Walter Bright wrote:
> On 11/2/2012 11:19 AM, Jacob Carlborg wrote:
> >I can absolutely understand why he did it but it would be really nice if you (Walter, Andrei and probably others as well) could be more transparent about things like these. I think this would really help the community.
> 
> I apologize for being circumspect about this, but I have to respect peoples' privacy and I cleared what I posted about Remedy with them before posting it.

There is no need to reveal anything private just because you have a road map.

Jens

On 11/2/2012 3:10 PM, Jens Mueller wrote:
> I see. Thanks for clarifying.
> If I want fast vector operations I have to use core.simd. The built-in
> vector operations won't fit the bill.

At the moment, yes.

However, Manu is working on developing a higher order layer.

On 3 November 2012 01:41, Walter Bright <newshound2@digitalmars.com> wrote:

> On 11/2/2012 3:10 PM, Jens Mueller wrote:
>
>> I see. Thanks for clarifying.
>> If I want fast vector operations I have to use core.simd. The built-in
>> vector operations won't fit the bill.
>>
>
I think a better quote would be "If i want *HARDWARE* vector operations..."; this is not automatically faster by nature, it requires strict self-control in terms of application, and very careful attention if you want your code to be portable.

At the moment, yes.
>
> However, Manu is working on developing a higher order layer.
>

I have a fork; some people are using it already. It still needs a lot of
work though; some compilers missing parts, platforms not supported.
That said, it's not an effort to address D's natural vector syntax, the key
goal is to provide a hardware SIMD API that is as orthogonal as possible
and portable (with confidence it will run reasonably well).
I wonder if druntime could be enhanced to use the SIMD stuff though in the
functions that perform the natural vector operations, might offer some nice
little boosts.

Manu wrote:
> On 3 November 2012 01:41, Walter Bright <newshound2@digitalmars.com> wrote:
> 
> > On 11/2/2012 3:10 PM, Jens Mueller wrote:
> >
> >> I see. Thanks for clarifying.
> >> If I want fast vector operations I have to use core.simd. The built-in
> >> vector operations won't fit the bill.
> >>
> >
> I think a better quote would be "If i want *HARDWARE* vector operations..."; this is not automatically faster by nature, it requires strict self-control in terms of application, and very careful attention if you want your code to be portable.
> 
> At the moment, yes.
> >
> > However, Manu is working on developing a higher order layer.
> >
> 
> I have a fork; some people are using it already. It still needs a lot of
> work though; some compilers missing parts, platforms not supported.
> That said, it's not an effort to address D's natural vector syntax, the key
> goal is to provide a hardware SIMD API that is as orthogonal as possible
> and portable (with confidence it will run reasonably well).
> I wonder if druntime could be enhanced to use the SIMD stuff though in the
> functions that perform the natural vector operations, might offer some nice
> little boosts.

Cool.
It'll be nice though if D's vector operations could be expressed on top
of it. I mean a[] + b[] is so much easier to read.

Jens

On 2012-39-03 12:11, Jens Mueller <jens.k.mueller@gmx.de> wrote:


>>
>> I have a fork; some people are using it already. It still needs a lot of
>> work though; some compilers missing parts, platforms not supported.
>> That said, it's not an effort to address D's natural vector syntax, the key
>> goal is to provide a hardware SIMD API that is as orthogonal as possible
>> and portable (with confidence it will run reasonably well).
>> I wonder if druntime could be enhanced to use the SIMD stuff though in the
>> functions that perform the natural vector operations, might offer some nice
>> little boosts.
>
> Cool.
> It'll be nice though if D's vector operations could be expressed on top
> of it. I mean a[] + b[] is so much easier to read.

Perhaps I'm the confused one here, but as I understand it, that's the
whole point of the latter part of the paragraph - array operations are
implemented in druntime, and that implementation might benefit from using
SIMD instructions.


-- 
Simen

Simen Kjaeraas wrote:
> On 2012-39-03 12:11, Jens Mueller <jens.k.mueller@gmx.de> wrote:
> 
> 
> >>
> >>I have a fork; some people are using it already. It still needs a lot of
> >>work though; some compilers missing parts, platforms not supported.
> >>That said, it's not an effort to address D's natural vector
> >>syntax, the key
> >>goal is to provide a hardware SIMD API that is as orthogonal as possible
> >>and portable (with confidence it will run reasonably well).
> >>I wonder if druntime could be enhanced to use the SIMD stuff
> >>though in the
> >>functions that perform the natural vector operations, might
> >>offer some nice
> >>little boosts.
> >
> >Cool.
> >It'll be nice though if D's vector operations could be expressed on top
> >of it. I mean a[] + b[] is so much easier to read.
> 
> Perhaps I'm the confused one here, but as I understand it, that's the whole point of the latter part of the paragraph - array operations are implemented in druntime, and that implementation might benefit from using SIMD instructions.

Sorry. I'm the one being confused. You're right Simen.

Jens