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

  • Wesley Fink - Tuesday, October 11, 2005 - link

    The published "ram guy" link is the one printed on the Corsair retail package. We also tried the link and it connects to the Corsair Help Forums.

    If you have another link please list it in the Comments.
    Reply
  • Madellga - Tuesday, October 11, 2005 - link

    I am using this OCZ kit (EL, not the one in the review) since August on a San Diego / DFI combo. It goes to 230@2.5-3-2 with 2.7V and 1T.

    I tried also 4 sticks (a friend bought it also) and we made to 220@2.5-3-2 with 2.7V and 2T.

    I didn't try above 230, as the OCZ Guy pointed the 230 to be the limit. I am using 180/200 or 166/200 to overclock the San Diego, leaving the memory between 220-230.

    It is rock solid, it can Prime all night without mistakes.

    I prefer to have more memory even if a bit slower - it is much worse to have Windows writting to the swap file.
    Reply
  • ElFenix - Tuesday, October 11, 2005 - link

    just to see how much the difference is when going from 1 gig to 2 gigs Reply
  • Wesley Fink - Tuesday, October 11, 2005 - link

    We tested many applications with 1GB vs. 2GB of ram. BF2 greatly benefited, but nothing else we've tested so far really improved much with 2GB. That will likely change with the release of newer, more demanding apps and games that take advantage of the new dual-core processors.

    One High-Performance memory company told us that after they saw what 2GB did for BF2 they ran 1 vs 2 on every game they could get their hands on. The goal was to publish benchmarks to show the advantage of buyers using 2GB instead of 1GB - and sell more memory. They privately told us they also found no real performance improvement in anything other than BF2.

    We do expect 2GB/4GB will make a difference in multithreaded and true 64-bit apps in the future. Of course multi-tasking also normally benefits from more memory.
    Reply
  • Johnmcl7 - Wednesday, October 12, 2005 - link

    The only other game I've seen people recommending 2GB for is the FEAR demo but of course it's not final yet.

    Good read though, I thought the discussion on the A64 and the various ram issues was particiularly useful.

    John
    Reply
  • Margalus - Wednesday, October 12, 2005 - link

    2Gb make a good difference in WoW also. Reply
  • Vesperan - Wednesday, October 12, 2005 - link

    Wesley,
    the memory combinations on the 'Why 1GB Dimms?' page could be shown as a 2x2 matrix (with 2/4 dimms on one axis and 1T/2T on other). Performance at each combination could be shown - except of course for 4 dimms at 1T. Currently the article contrasts the 2 dimms and 1T combination with 4 dimms and 2T, could it be possible for you to add 2 dimms at 2T?

    I would just like see the effect of 1T to 2T, or 2 dimms to 4 dimms ceterus paribus - that is, all else being equal. While I dont think the missing combination (2 dimms at 2T) will undermine your arguments made, I would like to see how it fits into the overall picture.
    Reply
  • Phantronius - Tuesday, October 11, 2005 - link

    I did, BF2 runs so much better as a result Reply
  • Phantronius - Tuesday, October 11, 2005 - link

    1st!!! Honestly, since i've given up overclocking, I threw in 2 1gig Platnium Corsair XMS modules in my new Athlon 64 setup and it works fine and stable, couldn't give a shit if my "timings" are as *looot* as they could be. Reply
  • DigitalFreak - Tuesday, October 11, 2005 - link

    Well good for you Reply

Log in

Don't have an account? Sign up now