CUDA under FreeBSD

[Polytropon]

On Sat, 9 Dec 2017 22:13:40 -0500, Baho Utot wrote:
> On 12/9/2017 9:45 PM, Jan Beich wrote:
> > Shane Ambler <FreeBSD at ShaneWare.Biz> writes:
> >
> >> On 04/12/2017 21:19, galtsev at kicp.uchicago.edu wrote:
> >>
> >>> On Mon, December 4, 2017 4:24 am, Carmel NY wrote:
> >>>> Out of morbid curiosity, I was wondering if anyone could tell me
> >>>> the real reason that Nvidia does not support CUDA under
> >>> Arrogance would be my guess.
> >> The morbid part is that they give us the linux libcuda, so we should be
> >> able to run linux binaries that use cuda, just not native apps.
> > Modern CUDA toolkit is 64bit but runtime only works on 32bit (bug 206711).
> > Building as -m32 is probably still possible but may not fit all workloads
> > nor run as fast.
> >
> >>>> FreeBSD? Also, what are the realistic expectations for it getting
> >>>> supported shortly?
> >>> Zero is my estimate. The way to let one's steam about them is just
> >>> not to buy ther hardware. Their attitude to open sourse and
> >>> unwillingness to disclose details of their hardware was always much
> >>> worse than that of their competitors (ATI/AMD, matrox...).
> >>>
> >>> This is just my opinion based on my subjective observations.
> >> I'm sure on an episode of bsdnow, they mentioned asking an nvidia dev
> >> at one of the conferences and they said there shouldn't be any technical
> >> reason, it just isn't enabled in the build and they would look into it.
> >> Still hasn't helped any.
> > Just like Vulkan, just like KMS, just like encoding/capture acceleration.
> > NVIDIA always conveniently forgets about FreeBSD. However, the ailment
> > isn't really specific to NVIDIA but affects most binary blob vendors.
> > For one, Widevine CDM is maintained by Google but EME itself was pushed
> > to W3C by Netflix, a FreeBSD vendor which conveniently forgot a browser
> > can run on FreeBSD.
> >
> 
> What is FreeBSD market share?

FreeBSD has no market share, as it does not participate in
market measurements such as "units sold" or "licenses obtained".
You cannot - I repeat: you _cannot_ tell the number of FreeBSD
installations.

You can hardly guess it.

The reason is simple: As I said, FreeBSD does not count "units
sold" or "licenses obtained", so all the installations made do
not increase any numbers. Additionally, FreeBSD is being used
in non-PC and non-server systems, such as embedded solutions,
appliances, routers, switches, firewalls, IoT, and so on. You
usually don't even _know_ if FreeBSD is running on a specific
device you are using.

The termini technic you are searching for are:

1. usage share = how many installations are present, how many
   people are using it, etc.

2. mind share = how many people or organisations are aware of
   FreeBSD existing

Those are numbers you also can hardly guess, and they are still
much more significant (especially no. 1) than market share.



> Could be the market share of FreeBSD is so small it is not worth their time?

The usage share (if you want to understand this as market share,
or at least as an approximation) is not significant for the
manufacturers producing those devices - and supplying the
corresponding software. So it's simply not worth their time
as it doesn't generate revenue that justifies that effort.



> Maybe the FreeBSD developers are too abrasive?

I don't think so. Typically developers invest their time in
getting hardware running when the required specifications and
documentation is made available, and some devices even get
reverse-engineered support.



> Or maybe some other reason?
> Linux is everywhere so maybe that is why Linux gets all the glory?

That is quite possible. Top computers are running Linux, top
companies are using Linux. Linux runs PCs, servers, peripherial
devices and appliances, so you could even say: Linux runs the
whole Internet... so, yes, it actually is everywhere.



-- 
Polytropon
Magdeburg, Germany
Happy FreeBSD user since 4.0
Andra moi ennepe, Mousa, ...