.09 Athlon 64: Value, Speed and Overclocking
by Wesley Fink on October 14, 2004 12:05 AM EST- Posted in
- CPUs
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 |
1.8Hz 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%) 290x9 |
2610MHz (+45%) 290x9 |
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.
Facebook
Twitter
RSS
89 Comments
View All Comments
slashbinslashbash - Thursday, October 14, 2004 - link
#36 - Athlon 64 processors are unlocked downward, so Wesley was able to go from 11x on the 3500 down to 9x. This downward unlocking allows overclockers to max-out their motherboards and RAM while keeping the CPU running at the same speed. Wesley could have easily achieved the same 2610MHz CPU speed with the 11x multiplier at FSB of 237, but the FSB would have slowed things down.Athlon 64FX processors are unlocked both up and down.
PrinceGaz - Thursday, October 14, 2004 - link
#34- SSE3 support along with other improvements are planned to be added with the E0 revision of the core. The current part is the D0 revision and the only performance improving features are the improved DRAM page closing policy, and second write-combining buffer. They explain why the 90nm parts were slightly faster than equivalent 130nm parts.#35- thanks for pointing out where it says they used a different HSF to the standard retail one. I guess that explains why he was able to put 1.6V in the 3000+ and take it up to 2610MHz without frying it :)
Entropy531 - Thursday, October 14, 2004 - link
#34, look at the CPU-Z screenshot. No SSE3.pio!pio! - Thursday, October 14, 2004 - link
How did you overclock both pieces to 290x9? Dont they have different locked multipliers?fic - Thursday, October 14, 2004 - link
HS used: Thermaltake Silent Boost K8From "Front Side Bus Overclocking Testbed" table in "Overclocking Results and Heat"
IdahoB - Thursday, October 14, 2004 - link
Great article, I'm liking what I see and it's definiately on my hot purchase list.However, I noticed you didn't discuss SSE3 support - I read somewhere else this isn't implemented yet - is that true, and if so when is SSE3 pencilled in for A64s?
tr00p - Thursday, October 14, 2004 - link
I would love for an overclocked SEMPRON 3200+ (939) to be included in this comparison. Initial reviews give this chip high expectations, but I want to see apples-to-apples in a well done review such as this one.SLI - Thursday, October 14, 2004 - link
What about the FX line? Might (have) asked them when they will transition to 90nm? This is important due to the FX having unlocked multipliers (I use Phase-Change and watercooling together so I'm looking to increase multipliers as well as FSB).AlphaFox - Thursday, October 14, 2004 - link
Was the retail HSF used for these overclocks?Also, I dont get why temperatures were not documented... maybe you could list the temps that these CPUs were running under prime95.
Spacecomber - Thursday, October 14, 2004 - link
This information on the overclocking capabilities of the new Atlon 64s is very helpful. The article is much appreciated.It looks like it makes even more important the question of what memories provide the best performance at close to DDR 600 speeds on the Athlon 64 platform. I know this has been addressed looking at the latest PC3200 memories, by Anandtech, but are there other memories with higher speed ratings that might also be considered. For example, what about the Ballistix PC4000; does it pick up where their PC3200 leaves off? Or, is the latest OCZ PC3200 high performance memory that you used the best memory for DDR 600 speeds (or thereabouts) on the NForce3 platform?
Space