Really now? Show me how to performance tune my Macbook Pro mid 2012 15 inch model that contains a traditional 1TB HDD (not SSD) so that a single large block read or write won't block all over I/O operations. Or hell, even any Mac that doesn't use an SSD. I can assure, it is needed and just to note, I can switch I/O scheduler on most Unix systems and Linux for performance (which is usually just a configuration variable in a text file).
Most of that's probably down to the godawful old HFS+ filesystem that needed to be relegated to legacy support a full decade ago. It's absolutely atrocious and a sign of Apple's indolence that they're only now within striking distance of releasing APFS to the wild. Positive change needed to be made on that front when George W. was in the White House.
In my experience, Windows is often snappier particularly the moment you start using cross platform 3D software or wanting to have applications that are asynchroniously doing I/O.
Amen to that. 3D software on the mac is also hobbled by Apple's refusal to update their OpenGL implementation; they're stuck at version 4.1 with a few extensions, performance has always lagged behind the competition, and the situation hasn't changed for years. In head to head benchmarks on a MacBook Air between the latest version of macOS and Windows 10, the latter's performance was sometimes 50% greater. No amount of honest marketing can paper over that kind of difference. All their engineers seem to be assigned to Metal now, which doesn't seem like a bad API. It's just restricted solely to iOS and macOS, and thus doesn't matter to any other platforms. macOS devices are being relegated to authentication dongles for making and maximizing convenience for using iOS apps. A few gimmicky R&D expenses don't make up for the sensation that the platform's sinking into the murk compared to the competition.
Not(e) that macOS's BSD subsystem is proprietary and is beaten by Windows' old POSIX subsystem.
Yes, and the Bash shell for Windows 10 is only going to open that gap wider going forward.
If there was ever a true multi-threaded application AMD would take the prize. As such Intel dominates because of single threaded applications.
There are embarrassingly well-threaded applications where AMD does well. The x264 encoder does a fantastic job and hammers all 8 of the cores in my FX-8320 at >90% utilization, and it was cheerfully faster at that than the i5 3570K I used to keep around. But IPC does ultimately win out, and Haswell's AVX2 support is sufficient to let an i5 4690K generally pull out ahead of my FX. That's especially true on interlaced media, where the deinterlacer's essentially single-threaded and the rest of the chip's basically waiting for that single core to finish before tackling the rest of the workload. For most other uses it's somewhere around a Nehalem quad core: certainly fast enough for what I do, but the overall performance outside of niche applications isn't impressive in absolute terms. At least it took to undervolting well, and it's a friggin' behemoth for virtualization.
Elegance and truth are inversely related. -- Becker's Razor