Hi: The following patch adds define_insn_and_split to optimize vpmovmskb %xmm0, %eax - movzwl %ax, %eax notl %eax
Bootstrapped/regtested on x86_64-linux-gnu {,-m32}. Ok for trunk? gcc/ChangeLog PR target/98461 * config/i386/sse.md (*sse2_pmovskb_zexthisi): New define_insn_and_split for zero_extend of subreg HI of pmovskb result. gcc/testsuite/ChangeLog * gcc.target/i386/sse-pr98461-2.c: New test. --- gcc/config/i386/sse.md | 11 +++++++++++ gcc/testsuite/gcc.target/i386/sse2-pr98461-2.c | 13 +++++++++++++ 2 files changed, 24 insertions(+) create mode 100644 gcc/testsuite/gcc.target/i386/sse2-pr98461-2.c diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index d84103807ff..4ed6b9ae476 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -16099,6 +16099,17 @@ (define_insn "*sse2_pmovmskb_ext" (set_attr "prefix" "maybe_vex") (set_attr "mode" "SI")]) +(define_insn_and_split "*sse2_pmovskb_zexthisi" + [(set (match_operand:SI 0 "register_operand") + (zero_extend:SI (subreg:HI (unspec:SI + [(match_operand:V16QI 1 "register_operand")] + UNSPEC_MOVMSK) 0)))] + "TARGET_SSE2" + "#" + "&& 1" + [(set (match_dup 0) + (unspec:SI [(match_dup 1)] UNSPEC_MOVMSK))]) + (define_split [(set (match_operand:SI 0 "register_operand") (unspec:SI diff --git a/gcc/testsuite/gcc.target/i386/sse2-pr98461-2.c b/gcc/testsuite/gcc.target/i386/sse2-pr98461-2.c new file mode 100644 index 00000000000..60fc1f3e9c1 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/sse2-pr98461-2.c @@ -0,0 +1,13 @@ +/* PR target/98461 */ +/* { dg-do compile } */ +/* { dg-options "-O2 -msse2 -mno-sse3 -masm=att" } */ +/* { dg-final { scan-assembler-times "\tpmovmskb\t" 1 } } */ +/* { dg-final { scan-assembler-not "\tmovzwl" } } */ +/* { dg-final { scan-assembler-times "\tnotl" 1 } } */ + +#include <immintrin.h> + +unsigned int movemask_not1(__m128i logical) { + unsigned short res = (unsigned short)(_mm_movemask_epi8(logical)); + return ~res; +} -- 2.18.1 -- BR, Hongtao