From 94fc87ecdf45e2455deb7ee50e13765c98d4e904 Mon Sep 17 00:00:00 2001 From: Tamar Christina Date: Thu, 8 Jun 2017 07:38:42 +0000 Subject: [PATCH] re PR middle-end/77925 (Add __builtin_issubnormal) 2017-06-08 Tamar Christina PR middle-end/77925 PR middle-end/77926 PR middle-end/66462 * gcc/builtins.c (fold_builtin_fpclassify): Remove. (fold_builtin_interclass_mathfn): Remove. (expand_builtin): Add builtins to lowering list. (fold_builtin_n): Remove fold_builtin_varargs. (fold_builtin_varargs): Remove. * gcc/builtins.def (BUILT_IN_ISZERO, BUILT_IN_ISSUBNORMAL): New. * gcc/real.h (get_min_float): New. (real_format): Add is_ieee_compatible field. * gcc/real.c (get_min_float): New. (ieee_single_format): Set is_ieee_compatible flag. * gcc/gimple-low.c (lower_stm): Define BUILT_IN_FPCLASSIFY, CASE_FLT_FN (BUILT_IN_ISINF), BUILT_IN_ISINFD32, BUILT_IN_ISINFD64, BUILT_IN_ISINFD128, BUILT_IN_ISNAND32, BUILT_IN_ISNAND64, BUILT_IN_ISNAND128, BUILT_IN_ISNAN, BUILT_IN_ISNORMAL, BUILT_IN_ISZERO, BUILT_IN_ISSUBNORMAL, CASE_FLT_FN (BUILT_IN_FINITE), BUILT_IN_FINITED32 BUILT_IN_FINITED64, BUILT_IN_FINITED128, BUILT_IN_ISFINITE. (lower_builtin_fpclassify, is_nan, is_normal, is_infinity): New. (is_zero, is_subnormal, is_finite, use_ieee_int_mode): Likewise. (lower_builtin_isnan, lower_builtin_isinfinite): Likewise. (lower_builtin_isnormal, lower_builtin_iszero): Likewise. (lower_builtin_issubnormal, lower_builtin_isfinite): Likewise. (emit_tree_cond, get_num_as_int, emit_tree_and_return_var): New. (mips_single_format): Likewise. (motorola_single_format): Likewise. (spu_single_format): Likewise. (ieee_double_format): Likewise. (mips_double_format): Likewise. (motorola_double_format): Likewise. (ieee_extended_motorola_format): Likewise. (ieee_extended_intel_128_format): Likewise. (ieee_extended_intel_96_round_53_format): Likewise. (ibm_extended_format): Likewise. (mips_extended_format): Likewise. (ieee_quad_format): Likewise. (mips_quad_format): Likewise. (vax_f_format): Likewise. (vax_d_format): Likewise. (vax_g_format): Likewise. (decimal_single_format): Likewise. (decimal_quad_format): Likewise. (iee_half_format): Likewise. (mips_single_format): Likewise. (arm_half_format): Likewise. (real_internal_format): Likewise. * gcc/doc/extend.texi: Add documentation for built-ins. * gcc/c/c-typeck.c (convert_arguments): Add BUILT_IN_ISZERO and BUILT_IN_ISSUBNORMAL. gcc/testsuite/ 2017-06-08 Tamar Christina * gcc.target/aarch64/builtin-fpclassify.c: New codegen test. * gcc.dg/fold-notunord.c: Removed. * gcc.dg/torture/floatn-tg-4.h: Add tests for iszero and issubnormal. * gcc.dg/torture/float128-tg-4.c: Likewise. * gcc.dg/torture/float128x-tg-4: Likewise. * gcc.dg/torture/float16-tg-4.c: Likewise. * gcc.dg/torture/float32-tg-4.c: Likewise. * gcc.dg/torture/float32x-tg-4.c: Likewise. * gcc.dg/torture/float64-tg-4.c: Likewise. * gcc.dg/torture/float64x-tg-4.c: Likewise. * gcc.dg/pr28796-1.c: Add -O2. * gcc.dg/builtins-43.c: Check lower instead of gimple. * gcc.dg/tg-tests.h: Add iszero and issubnormal. * gcc.dg/pr77925.c: Add to test safe cases. From-SVN: r249005 --- gcc/ChangeLog | 54 ++ gcc/builtins.c | 374 +------ gcc/builtins.def | 2 + gcc/c/c-typeck.c | 2 + gcc/doc/extend.texi | 53 +- gcc/gimple-low.c | 910 +++++++++++++++++- gcc/real.c | 34 + gcc/real.h | 18 + gcc/testsuite/ChangeLog | 17 + gcc/testsuite/gcc.dg/builtins-43.c | 4 +- gcc/testsuite/gcc.dg/fold-notunord.c | 9 - gcc/testsuite/gcc.dg/pr28796-1.c | 2 +- gcc/testsuite/gcc.dg/pr77925.c | 11 + gcc/testsuite/gcc.dg/tg-tests.h | 47 +- gcc/testsuite/gcc.dg/torture/float128-tg-4.c | 11 + gcc/testsuite/gcc.dg/torture/float128x-tg-4.c | 11 + gcc/testsuite/gcc.dg/torture/float16-tg-4.c | 11 + gcc/testsuite/gcc.dg/torture/float32-tg-4.c | 11 + gcc/testsuite/gcc.dg/torture/float32x-tg-4.c | 11 + gcc/testsuite/gcc.dg/torture/float64-tg-4.c | 11 + gcc/testsuite/gcc.dg/torture/float64x-tg-4.c | 11 + gcc/testsuite/gcc.dg/torture/floatn-tg-4.h | 99 ++ .../gcc.target/aarch64/builtin-fpclassify.c | 22 + 23 files changed, 1355 insertions(+), 380 deletions(-) delete mode 100644 gcc/testsuite/gcc.dg/fold-notunord.c create mode 100644 gcc/testsuite/gcc.dg/pr77925.c create mode 100644 gcc/testsuite/gcc.dg/torture/float128-tg-4.c