Core i7 8700K vs. Ryzen 7 2700X With Rise of The Tomb Raider On Linux

[phoronix]

Phoronix: Core i7 8700K vs. Ryzen 7 2700X With Rise of The Tomb Raider On Linux

Here are our latest Linux gaming benchmarks comparing the Intel Core i7 8700K to the newly-released Ryzen 7 2700X. The focus in this article is on the Rise of the Tomb Raider Linux port released last week by Feral Interactive and powered by Vulkan.

http://www.phoronix.com/vr.php?view=26243

[johanb]

Seems like Geothermal Valley was the only scene where it was not a GPU bottleneck and you can see how Intel has a slight edge, less so on higher quality settings however.
Anyone know why specifically Geothermal Valley is so CPU intensive?

[riklaunim]

There is a reason why many CPU comparisons is done with the most powerful GPUs and/or games running on resolutions even smaller than 1080p.

[dungeon]

Anyone know why specifically Geothermal Valley is so CPU intensive?

Likely these so much particles anim from falls, that and smoke is usual CPU killer

[theriddick]

Pretty good results considering the 8700 has a clear clock advantage. If AMD ever releases cpu's with similar clock rates they will dominate easily.

[johanb]

Pretty good results considering the 8700 has a clear clock advantage. If AMD ever releases cpu's with similar clock rates they will dominate easily.

There's no way to know if that's true considering that this case is a GPU bottleneck.
To find out, match the clock speed of one intel and one ryzen processor and run multiple benchmarks which have a CPU bottleneck.

[leipero]

With over 800MHz and slightly better IPC, ofc. 8700k would be in front in many cases where poor multi-threaded coding is done, it would be insane to state "CPU bottleneck" because of bad software as many reviewers on the web do. It is very likely that difference would be bigger on low settings with 1080ti, but that is not really realistic scenario, who would buy such expensive GPU's and CPU's to play on low settings, no one ofc. I would be more interested in Windows vs. GNU/Linux performance of the game, that would be interesting to see.

There is a reason why many CPU comparisons is done with the most powerful GPUs and/or games running on resolutions even smaller than 1080p.

Yes, to show curent state of the software and how different hardware reacts to it, and how may or may not react in the future with newer software. There is an argument that poorly coded software will always exist, and that is really true, however, gaming industry in recent years/decade move more towards game studios using already established "engines", and their work is usually "gmae only" related work with the "engine", while it is the job of the "engine" to scale with hardware and be upgraded etc. So, it is not out of the question that there could be cheap/free engine that would be decent for hardware and very usable for game developers in the future.

Unity is bad example here, and I have no clue if it's free or not, I know you can download and develop in Unity (even on GNU/Linux) because I tried it, but I'm not sure of licensing since I didn't do any project on it, just wanted to get familiar with the topic. I also do not know how well Unity does multi-threaded workloads, but while using low-IPC CPU with some Unity games I never had any (CPU related) issues with performance. So, it is very egoistic to claim anything considering the future based on current time and relatively short history of multi-threaded gaming in my opinion (what is suposed reason behind those tests, especially on Windows platform).

[leipero]

There's no way to know if that's true considering that this case is a GPU bottleneck.
To find out, match the clock speed of one intel and one ryzen processor and run multiple benchmarks which have a CPU bottleneck.

The first (including 2xxx) generation of Ryzen is slightly worse than last generation of Intel CPU's, it is also even less worse than some older generations, that's acording to the one test:

http://www.guru3d.com/articles_pages/amd_ryzen_7_2700x_review,9.html

That's not really enough difference to make drastic performance gap, so it is mainly because frequency difference.

[davidbepo]

nice results ryzen 2000 is really competitive

[Jahimself]

That's seems to be a good implementation of vulkan, and a very interesting performance of the 2700x