diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc index 2e0d12c010881e45ff9c7ed41aef484acaf66b0d..9c92b07d5cd84c64611eb66aa0ee0136ea526085 100644 --- a/gcc/config/i386/i386-expand.cc +++ b/gcc/config/i386/i386-expand.cc @@ -4510,15 +4510,86 @@ ix86_expand_int_sse_cmp (rtx dest, enum rtx_code code, rtx cop0, rtx cop1, case GTU: break; - case NE: case LE: case LEU: + /* x <= cst can be handled as x < cst + 1 unless there is + wrap around in cst + 1. */ + if (GET_CODE (cop1) == CONST_VECTOR + && GET_MODE_INNER (mode) != TImode) + { + unsigned int n_elts = GET_MODE_NUNITS (mode), i; + machine_mode eltmode = GET_MODE_INNER (mode); + for (i = 0; i < n_elts; ++i) + { + rtx elt = CONST_VECTOR_ELT (cop1, i); + if (!CONST_INT_P (elt)) + break; + if (code == GE) + { + /* For LE punt if some element is signed maximum. */ + if ((INTVAL (elt) & (GET_MODE_MASK (eltmode) >> 1)) + == (GET_MODE_MASK (eltmode) >> 1)) + break; + } + /* For LEU punt if some element is unsigned maximum. */ + else if (elt == constm1_rtx) + break; + } + if (i == n_elts) + { + rtvec v = rtvec_alloc (n_elts); + for (i = 0; i < n_elts; ++i) + RTVEC_ELT (v, i) + = GEN_INT (INTVAL (CONST_VECTOR_ELT (cop1, i)) + 1); + cop1 = gen_rtx_CONST_VECTOR (mode, v); + std::swap (cop0, cop1); + code = code == LE ? GT : GTU; + break; + } + } + /* FALLTHRU */ + case NE: code = reverse_condition (code); *negate = true; break; case GE: case GEU: + /* x >= cst can be handled as x > cst - 1 unless there is + wrap around in cst - 1. */ + if (GET_CODE (cop1) == CONST_VECTOR + && GET_MODE_INNER (mode) != TImode) + { + unsigned int n_elts = GET_MODE_NUNITS (mode), i; + machine_mode eltmode = GET_MODE_INNER (mode); + for (i = 0; i < n_elts; ++i) + { + rtx elt = CONST_VECTOR_ELT (cop1, i); + if (!CONST_INT_P (elt)) + break; + if (code == GE) + { + /* For GE punt if some element is signed minimum. */ + if (INTVAL (elt) < 0 + && ((INTVAL (elt) & (GET_MODE_MASK (eltmode) >> 1)) + == 0)) + break; + } + /* For GEU punt if some element is zero. */ + else if (elt == const0_rtx) + break; + } + if (i == n_elts) + { + rtvec v = rtvec_alloc (n_elts); + for (i = 0; i < n_elts; ++i) + RTVEC_ELT (v, i) + = GEN_INT (INTVAL (CONST_VECTOR_ELT (cop1, i)) - 1); + cop1 = gen_rtx_CONST_VECTOR (mode, v); + code = code == GE ? GT : GTU; + break; + } + } code = reverse_condition (code); *negate = true; /* FALLTHRU */ @@ -4556,6 +4627,11 @@ ix86_expand_int_sse_cmp (rtx dest, enum rtx_code code, rtx cop0, rtx cop1, } } + if (GET_CODE (cop0) == CONST_VECTOR) + cop0 = force_reg (mode, cop0); + else if (GET_CODE (cop1) == CONST_VECTOR) + cop1 = force_reg (mode, cop1); + rtx optrue = op_true ? op_true : CONSTM1_RTX (data_mode); rtx opfalse = op_false ? op_false : CONST0_RTX (data_mode); if (*negate) @@ -4752,13 +4828,13 @@ ix86_expand_int_sse_cmp (rtx dest, enum rtx_code code, rtx cop0, rtx cop1, if (*negate) std::swap (op_true, op_false); + if (GET_CODE (cop1) == CONST_VECTOR) + cop1 = force_reg (mode, cop1); + /* Allow the comparison to be done in one mode, but the movcc to happen in another mode. */ if (data_mode == mode) - { - x = ix86_expand_sse_cmp (dest, code, cop0, cop1, - op_true, op_false); - } + x = ix86_expand_sse_cmp (dest, code, cop0, cop1, op_true, op_false); else { gcc_assert (GET_MODE_SIZE (data_mode) == GET_MODE_SIZE (mode)); diff --git a/gcc/config/i386/predicates.md b/gcc/config/i386/predicates.md index 2a3f07224cc8155b803eda5331975c38336f5315..f995503838654969b5fa7508bc0d2c412a8b5e0b 