Why 1GB DIMMs?

In past memory reviews, we have said a lot about the impact of the 2T Command Rate on memory performance. We have speculated with others that the Rev. E AMD processor would remove the 2T requirement for 4 DIMMs, but in fact, the release Rev. E still required a 2T Command Rate with 4 DIMMs on the new on-CPU memory controller. So, what is the impact of going from 1T with 2 DIMMs to 2T with 4 DIMMs?

Here, you see tests of 2 vs. 4 DIMMs of our standard OCZ PC3200 Platinum Rev. 2 based on Samsung TCCD memory chips. In all tests, the timings were 2-2-2-7 and the only difference was the 1T Command Rate with 2 DIMMs and 2T with 4 DIMMs:

Quake3 fps Sandra UNBuffered Sandra Standard Buffered Super PI 2M places
(time in sec)
Wolfenstein - Radar - Enemy Territory fps
2x512MB
2-2-2-7
2.6V 1T
550.2 INT 2621
FLT 2738
INT 5984
FLT 5938
80 121.1
4x512MB
2-2-2-7
2.6V 2T
529.6 INT 2276
FLT 2362
INT 4925
FLT 5938
83 116.9
1T Performance Increase 3.9% 15.5% 21.1% 3.8% 3.6%

For best comparison, we reran all benchmarks with the exact same settings for 2 DIMMs and 4 DIMMs, the only difference being 1T or 2T timings. We could have achieved faster timings (and a bigger performance difference) by tweaking each set of tests for best bandwidth. Therefore, these should be considered best case (lowest) performance differences.

As you can clearly see, the memory-only Sandra tests show a 21% drop in memory bandwidth in the standard buffered test when reducing to a 2T Command Rate. The more real-world Unbuffered Sandra test still shows a 15.5% bandwidth drop. Games and Super Pi, where memory is just one small component of the overall result, show about a 4% performance reduction. These represent the impact of this memory change on the overall system performance, where the Sandra scores measure impact on memory alone.

The second area where 4 DIMMs have a significant impact compared to 2 DIMMs is overclocking. This won't matter to those who run their systems at stock speeds, but it will be very important to those who try to squeeze the best performance from their memory. Here, we compared overclocking with our stock OCZ PC3200 Platinum Rev. 2 with 2 and 4 DIMMs. Again, we kept timings and settings exactly the same.

Highest Overclock at 9X Ratio
(4000+ Rev. E)
2x512MB
2.5-4-3-7 1T
318 (DDR636)
4x512MB
2.5-4-3-7 2T
240 (529.6)
2 DIMM Performance Increase 295%

Using the same DIMMs and same timings, we could only reach a 240 Processor Clock or +20% with 4 DIMMs. Two DIMMs allowed an overclock to 318 or +59%. With two DIMMs, we could overclock almost 3 times higher than with 4 DIMMs. You can likely overclock a bit higher with 4 DIMMs by further tweaking memory timings, but 4 DIMM overclocking will always fall far short of 2 DIMMs on current Athlon 64 memory controllers.

Higher performance at 1T vs. 2T and higher overclocking potential are certainly strong motivations to use 1GB DIMMs instead of 512Mb DIMMs when you want to populate an Athlon 64 board with 2GB. However, the gain of 1T in the past has often been more than offset by the slow memory timings available on 1GB DIMMs. The Athlon 64 controller is much lower latency than current Intel solutions, and thus, is much more bandwidth-sensitive to memory timings than a comparable Intel solution. We have shown in past memory reviews that slower memory timings can more than offset the 3.6% to 3.9% real-world performance loss that results in 4 DIMMs at 2T Command Rate. However, the availability of DDR400 1GB DIMMs rated as fast as 2-3-2 at DDR433 certainly has the potential to change this picture.

Index Impact of Athlon 64 Memory Controllers on 1GB DIMM Performance
POST A COMMENT

40 Comments

View All Comments

  • woodspire - Thursday, June 29, 2006 - link

    What happen if instead of using 4x 512 memory you use 2 x 512 and 2 x 1024. Same speed (PC-3200), same timing, and even same brand.