create mode 100644 gcc/testsuite/gcc.dg/torture/float128x-tg-4.c create mode 100644 gcc/testsuite/gcc.dg/torture/float16-tg-4.c create mode 100644 gcc/testsuite/gcc.dg/torture/float32-tg-4.c create mode 100644 gcc/testsuite/gcc.dg/torture/float32x-tg-4.c create mode 100644 gcc/testsuite/gcc.dg/torture/float64-tg-4.c create mode 100644 gcc/testsuite/gcc.dg/torture/float64x-tg-4.c create mode 100644 gcc/testsuite/gcc.dg/torture/floatn-tg-4.h create mode 100644 gcc/testsuite/gcc.target/aarch64/builtin-fpclassify.c diff --git a/gcc/ChangeLog b/gcc/ChangeLog index f07dc97d21e..15dbf0aebc9 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,57 @@ +2017-06-08 Tamar Christina + + PR middle-end/77925 + PR middle-end/77926 + PR middle-end/66462 + + * gcc/builtins.c (fold_builtin_fpclassify): Remove. + (fold_builtin_interclass_mathfn): Remove. + (expand_builtin): Add builtins to lowering list. + (fold_builtin_n): Remove fold_builtin_varargs. + (fold_builtin_varargs): Remove. + * gcc/builtins.def (BUILT_IN_ISZERO, BUILT_IN_ISSUBNORMAL): New. + * gcc/real.h (get_min_float): New. + (real_format): Add is_ieee_compatible field. + * gcc/real.c (get_min_float): New. + (ieee_single_format): Set is_ieee_compatible flag. + * gcc/gimple-low.c (lower_stm): Define BUILT_IN_FPCLASSIFY, + CASE_FLT_FN (BUILT_IN_ISINF), BUILT_IN_ISINFD32, BUILT_IN_ISINFD64, + BUILT_IN_ISINFD128, BUILT_IN_ISNAND32, BUILT_IN_ISNAND64, + BUILT_IN_ISNAND128, BUILT_IN_ISNAN, BUILT_IN_ISNORMAL, BUILT_IN_ISZERO, + BUILT_IN_ISSUBNORMAL, CASE_FLT_FN (BUILT_IN_FINITE), BUILT_IN_FINITED32 + BUILT_IN_FINITED64, BUILT_IN_FINITED128, BUILT_IN_ISFINITE. + (lower_builtin_fpclassify, is_nan, is_normal, is_infinity): New. + (is_zero, is_subnormal, is_finite, use_ieee_int_mode): Likewise. + (lower_builtin_isnan, lower_builtin_isinfinite): Likewise. + (lower_builtin_isnormal, lower_builtin_iszero): Likewise. + (lower_builtin_issubnormal, lower_builtin_isfinite): Likewise. + (emit_tree_cond, get_num_as_int, emit_tree_and_return_var): New. + (mips_single_format): Likewise. + (motorola_single_format): Likewise. + (spu_single_format): Likewise. + (ieee_double_format): Likewise. + (mips_double_format): Likewise. + (motorola_double_format): Likewise. + (ieee_extended_motorola_format): Likewise. + (ieee_extended_intel_128_format): Likewise. + (ieee_extended_intel_96_round_53_format): Likewise. + (ibm_extended_format): Likewise. + (mips_extended_format): Likewise. + (ieee_quad_format): Likewise. + (mips_quad_format): Likewise. + (vax_f_format): Likewise. + (vax_d_format): Likewise. + (vax_g_format): Likewise. + (decimal_single_format): Likewise. + (decimal_quad_format): Likewise. + (iee_half_format): Likewise. + (mips_single_format): Likewise. + (arm_half_format): Likewise. + (real_internal_format): Likewise. + * gcc/doc/extend.texi: Add documentation for built-ins. + * gcc/c/c-typeck.c (convert_arguments): Add BUILT_IN_ISZERO + and BUILT_IN_ISSUBNORMAL. + 2017-06-07 Carl Love * config/rs6000/rs6000-c: The return type of the following diff --git a/gcc/builtins.c b/gcc/builtins.c index 30462ad0f41..254dab6bfa1 100644 --- a/gcc/builtins.c +++ b/gcc/builtins.c @@ -165,7 +165,6 @@ static tree fold_builtin_0 (location_t, tree); static tree fold_builtin_1 (location_t, tree, tree); static tree fold_builtin_2 (location_t, tree, tree, tree); static tree fold_builtin_3 (location_t, tree, tree, tree, tree); -static tree fold_builtin_varargs (location_t, tree, tree*, int); static tree fold_builtin_strpbrk (location_t, tree, tree, tree); static tree fold_builtin_strspn (location_t, tree, tree); @@ -2227,19 +2226,8 @@ interclass_mathfn_icode (tree arg, tree fndecl) switch (DECL_FUNCTION_CODE (fndecl)) { CASE_FLT_FN (BUILT_IN_ILOGB): - errno_set = true; builtin_optab = ilogb_optab; break; - CASE_FLT_FN (BUILT_IN_ISINF): - builtin_optab = isinf_optab; break; - case BUILT_IN_ISNORMAL: - case BUILT_IN_ISFINITE: - CASE_FLT_FN (BUILT_IN_FINITE): - case BUILT_IN_FINITED32: - case BUILT_IN_FINITED64: - case BUILT_IN_FINITED128: - case BUILT_IN_ISINFD32: - case BUILT_IN_ISINFD64: - case BUILT_IN_ISINFD128: - /* These builtins have no optabs (yet). */ + errno_set = true; + builtin_optab = ilogb_optab; break; default: gcc_unreachable (); @@ -2258,8 +2246,7 @@ interclass_mathfn_icode (tree arg, tree fndecl) } /* Expand a call to one of the builtin math functions that operate on - floating point argument and output an integer result (ilogb, isinf, - isnan, etc). + floating point argument and output an integer result (ilogb, etc). Return 0 if a normal call should be emitted rather than expanding the function in-line. EXP is the expression that is a call to the builtin function; if convenient, the result should be placed in TARGET. */ @@ -6605,11 +6592,7 @@ expand_builtin (tree exp, rtx target, rtx subtarget, machine_mode mode, CASE_FLT_FN (BUILT_IN_ILOGB): if (! flag_unsafe_math_optimizations) break; - gcc_fallthrough (); - CASE_FLT_FN (BUILT_IN_ISINF): - CASE_FLT_FN (BUILT_IN_FINITE): - case BUILT_IN_ISFINITE: - case BUILT_IN_ISNORMAL: + target = expand_builtin_interclass_mathfn (exp, target); if (target) return target; @@ -6917,8 +6900,25 @@ expand_builtin (tree exp, rtx target, rtx subtarget, machine_mode mode, } break; + CASE_FLT_FN (BUILT_IN_ISINF): + case BUILT_IN_ISNAND32: + case BUILT_IN_ISNAND64: + case BUILT_IN_ISNAND128: + case BUILT_IN_ISNAN: + case BUILT_IN_ISINFD32: + case BUILT_IN_ISINFD64: + case BUILT_IN_ISINFD128: + case BUILT_IN_ISNORMAL: + case BUILT_IN_ISZERO: + case BUILT_IN_ISSUBNORMAL: + case BUILT_IN_FPCLASSIFY: case BUILT_IN_SETJMP: - /* This should have been lowered to the builtins below. */ + CASE_FLT_FN (BUILT_IN_FINITE): + case BUILT_IN_FINITED32: + case BUILT_IN_FINITED64: + case BUILT_IN_FINITED128: + case BUILT_IN_ISFINITE: + /* These should have been lowered to the builtins in gimple-low.c. */ gcc_unreachable (); case BUILT_IN_SETJMP_SETUP: @@ -8258,184 +8258,19 @@ fold_builtin_modf (location_t loc, tree arg0, tree arg1, tree rettype) return NULL_TREE; } -/* Given a location LOC, an interclass builtin function decl FNDECL - and its single argument ARG, return an folded expression computing - the same, or NULL_TREE if we either couldn't or didn't want to fold - (the latter happen if there's an RTL instruction available). */ - -static tree -fold_builtin_interclass_mathfn (location_t loc, tree fndecl, tree arg) -{ - machine_mode mode; - - if (!validate_arg (arg, REAL_TYPE)) - return NULL_TREE; - - if (interclass_mathfn_icode (arg, fndecl) != CODE_FOR_nothing) - return NULL_TREE; - - mode = TYPE_MODE (TREE_TYPE (arg)); - - bool is_ibm_extended = MODE_COMPOSITE_P (mode); - /* If there is no optab, try generic code. */ - switch (DECL_FUNCTION_CODE (fndecl)) - { - tree result; - CASE_FLT_FN (BUILT_IN_ISINF): - { - /* isinf(x) -> isgreater(fabs(x),DBL_MAX). */ - tree const isgr_fn = builtin_decl_explicit (BUILT_IN_ISGREATER); - tree type = TREE_TYPE (arg); - REAL_VALUE_TYPE r; - char buf[128]; - - if (is_ibm_extended) - { - /* NaN and Inf are encoded in the high-order double value - only. The low-order value is not significant. */ - type = double_type_node; - mode = DFmode; - arg = fold_build1_loc (loc, NOP_EXPR, type, arg); - } - get_max_float (REAL_MODE_FORMAT (mode), buf, sizeof (buf)); - real_from_string (&r, buf); - result = build_call_expr (isgr_fn, 2, - fold_build1_loc (loc, ABS_EXPR, type, arg), - build_real (type, r)); - return result; - } - CASE_FLT_FN (BUILT_IN_FINITE): - case BUILT_IN_ISFINITE: - { - /* isfinite(x) -> islessequal(fabs(x),DBL_MAX). */ - tree const isle_fn = builtin_decl_explicit (BUILT_IN_ISLESSEQUAL); - tree type = TREE_TYPE (arg); - REAL_VALUE_TYPE r; - char buf[128]; - - if (is_ibm_extended) - { - /* NaN and Inf are encoded in the high-order double value - only. The low-order value is not significant. */ - type = double_type_node; - mode = DFmode; - arg = fold_build1_loc (loc, NOP_EXPR, type, arg); - } - get_max_float (REAL_MODE_FORMAT (mode), buf, sizeof (buf)); - real_from_string (&r, buf); - result = build_call_expr (isle_fn, 2, - fold_build1_loc (loc, ABS_EXPR, type, arg), - build_real (type, r)); - /*result = fold_build2_loc (loc, UNGT_EXPR, - TREE_TYPE (TREE_TYPE (fndecl)), - fold_build1_loc (loc, ABS_EXPR, type, arg), - build_real (type, r)); - result = fold_build1_loc (loc, TRUTH_NOT_EXPR, - TREE_TYPE (TREE_TYPE (fndecl)), - result);*/ - return result; - } - case BUILT_IN_ISNORMAL: - { - /* isnormal(x) -> isgreaterequal(fabs(x),DBL_MIN) & - islessequal(fabs(x),DBL_MAX). */ - tree const isle_fn = builtin_decl_explicit (BUILT_IN_ISLESSEQUAL); - tree type = TREE_TYPE (arg); - tree orig_arg, max_exp, min_exp; - machine_mode orig_mode = mode; - REAL_VALUE_TYPE rmax, rmin; - char buf[128]; - - orig_arg = arg = builtin_save_expr (arg); - if (is_ibm_extended) - { - /* Use double to test the normal range of IBM extended - precision. Emin for IBM extended precision is - different to emin for IEEE double, being 53 higher - since the low double exponent is at least 53 lower - than the high double exponent. */ - type = double_type_node; - mode = DFmode; - arg = fold_build1_loc (loc, NOP_EXPR, type, arg); - } - arg = fold_build1_loc (loc, ABS_EXPR, type, arg); - - get_max_float (REAL_MODE_FORMAT (mode), buf, sizeof (buf)); - real_from_string (&rmax, buf); - sprintf (buf, "0x1p%d", REAL_MODE_FORMAT (orig_mode)->emin - 1); - real_from_string (&rmin, buf); - max_exp = build_real (type, rmax); - min_exp = build_real (type, rmin); - - max_exp = build_call_expr (isle_fn, 2, arg, max_exp); - if (is_ibm_extended) - { - /* Testing the high end of the range is done just using - the high double, using the same test as isfinite(). - For the subnormal end of the range we first test the - high double, then if its magnitude is equal to the - limit of 0x1p-969, we test whether the low double is - non-zero and opposite sign to the high double. */ - tree const islt_fn = builtin_decl_explicit (BUILT_IN_ISLESS); - tree const isgt_fn = builtin_decl_explicit (BUILT_IN_ISGREATER); - tree gt_min = build_call_expr (isgt_fn, 2, arg, min_exp); - tree eq_min = fold_build2 (EQ_EXPR, integer_type_node, - arg, min_exp); - tree as_complex = build1 (VIEW_CONVERT_EXPR, - complex_double_type_node, orig_arg); - tree hi_dbl = build1 (REALPART_EXPR, type, as_complex); - tree lo_dbl = build1 (IMAGPART_EXPR, type, as_complex); - tree zero = build_real (type, dconst0); - tree hilt = build_call_expr (islt_fn, 2, hi_dbl, zero); - tree lolt = build_call_expr (islt_fn, 2, lo_dbl, zero); - tree logt = build_call_expr (isgt_fn, 2, lo_dbl, zero); - tree ok_lo = fold_build1 (TRUTH_NOT_EXPR, integer_type_node, - fold_build3 (COND_EXPR, - integer_type_node, - hilt, logt, lolt)); - eq_min = fold_build2 (TRUTH_ANDIF_EXPR, integer_type_node, - eq_min, ok_lo); - min_exp = fold_build2 (TRUTH_ORIF_EXPR, integer_type_node, - gt_min, eq_min); - } - else - { - tree const isge_fn - = builtin_decl_explicit (BUILT_IN_ISGREATEREQUAL); - min_exp = build_call_expr (isge_fn, 2, arg, min_exp); - } - result = fold_build2 (BIT_AND_EXPR, integer_type_node, - max_exp, min_exp); - return result; - } - default: - break; - } - - return NULL_TREE; -} - -/* Fold a call to __builtin_isnan(), __builtin_isinf, __builtin_finite. +/* Fold a call to __builtin_isinf_sign. ARG is the argument for the call. */ static tree -fold_builtin_classify (location_t loc, tree fndecl, tree arg, int builtin_index) +fold_builtin_classify (location_t loc, tree arg, int builtin_index) { - tree type = TREE_TYPE (TREE_TYPE (fndecl)); - if (!validate_arg (arg, REAL_TYPE)) return NULL_TREE; switch (builtin_index) { - case BUILT_IN_ISINF: - if (!HONOR_INFINITIES (arg)) - return omit_one_operand_loc (loc, type, integer_zero_node, arg); - - return NULL_TREE; - case BUILT_IN_ISINF_SIGN: { /* isinf_sign(x) -> isinf(x) ? (signbit(x) ? -1 : 1) : 0 */ @@ -8468,106 +8303,11 @@ fold_builtin_classify (location_t loc, tree fndecl, tree arg, int builtin_index) return tmp; } - case BUILT_IN_ISFINITE: - if (!HONOR_NANS (arg) - && !HONOR_INFINITIES (arg)) - return omit_one_operand_loc (loc, type, integer_one_node, arg); - - return NULL_TREE; - - case BUILT_IN_ISNAN: - if (!HONOR_NANS (arg)) - return omit_one_operand_loc (loc, type, integer_zero_node, arg); - - { - bool is_ibm_extended = MODE_COMPOSITE_P (TYPE_MODE (TREE_TYPE (arg))); - if (is_ibm_extended) - { - /* NaN and Inf are encoded in the high-order double value - only. The low-order value is not significant. */ - arg = fold_build1_loc (loc, NOP_EXPR, double_type_node, arg); - } - } - arg = builtin_save_expr (arg); - return fold_build2_loc (loc, UNORDERED_EXPR, type, arg, arg); - default: gcc_unreachable (); } } -/* Fold a call to __builtin_fpclassify(int, int, int, int, int, ...). - This builtin will generate code to return the appropriate floating - point classification depending on the value of the floating point - number passed in. The possible return values must be supplied as - int arguments to the call in the following order: FP_NAN, FP_INFINITE, - FP_NORMAL, FP_SUBNORMAL and FP_ZERO. The ellipses is for exactly - one floating point argument which is "type generic". */ - -static tree -fold_builtin_fpclassify (location_t loc, tree *args, int nargs) -{ - tree fp_nan, fp_infinite, fp_normal, fp_subnormal, fp_zero, - arg, type, res, tmp; - machine_mode mode; - REAL_VALUE_TYPE r; - char buf[128]; - - /* Verify the required arguments in the original call. */ - if (nargs != 6 - || !validate_arg (args[0], INTEGER_TYPE) - || !validate_arg (args[1], INTEGER_TYPE) - || !validate_arg (args[2], INTEGER_TYPE) - || !validate_arg (args[3], INTEGER_TYPE) - || !validate_arg (args[4], INTEGER_TYPE) - || !validate_arg (args[5], REAL_TYPE)) - return NULL_TREE; - - fp_nan = args[0]; - fp_infinite = args[1]; - fp_normal = args[2]; - fp_subnormal = args[3]; - fp_zero = args[4]; - arg = args[5]; - type = TREE_TYPE (arg); - mode = TYPE_MODE (type); - arg = builtin_save_expr (fold_build1_loc (loc, ABS_EXPR, type, arg)); - - /* fpclassify(x) -> - isnan(x) ? FP_NAN : - (fabs(x) == Inf ? FP_INFINITE : - (fabs(x) >= DBL_MIN ? FP_NORMAL : - (x == 0 ? FP_ZERO : FP_SUBNORMAL))). */ - - tmp = fold_build2_loc (loc, EQ_EXPR, integer_type_node, arg, - build_real (type, dconst0)); - res = fold_build3_loc (loc, COND_EXPR, integer_type_node, - tmp, fp_zero, fp_subnormal); - - sprintf (buf, "0x1p%d", REAL_MODE_FORMAT (mode)->emin - 1); - real_from_string (&r, buf); - tmp = fold_build2_loc (loc, GE_EXPR, integer_type_node, - arg, build_real (type, r)); - res = fold_build3_loc (loc, COND_EXPR, integer_type_node, tmp, fp_normal, res); - - if (HONOR_INFINITIES (mode)) - { - real_inf (&r); - tmp = fold_build2_loc (loc, EQ_EXPR, integer_type_node, arg, - build_real (type, r)); - res = fold_build3_loc (loc, COND_EXPR, integer_type_node, tmp, - fp_infinite, res); - } - - if (HONOR_NANS (mode)) - { - tmp = fold_build2_loc (loc, ORDERED_EXPR, integer_type_node, arg, arg); - res = fold_build3_loc (loc, COND_EXPR, integer_type_node, tmp, res, fp_nan); - } - - return res; -} - /* Fold a call to an unordered comparison function such as __builtin_isgreater(). FNDECL is the FUNCTION_DECL for the function being called and ARG0 and ARG1 are the arguments for the call. @@ -8868,40 +8608,8 @@ fold_builtin_1 (location_t loc, tree fndecl, tree arg0) case BUILT_IN_ISDIGIT: return fold_builtin_isdigit (loc, arg0); - CASE_FLT_FN (BUILT_IN_FINITE): - case BUILT_IN_FINITED32: - case BUILT_IN_FINITED64: - case BUILT_IN_FINITED128: - case BUILT_IN_ISFINITE: - { - tree ret = fold_builtin_classify (loc, fndecl, arg0, BUILT_IN_ISFINITE); - if (ret) - return ret; - return fold_builtin_interclass_mathfn (loc, fndecl, arg0); - } - - CASE_FLT_FN (BUILT_IN_ISINF): - case BUILT_IN_ISINFD32: - case BUILT_IN_ISINFD64: - case BUILT_IN_ISINFD128: - { - tree ret = fold_builtin_classify (loc, fndecl, arg0, BUILT_IN_ISINF); - if (ret) - return ret; - return fold_builtin_interclass_mathfn (loc, fndecl, arg0); - } - - case BUILT_IN_ISNORMAL: - return fold_builtin_interclass_mathfn (loc, fndecl, arg0); - case BUILT_IN_ISINF_SIGN: - return fold_builtin_classify (loc, fndecl, arg0, BUILT_IN_ISINF_SIGN); - - CASE_FLT_FN (BUILT_IN_ISNAN): - case BUILT_IN_ISNAND32: - case BUILT_IN_ISNAND64: - case BUILT_IN_ISNAND128: - return fold_builtin_classify (loc, fndecl, arg0, BUILT_IN_ISNAN); + return fold_builtin_classify (loc, arg0, BUILT_IN_ISINF_SIGN); case BUILT_IN_FREE: if (integer_zerop (arg0)) @@ -9098,7 +8806,6 @@ fold_builtin_n (location_t loc, tree fndecl, tree *args, int nargs, bool) ret = fold_builtin_3 (loc, fndecl, args[0], args[1], args[2]); break; default: - ret = fold_builtin_varargs (loc, fndecl, args, nargs); break; } if (ret) @@ -9989,37 +9696,6 @@ fold_builtin_object_size (tree ptr, tree ost) return NULL_TREE; } -/* Builtins with folding operations that operate on "..." arguments - need special handling; we need to