On 24/03/11 13:22, Richard Earnshaw wrote:
OK
Committed, thanks.
Andrew
On Tue, 2011-03-22 at 14:08 +, Andrew Stubbs wrote:
> And again, with the patch ...
>
> On 22/03/11 14:05, Andrew Stubbs wrote:
> > On 14/03/11 18:17, Richard Earnshaw wrote:
> > > I think the order should be: not-a8, core-regs, core-regs, only-a8.
> >
> > Ok, how about this?
> >
> > I've te
And again, with the patch ...
On 22/03/11 14:05, Andrew Stubbs wrote:
On 14/03/11 18:17, Richard Earnshaw wrote:
> I think the order should be: not-a8, core-regs, core-regs, only-a8.
Ok, how about this?
I've tested that it still builds spec2k crafty.
Andrew
2011-03-22 Bernd Schmidt
On Tue, 2011-03-22 at 14:05 +, Andrew Stubbs wrote:
> On 14/03/11 18:17, Richard Earnshaw wrote:
> > I think the order should be: not-a8, core-regs, core-regs, only-a8.
>
> Ok, how about this?
>
> I've tested that it still builds spec2k crafty.
>
> Andrew
>
ENOPATCH
R.
On 14/03/11 18:17, Richard Earnshaw wrote:
> I think the order should be: not-a8, core-regs, core-regs, only-a8.
Ok, how about this?
I've tested that it still builds spec2k crafty.
Andrew
On Mon, 2011-03-14 at 17:55 +, Andrew Stubbs wrote:
> On 14/03/11 17:10, Richard Earnshaw wrote:
> > Finally, alternatives from an insn are normally selected left-to-right
> > from those available in a pattern, all other things being equal. So
> > really the A8-only alternative should come af
On 14/03/11 17:10, Richard Earnshaw wrote:
Finally, alternatives from an insn are normally selected left-to-right
from those available in a pattern, all other things being equal. So
really the A8-only alternative should come after the core registers
alternatives if its less preferable.
OK, I c
On 03/14/2011 06:10 PM, Richard Earnshaw wrote:
>
> On Sun, 2011-03-13 at 16:31 +, Andrew Stubbs wrote:
>> This patch discourages the use of NEON for integer operations on ARM
>> Cortex-A8.
>>
>> The problem is that transferring data from NEON/VFP registers to core
>> registers is prohibitiv
On Sun, 2011-03-13 at 16:31 +, Andrew Stubbs wrote:
> This patch discourages the use of NEON for integer operations on ARM
> Cortex-A8.
>
> The problem is that transferring data from NEON/VFP registers to core
> registers is prohibitively expensive on A8. This should not affect
> Cortex-A9
This patch discourages the use of NEON for integer operations on ARM
Cortex-A8.
The problem is that transferring data from NEON/VFP registers to core
registers is prohibitively expensive on A8. This should not affect
Cortex-A9 in the same way.
This change gives a 6% increase in performance o
10 matches
Mail list logo
