Are AMD Athlon/Sempron APUs Fast Enough For Steam On Linux, Steam Machines?
Written by Michael Larabel in Linux Gaming on 15 April 2014. Page 2 of 2. 21 Comments

With Counter-Strike: Source the four AM1 APUs appeared largely CPU bound, which is to be expected with the Source Engine, given the difference in frame-rates between the resolutions. With the highest-end AMD Athlon 5350, it topped out just below 60 FPS when running at only 1024 x 768... However, when running at the more common 1920 x 1080 resolution, the Counter-Strike: Source benchmark with stock settings was averaging out to about 40 FPS.

The AMD Athlon 5150 sports a similar GPU but its four Jaguar cores operate at only 1.6GHz rather than 2.05GHz, but at 1680 x 1050 and 1920 x 1080 the performance between these two Athlon APUs were close with the GPU being pushed heavily.

For the AMD Sempron APUs with the Catalyst Linux driver, they topped out at 46 FPS for the Sempron 3850 and 34 FPS for the Sempron 2650... That's at 1024 x 768; at 1920 x 1080, they bottomed out to average frame-rates of 28~33 FPS, which certainly isn't playable for a first person shooter.

In case you missed it from earlier in the week, we did deliver AMD Athlon/Sempron overclocking results of this hardware. However, in the best case scenario you will only be getting about 7~8% better performance.

With Half-Life 2: Lost Coast and using the onboard graphics, none of the four APUs could average out above 60 FPS. At 1920 x 1080, they were all below 30 FPS. Of course, with Catalyst being significantly faster than the RadeonSI Gallium3D driver for this hardware right now, the open-source driver performance would be even lower.

When running Portal the AM1 APUs were running with their highest frame-rates, but still I wouldn't recommend any Steam Machines use these new APUs, at least with the integrated Radeon R3 Graphics, since they have problems pushing even 30 FPS with the Catalyst driver at 1920 x 1080 for Source Engine games on Linux. When using the RadeonSI Gallium3D driver, the performance will be lower, as shown earlier today in the open-source vs. closed-source comparison. Coming up in another Phoronix article in the next few days will be benchmarks when running discrete graphics cards with these 25-Watt APUs to see how their overall performance compares, among other interesting AM1 Linux articles and benchmarks.

Have other test requests for this hardware on Linux? Let us know, especially if you are a Phoronix Premium subscriber. Find all of the test data from this article via 1404158-KH-SOURCEENG02.

If you enjoyed this article consider joining Phoronix Premium to view this site ad-free, multi-page articles on a single page, and other benefits. PayPal tips are also graciously accepted. Thanks for your support.


Related Articles
About The Author
Author picture

Michael Larabel is the principal author of Phoronix.com and founded the site in 2004 with a focus on enriching the Linux hardware experience. Michael has written more than 20,000 articles covering the state of Linux hardware support, Linux performance, graphics drivers, and other topics. Michael is also the lead developer of the Phoronix Test Suite, Phoromatic, and OpenBenchmarking.org automated benchmarking software. He can be followed via Twitter or contacted via MichaelLarabel.com.


Trending Linux News