100644 --- a/gcc/config/i386/predicates.md +++ b/gcc/config/i386/predicates.md @@ -1235,6 +1235,13 @@ (ior (match_operand 0 "register_operand") (match_operand 0 "vector_memory_operand"))) +; Return true when OP is register_operand, vector_memory_operand +; or const_vector. +(define_predicate "vector_or_const_vector_operand" + (ior (match_operand 0 "register_operand") + (match_operand 0 "vector_memory_operand") + (match_code "const_vector"))) + (define_predicate "bcst_mem_operand" (and (match_code "vec_duplicate") (and (match_test "TARGET_AVX512F") diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index fa93ae7bf21574f862133f16b7ac3aa544a69f8e..9a4fc01856dd6c2f889021a1dfbc82206bb1791d 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -4311,7 +4311,7 @@ [(set (match_operand:<sseintvecmode> 0 "register_operand") (match_operator:<sseintvecmode> 1 "" [(match_operand:VI_256 2 "register_operand") - (match_operand:VI_256 3 "nonimmediate_operand")]))] + (match_operand:VI_256 3 "nonimmediate_or_const_vector_operand")]))] "TARGET_AVX2" { bool ok = ix86_expand_int_vec_cmp (operands); @@ -4323,7 +4323,7 @@ [(set (match_operand:<sseintvecmode> 0 "register_operand") (match_operator:<sseintvecmode> 1 "" [(match_operand:VI124_128 2 "register_operand") - (match_operand:VI124_128 3 "vector_operand")]))] + (match_operand:VI124_128 3 "vector_or_const_vector_operand")]))] "TARGET_SSE2" { bool ok = ix86_expand_int_vec_cmp (operands); @@ -4335,7 +4335,7 @@ [(set (match_operand:V2DI 0 "register_operand") (match_operator:V2DI 1 "" [(match_operand:V2DI 2 "register_operand") - (match_operand:V2DI 3 "vector_operand")]))] + (match_operand:V2DI 3 "vector_or_const_vector_operand")]))] "TARGET_SSE4_2" { bool ok = ix86_expand_int_vec_cmp (operands); @@ -4397,7 +4397,7 @@ [(set (match_operand:<sseintvecmode> 0 "register_operand") (match_operator:<sseintvecmode> 1 "" [(match_operand:VI_256 2 "register_operand") - (match_operand:VI_256 3 "nonimmediate_operand")]))] + (match_operand:VI_256 3 "nonimmediate_or_const_vector_operand")]))] "TARGET_AVX2" { bool ok = ix86_expand_int_vec_cmp (operands); @@ -4409,7 +4409,7 @@ [(set (match_operand:<sseintvecmode> 0 "register_operand") (match_operator:<sseintvecmode> 1 "" [(match_operand:VI124_128 2 "register_operand") - (match_operand:VI124_128 3 "vector_operand")]))] + (match_operand:VI124_128 3 "vector_or_const_vector_operand")]))] "TARGET_SSE2" { bool ok = ix86_expand_int_vec_cmp (operands); @@ -4421,7 +4421,7 @@ [(set (match_operand:V2DI 0 "register_operand") (match_operator:V2DI 1 "" [(match_operand:V2DI 2 "register_operand") - (match_operand:V2DI 3 "vector_operand")]))] + (match_operand:V2DI 3 "vector_or_const_vector_operand")]))] "TARGET_SSE4_2" { bool ok = ix86_expand_int_vec_cmp (operands); diff --git a/gcc/testsuite/gcc.target/i386/pr107546.c b/gcc/testsuite/gcc.target/i386/pr107546.c new file mode 100644 index 0000000000000000000000000000000000000000..e5cf56d762058448871bfc64688088322fc230f0 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr107546.c @@ -0,0 +1,19 @@ +/* PR target/107546 */ +/* { dg-do compile } */ +/* { dg-options "-O2 -msse2 -mno-xop -mno-avx512f" } */ +/* { dg-final { scan-assembler-not "pcmpeqb\t" } } */ +/* { dg-final { scan-assembler-times "pcmpgtb\t" 2 } } */ + +typedef signed char V __attribute__((vector_size(16))); + +V +foo (V x) +{ + return x < 48; +} + +V +bar (V x) +{ + return x >= (V) { 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57 }; +}