The Chips

Launching on the socket 939 platform today are the Athlon 64 3500+, 3800+ and FX-53 CPUs. As we have mentioned in previous news articles, these new CPUs include the 3500+, 3800+ and FX-53. The 3500+ will run at 2.2GHz while the 3800+ and FX-53 will run at 2.4GHz each. Here's a comparison shot of a 940 pinout and a 939 pinout:


This is a socket 940 processor


This is a socket 939 processor

Aside from the difference in packaging, the only new thing about these processors is their on die memory controller. These parts are the first to be equipped with a memory controller that can handle dual channel unbuffered DDR memory. As we have seen, integrating a memory controller on die has been a successful way of maintaining performance for AMD, but the drawback is when AMD wants to make its processors work with a new type of memory: they need to redesign part of the silicon.

Here's a table that lays out the processors and their specifications adopted from one of our earlier roadmap articles:

Current AMD Athlon 64 and FX processors
  Clock Speed Cache Size Dual Channel Unbuffered
Athlon 64 FX-55 (939)
2.6GHz
1MB
Yes
Yes
Athlon 64 FX-53 (939)
2.4GHz
1MB
Yes
Yes
Athlon 64 FX-53 (940)
2.4GHz
1MB
Yes
No
Athlon 64 3800+ (939)
2.4GHz
512KB
Yes
Yes
3700+ (754) ???
2.4GHz
1MB
No
Yes
Athlon 64 3500+ (939)
2.2GHz
512KB
Yes
Yes
Athlon 64 3400+ (754)
2.2GHz
1MB
No
Yes

The questions are next to the 754 pin 3700+ part because we haven't seen one yet, and we didn't run any numbers for that particular configuration.

The 939 pin Athlon 64 parts we know about have 512kB L2 caches, this means that he 3500+ actually has less cache than the equivalently clocked 3400+ 754 pin CPU (the same is true when comparing the 3700+ 1MB part to the 3800+). If we are to expect performance to match the rating system, this means that AMD expects the addition of a dual channel memory controller to more than make up for a halving of the cache.

The slight name change in equivalently clocked parts has had us wondering for a while if we would see the expected increase in performance. With an increase in rating of 100 points for the 3400+ and 3700+, we would expect to maximally see 2.9% and 2.7% increases in performance. Anything around the 2% mark will be enough for us to be comfortable with the new naming scheme, but we certainly don't want to see too many lower numbers.

Normally in testing, we consider a less than 3% margin to be essentially equivalent performance, but this time around we will be paying a little closer attention to any small increases in performance in order to determine whether or not this new performance rating is deserved.

The new FX-53 part number has obviously not changed, as its model number is dependant upon clock speed. We will also not be seeing as significant a performance increase from 940 to 939 pin platforms as upgrading to dual channel from single channel will have a higher impact on performance than moving from registered to unbuffered memory. On the 939 platform, the only performance factor that separates the FX series from the rest of the Athlon 64 line will be its 1MB L2 cache size. Of course, to help maintain its status as an enthusiast part, the FX series will also be completely multiplier unlocked.

But there is a caveat to that as well. With the advent of AMD's Cool'n'Quiet (which is similar in affect to Intel's Enhanced SpeedStep), motherboard makers who choose to implement the technology will be able to offer their users downwardly unlocked multipliers for the Athlon 64 platform. Being able to decrease the multiplier is very important for hardcore overclockers as much higher bus speeds (and thus RAM speeds) are attainable when the core multiplier can be lowered.

What's In A New Socket The Test
Comments Locked

38 Comments

View All Comments

  • Viditor - Saturday, June 5, 2004 - link

    #37 - "Doesn't seem to me to make any sense spending 5 Grand on a 64 bit system until the OS is available?"

