x86: don't use AVX512BW vmovdqu variants without -mavx512bw
commitf87ff9a27c515de066d05889b2be091a67f699b9
authorjbeulich <jbeulich@138bc75d-0d04-0410-961f-82ee72b054a4>
Wed, 3 Jan 2018 10:42:08 +0000 (3 10:42 +0000)
committerjbeulich <jbeulich@138bc75d-0d04-0410-961f-82ee72b054a4>
Wed, 3 Jan 2018 10:42:08 +0000 (3 10:42 +0000)
tree26c96624b0d0ddcb91294085689f0404c1ebfba1
parent8e8f6434760cfe2a1c6c9644181189fdb4d987bb
x86: don't use AVX512BW vmovdqu variants without -mavx512bw

Simply mirror the MODE_XI logic of handling unaligned operands in
mov<mode>_internal into MODE_TI / MODE_OI handling.

gcc/
2018-01-03  Jan Beulich  <jbeulich@suse.com>

* sse.md (mov<mode>_internal): Tighten condition for when to use
vmovdqu<ssescalarsize> for TI and OI modes.

gcc/testsuite/
2018-01-03  Jan Beulich  <jbeulich@suse.com>

* gcc.target/i386/avx512vl-no-vmovdqu8.c,
gcc.target/i386/avx512vl-no-vmovdqu16.c: New.

git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@256170 138bc75d-0d04-0410-961f-82ee72b054a4
gcc/ChangeLog
gcc/config/i386/sse.md
gcc/testsuite/ChangeLog
gcc/testsuite/gcc.target/i386/avx512vl-no-vmovdqu16.c [new file with mode: 0644]
gcc/testsuite/gcc.target/i386/avx512vl-no-vmovdqu8.c [new file with mode: 0644]