[cfe-dev] Adding "simd" pragma to Clang

["C. Bergström"]

On 02/17/14 07:05 PM, Renato Golin wrote:
> On 17 February 2014 11:46, "C. Bergström" <cbergstrom at pathscale.com> wrote:
>> What about trying to extend OMP pragma to cleanly fit your goals?
> So, for this first implementation, I'm trying to steer away from
> re-inventing the wheel. GCC does implement some of the Cilk/OMP4, and
> will continue in that direction, so at least, even if it's old-school,
> we'll get similar behaviour.
>
>
>> Cilk is far from any standard, not used in the real world(???) and fairly
>> tied to Intel. (I'm not apposed to this, but something to think about)
> GCC implements some of them.
I'm not a big fan of using gcc as a reference to determine future goals.

I also see no future or large adoption of clik in the real world. afaik 
Intel contributed it, but I don't know who is actually using it and if 
the performance is good enough (gcc implementation) to actually offset 
the efforts involved.
----------------
Some clean extension to OMP doesn't have to be long term
1) Your proposal could be implemented now and just used as a POC (proof 
of concept) for the working group
2) It would show clear deficiencies in the standard that have real world 
value/usage

By playing nice with OMP now - myself and possibly others would have a 
much easier time helping with future maintenance and any changes which 
would be needed. (clang, llvm ir or target specific) Imagine this more 
like TR1.. This would also possibly help avoid duplicate efforts long 
term, users having to migrate from one set of pragma to another and 
bringing people with interest in solving the problem to help clearly 
define the behavior. This may start out "harmless", but I suspect is 
quite a complex problem and would probably evolve down it's own path if 
allowed.

Lastly - how would this non-omp set of pragma end up playing nice with omp?