Re: [patch] Excessive alignment in ix86_data_alignment

2014-11-26 Thread Petr Murzin
On 09 Oct 08:25, H.J. Lu wrote: > On Thu, Oct 9, 2014 at 1:37 AM, Uros Bizjak wrote: > > On Thu, Oct 9, 2014 at 10:25 AM, Kirill Yukhin > > wrote: > >> On 08 Oct 23:02, Petr Murzin wrote: > >>> Hi, > >>> I have measured performance impact on Haswell platform according to this > >>> input: > >>>

Re: [patch] Excessive alignment in ix86_data_alignment

2014-10-23 Thread Petr Murzin
On 09 Oct 08:25, H.J. Lu wrote: > On Thu, Oct 9, 2014 at 1:37 AM, Uros Bizjak wrote: > > On Thu, Oct 9, 2014 at 10:25 AM, Kirill Yukhin > > wrote: > >> On 08 Oct 23:02, Petr Murzin wrote: > >>> Hi, > >>> I have measured performance impact on Haswell platform according to this > >>> input: > >>>

Re: [patch] Excessive alignment in ix86_data_alignment

2014-10-09 Thread H.J. Lu
On Thu, Oct 9, 2014 at 1:37 AM, Uros Bizjak wrote: > On Thu, Oct 9, 2014 at 10:25 AM, Kirill Yukhin > wrote: >> On 08 Oct 23:02, Petr Murzin wrote: >>> Hi, >>> I have measured performance impact on Haswell platform according to this >>> input: >>> https://gcc.gnu.org/ml/gcc-patches/2014-06/msg00

Re: [patch] Excessive alignment in ix86_data_alignment

2014-10-09 Thread Uros Bizjak
On Thu, Oct 9, 2014 at 10:25 AM, Kirill Yukhin wrote: > On 08 Oct 23:02, Petr Murzin wrote: >> Hi, >> I have measured performance impact on Haswell platform according to this >> input: >> https://gcc.gnu.org/ml/gcc-patches/2014-06/msg00978.html What about older processors? The optimization was i

Re: [patch] Excessive alignment in ix86_data_alignment

2014-10-09 Thread Kirill Yukhin
On 08 Oct 23:02, Petr Murzin wrote: > Hi, > I have measured performance impact on Haswell platform according to this > input: > https://gcc.gnu.org/ml/gcc-patches/2014-06/msg00978.html Same in plain text: For `-O2': TestPrevious Current Ratio(%) 400.perlbench 46.2000 46.2000 +0% 401.b