FreeChainXenon/gcc
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

sse.md (vec_unpacks_lo_hi): Always use kmovw to support AVX512F target.

Browse source 
gcc/

	* config/i386/sse.md (vec_unpacks_lo_hi): Always
	use kmovw to support AVX512F target.

From-SVN: r235270
This commit is contained in:
Ilya Enkovich 2016-04-20 11:47:13 +00:00 • committed by Ilya Enkovich
parent e6d62b46c8
commit ab04f5cd79
2 changed files with 8 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
gcc/ChangeLog
View file

@ -1,3 +1,8 @@
2016-04-20 Ilya Enkovich <ilya.enkovich@intel.com>
* config/i386/sse.md (vec_unpacks_lo_hi): Always
use kmovw to support AVX512F target.
2016-04-20 Bin Cheng <bin.cheng@arm.com>
* tree-scalar-evolution.c (interpret_rhs_expr): Handle BIT_AND_EXPR.

6
gcc/config/i386/sse.md
View file

@ -13233,9 +13233,9 @@
"ix86_expand_sse_unpack (operands[0], operands[1], true, false); DONE;")
(define_expand "vec_unpacks_lo_hi"
[(set (match_operand:QI 0 "register_operand")
(subreg:QI (match_operand:HI 1 "register_operand") 0))]
"TARGET_AVX512DQ")
[(set (subreg:HI (match_operand:QI 0 "register_operand") 0)
(match_operand:HI 1 "register_operand"))]
"TARGET_AVX512F")
(define_expand "vec_unpacks_lo_si"
[(set (match_operand:HI 0 "register_operand")