diff options
author | Haochen Jiang <haochen.jiang@intel.com> | 2022-02-08 10:51:26 +0800 |
---|---|---|
committer | Hongyu Wang <hongyu.wang@intel.com> | 2022-05-12 17:30:43 +0800 |
commit | 3c9364f29e7e47eb9de33f2d8843d5b00284ceca (patch) | |
tree | 8d5b5d22227232ca4f5708e63a075d0ef7090e6f /gcc | |
parent | 7f78783dbedca0183d193e475262ca3c489fd365 (diff) | |
download | gcc-3c9364f29e7e47eb9de33f2d8843d5b00284ceca.zip gcc-3c9364f29e7e47eb9de33f2d8843d5b00284ceca.tar.gz gcc-3c9364f29e7e47eb9de33f2d8843d5b00284ceca.tar.bz2 |
i386: Add combine splitter to transform pxor/pcmpeqb/pmovmskb/cmp 0xffff to ptest.
gcc/ChangeLog:
PR target/104371
* config/i386/sse.md (vi1avx2const): New define_mode_attr.
(pxor/pcmpeqb/pmovmskb/cmp 0xffff to ptest splitter):
New define_split pattern.
gcc/testsuite/ChangeLog:
PR target/104371
* gcc.target/i386/pr104371-1.c: New test.
* gcc.target/i386/pr104371-2.c: Ditto.
Diffstat (limited to 'gcc')
-rw-r--r-- | gcc/config/i386/sse.md | 18 | ||||
-rw-r--r-- | gcc/testsuite/gcc.target/i386/pr104371-1.c | 13 | ||||
-rwxr-xr-x | gcc/testsuite/gcc.target/i386/pr104371-2.c | 13 |
3 files changed, 44 insertions, 0 deletions
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index a63df0d..6578104 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -20177,6 +20177,24 @@ (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 && (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 0000000..b4373c5 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr104371-1.c @@ -0,0 +1,13 @@ +/* { 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> + +int 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 0000000..3431ffc --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr104371-2.c @@ -0,0 +1,13 @@ +/* { 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> + +int is_zero256(__m256i x) +{ + return _mm256_movemask_epi8(_mm256_cmpeq_epi8(x, _mm256_setzero_si256())) == 0xffffffff; +} |