SPD that specifies DDR333 will not run at DDR400 even if the BIOS shows it.

Over the past months, we have come to rely on CPUz as a fairly accurate utility to show not only the frequency setting but also the latencies at which the modules are running and we used it here to verify the operating parameters of every single module before we started running benchmarks and further, in between, the reasons will become obvious on the following pages.

       

Click for larger images.

Left: CPUz screenshots of the Mushkin DIMMs running at 2:3:2. Center: all four modules in this round-up were capable of running at 2.5:3:3. Right: The Kingston and the Samsung Modules are running at 3:3:3 by default. Note also that in all cases, the frequency is shown correctly as 200 MHz (clock rate which corresponds to 400 MHz data rate or PC3200 mode)

next page:    => Sandra and Cachemem =>

Click Here!

If you enjoyed reading this article and found it useful, please consider making a small donation to LostCircuits.
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 1998 - 2007 LostCircuits