Final Words

Based on the tests that we’ve seen here today, AMD’s reluctance to move to higher bandwidth DDR2 offerings makes a lot more sense. The plain fact of the matter is that at the current clock speeds at which the Athlon 64 and X2 line are running, most desktop applications see virtually no benefit from higher bandwidth memory. It is possible that server usage models may show a greater performance boost, but it is highly unlikely for a mission critical server to be equipped with anything that isn’t an officially supported standard - especially memory.

While some have been critical of AMD’s unwillingness to embrace DDR2 when Intel did, it would appear that the quest for more bandwidth simply wasn’t in AMD’s best interests. These Athlon 64 and X2 cores that we have here today are far better suited for use with low latency and lower priced DDR400 than anything that offers higher bandwidth.

Down the road, as CPU speeds and the sheer number of cores goes up, then higher bandwidth memories will definitely make much more sense. But for now, for the majority of the population, these new memory dividers won’t do much for you.

The performance improvements themselves aren’t tangible, but if you are trying to squeeze every last ounce of performance out of your system, then these new memory dividers offer you one more avenue to do so. If you have memory that can run at higher than DDR400 speeds without any reduction in latency, then by all means, explore the new dividers; just don’t expect them to change your life.

The one exception to the rule seems to be heavy multitasking scenarios. As we saw from our simple DVDShrink + Doom 3 test, when you run two very memory bandwidth dependent applications on a dual core processor at the same time, the benefits of these faster memory speeds really starts to show itself. We measured a 6.5% increase in performance in the aforementioned test, but next to no performance improvement in other lighter multitasking scenarios. As we continue to develop our multitasking benchmark suites, we will now start looking at how added memory bandwidth, made possible through these new dividers, changes the performance picture.

Single Core + New Memory Dividers
Comments Locked

37 Comments

View All Comments

  • wien - Monday, July 11, 2005 - link

    #15: It's not like they will stop making s939 CPUs the instant they launch M2. You'll be fine for a couple of years for sure.
  • PrinceGaz - Monday, July 11, 2005 - link

    #13- Lots of mobos support 3.3V RAM voltage. Only problem is they take PC66/100/133 modules rather tahn DDR :)
  • AnnihilatorX - Monday, July 11, 2005 - link

    Well in the end AMD still planned to move to DDR2
    To me they said S939 would last long
    But they are moving to socket M2 and DDR2 next year

    It would have been much better if they stick to s939 and wait for DDR3 instead

    #12 I think it's next year
  • Viditor - Monday, July 11, 2005 - link

    "According to [H] it is the San Diego core which has the improved (fixed) memory controller (see quote below). So do you have to be careful to get San Diego or is Venice ok?"

    San Diego, Venice, DC Opterons, and the X2 all have the improved memory controllers...
  • elecrzy - Monday, July 11, 2005 - link

    #11: how many mobo's do you know support 3.3V+ RAM voltage and how many RAM sticks to you know support DDR500 with 2225 timing?
  • bupkus - Monday, July 11, 2005 - link

    When does AMD's roadmap start using DDR2?
  • JustAnAverageGuy - Monday, July 11, 2005 - link

    A64s aren't bandwidth starved. We knew that much already :)

    When you crank up the HT\FSB speeds you're normalyl trying to get the CPU clock speed up. Dividers just help if the memory can't keep up. :)
    What's with all the OCZ+DFI love going on around here anyway? :)
  • GTMan - Monday, July 11, 2005 - link

    According to [H] it is the San Diego core which has the improved (fixed) memory controller (see quote below). So do you have to be careful to get San Diego or is Venice ok?

    "The San Diego core brings with it some very important things. Primarily, it has what AMD terms as a “more flexible memory controller.” We at HardOCP would prefer to call it a “fixed memory controller.” “Fixed” as in the older one was broken."

    http://www.hardocp.com/article.html?art=Nzg3
  • creathir - Monday, July 11, 2005 - link

    Well, I for one am just GLAD Anand is not dead... was begining to wonder... Maybe you got invited up to Redmond for a little chat due to you article that got pulled? At least you're alive and the M$ob did not get ya...
    Great work on the article. I suppose as long as I do not play BF2 on one screen while rendering a scene in 3DStudioMax on another, I should be fine.
    - Creathir
  • Joepublic2 - Monday, July 11, 2005 - link

    "i remember when ddr400 wasn't official..."

    I do too, DDR333 was intended to be the last speed grade of DDR. Samsung and other memory makers had good yields of DDR400, and were having big problems with DDR2. Those have been fixed, and DDR2 is ready to go, having recently become even less expensive that DDR.

    http://www.xbitlabs.com/news/memory/display/200507...

Log in

Don't have an account? Sign up now