Technology

I don't care why they got their shit together, I'm happy as long as they fix the open source drivers.

Nvidia was "forced" to integrate Linux into its ecosystem

100% bullcrap.

Nvidia's servers for data processing have always run Linux. And you know what those servers run? It's not Windows, that's for sure. So why would they write multiple versions of a driver for the same hardware interface? Their servers use the same drivers that you would use for gaming on a Linux desktop system.

In fact, no version of Windows is supported on their DGX servers, and AFAIK you can't even install Windows on it (even if you managed, it wouldn't be usable).

Long story short, a vendor we were working with (about 6 or 7 years ago now), was working on their Linux version of their SDK. We wanted to do some preliminary testing on Nvidia's new T4s that at this point were only available via Nvidia's testing datacenter (which we had access to).

During a call with some of the Nvidia engineers I had to ask the awkward question of "any chance there's a Windows server we can test on?". I knew it was a cringe question and I died a little during the 10 second silence until one of the Nvidia guys finally replied with "no one uses Windows for this stuff". And he said it slowly like the reply to such a question needed to go slow to be understood, because who else would ask that question unless you're slow in the head?

Nvidia has always been hostile to the Linux community or negligent to say the least

People say "hostile", but I think a better word is arrogant. They wanted to force the industry to use their own implementations they owned or pioneered like egl-stream instead of open standards. But AMD and Intel have proven that open source graphics drivers not only work, but benefit from being open so that the community can scratch their own itches and fix issues faster.

Man, I completely forgot about that. That's honestly wild to think about in retrospect...

Don't know about "always." In recent years, like the past 10 years, definitely. But I remember a time when Nvidia was the only reasonable recommendation for a graphics card on Linux, because Radeon was so bad. This was before Wayland, and probably even before AMD bought ATI. And it was certainly long before the amdgpu drivers existed.

Am I missing something here? Nvidia never caved to their demands IIRC

Honestly, for real, a lot of low-power PCs are really useful once they have crap like Windows off of them and a lightweight Linux distro on them.

Up until the early 2000s, serial computation speed doubled about every 18 months. That meant that virtually all software just ran twice as quickly every 18 months of CPU advances. And since taking advantage of that was trivial, new software releases did, traded CPU cycles for shorter development time or more functionality, demanded current hardware to run at a reasonable clip.

In that environment, it was quite important to upgrade the CPU.

But that hasn't been happening for about twenty years now. Serial computation speed still increases, but not nearly as quickly any more.

This is about ten years old now:

https://preshing.com/20120208/a-look-back-at-single-threaded-cpu-performance/

Throughout the 80’s and 90’s, CPUs were able to run virtually any kind of software twice as fast every 18-20 months. The rate of change was incredible. Your 486SX-16 was almost obsolete by the time you got it through the door. But eventually, at some point in the mid-2000’s, progress slowed down considerably for single-threaded software – which was most software.

Perhaps the turning point came in May 2004, when Intel canceled its latest single-core development effort to focus on multicore designs. Later that year, Herb Sutter wrote his now-famous article, The Free Lunch Is Over. Not all software will run remarkably faster year-over-year anymore, he warned us. Concurrent software would continue its meteoric rise, but single-threaded software was about to get left in the dust.

If you’re willing to trust this line, it seems that in the eight years since January 2004, mainstream performance has increased by a factor of about 4.6x, which works out to 21% per year. Compare that to the 28x increase between 1996 and 2004! Things have really slowed down.

We can also look at about the twelve years since then, which is even slower:

https://www.cpubenchmark.net/compare/2026vs6296/Intel-i7-4960X-vs-Intel-Ultra-9-285K

This is using a benchmark to compare the single-threaded performance of the i7 4960X (Intel's high-end processor back at the start of 2013) to that of the Intel Ultra 9 285K, the current one. In those ~12 years, the latest processor has managed to get single-threaded performance about (5068/2070)=~2.448 times the 12-year-old processor. That's (5068/2070)^(1/12)=1.07747, about a 7.7% performance improvement per year. The age of a processor doesn't matter nearly as much in that environment.

We still have had significant parallel computation increases. GPUs in particular have gotten considerably more powerful. But unlike with serial compute, parallel compute isn't a "free" performance improvement -- software needs to be rewritten to take advantage of that, it's often hard to parallelize solving problems, and some problems cannot be solved in parallel.

Honestly, I'd say that the most-noticeable shift is away from rotational drives to SSDs -- there are tasks for which SSDs can greatly outperform rotational drives.

Nvidia drivers on Linux are messy and have been for a long time. It took them ages to fix Vsync in Wayland. If you want to run Linux, go AMD (or Intel).

https://www.nvidia.com/en-us/project-digits/

Yes, actually lmao