    5 GRAND?!?!?!
    What are you PUTTING in there?
    Even the most expensive (FX53) chip is ~$840, and the ASUS mobo is ~$190...
  • tmhartsr - Friday, June 4, 2004 - link

    Hey guys - where is the 64 bit OS? Doesn't seem to me to make any sense spending 5 Grand on a 64 bit system until the OS is available? Also really need PCI Express MOBO. But especially - how about an update on the OS. Perfect opportunity for an Apple OS-64 written especially for the AMD 64?!#*
  • Falco. - Thursday, June 3, 2004 - link

    will the S754/940 heat sink and fans work with 939 ??
  • XRaider - Wednesday, June 2, 2004 - link

    Thanks Viditor, I appreciate it! :) I will have to keep my eyes open on this heat stuff and see what other people will state about this.
  • TrogdorJW - Tuesday, June 1, 2004 - link

    Pretty interesting, but I'm not super surprised by the results. I would imagine that the 3700+ CPU would be about the same distance from the 3800+ as the 3400+ is from the 3500+. Given the prices, I really don't see much reason for celebrating the release (finally!) of socket 939.

    I did some speculation on some other forums about some related issues AMD and Intel seem to be encountering, for any who want to read a longer post:
    http://forums.firingsquad.com/firingsquad/board/me...
  • Viditor - Tuesday, June 1, 2004 - link

    XRaider - To be clear, AMD and Intel actually report 2 different numbers when they talk about heat dissapation.
    AMD reports the MAXIMUM TDP FOR THE WHOLE CPU LINE (both now and in the future...) This means that 104watts is the max thermal design power (the absolute worst it could get) for all 939 cpus at 13nm.

    Intel reports ONLY THE "TYPICAL" TDP FOR THE SPECIFIED CHIP. This means that Intel runs a series of software (they won't release WHICH software they use) and measure the power at that time. They don't report the actual maximum theoretical thermal levels. Intel have a different TDP listed for each processor, and often a different TDP for different stepping of processors.

    So, to answer your question (sorry about the length), while the 939 line of parts have an absolute theoretical max of 104 watts, you will probably see it somewhere in the 80's...
  • mikeymasta - Tuesday, June 1, 2004 - link

    These benchmarks look great, but I REALLY would appreciate it if we could see some OpenSSL benchmarks?
    Because I would love to get my boss to get an AMD based server but hes one of those know all "Intel' is always better type people
    In the server enviroment just an openssl benchmark could turn things around.
    Just install linux or FreeBSD, you could even use a live linux CD so you dont have to install and then just type "openssl speed"
    most linux dists would have openssl in
    /usr/bin/openssl
    /usr/bin/openssl speed > speed_log 2>&1
    to log it to a file
    We are thinking about getting the Sun based AMD
    http://www.sun.com/servers/entry/v20z/ but it costs a lot!

    If you could do that for all new CPU benchmarks I would be very happy.
  • Pumpkinierre - Tuesday, June 1, 2004 - link

    #23 The french site said the spec is 104W and found the heatsink temp (applied above) to be 50C under load and 60C@1.8V overclocking (216MHz) on a 3800+ using a MSI K8Nneo2 (nf3-250) and Asus A8V (K8T800pro). Overall they stated that the cpu ran hot compared to S754 a64s:

    http://www.x86-secret.com/articles/cpu/s939/s939-7...

    Both mobos BIOSs defaulted to DDR333 with 4 double sided DIMMS.

    Xbit say that 104W is the overall spec for S939 but present 130nm cpus stay at 89W TDP (Prescott anyone?). However the temps (cpu diode-Asus A8V)are mildly frightening: 41-64 (idle-load) for the 3800+ but the 3500+ is the coolest 38-58. They even get 40-60C with the 3400+ (but dont quote ambient) which still makes me wonder about the coolness of these cpus. They got the 3500+ to 232MHz FSB and the 3800+ to 215 but didnt quote the voltage. They quoted the same AMD info for the DIMMS:
    http://www.xbitlabs.com/articles/cpu/display/athlo...

    All in all it looks like the heat issues arent confined to Intel biut Cool and Quiet might help out.
  • Pollock - Tuesday, June 1, 2004 - link

    "In the final analysis, we aren't talking about the be all end all of platforms and performance, but, certainly, anyone who wants an Athlon 64 system should look no further than socket 939 for its flexibility, overclockability, and performance."
    I don't remember reading much about overclockability anywhere? Yeah, maybe a statement about the higher HT speed possibly helping, but I want to know more than that!
  • SHO235V8 - Tuesday, June 1, 2004 - link

    Derek, what about the compatability issues and heat issues? Any news on these fronts and when will these parts be available? I have been waiting for the 939 for some time and my desktop gets slower everyday! Thanks ;)

Log in

Don't have an account? Sign up now