Kirill Batuzov writes:
> To be able to generate vector operations in a TCG backend we need to do
> several things.
>
> 1. We need to tell the register allocator about vector target's register.
>In case of x86 we'll use xmm0..xmm7. xmm7 is designated as a scratch
>
On 01/18/2017 05:05 AM, Kirill Batuzov wrote:
Why are you not defining xmm8-15?
At first I thought about supporting both x86_64 and i386 targets, but
put this idea away (at least for the time being). Since defining xmm8-15
does not contradict anything (as I see it now) I'll add them too.
On Tue, 17 Jan 2017, Richard Henderson wrote:
> On 01/17/2017 01:07 AM, Kirill Batuzov wrote:
> > To be able to generate vector operations in a TCG backend we need to do
> > several things.
> >
> > 1. We need to tell the register allocator about vector target's register.
> >In case of x86
On 01/17/2017 01:07 AM, Kirill Batuzov wrote:
To be able to generate vector operations in a TCG backend we need to do
several things.
1. We need to tell the register allocator about vector target's register.
In case of x86 we'll use xmm0..xmm7. xmm7 is designated as a scratch
register,
To be able to generate vector operations in a TCG backend we need to do
several things.
1. We need to tell the register allocator about vector target's register.
In case of x86 we'll use xmm0..xmm7. xmm7 is designated as a scratch
register, others can be used by the register allocator.
2.