Core i7 7700K vs. Ryzen 7 1800X With Ubuntu 17.04 + Linux 4.12

[aufkrawall]

acpi-cpufreq ondemand butchered fps in some 3D applications like Unigine Valley compared to intel pstate powersave on my 2500k. So it's very likely that the Ryzen CPU runs very disadvantaged in games.
If you want a fair test, please set every CPU to acpi-cpufreq performance instead.
(Intel likely would still be quite faster in those tested games though, they are no multithread jewels.)

[xpander]

Can you run the same Gaming tests with a decent nvidia GPU like 1070 or 1080. as in my experience i get pretty much same or only slightly lower framerates compared to kaby lake cpus with my ryzen 1700X @3.9ghz and 2666mhz memory speed with a GTX 1070

[Strunkenbold]

Thx for the test, but I dont understand why the first comparison in march was made with 4k while we now only have FullHD. Id loved to see the development during the last 2 months...
If you arent a pro gamer, you usually dont care if a game runs with 150 fps or 200 fps. Interesting would be numbers below the 100 fps mark. But the games used here are way too old thus running way too fast.
Civ 6 looks very bad, Tomb Raider too. Looks like there is something broken...

[torsionbar28]

You can spin it as you like, the tests clearly show a cheaper i7 having fewer cores can still get some things done quicker than Ryzen.
They're both good choices, but you have to match them to your needs, cause there no longer a king of the hill all around.

Spin it? Lol, you're repeating back my own conclusion. A Ferrari is a heck of a lot faster than a dump truck. Which one is "better" depends on the task at hand. The Ferrari is awfully slow at moving 20,000 lbs of mulch...

[bug77]

We're comparing a 4 core processor to an 8 core processor in this review, so it's a lopsided comparison. From a theoretical perspective, of course 4 cores will outperform 8 cores in a single-threaded benchmark, within the same process node and TDP envelope. No surprise there. When you compare intel's 8 core offerings with Ryzen, you see Ryzen delivering equal or greater performance across the board, at a much lower price point.

Sure AMD is marketing Ryzen to gamers, but the value proposition is still there even if it's lags intel slightly in single-thread performance. Does it really matter that Ryzen delivers 182 frames per second while intel does 190? The frame rates here are all so high, it really makes no difference, so unless you're doing VR @ 4k or something like that, the smart money goes for the best value.

You can spin it as you like, the tests clearly show a cheaper i7 having fewer cores can still get some things done quicker than Ryzen.
They're both good choices, but you have to match them to your needs, cause there no longer a king of the hill all around.

[Holograph]

I feel like every Ryzen review I read over time is actually making it look worse, when initially I expected things to get better.

It could just be me.

And no, I didn't expect Ryzen to win overall here. But I expect it to put up a decent fight. And I'm not sure it did even that.

It seems that hardware reviews these days just make me realize, more and more, that PCs have become boring appliances that will probably never excite me again.

[AndyChow]

The Apache benchmark was surprising.

[fuzz]

You only looked at the gaming benchmarks, didn't you? Ryzen is faster in all the tasks I care for. Besides, I can just buy 1700 and overclock till 3.9 to 4.0 Ghz. Faster than stock 1800X. What a silly comparison.

I'm not the one saying I'm disappointed, mostly just pointing out to others that there is no reason to be disappointed in Ryzen. Or did you misquote?

[efikkan]

What a mixed bag this is... Ryzen obviously has got some great potential, which is really good. But it will take a while until the software developers tap into it. Some will likely ignore it and stay focused on Intel, like it's the case with graphics (and game makers more often focusing on Nvidia).

Ryzen is a better superscalar, so there is indeed some theoretical potential. In theory, it should handle 33% or more operations per clock for mixed int and float, provided the prefetcher is keeping all those ALUs and FPUs fed of course. And that really is the fault with Ryzen this far; except for AVX, it does have more computational resources than Intel, but Intel is much better at saturating their resources.

There are two ways of solving this;
1) Make all performance critical software cache friendly. In most cases this would require complete rewrites of applications so it's not going to happen anytime soon. And considering that the trend in development is still adding more bloat, it doesn't seem like this is going to improve overall. Making software cache optimized will make it scale well on both vendors, but it will help AMD even more.
2) Make a better prefetcher for the CPU. If AMD had a prefetcher just as good as Intel, Ryzen would scale much better (per core) in any application which is not AVX-dominant.

[Luke_Wolf]

It's wildly incorrect to characterize games as single threaded in today's environment. The games of yesteryear are designed around 4 cores, the games of the past few years that are more performance intensive are generally designed around 8 cores, and anything within the past year or two that's intensive (Doom, Watchdogs 2, and Battlefield 1 as prime examples) can thread out to as many cores as you can give it. Anything single threaded is a very bad console port. Do I need to post the utilization screenshot again?

Now due to the nature of the wrappers and OpenGL vs DX11/12 the Linux ports in some instances are going to be much more single threaded and tending towards low core counts... but Vulkan is the future on Linux, so said ports should improve by consequence.