Any usable SIMD implementation?

[Iain Buclaw via Digitalmars-d]

On 13 April 2016 at 11:13, Marco Leise via Digitalmars-d
<digitalmars-d at puremagic.com> wrote:
> Am Wed, 13 Apr 2016 09:51:25 +0200
> schrieb Iain Buclaw via Digitalmars-d
> <digitalmars-d at puremagic.com>:
>
>> On 13 April 2016 at 07:59, Walter Bright via Digitalmars-d
>> <digitalmars-d at puremagic.com> wrote:
>> > But core.cpuid needs to be made to work in GDC, whatever it takes to do so.
>> >
>>
>> Indeed, it's been on my TODO list for a long time, among many other things. :-)
>
> Would you want to implement this in the compiler like the
> checkedint functions? I guess that's the only way to guarantee
> cross-module inlining with GDC. Otherwise I would use
> __builtin_cpu_supports (const char *feature). (GCC practically
> has its own internal core.cpuid implementation made of
> intrinsics.)
>
> --
> Marco
>

Yes, cpu_supports is a good way to do it as we only need to invoke
__builtin_cpu_init once and cache all values when running 'shared
static this()'.

I would also like to be able to support other processes too.  ARM is a
high priority one which should follow suit.