Testing 35 AMD Processors

Ad

Altogether, we measured the energy consumption of 35 different AMD processors. Among them are two Phenom models, 16 classic Athlon 64 X2 versions with different steppings, six "Energy Efficient" CPUs, six Sempron 64 processors, the older Athlon 64 FX-62, the famous BE-2350, as well as the three new "e"-Models of the 4X50 series.

35 amd cpus

The following chart shows core voltages of the different processor models that were measured on the MSI K9A2 Platinum motherboard.

AMD Processors Tested
Processor Clock Rate Tension Stepping Process Core
Phenom 9600 Black Edition 2.30 GHz 1.250 V B2 65 nm Agena
Phenom 9500 2.20 GHz 1.250 V B2 65 nm Agena
Athlon 64 X2 6400+ 3.20 GHz 1.248 V F3 90 nm Windsor
Athlon 64 X2 6000+ 3.00 GHz 1.408 V F3 90 nm Windsor
Athlon 64 X2 5600+ 2.80 GHz 1.408 V F3 90 nm Windsor
Athlon 64 X2 5200+ 2.60 GHz 1.408 V F3 90 nm Windsor
Athlon 64 X2 5000+ 2.60 GHz 1.408 V F2 90 nm Windsor-512
Athlon 64 X2 4600+ 2.40 GHz 1.304 V F2 90 nm Windsor-512
Athlon 64 X2 4200+ 2.20 GHz 1.304 V F2 90 nm Windsor-512
Athlon 64 X2 3800+ 2.00 GHz 1.304 V F2 90 nm Windsor-512
Athlon 64 X2 5400+ 2.80 GHz 1.304 V F3 90 nm Windsor-512
Athlon 64 X2 5000+ 2.60 GHz 1.352 V F3 90 nm Windsor-512
Athlon 64 X2 4600+ 2.40 GHz 1.352 V F3 90 nm Windsor-512
Athlon 64 X2 3800+ 2.00 GHz 1.352 V F3 90 nm Windsor-512
Athlon 64 FX-62 2.80 GHz 1.352 V F2 90 nm Windsor
Athlon 64 X2 5200+ 2.60 GHz 1.408 V F2 90 nm Windsor
Athlon 64 X2 4800+ 2.40 GHz 1.408 V F2 90 nm Windsor
Athlon 64 X2 4400+ 2.20 GHz 1.408 V F2 90 nm Windsor
Athlon 64 X2 4000+ 2.00 GHz 1.408 V F2 90 nm Windsor
Athlon 64 X2 5000+ EE 2.60 GHz 1.408 V G1 65 nm Brisbane
Athlon 64 X2 4800+ EE 2.50 GHz 1.352 V G1 65 nm Brisbane
Athlon 64 X2 4400+ EE 2.30 GHz 1.352 V G1 65 nm Brisbane
Athlon 64 X2 4800+ EE 2.10 GHz 1.352 V G1 65 nm Brisbane
Athlon 64 X2 3800+ EE 2.00 GHz 1.352 V F2 90 nm Windsor
Athlon 64 X2 3600+ EE 1.90 GHz 1.352 V G1 65 nm Brisbane
Athlon 64 X2 BE-2350 2.10 GHz 1.152 V G1 65 nm Brisbane
Athlon 64 X2 BE-2300 1.90 GHz 1.152 V G1 65 nm Brisbane
Athlon X2 4850e 2.50 GHz 1.256 V G2 65 nm Brisbane
Athlon X2 4450e 2.30 GHz 1.256 V G2 65 nm Brisbane
Athlon X2 4050e 2.10 GHz 1.256 V G2 65 nm Brisbane
Sempron 64 3600+ 2.00 GHz 1.352 V F2 90 nm Orleans
Sempron 64 3400+ 1.80 GHz 1.352 V F2 90 nm Orleans
Sempron 64 3000+ 1.60 GHz 1.352 V F2 90 nm Orleans
Sempron 64 3500+ 2.00 GHz 1.352 V F2 90 nm Manila
Sempron 64 3200+ 1.80 GHz 1.352 V F2 90 nm Manila
Sempron 64 2800+ 1.60 GHz 1.352 V F2 90 nm Manila


Talkback
dcdc 07/05/2008 10:28
Hide
-0+
dcdc
my media centre based on a 3700+ (S939, single core san diego, 1MB, 2.2GHz) only uses 56-58W while running rosetta@home! That's including 1.25GB DDR (3 sticks), a freeview TV tuner, and a 2GB compactflash card on a Seasonic S12 330W PSU. It's undervolted as far as it'd go though...
darthpoik 09/05/2008 12:07
Hide
-0+
darthpoik
What about performance per watt comparisons, which would have been the best comparison you could have made in such an article.
Anonymous 18/05/2008 12:28
Hide
-0+
If you had a system that consumed 300W of power (forget about idle and full load differences for this question!!) with a 500W PSU, what would your power consumption be for the purpose of energy bill calculation?

Am I correct in believing that the rating of your PSU is the maximum power it can supply, and that it only actually draws what the system asks for? So in this case, your overall system power use would be 300W?

So, if you install a much more powerful PSU than you currently need (for the sake of future SLI upgrades) you wouldn't be wasting electricity?

Note You are going to post a comment as anonymous.



  •
Submit my comment
Google Ads