Re: Ping: [PATCH] x86: don't use AVX512BW vmovdqu variants without -mavx512bw

2018-01-02 Thread Jan Hubicka
> >>> On 02.01.18 at 11:05, wrote: > >> >>> On 13.12.17 at 10:33, wrote: > >> > Simply mirror the MODE_XI logic of handling unaligned operands in > >> > mov_internal into MODE_TI / MODE_OI handling. > >> > > >> > gcc/ > >> > 2017-12-13 Jan Beulich > >> > > >> > * sse.md (mov_internal): Tigh

Re: Ping: [PATCH] x86: don't use AVX512BW vmovdqu variants without -mavx512bw

2018-01-02 Thread Jan Beulich
>>> On 02.01.18 at 11:05, wrote: >> >>> On 13.12.17 at 10:33, wrote: >> > Simply mirror the MODE_XI logic of handling unaligned operands in >> > mov_internal into MODE_TI / MODE_OI handling. >> > >> > gcc/ >> > 2017-12-13 Jan Beulich >> > >> >* sse.md (mov_internal): Tighten condition fo

Re: Ping: [PATCH] x86: don't use AVX512BW vmovdqu variants without -mavx512bw

2018-01-02 Thread Jan Hubicka
> >>> On 13.12.17 at 10:33, wrote: > > Simply mirror the MODE_XI logic of handling unaligned operands in > > mov_internal into MODE_TI / MODE_OI handling. > > > > gcc/ > > 2017-12-13 Jan Beulich > > > > * sse.md (mov_internal): Tighten condition for when to use > > vmovdqu for TI and

Ping: [PATCH] x86: don't use AVX512BW vmovdqu variants without -mavx512bw

2018-01-02 Thread Jan Beulich
>>> On 13.12.17 at 10:33, wrote: > Simply mirror the MODE_XI logic of handling unaligned operands in > mov_internal into MODE_TI / MODE_OI handling. > > gcc/ > 2017-12-13 Jan Beulich > > * sse.md (mov_internal): Tighten condition for when to use > vmovdqu for TI and OI modes. > >

[PATCH] x86: don't use AVX512BW vmovdqu variants without -mavx512bw

2017-12-13 Thread Jan Beulich
Simply mirror the MODE_XI logic of handling unaligned operands in mov_internal into MODE_TI / MODE_OI handling. gcc/ 2017-12-13 Jan Beulich * sse.md (mov_internal): Tighten condition for when to use vmovdqu for TI and OI modes. gcc/testsuite/ 2017-12-13 Jan Beulich