Intel Core i9 9900K Linux Benchmarks - 15-Way Intel/AMD Comparison On Ubuntu 18.10

[phoronix]

Phoronix: Intel Core i9 9900K Linux Benchmarks - 15-Way Intel/AMD Comparison On Ubuntu 18.10

Intel sent over the Core i9 9900K as their first 9th Gen Coffeelake-S CPU hitting store shelves today. With the embargo on that now expired, let's have a look at how well this eight-core / sixteen-thread processor performs under Linux.

http://www.phoronix.com/vr.php?view=26993

[Spooktra]

Nice review, thanks. Just 2 things, would have been nice to see some encoding benchmarks, such as x264, x265 and vp9 and you could have mentioned that the 9900k supports Optane DIMM, that's what the premium is for. I wouldn't buy one of these now but when motherboards that support Optane DIMMs are available and when said DIMMs hit the shelves, the 9900k will take one a whole new life.

[Michael]

There ought to be timed gentoo compilation benchmark.

What really is the point? There is already kernel and LLVM compilation to assess compiler performance...

[schmidtbag]

This is better than I was expecting. Sure gets you to wonder why Intel was so focused on cheating with PT.

[L_A_G]

This was pretty much exactly how I expected an 8 core Intel to perform to the 8 core Ryzen CPUs so I guess the review itself was pretty unsurprising as reviews go.

The real story here is how hard AMD has kicked Intel in the backside as evidenced by them going from 4C/8T to 8C/16T in their higher end consumer models in a matter of 18 months after previously sticking to 4C/8T for years and years. That and how these new chips are so much bigger on the silicon substrate than their 4C/8T predecessors that their 14nm node capacity has run out.

[anarki2]

DD that last page. And to this day, I have to argue with people about the energy inefficiency of AMD CPUs.

Anyways, lackluster release for sure. Gonna stick to my 8700K plans I guess.

[jrch2k8]

Well this release from Intel was very underwhelming, sure is faster(also probably Michael didn't use tight memory timings on ryzen, but that is expected) but the temperature issues(reported by several reviewers already) and the massive cost difference(z390 premium mobo + a though cooler + 200$+ price difference with the actual CPU) make it a very niche CPU and barely worth it(outside rich people that want bragging rights) for some users.

Honestly the 2700 murders intel i9 series on value and if you need better i truly believe a Threadripper(even the first gen) 12/16 cores will offer way more value(taking into account all the extra goodies on x399)

so, meh

[Wielkie G]

DD that last page. And to this day, I have to argue with people about the energy inefficiency of AMD CPUs.

Anyways, lackluster release for sure. Gonna stick to my 8700K plans I guess.

https://www.anandtech.com/show/13400/intel-9th-gen-core-i9-9900k-i7-9700k-i5-9600k-review/21

221W vs 117W doesn't look so good anymore...

[tuxd3v]

...some years Ago, AMD released the Carrizo APUs, and it was very nice what they have done...
They rerouted the connections inside the CPU, connections on transistors, etc, the result was amazing, only with this..

They saved space, APU consumed less energy and I think was at least 15% faster...
I think Intel, learned with AMD , and have done the same here..

The fab process mantain, and still they pushed it up to 5GHZ, also it seems that the power engine, received a very good improovment.

Now, since AMD Ryzen is a new CPU...
Does AMD applied already, the same optimisations that was applied earlier on Kavery -> Carrizo transition ??
I never read about this optimisations...
And this optimisations are the second stage of evolution, kavery -> carrizo showed that,( without changing almost nothing , they gained a lot..)

Could it be that, they are in newer 2600E, 2700E processors, has a 2nd stage?

[stargazer]

Michael, as the ability to multitask increases and people do more simultaneously with their systems, have you thought about setting up benchmarks with multiple tasks in parallel? So for instance, web browsing to multiple sites (stored locally to eliminate network variability) with concurrent download and unzip of a zip file while a music or video player is running all while an antivirus is scanning in the background. That might be a more meaningful comparison for modern concurrency and usage of CPUs than single application stress tests. I think it might also provide some additional differentiation between AMD and Intel due to the higher context switching in this sort of scenario.