AMD’s 90nm Athlon 64s have been almost everything that the enthusiast community has wanted them to be. Being little more than a die shrink, the 90nm chips are cooler, can run faster, and are cheaper to make than their 130nm counterparts. But the improvements didn’t stop with the move to 90nm. More recently, AMD has released their Revision E 90nm Athlon 64 cores, which featured a number of small improvements.

One of the biggest improvements to Rev E on paper was the added support for SSE3 instructions, originally introduced on Intel’s 90nm Prescott based Pentium 4. When the Rev E cores had first arrived on the scene, we took a look at the performance improvements offered by SSE3 support and came up empty handed .

There were a number of other improvements made to the Rev E core, including an updated memory controller - boasting support for mismatched DIMM sizes per channel, improved memory access performance for integrated graphics cores and a few other performance tweaks that AMD hasn’t gone into much detail about.

One such barely mentioned improvement was support for a handful of new memory dividers. With an on-die memory controller, AMD has to be particularly careful about adopting new memory technologies, as the wrong choice could leave them with a bunch of CPUs that are basically un-sellable. Over a year ago, AMD had been talking about bringing support for faster than DDR400 speeds to the Athlon 64 - assuming JEDEC would ratify the specifications. AMD waited until the very latest possible moment to decide on whether DDR2 or a faster DDR1 memory controller would be in their future, which is why it took them until just a few months ago to really start talking about DDR2 support. Potentially as a backup plan, the Rev E chips include unofficial support for memory faster than DDR400, without overclocking the Hyper Transport bus.

AMD obviously didn’t speak much about support for these higher speed DRAM options, mainly because they are not official specs, and thus, AMD doesn’t officially support them. But, the fact of the matter is that many folks have faster-than-DDR400 memory, and the new Rev E CPUs can now take advantage of that.

The New Memory Speeds


View All Comments

  • Murthunder - Wednesday, July 13, 2005 - link

    So what is the best memory for good overclocks yet is still stable? I originally tried a pair of Corsair TWINX1024-4000 Pro XMS sticks and my DFI LANParty UT nForce4 Ultra-D board would fail to post. I swapped the XMS for two 512MB sticks of Kingston ValueRam DDR333 c2.5 and my board has been stable ever since and faster than anything else I have. Any suggestions for an OC newbie who can't afford to simply keep trying different sticks until something works? Reply
  • Myrandex - Tuesday, July 12, 2005 - link

    An interesting comparison would be an Athlon64 w/ DDR500 and a close to equivilently clocked Athlon64 w/ the HTT running at 250 to make the memory DDR500. Reply
  • semo - Tuesday, July 12, 2005 - link

    #32, man if i could get those here in the uk (at that price).

    so Zebo, what do you mean that you can't run a64 in sync with memory. for example: if i get those:
    and a dfi lanparty ultra d with a 3000 venice, would i be able to get a decent overclock?
  • Zebo - Monday, July 11, 2005 - link

    It's really a shame anand did'nt do 3-3-3 like 99% of PC4200 sold runs @ 250... Reply
  • PrinceGaz - Monday, July 11, 2005 - link

    Quite right Zebo, what this shows is that even the dual-core A64 processors when running multiple threads get little benefit from faster memory even at the same tight timings. Also as you say there is no such thing as a synchronous memory speed that might provide a performance advantage, as all memory speeds are in reality a divider from the CPU core speed. Running good PC3200 memory at or as much as it'll go above DDR400 2-2-2 is probably the best option. And if you want 2GB, get 2x 1GB modules so you can still run them at 1T command-rate as that's a better bet than four single-sided 512MB modules.

    One thing to bear in mind is if you enable Cool 'n' Quiet, that the memory may actually run faster at the lower CPU multipliers when it is set to other than DDR400 in the BIOS (DDR400 ensures the memory divider is always equal to the CPU multiplier).
  • Zebo - Monday, July 11, 2005 - link

    512 sticks

    1024 sticks

    #31 -- sure at a price, in the case of UTT is a pretty serious one if you ask me.. high volts.. high noise from fans.. high cost.. which may not be best usage of funds.. maybe that $150 saved is better spent on 7800GTX instead of 6800Ultra..or something like that.
  • AdamK47 3DS - Monday, July 11, 2005 - link

    I'm a long time overclocker so a couple percent faster means something. If the option is there and it runs stable then go for it. All these little percentages add up in a heavily tweaked system. Overclocking the video, CPU, memory, and bus can all add up. Reply
  • Zebo - Monday, July 11, 2005 - link

    PS I recommend Crucial sticks (not the 8T).. they have micron G abord..same as Ballistix for half price (but not speed binned so no guarantees).. Search around though.. many many including myself hit 2-2-2 with both 1024 x 2 and 512 x 2 configs. Reply
  • Zebo - Monday, July 11, 2005 - link

    1. Keep in mind anand kept 2-2-2, low latency up to 250Mhz and *still* saw little difference.. fact is only one type, well two if you include anceint but still the best BH-5, can run this bandwidth and latency, Windbond UTT. This ram seems failure prone, watchout! The volts required, eg 3.5+, to attain those LL and bandwidth are extremely dangerous without active cooling on the ram. This ram is also "untested" (UTT) from windbond adding in an extra layer of uncertainty...Add in 2-3x the cost of regualar value muskin/corsiar/OCZ/Crucial which *can* all hit 2-2-2@200 with ~2.8V make this choice pretty lame considering the marginal payoffs. If you like cyber olympics and compete on the margins 0-5% by all means go for it...but 99% of y'all could find much better application of your funds.

    2. All other high bandwidth ram run crappy timings @ 250Mhz which will get stomped by LL @ 200. I've shown in forums you basically need 100mhz extra (not even 50) to hang with 200Mhz 2-2-2 when running ram 3-4-3, aka loose timings. Not worth buyin the high bandwidth stuff either when value muskin/corsiar/OCZ/Crucial which *can* all hit 2-2-2@200 with ~2.8V.

    3. Overclcokers who want to run 1:1... there is no such thing as 1:1 in A64 archtecture.. all memory run async. So no problemo, no performance hit using 166/150/133 memsetting with value muskin/corsiar/OCZ/Crucial and shooting for 2-2-2@200 while clocking CPU to high heaven with proper HTT/FSB adjustments.

    4. We see why AMD is'nt dieing for DDR2 this last year+.. and *when* they finally jump on board it will be at 667 instead of 533Mhz.. They can't afford the performance hit 533 will give, I'd be very surprised if 667 DDR2 is faster for AMD unless you run Crucials which is capable of 3-2-2.

    In sum -- don't believe the hype. Get good cheap safe X2/A64 and DDR -- you'll be fast for a very long time.
  • robster3323 - Monday, July 11, 2005 - link

    Is it possible to measure this stuff on a multi socket board? One of AMD's big selling points of HyperTransport is that other CPU's in other sockets can get to other memory faster. I wonder what impact these faster memories would have on socket to socket memory access?
    In other words socket one is direct connected to mem slot 1, the data in mem slot one is needed by a CPU in socket two, transiting the Hypertransport. How much benefit do the faster memories present?

Log in

Don't have an account? Sign up now