On Thu, Apr 12, 2012 at 3:16 PM, Richard Guenther
wrote:
> On Thu, Apr 12, 2012 at 1:05 PM, Igor Zamyatin wrote:
>> On Wed, Apr 11, 2012 at 12:39 PM, Richard Guenther
>> wrote:
>>> On Tue, Apr 10, 2012 at 8:43 PM, Igor Zamyatin wrote:
Hi All!
Here is a patch that enables unroll a
> > So would need much more benchmarking on macro workloads first at least.
>
> Like what, for example? I believe in this case everything also
> strongly depends on test usage model (e.g. it usually compiled with Os
> not O2) and, let's say, internal test structure - whether there are
> hot loops
On Thu, Apr 12, 2012 at 1:05 PM, Igor Zamyatin wrote:
> On Wed, Apr 11, 2012 at 12:39 PM, Richard Guenther
> wrote:
>> On Tue, Apr 10, 2012 at 8:43 PM, Igor Zamyatin wrote:
>>> Hi All!
>>>
>>> Here is a patch that enables unroll at O2 for Atom.
>>>
>>> This gives good performance boost on EEMBC
On Wed, Apr 11, 2012 at 12:39 PM, Richard Guenther
wrote:
> On Tue, Apr 10, 2012 at 8:43 PM, Igor Zamyatin wrote:
>> Hi All!
>>
>> Here is a patch that enables unroll at O2 for Atom.
>>
>> This gives good performance boost on EEMBC 2.0 (~+8% in Geomean for 32
>> bits) with quite moderate code siz
On Wed, Apr 11, 2012 at 5:34 PM, Andi Kleen wrote:
> Richard Guenther writes:
>>
>> 5% is not moderate. Your patch does enable unrolling at -O2 but not -O3,
>> why? Why do you disable register renaming? check_imull requires a function
>> comment.
>>
>> This completely looks like a hack for EEMB
Richard Guenther writes:
>
> 5% is not moderate. Your patch does enable unrolling at -O2 but not -O3,
> why? Why do you disable register renaming? check_imull requires a function
> comment.
>
> This completely looks like a hack for EEMBC2.0, so it's definitely not ok.
>
> -O2 is not supposed to
On Tue, Apr 10, 2012 at 8:43 PM, Igor Zamyatin wrote:
> Hi All!
>
> Here is a patch that enables unroll at O2 for Atom.
>
> This gives good performance boost on EEMBC 2.0 (~+8% in Geomean for 32
> bits) with quite moderate code size increase (~5% for EEMBC2.0, 32
> bits).
5% is not moderate. You
Hi All!
Here is a patch that enables unroll at O2 for Atom.
This gives good performance boost on EEMBC 2.0 (~+8% in Geomean for 32
bits) with quite moderate code size increase (~5% for EEMBC2.0, 32
bits).
Tested for i386 and x86-64, ok for trunk?
Thanks,
Igor
ChangeLog:
2012-04-10 Yakovlev V