    Still acheving dual channel ?
    Reply
  • qquizz - Saturday, December 10, 2005 - link

    Sounds great and all but a query at Pricewatch brought up a blank.
    Where can you buy the OCZ PC4000 EB Platinum Edition
    Reply
  • Hurricanesan - Friday, November 11, 2005 - link

    I'm looking for 2Gb memories for my new computer.
    I had an hard time choosing between the Corsair 3500LLPro and the OCZ 1024MB EB Platinum.
    This morning, I've noticed this test. Since the OCZ was able to go up to 500Mhz and I plan using an A8N32-SLI, the choice looked easy.
    But a friend of mine pointed out an old story in which OCZ was giving very good sample to the press and lesser products in the shops. I've looked about that story and now it seems to me that OCZ is really unstable in its production and not very clean ... or used to be.

    I would really not like to buy those memories and find that they can't stand their specification.

    Since right now it seems that both the Corsair and the OCZ are not available in stores less that 2 hours plane from me, I have a week to make up my mind.

    If anyone can help me balance one way or the other, please post.

    Reply
  • KriegsMaschine - Tuesday, November 29, 2005 - link

    OCZ is the best brand I'd say. I currently have Corsair Twinx C2Pro "2x512 ddr400 Cas 2.5" and it's good... but WAY TOO expensive for it's quality. You pay too much for the brand like you would by getting a cloth from a designer. OCZ have the best performance while having reasonable prices and quality stuff for Value, Mainstream and High-End. Their tech support is very good too, as all their products. My next PSU will be OCZ ModStream 450watts.

    Nice article. I was thinking these days about going from 2x512 to 4x512 with my Athlon64 since it's less expensive than 2x1Gb and generaly have better timing but after reading that 1T Command was impossible with 4 DIMMS... I changed idea!


    What would had been nice for the review would had been some more real game benchmarks. I mean not old stuff like Quake 3 because who care to have +20fps when you already got 550! Some newer stuff such as UT2003, FEAR, BF2, FarCry, HL2 would had been a better choice. To me those SuperPi, SandraMark... means almost nothing. All I want when getting such expensive rams is more FPS in games. Comparing 2x1Gb in 1T Command vs 2x1Gb in 2T Command would had been better too because don't you think 2x512Mb vs 2x1Gb is unfair? 0_o
    Reply
  • Shimmishim - Wednesday, October 12, 2005 - link

    what the heck? no 2x1 crucial ballistix? wow. i have a set that can do 290 mhz 1:1 with 3-3-3-7 timings and only 2.8 volts. Reply
  • leexgx - Saturday, November 05, 2005 - link

    do not think it was out then (or it was not sent to anandtech)

    i just got the Crucial 2GB DDR PC4000 Ballistix from overclockers and its less then £200 for this week only (norm £240) (got the A8N-SLI premium as well)

    i good to see that Ballistix stuff can do that

    i probley just set me X2 3800+ at 250 so me ram is doing the same (got it at 241 now on the cpu it norm runs at 200 so its an 410mhz oc {4600+ x2})
    Reply
  • ricleo2 - Wednesday, October 12, 2005 - link

    After some recommendations from the forum here, I just got 2 sticks of GSKILL PC4000 at one gig apiece to replace my OCZ 2 sticks at 512 Megs apiece in my MSI K8N SLI PLATINUM. After comparing benchmarking results, before and after, it was not even close. RMA already approved from NEWEGG. Reply
  • phidjit - Wednesday, October 12, 2005 - link

    It's 1024, with 2-3-2-5 timings and runs at DDR433, it seems like it would have been a better comparison to the Corsair "CMX1024-3500LL PRO" (also 1024, DDR443, but 2-3-2-6 timings).

    Anyone seen benchmarks for the gigaram mach10000?

    It looks like it could be a bargin.

    phidjit
    Reply
  • qquizz - Wednesday, October 12, 2005 - link

    These are the type of articles I come to AT to get. Thanks Wes. Reply
  • znir - Wednesday, October 12, 2005 - link

    Thanks for the information in the review. however, i think it would be good to see result of 4x512MB high performance sticks like the OCZ PC4000 VX. Reply

Log in

Don't have an account? Sign up now