AMD Athlon 64 FX-60: A Dual-Core farewell to Socket-939
by Anand Lal Shimpi on January 9, 2006 11:59 PM EST- Posted in
- CPUs
Gaming Performance using Battlefield 2, Call of Duty 2 and Quake 4
Gaming performance is pretty respectable for the Pentium EE 955, with the chip being quite competitive with AMD's Athlon 64 X2 4800+.
The most interesting thing we found is that even with a high end GPU like the Radeon X1800 XT, a number of games are still quite GPU limited even at 1024x768, which is why you don't see F.E.A.R. and Splinter Cell: CT here. Even some of the games that we did required us to turn down some of the detail settings to start to stress the CPUs.
The pendulum often swings between games being CPU and GPU limited, and it seems that with the latest generation of games, we are definitely more GPU limited.
We should also mention that we had to re-run our AMD numbers in this test since the last review as we were seeing sub-par AMD performance. A clean install and re-run of the numbers yielded the results that you see today; the Intel numbers didn't change.
We did run with SMP support disabled, as we found in our last article that the game gave us higher frame rates without it enabled.
For Quake 4, we turned to the latest 1.05 beta SMP patch, with SMP enabled, to give us these results. When more multithreaded games start shipping, you should see a performance breakdown similar to this, with the single core FX-57 not able to keep up with the new king of the hill: the FX-60.
Gaming performance is pretty respectable for the Pentium EE 955, with the chip being quite competitive with AMD's Athlon 64 X2 4800+.
The most interesting thing we found is that even with a high end GPU like the Radeon X1800 XT, a number of games are still quite GPU limited even at 1024x768, which is why you don't see F.E.A.R. and Splinter Cell: CT here. Even some of the games that we did required us to turn down some of the detail settings to start to stress the CPUs.
The pendulum often swings between games being CPU and GPU limited, and it seems that with the latest generation of games, we are definitely more GPU limited.
Battlefield 2 performance of the FX-60 is quite strong; however, the single core FX-57 is still able to hold a slight advantage over the newcomer. The performance difference isn't noticeable, but it is worth pointing out.
We should also mention that we had to re-run our AMD numbers in this test since the last review as we were seeing sub-par AMD performance. A clean install and re-run of the numbers yielded the results that you see today; the Intel numbers didn't change.
Once again, Call of Duty 2 shows that the FX-60 is nipping at the heels of the FX-57, but not exactly outperforming it. That being said, our CoD2 test appears to be quite GPU bound even at 1024 x 768 with a X1800 XT, so the difference in performance here is minor at best.
We did run with SMP support disabled, as we found in our last article that the game gave us higher frame rates without it enabled.
For Quake 4, we turned to the latest 1.05 beta SMP patch, with SMP enabled, to give us these results. When more multithreaded games start shipping, you should see a performance breakdown similar to this, with the single core FX-57 not able to keep up with the new king of the hill: the FX-60.
94 Comments
View All Comments
Betwon - Tuesday, January 10, 2006 - link
Let's see the real test(better than anandtech).After OC, the tests bentween Intel 955 and AMD FX-60:
http://www.xbitlabs.com/articles/cpu/display/athlo...">http://www.xbitlabs.com/articles/cpu/display/athlo...
Cygni - Tuesday, January 10, 2006 - link
I have to say, im pretty surprised by the results in single threaded apps, like most games. Despite a 200mhz deficit, it still beats the 57... pretty interesting. Im guessing that the second core is getting SOMETHING to it... maybe the background OS procedures? Dunno.Betwon - Tuesday, January 10, 2006 - link
Stop surprising.Because The benchmark of Business Winstone 2004,Overall WorldBench 5 and Office Productivity SYSMark 2004 may be benefit from multi-core.(a little or more?)
For the multi-thread-paralle apps:
Not only Fx-60 but also PD 820 beat, beats FX-57.
http://images.anandtech.com/graphs/amd%20athlon%20...">http://images.anandtech.com/graphs/amd%...lon%2064...
http://images.anandtech.com/graphs/amd%20athlon%20...">http://images.anandtech.com/graphs/amd%...lon%2064...
http://images.anandtech.com/graphs/amd%20athlon%20...">http://images.anandtech.com/graphs/amd%...lon%2064...
http://images.anandtech.com/graphs/amd%20athlon%20...">http://images.anandtech.com/graphs/amd%...lon%2064...
http://images.anandtech.com/graphs/amd%20athlon%20...">http://images.anandtech.com/graphs/amd%...lon%2064...
highlandsun - Tuesday, January 10, 2006 - link
Agreed. The only way you'd see truly single-threaded performance on a machine would be running something like DOS that has no task scheduler whatsoever.Betwon - Tuesday, January 10, 2006 - link
No surprise about games.FX-60 is defeated by FX-57 in most games.
Only in the SMP games, FX-60 beats the FX-57, And PD 820 beats the FX-57 too.
Betwon - Tuesday, January 10, 2006 - link
No surprise about games.FX-60 is defeated by FX-57 in most games.
Only in the SMP games, FX-60 beats the FX-57, And PD 820 beats the FX-57 too.
Avalon - Tuesday, January 10, 2006 - link
I'm still amazed at the performance difference in Quake 4 between the P-D 820 and FX-60, plus the fact that dual core optimizations in the game engine enable noticeable framerate gains.Xenoterranos - Tuesday, January 10, 2006 - link
Didn't Carmack himself day that that was basically a dry-run, that they didn't really how to go about multithreading it from the start. If Carmack is basically saying that the result we see here are preliminary and "rough", I can't wait until trully optimized code comes along to max both those cores out! Maybe then a quad-sli system will be able to do some damage without suffering the diminishing returns we've recently seen.latrosicarius - Tuesday, January 10, 2006 - link
I think the future of graphics will be single cards with multiple chips/cores.Furen - Tuesday, January 10, 2006 - link
Dont get me started on diminishing returns... lol