Corsair and Asus Reach DDR2-1066

It was clear in our early testing of the Asus P5WD2 Premium that Asus was interested in showing the standout memory performance of their new 955X motherboard. Toward this end, Asus, Corsair and OCZ all worked on low-latency DDR2 memory solutions that would perform well in the P5DW2.

OCZ and Corsair both supplied low-latency DDR2-667 512MB DIMM pairs for benchmarking with the Asus P5WD2 Premium.

OCZ supplied PC2-5400 512MB EB rated at 4-2-2-8 at DDR2-667.

Click to enlarge.

Corsair supplied their CM2X512A-5400UL.

It was established quickly that both memories could do DDR2-667 at 4-2-2-4 timings on the P5WD2, so we pushed both to DDR2-800. Both ran with complete stability at DDR2-800, at the still aggressive 4-3-2-4 timings. Since neither memory pair had any problem with DDR2-667 or DDR2-800, all benchmarks were run at both memory speeds. DDR2-667 is the rated speed of 955x memory, and DDR2-800 is the next logical speed rating.

The next memory milestone is DDR2-1066, which is an exact 2:1 ratio with the 3.46EE introduced with the 925XE motherboard (Intel CPU is quad-pumped and memory is Double Data Rate). Intel's Pentium D chips are currently based on 800FSB, but the 955X does support 1066FSB. With this in mind, we mounted an Intel 3.46 Extreme Edition with a 1066 FSB.

Click to enlarge.

We were amazed to find that the Corsair CM2X512A-5400UL could reach DDR2-1066. This yielded a Sandra standard bandwidth of just over 6400 MB/sec. To put this in perspective, this is the first motherboard and memory that we have ever tested capable of running at DDR2-1066. Frankly, 1066 required slower 5-5-5-15 timings at the maximum 2.3V available on the Asus. We also needed to push all chipset and bus voltages to the maximum and set CPU voltage at 1.60V to achieve this milestone.

These compromises are reflected in the unbuffered bandwidth of about 3300 to 3400 MB/s. 1066 was the absolute maximum that we could reach and we would not call that speed 100% stable. However, none of these qualifications take away the remarkable DDR2-1066 milestone that Corsair and Asus have achieved.

The OCZ PC2-5400 took a different approach at the top of the performance curve.

Click to enlarge.

The OCZ reached DDR2-1000 on the Asus P5DW2 Premium, but at faster 5-3-2-4 timings.

This yielded slightly slower Sandra standard scores at about 6200 MB/sec.

However, the unbuffered Sandra scores were higher than Corsair at 3500 to 3600 MB/sec.

We'll leave it to the memory manufacturers to argue which is better, since performance of the Corsair and OCZ is essentially the same on the new Asus P5DW2 Premium. However, no matter how you view the results, Corsair has earned the title of fastest memory speed in this round at DDR2-1066. There is also the advantage of being able to run the 3.46EE processor at the full rated speed of 1066 FSB with the memory running at 1066.

nForce4 Intel Considerations

The Asus P5ND2-SLI also had no difficulty in reaching DDR2-800 memory performance. However, one of the marketing points made by NVIDIA is the 1T Command Rate that can be used with the nF4 Intel Edition at DDR2-667. The P5ND2-SLI does indeed handle a 1T Command Rate at DDR2-667, but by DDR2-800, a 2T Command Rate was required for stable operation. On the nF4 Intel platform, the performance impact of a 2T Command Rate appears to be rather small, as the nF4 Intel performance remains very competetive with the 955x as far as it goes. However, at just over DDR2-900, the nF4 Intel appears to hit a wall - with the same memories that do DDR2-1000 to DDR2-1066 on the 955x. As a result, we have no screen captures or results to post for the Asus P5ND2-SLI above DDR2-800.

