$499 AMD Ryzen 9 3900X Almost as Fast as $2000 Intel Core I9-9980XE

+1. I've heard some optimizations in scientific computing (e.g. Gaussian 16, from someone who does chemistry) is not available without AVX, but I'm not a practitioner of scientific computing, and know nothing about the current situation. Could anyone share your experience? Also, what is the performance figure of multimedia/encoding performance?

You could do it via KVM-based virtualization without a ton of trouble.

in ZEN2:

"The key highlight improvement for floating point performance is full AVX2 support. AMD has increased the execution unit width from 128-bit to 256-bit, allowing for single-cycle AVX2 calculations, rather than cracking the calculation into two instructions and two cycles. This is enhanced by giving 256-bit loads and stores, so the FMA units can be continuously fed. AMD states that due to its energy aware scheduling, there is no predefined frequency drop when using AVX2 instructions (however frequency may be reduced dependent on temperature and voltage requirements, but that’s automatic regardless of instructions used)"

"In the floating point unit, the queues accept up to four micro-ops per cycle from the dispatch unit which feed into a 160-entry physical register file. This moves into four execution units, which can be fed with 256b data in the load and store mechanism.

Other tweaks have been made to the FMA units than beyond doubling the size – AMD states that they have increased raw performance in memory allocations, for repetitive physics calculations, and certain audio processing techniques.

Another key update is decreasing the FP multiplication latency from 4 cycles to 3 cycles. That is quite a significant improvement. AMD has stated that it is keeping a lot of the detail under wraps, as it wants to present it at Hot Chips is August. We’ll be running a full instruction analysis for our reviews on July 7th."

https://www.anandtech.com/print/14525/amd-zen-2-microarchite...

> Any significant differences in regards to scientific applications or machine learning?

The PCIe4.0 is good for Data Science ( NVMe Disk / GPU machine learning )

"Corsair MP600 SSDs will offer up to 4950 MB/s sequential read speed as well as up to 4250 MB/s sequential write speed when used with a PCIe 4.0 x4 interface, which is substantially faster when compared to modern PCIe 3.0 x4 drives."

https://www.anandtech.com/show/14584/corsair-mp600-pcie-4-ss...

It may be part of iOS 13 proper, I was just giving it as an example of a newer feature that makes sense with a larger screen like an iPad whereas maybe not as much with a (relatively) small screen like the iPhone.

Regardless, iPadOS is shaping up to be the latest iOS release with some extra features that maybe don't make sense on iPhone (at least until they prove great in iPadOS and there's a push by users to include it in iPhone as well). It'll most likely get anything that iOS/iPhone gets but then has its own so they rebrand it as a new OS (seems iOS+ or something denoting they're inherently the same would be more helpful). Having iPad's home screen grid be limited to the number of icons the way it did was apparently keeping it in parity with iOS/iPhone. Allowing that aspect to be "extended" by iPadOS to include docking the notification widgets/Today View on the primary home screen (wish it could stay for all home screens, but I digress) is a net gain.

I'm considering Intel for my next workstation because I want to be able to run macOS at least in VirtualBox (or just run Hackintosh, did not decide yet). For some reason macOS does not like AMD CPUs.