Hi all, This patch aims to add a combine splitter to transform pxor/pcmpeqb/pmovmskb/cmp 0xffff to ptest.
Regtested on x86_64-pc-linux-gnu. Ok for trunk? BRs, Haochen gcc/ChangeLog: PR target/104371 * config/i386/sse.md: Add new define_mode_attr and define_split. gcc/testsuite/ChangeLog: PR target/104371 * gcc.target/i386/pr104371-1.c: New test. * gcc.target/i386/pr104371-2.c: Ditto. --- gcc/config/i386/sse.md | 19 +++++++++++++++++++ gcc/testsuite/gcc.target/i386/pr104371-1.c | 14 ++++++++++++++ gcc/testsuite/gcc.target/i386/pr104371-2.c | 14 ++++++++++++++ 3 files changed, 47 insertions(+) create mode 100644 gcc/testsuite/gcc.target/i386/pr104371-1.c create mode 100755 gcc/testsuite/gcc.target/i386/pr104371-2.c diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index 7b791def542..71afda73c8f 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -20083,6 +20083,25 @@ (set_attr "prefix" "maybe_vex") (set_attr "mode" "SI")]) +;; Optimize pxor/pcmpeqb/pmovmskb/cmp 0xffff to ptest. +(define_mode_attr vi1avx2const + [(V32QI "0xffffffff") (V16QI "0xffff")]) + +(define_split + [(set (reg:CCZ FLAGS_REG) + (compare:CCZ (unspec:SI + [(eq:VI1_AVX2 + (match_operand:VI1_AVX2 0 "vector_operand") + (match_operand:VI1_AVX2 1 "const0_operand"))] + UNSPEC_MOVMSK) + (match_operand 2 "const_int_operand")))] + "TARGET_SSE4_1 && ix86_match_ccmode (insn, CCmode) + && (INTVAL (operands[2]) == (int) (<vi1avx2const>))" + [(set (reg:CC FLAGS_REG) + (unspec:CC [(match_dup 0) + (match_dup 0)] + UNSPEC_PTEST))]) + (define_expand "sse2_maskmovdqu" [(set (match_operand:V16QI 0 "memory_operand") (unspec:V16QI [(match_operand:V16QI 1 "register_operand") diff --git a/gcc/testsuite/gcc.target/i386/pr104371-1.c b/gcc/testsuite/gcc.target/i386/pr104371-1.c new file mode 100644 index 00000000000..df7c0b074e3 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr104371-1.c @@ -0,0 +1,14 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -msse4" } */ +/* { dg-final { scan-assembler "ptest\[ \\t\]" } } */ +/* { dg-final { scan-assembler-not "pxor\[ \\t\]" } } */ +/* { dg-final { scan-assembler-not "pcmpeqb\[ \\t\]" } } */ +/* { dg-final { scan-assembler-not "pmovmskb\[ \\t\]" } } */ + +#include <smmintrin.h> +#include <stdbool.h> + +bool is_zero(__m128i x) +{ + return _mm_movemask_epi8(_mm_cmpeq_epi8(x, _mm_setzero_si128())) == 0xffff; +} diff --git a/gcc/testsuite/gcc.target/i386/pr104371-2.c b/gcc/testsuite/gcc.target/i386/pr104371-2.c new file mode 100755 index 00000000000..f0d0afd5897 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr104371-2.c @@ -0,0 +1,14 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -mavx2" } */ +/* { dg-final { scan-assembler "vptest\[ \\t\]" } } */ +/* { dg-final { scan-assembler-not "vpxor\[ \\t\]" } } */ +/* { dg-final { scan-assembler-not "vpcmpeqb\[ \\t\]" } } */ +/* { dg-final { scan-assembler-not "vpmovmskb\[ \\t\]" } } */ + +#include <immintrin.h> +#include <stdbool.h> + +bool is_zero256(__m256i x) +{ + return _mm256_movemask_epi8(_mm256_cmpeq_epi8(x, _mm256_setzero_si256())) == 0xffffffff; +} -- 2.18.1