[Info-vax] Some of what I'm reading...

[Scott Dorsey]

IanD  <iloveopenvms at gmail.com> wrote:
>The take away for me is that gpus cannot be ignored going forward, they are=
> pivotal in anything machine learning related and applications lacking a ma=
>chine learning component are starting to look a little tired, especially as=
> we move into stream based learning models and workloads. Now SQL execution=
> may start levering them

The problem here is that much of the internals on the GPUs are either 
undocumented or poorly documented, so you need to be using the 
GPU-vendor-provided programming environment and libraries and duplicating
that environment is difficult.

If a new operating system wishes GPU support, then, they need to get the
GPU vendor on board to provide these tools.  This is nontrivial.

I will say that the environments where GPUs are a biggest win are those
where VMS is never going to be a big player again, such as for scientific
computing and dsp.  This makes it difficult to convince the GPU vendors
that there is a market for them in porting to VMS.

You can think of the GPU as being just like the Floating Point Systems
and Mercury array processors for the vax, providing high speed vector
operations from a bag hanging off the side of the CPU's buss.
--scott


-- 
"C'est un Nagra. C'est suisse, et tres, tres precis."