Overclocking Results and Heat

One of the most pressing questions that many are asking about the new 90nm processors is how they overclock. Will the die-shrink deliver the kind of headroom seen on the Intel Northwood chips when they were first introduced? Our first tests with the 90nm 3500+ were quite good, so we bought a 90nm 3000+ to see if results were comparable.

 Front Side Bus Overclocking Testbed
   90nm A64 3500+  90nm A64 3000+
Processor: 2.2GHz
512k L2 Cache
512k L2 Cache
CPU Voltage: Default (1.4V) +8.3% (1.52V)
Cooling: Thermaltake Silent Boost K8 Heatsink/Fan Thermaltake Silent Boost K8 Heatsink/Fan
Power Supply: OCZ PowerStream 520 OCZ PowerStream 520
Memory Timings: 2.5-4-4-10 1T 2.5-4-4-10 1T
Memory Voltage: 2.75V 2.8V
Maximum OC: 2610 (+18.6%)
2610MHz (+45%)

As you can see, the 3500+ and the 3000+ both topped out at about 2.6GHz (anticipated FX55 speed) with default or modestly increased CPU voltage and air cooling. This is a decent overclock of about 20% on the 3500+, but the 3000+ reached the same 2.6GHz overclock from a much lower stock speed of 1.8GHz. This means that the new 90nm 3000+ overclocked an outstanding 45% with modest increases in CPU voltage.

The only real difference in overclocking the 3500+ and 3000+ in our tests was that the 3000+ required a little more CPU voltage and memory voltage to reach the same overclocks achieved with the 3500+. This 45% overclock is exciting, and it gives us reason to expect even better headroom possibilities when AMD gets the 90nm process tweaked. Since these two 90nm parts came from different sources and were purchased from dealers, we feel comfortable that they are representative of the 90nm chips available in the market. Overclocking results are never guaranteed, but these first results with AMD 90nm processors are full of promise. If the 90nm 3000+ performs this well in larger samples, it will become the darling of the Enthusiast community.

All Performance benchmarks were repeated at the highest overclock that we could achieve - 290x9.

The Overclocked Performance results are included in the Performance Comparison charts to show the performance headroom found with the new 90nm chips. For better comparison, results are also included for the fastest processors currently available from AMD (FX53) and Intel (560 - 3.6GHz).

Thermal Performance

AMD claims that their 90nm process generates less heat than the 130nm process and requires lower wattages. Of course, the heat that is generated is concentrated in a much smaller area than the larger 130nm die. We will not likely know the true impact of the 90nm shrink on heat dissipation until AMD produces their fastest CPUs in 90nm, so we decided not to run comprehensive heat tests until the faster processors were available in 90nm.

We did check reported temperatures in the BIOS to get an idea of the temperature trends with the new 90nm process. At the same stock speeds, the 90nm and 130nm chips were showing the same CPU temperatures. There was neither improvement from the 90nm nor any indication of running hotter. Overclocked to 290x9, the 90nm parts were 1 to 5 degrees Celsius cooler than a 130nm FX53 chip clocked to the same 290x9. These results are not the objective tests that we will run on high-speed 90nm parts, but they confirmed that the AMD 90nm process appears to run at least as cool as current 130nm processors.

Performance Test: Configuration General Performance


View All Comments

  • gchen77 - Wednesday, March 30, 2005 - link

    Can someone please explain the effects of raising vcore?
    I'm a relatively newbie to overclocking but I remember in the past (with Athlon XPs) raising vcore was almost certain death unless you had water cooling or your pc running in a freezer :)
  • jer - Wednesday, December 08, 2004 - link

    Wesley Fink,

    could u make a screenshot of the Memory tab in CPU-Z of the 90nm A64 3000+ cpu ??

    thx so much
  • Goomzz - Saturday, December 04, 2004 - link

    Just got my winchester 3000+ and my MSI K8N MSI Neo2 Plat. Since it's an x-mas gift can put it together until then. Putting it with Corsair XMS DDR 400 memory. I'll let you guys know how it goes. Reply
  • Goomzz - Saturday, December 04, 2004 - link

  • romano25 - Wednesday, November 24, 2004 - link

    I dont get it...
    1)IS 3500 64 voltage 1.5 Volts?
    2)Looks like the decreased the CPu multiplier on 3500 coz by default it is 11? Why? Does it affect ur performance?
  • romano25 - Wednesday, November 24, 2004 - link

  • bobbozzo - Monday, November 22, 2004 - link

    #82: it's been answered: get a board (MSI) that allows the Memory & FSB to run at an adjustable ratio, so the memory can run slower than the FSB. Reply
  • scius - Tuesday, November 16, 2004 - link

    Cheaper Ram Altnernatives:
    A few other readers have mentioned this, but it seems there hasn't been much of an answer (though a few worthy attempts, notably that the 3200+ is probably a better choice).

    The Question: What ram would let us run at the highest FSB for the least $.

    Obviously you can just buy the faster stuff (DDR500, or whatever), but there must be sticks that, with looser timings(small cost), can let your processor scream(huge gains) while staying relatively stable.

    Anyway, I haven't found any articles about it, but if anyone has, or has some personal experience here, i'm sure we're all eager to hear it.
  • VoodooGamez - Thursday, November 04, 2004 - link

    Great article Wesley! Reply
  • cryptonomicon - Wednesday, November 03, 2004 - link

    great article anand!

    The 90nm process sounds like a great improvement (especially for oc).

Log in

Don't have an account? Sign up now