Navigate: Advice Beginners BIOS Guide CPUs Links Mainboards Memory Network Storage Video/Sound Cards Contact Forum SiteMap Sponsors WebNews Home	.	.
Prices: Mainboards ABIT ASUS Chaintech Shuttle Soyo Tyan CPU Intel P4 2.4C-800 P4 2.6C-800 P4 2.8C-800 P4 3.0-800 P4 3.2-800 AMD AthlonXP XP 1700+ XP 2000+ XP 2400+ XP 2500+ XP 2700+ XP 3000+ XP 3200+ Athlon64 Athlon64 3200+ Athlon64 FX-51 Opteron Opteron 240 Opteron 242 Opteron 244 Opteron 246 Memory Corsair Crucial Kingston Mushkin OCZ Search Prices:

LOSTCIRCUITS	SHORTCUTS: How many Hoover Dams? Isolating Power Dual Stress Liner Venice Improvements Test Conditions Power/Temperature Coefficient Idle vs. Burn-In 3D Rendering 3DMarks DOOM3 and Prime95 Overclocking & Conclusions Give Us Some Feedback on this Review
AMD Athlon64 "Venice" May Low Power be with you!
(Review by MS May 2, 2005)

Test Setup

*The ClawHammer is the only core with 1MB L2 cache, all other cores only feature 512 kB L2. To put the impact of the larger cache vs. clock speed into perspective, we added numbers for the 4000+ Clawhammer running at an 11x multiplier for 2200 MHz core speed. Since the TruePerformance Initiative rating of current AMD processors only adds confusion, we refer to each CPU by core name and real clock speed.

We used an OCZ Powerstream 520 PSU where the 12V rail was adjusted to exactly 12V.

We used a Fluke 80i-410 AC/DC current probe in combination with a Wavetek Meterman 33XR multimeter to measure current through the isolated +12V supply lines feeding into the CPU VRM. To increase granularity of the measurements, we ran the supply lines in a triple loop through the clamp. The clamp itself was calibrated using a BK Precision model 1692, 30V – 40 A DC power supply. Since there is a temperature dependency of the probe, we monitored the zero-current offset at the beginning of each measurement as well as at the end of each run. If the values drifted during we retook the measurements. Despite these precautions there are possible deviations of the read-out from the real current, however, these errors mostly affect the lower (processor idle) measurements. We estimate that the errors should not be more than 10% at the lower end of the data and less than 5% in the mid and higher data range. Moreover, since the same procedures were applied to all processors tested, there may be an offset in the absolute numbers, however, the relation of the individual cores to each other with respect to power consumption should be fairly accurate (and further matches AMD’s numbers).

Unfortunately, the equipment does not support logging of the current over time, meaning that we had to manually write down the numbers. In applications that are running at steady state conditions, this is not a problem, however, especially in graphics benchmarks, we noted considerable fluctuations of the current draw. In this case, we used the highest sustained value during each run as metric. Also, since we were monitoring the 12V supply current, the actual CPU core voltage does not impact the current / power draw. One additional potential problem concerns the efficacy of the CPU VRM which is something that we could not factor into our final power calculations. Again, since all benchmarks were run on the identical setup, this may impinge the absolute numbers but not the relative differences between the four CPUs tested.

One thing to keep in mind is that the maximum current draw (ICCmax) of any processor can hardly be reached in real life, that is, even at 100 % workload, the processor will draw substantially less current than under worst case scenario conditions that are used to simulate ICCmax and the thermal envelope. Therefore, even if a given processor is rated at e.g. 90W, real life stress tests will maybe able to elicit 70W power consumption.

next page: => Temperature vs. Power =>