You mean Intel's compiler that's often been shown to not incorporate hardware features and optimizations for processors other than their own?
The same works the other way around though too. If on Intel you use something open source like OpenBlas instead of MKL performance is tanked. Or to see it in a different way it leaves a lot of untapped Intel potential. Below is a benchmark comparing a 14core Xeon (175W) against the “12core” (dual-hexacore) Ryzen 3900X. With both using OpenBlas the Xeon is only 1.137x faster which someone may attribute to the core count difference (14 is 1.167x bigger than 12 but the 3900X is running at higher clock speeds). But see how with MKL the Intel processor is now 2.18x faster than before and 2.48x faster compared to the 3900X.
Maybe you should start a review site aggregating only the handful of outlier results supporting your argument while ignoring the bulk of other results. : D
No doubt there is plenty of software and workloads where the 10900K will perform a little better, whether due to compiler optimizations, limited threading, or just architectural differences favoring certain tasks, but for heavily-threaded software, it is often at a core disadvantage resulting in lower performance than the competition in many applications.
So let me see: Google Tensorflow, Microsoft Office, WinRar, Adobe Premiere Pro, Adobe After Effects, Photoshop, LAME, MySQL TCP-C, Metashape, etc …AND on occasion Blender and 7zip … AND … pretty much ALL Games AND a lot of professional engineering and scientific software are all outliers. And what exactly constitutes the “bulk of the results”? Cinebench, Handbrake and Pov Ray? And has actually any of these reviewers even bothered making a real project on the actual Cinema4D (instead of just running Cinebench) and comment on the user experience? Because if they did they would have noticed for example the Intel Image denoiser that many Cinema4D users love to use as it saves them a lot of time. If they did they would bother to render something different. They would have also been using R21 instead of R20.
Intel is at the very least offering more processor for the money than they were with the 9900K though, and their slashing prices for a given core count makes this generation a better value than their 9th-gen offerings, and a lot more competitive with Ryzen. The revised pricing makes this a relatively decent lineup, in my opinion, aside from the cooling requirements for these higher-end parts. But ultimately, the 3900X is a year-old processor that is currently priced similar to the 8-core i7-10700K, not the i9-10900K, and that's even before getting into cooling.
Well you have to thank Intel for AMD lowering their pricing on the 3900X. Competition works both ways. Also Intel offers the 10900KF (with no igpu like the 3900X) for less. And let's not forget the 10900 and 10900F which you can run with power limits removed and run it at 4.6GHz all-core turbo indefinitely (and 5.2GHz turbo single threaded indefinitely). This will achieve pretty much near identical performance to the stock 10900K (with power limits removed). And on Z motherboards you CAN use XMP profile on all SKUs (including non K skus). A 10900F has MSRP of $422. The 3900x on Amazon currently retails for $419.99.
Facebook
Twitter
Instagram