Memory Stress Testing Test Setup
Comments Locked


View All Comments

  • chawkfan2002 - Thursday, June 2, 2005 - link

    In reading your article you indicate the “Corsair CM2X512A-5400UL could reach DDR2-1066” I am trying to determine how the memory speed is actually DDR2-1066? Your illustration indicates the FSB at 1068MHz (1066MHz) do you have any screenshot that shows the memory speed at 1066MHz? If the FSB is at 1066MHz then the memory bus is only at 534MHz (FSB 1066/4=266 actual speed… Memory bus 266x2=533 Double Data Rate) I have tried the FSB at 266 and manually changed the memory speed to DDR2-800, Memtest+ still shows actual speed at 534MHz

    Any information you can provide on how to achieve the 1066MHz actual memory speed will be most graciously accepted.
  • Makyla - Friday, May 20, 2005 - link

  • ElFenix - Monday, May 16, 2005 - link

    just because a lot of people got it wrong doesn't mean it's right. the first definition is the only proper one. that is like saying that because it is popular, on the internet, to say "he should of done that" means that 'of' is a proper substitute for 'have.'

    as for heat sink, much of that is the same. i suggest you take a look here:
  • ElFenix - Monday, May 16, 2005 - link

    ""a fan doesn't actually cool anything, it just pushes air around"

    Try disabling the fans in your rig and A/C, take temp readings before and after and get back with us. Moving same temp to same temp isn't cooling. Moving cooler air (or water or other) to something that is hotter (chip, compressor, radiator, etc) most definitely actively cools it."

    no, the conducting of heat from the radiator to the air through natural processes cools it. an air conditioner actually moves the heat against the temperature gradient. a fan cannot do that. a fan, again, isn't actually cooling anything. just because there is a moving part moving the air at a faster than natural current does not mean that the cooling is active. it is not. you're still relying on the normal radiator-air interaction. now a peltier actually moves the heat. that is active cooling. a fan only passively cools.
  • Viditor - Thursday, May 12, 2005 - link

    How about this board

    SUPER H8DCE Serverboard ( OEM White Box ) for System only
    Dual AMD Opteron 200 series Processor supported-940 pin ZIF Socket
    nVIDIA nForce Pro 2200 & 2050 Chipset
    Up to16/16/32 GB of ECC Registered DDR 400/333/266 SDRAM
    nVIDIA nForce Pro 2200 & 2050 SATA II controller for 8 SATA ports
    Dual nVIDIA nForce Pro 2200 & 2050 Gigabit Ethernet
    AC'97 audio CODEC high quality 6-channel sound
    2 X PCI-Express x16 + 2 X PCI-Express x4 + 3 X 32 bit PCI

    Dual dual Opterons with SLI...
  • Darth Farter - Thursday, May 12, 2005 - link

    Wesley Fink,

    do you know at what msrp Intel puts them (955/945)?
    also for the nf4(&ati) dual core compatible boards?
  • Wesley Fink - Wednesday, May 11, 2005 - link

    #26 - As we said in the review, we were able to enable SLI on the 955x using the old, almost unavailable nVidia 66.75 drivers. However, none of our SLI-enabled games worked properly. It was our original intention to compare the SLI performance (and we have P5ND2-SLI benchmarks), but the "Semi-SLI" was not completely working. Until the P5WD2 SLI works, and works with readily available drivers, the fact there are 2 x16 slots on the Asus 955x is academic for SLI - a promise for the future.
  • Capt Caveman - Wednesday, May 11, 2005 - link

    Small Win. If you go to Asus's website, they have updated it. They now list two editions of the P5WD2 Premium board and list the Wifi-TV Card as either bundled or optional. Of course, they have yet to email me back. Or offer the Wifi-TV Card.
  • niz - Wednesday, May 11, 2005 - link

    Its a shame that they didn't bother to benchmark comparative SLI performance between the two motherboards.

    I'd like to know whether the diffrerence between the PciE slot timings (x8/x8 and x16/x2-4) really makes any difference to SLI performance.
  • HardwareD00d - Wednesday, May 11, 2005 - link

    They will probably be able to reach DDR2-4096 speeds pretty soon by setting timings to 20-20-20-60 and hooking up a 9v battery to it.

Log in

Don't have an account? Sign up now