store the arguments in a convenient - data structure before attempting any folding. Fortunately there are - only a few builtins that fall into this category. FNDECL is the - function, EXP is the CALL_EXPR for the call. */ - -static tree -fold_builtin_varargs (location_t loc, tree fndecl, tree *args, int nargs) -{ - enum built_in_function fcode = DECL_FUNCTION_CODE (fndecl); - tree ret = NULL_TREE; - - switch (fcode) - { - case BUILT_IN_FPCLASSIFY: - ret = fold_builtin_fpclassify (loc, args, nargs); - break; - - default: - break; - } - if (ret) - { - ret = build1 (NOP_EXPR, TREE_TYPE (ret), ret); - SET_EXPR_LOCATION (ret, loc); - TREE_NO_WARNING (ret) = 1; - return ret; - } - return NULL_TREE; -} - /* Initialize format string characters in the target charset. */ bool diff --git a/gcc/builtins.def b/gcc/builtins.def index 58d78dbbdee..db45c0771fb 100644 --- a/gcc/builtins.def +++ b/gcc/builtins.def @@ -845,6 +845,8 @@ DEF_EXT_LIB_BUILTIN (BUILT_IN_ISINFL, "isinfl", BT_FN_INT_LONGDOUBLE, ATTR_CO DEF_EXT_LIB_BUILTIN (BUILT_IN_ISINFD32, "isinfd32", BT_FN_INT_DFLOAT32, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_EXT_LIB_BUILTIN (BUILT_IN_ISINFD64, "isinfd64", BT_FN_INT_DFLOAT64, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_EXT_LIB_BUILTIN (BUILT_IN_ISINFD128, "isinfd128", BT_FN_INT_DFLOAT128, ATTR_CONST_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_ISZERO, "iszero", BT_FN_INT_VAR, ATTR_CONST_NOTHROW_TYPEGENERIC_LEAF) +DEF_GCC_BUILTIN (BUILT_IN_ISSUBNORMAL, "issubnormal", BT_FN_INT_VAR, ATTR_CONST_NOTHROW_TYPEGENERIC_LEAF) DEF_C99_C90RES_BUILTIN (BUILT_IN_ISNAN, "isnan", BT_FN_INT_VAR, ATTR_CONST_NOTHROW_TYPEGENERIC_LEAF) DEF_EXT_LIB_BUILTIN (BUILT_IN_ISNANF, "isnanf", BT_FN_INT_FLOAT, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_EXT_LIB_BUILTIN (BUILT_IN_ISNANL, "isnanl", BT_FN_INT_LONGDOUBLE, ATTR_CONST_NOTHROW_LEAF_LIST) diff --git a/gcc/c/c-typeck.c b/gcc/c/c-typeck.c index 467552cef4b..92aab54d416 100644 --- a/gcc/c/c-typeck.c +++ b/gcc/c/c-typeck.c @@ -3241,6 +3241,8 @@ convert_arguments (location_t loc, vec arg_loc, tree typelist, case BUILT_IN_ISINF_SIGN: case BUILT_IN_ISNAN: case BUILT_IN_ISNORMAL: + case BUILT_IN_ISZERO: + case BUILT_IN_ISSUBNORMAL: case BUILT_IN_FPCLASSIFY: type_generic_remove_excess_precision = true; break; diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi index d467a1652ee..7d3933539e7 100644 --- a/gcc/doc/extend.texi +++ b/gcc/doc/extend.texi @@ -10501,6 +10501,10 @@ in the Cilk Plus language manual which can be found at @findex __builtin_isgreater @findex __builtin_isgreaterequal @findex __builtin_isinf_sign +@findex __builtin_isinf +@findex __builtin_isnan +@findex __builtin_iszero +@findex __builtin_issubnormal @findex __builtin_isless @findex __builtin_islessequal @findex __builtin_islessgreater @@ -11564,7 +11568,54 @@ constant values and they must appear in this order: @code{FP_NAN}, @code{FP_INFINITE}, @code{FP_NORMAL}, @code{FP_SUBNORMAL} and @code{FP_ZERO}. The ellipsis is for exactly one floating-point value to classify. GCC treats the last argument as type-generic, which -means it does not do default promotion from float to double. +means it does not do default promotion from @code{float} to @code{double}. +@end deftypefn + +@deftypefn {Built-in Function} int __builtin_isnan (...) +This built-in implements the C99 isnan functionality which checks if +the given argument represents a NaN. The return value of the +function will either be a 0 (false) or a 1 (true). +On most systems, when an IEEE 754 floating-point type is used this +built-in does not produce a signal when a signaling NaN is used. + +GCC treats the argument as type-generic, which means it does +not do default promotion from @code{float} to @code{double}. +@end deftypefn + +@deftypefn {Built-in Function} int __builtin_isinf (...) +This built-in implements the C99 isinf functionality which checks if +the given argument represents an infinite number. The return +value of the function will either be a 0 (false) or a 1 (true). + +GCC treats the argument as type-generic, which means it does +not do default promotion from @code{float} to @code{double}. +@end deftypefn + +@deftypefn {Built-in Function} int __builtin_isnormal (...) +This built-in implements the C99 isnormal functionality which checks if +the given argument represents a normal number. The return +value of the function will either be a 0 (false) or a 1 (true). + +GCC treats the argument as type-generic, which means it does +not do default promotion from @code{float} to @code{double}. +@end deftypefn + +@deftypefn {Built-in Function} int __builtin_iszero (...) +This built-in implements the TS 18661-1:2014 iszero functionality which checks if +the given argument represents the number 0 or -0. The return +value of the function will either be a 0 (false) or a 1 (true). + +GCC treats the argument as type-generic, which means it does +not do default promotion from @code{float} to @code{double}. +@end deftypefn + +@deftypefn {Built-in Function} int __builtin_issubnormal (...) +This built-in implements the TS 18661-1:2014 issubnormal functionality which checks if +the given argument represents a subnormal number. The return +value of the function will either be a 0 (false) or a 1 (true). + +GCC treats the argument as type-generic, which means it does +not do default promotion from @code{float} to @code{double}. @end deftypefn @deftypefn {Built-in Function} double __builtin_inf (void) diff --git a/gcc/gimple-low.c b/gcc/gimple-low.c index 619b9d7bfb1..1cc4a4dd699 100644 --- a/gcc/gimple-low.c +++ b/gcc/gimple-low.c @@ -30,6 +30,9 @@ along with GCC; see the file COPYING3. If not see #include "calls.h" #include "gimple-iterator.h" #include "gimple-low.h" +#include "stor-layout.h" +#include "target.h" +#include "gimplify.h" /* The differences between High GIMPLE and Low GIMPLE are the following: @@ -72,6 +75,13 @@ static void lower_gimple_bind (gimple_stmt_iterator *, struct lower_data *); static void lower_try_catch (gimple_stmt_iterator *, struct lower_data *); static void lower_gimple_return (gimple_stmt_iterator *, struct lower_data *); static void lower_builtin_setjmp (gimple_stmt_iterator *); +static void lower_builtin_fpclassify (gimple_stmt_iterator *); +static void lower_builtin_isnan (gimple_stmt_iterator *); +static void lower_builtin_isinfinite (gimple_stmt_iterator *); +static void lower_builtin_isnormal (gimple_stmt_iterator *); +static void lower_builtin_iszero (gimple_stmt_iterator *); +static void lower_builtin_issubnormal (gimple_stmt_iterator *); +static void lower_builtin_isfinite (gimple_stmt_iterator *); static void lower_builtin_posix_memalign (gimple_stmt_iterator *); @@ -330,18 +340,69 @@ lower_stmt (gimple_stmt_iterator *gsi, struct lower_data *data) if (decl && DECL_BUILT_IN_CLASS (decl) == BUILT_IN_NORMAL) { - if (DECL_FUNCTION_CODE (decl) == BUILT_IN_SETJMP) + switch (DECL_FUNCTION_CODE (decl)) { + case BUILT_IN_SETJMP: lower_builtin_setjmp (gsi); data->cannot_fallthru = false; return; - } - else if (DECL_FUNCTION_CODE (decl) == BUILT_IN_POSIX_MEMALIGN - && flag_tree_bit_ccp - && gimple_builtin_call_types_compatible_p (stmt, decl)) - { - lower_builtin_posix_memalign (gsi); + + case BUILT_IN_POSIX_MEMALIGN: + if (flag_tree_bit_ccp + && gimple_builtin_call_types_compatible_p (stmt, decl)) + { + lower_builtin_posix_memalign (gsi); + return; + } + break; + + case BUILT_IN_FPCLASSIFY: + lower_builtin_fpclassify (gsi); + data->cannot_fallthru = false; + return; + + CASE_FLT_FN (BUILT_IN_ISINF): + case BUILT_IN_ISINFD32: + case BUILT_IN_ISINFD64: + case BUILT_IN_ISINFD128: + lower_builtin_isinfinite (gsi); + data->cannot_fallthru = false; + return; + + case BUILT_IN_ISNAND32: + case BUILT_IN_ISNAND64: + case BUILT_IN_ISNAND128: + CASE_FLT_FN (BUILT_IN_ISNAN): + lower_builtin_isnan (gsi); + data->cannot_fallthru = false; + return; + + case BUILT_IN_ISNORMAL: + lower_builtin_isnormal (gsi); + data->cannot_fallthru = false; + return; + + case BUILT_IN_ISZERO: + lower_builtin_iszero (gsi); + data->cannot_fallthru = false; + return; + + case BUILT_IN_ISSUBNORMAL: + lower_builtin_issubnormal (gsi); + data->cannot_fallthru = false; + return; + + CASE_FLT_FN (BUILT_IN_FINITE): + case BUILT_IN_FINITED32: + case BUILT_IN_FINITED64: + case BUILT_IN_FINITED128: + case BUILT_IN_ISFINITE: + lower_builtin_isfinite (gsi); + data->cannot_fallthru = false; return; + + default: + break; } } @@ -822,6 +883,841 @@ lower_builtin_setjmp (gimple_stmt_iterator *gsi) gsi_remove (gsi, false); } +/* This function will if ARG is not already a variable or SSA_NAME, + create a new temporary TMP and bind ARG to TMP. This new binding is then + emitted into SEQ and TMP is returned. */ +static tree +emit_tree_and_return_var (gimple_seq *seq, tree arg) +{ + if (TREE_CODE (arg) == SSA_NAME || VAR_P (arg)) + return arg; + + tree tmp = create_tmp_reg (TREE_TYPE (arg)); + gassign *stm = gimple_build_assign (tmp, arg); + gimple_seq_add_stmt (seq, stm); + return tmp; +} + +/* This function builds an if statement that ends up using explicit branches + instead of becoming a ternary conditional select. This function assumes you + will fall through to the next statements after the condition for the false + branch. The code emitted looks like: + + if (COND) + RESULT_VARIABLE = TRUE_BRANCH + GOTO EXIT_LABEL + else + ... + + SEQ is the gimple sequence/buffer to emit any new bindings to. + RESULT_VARIABLE is the value to set if COND. + EXIT_LABEL is the label to jump to in case COND. + COND is condition to use in the conditional statement of the if. + TRUE_BRANCH is the value to set RESULT_VARIABLE to if COND. */ +static void +emit_tree_cond (gimple_seq *seq, tree result_variable, tree exit_label, + tree cond, tree true_branch) +{ + /* Create labels for fall through. */ + tree true_label = create_artificial_label (UNKNOWN_LOCATION); + tree false_label = create_artificial_label (UNKNOWN_LOCATION); + gcond *stmt = gimple_build_cond_from_tree (cond, true_label, false_label); + gimple_seq_add_stmt (seq, stmt); + + /* Build the true case. */ + gimple_seq_add_stmt (seq, gimple_build_label (true_label)); + tree value = TREE_CONSTANT (true_branch) + ? true_branch + : emit_tree_and_return_var (seq, true_branch); + gimple_seq_add_stmt (seq, gimple_build_assign (result_variable, value)); + gimple_seq_add_stmt (seq, gimple_build_goto (exit_label)); + + /* Build the false case. */ + gimple_seq_add_stmt (seq, gimple_build_label (false_label)); +} + +/* This function returns a variable containing an reinterpreted ARG as an + integer. + + SEQ is the gimple sequence/buffer to write any new bindings to. + ARG is the floating point number to reinterpret as an integer. + LOC is the location to use when doing folding operations. */ +static tree +get_num_as_int (gimple_seq *seq, tree arg, location_t loc) +{ + tree type = TREE_TYPE (arg); + + const HOST_WIDE_INT type_width = TYPE_PRECISION (type); + + /* Re-interpret the float as an unsigned integer type + with equal precision. */ + tree int_arg_type = build_nonstandard_integer_type (type_width, true); + tree conv_arg = fold_build1_loc (loc, VIEW_CONVERT_EXPR, int_arg_type, arg); + return emit_tree_and_return_var (seq, conv_arg); +} + +/* Check if ARG which is the floating point number being classified is close + enough to IEEE 754 format to be able to go in the early exit code. */ +static bool +use_ieee_int_mode (tree arg) +{ + tree type = TREE_TYPE (arg); + machine_mode mode = TYPE_MODE (type); + + const real_format *format = REAL_MODE_FORMAT (mode); + machine_mode imode = int_mode_for_mode (mode); + bool is_ibm_extended = MODE_COMPOSITE_P (mode); + + return (format->is_binary_ieee_compatible + && FLOAT_WORDS_BIG_ENDIAN == WORDS_BIG_ENDIAN + /* Check if there's a usable integer mode. */ + && imode != BLKmode + && targetm.scalar_mode_supported_p (imode) + && !is_ibm_extended); +} + +/* Perform some IBM extended format fixups on ARG for use by FP functions. + This is done by ignoring the lower 64 bits of the number. + + MODE is the machine mode of ARG. + TYPE is the type of ARG. + LOC is the location to be used in fold functions. Usually is the location + of the definition of ARG. */ +static bool +perform_ibm_extended_fixups (tree *arg, machine_mode *mode, + tree *type, location_t loc) +{ + bool is_ibm_extended = MODE_COMPOSITE_P (*mode); + if (is_ibm_extended) + { + /* NaN and Inf are encoded in the high-order double value + only. The low-order value is not significant. */ + *type = double_type_node; + *mode = DFmode; + *arg = fold_build1_loc (loc, NOP_EXPR, *type, *arg); + } + + return is_ibm_extended; +} + +/* Generates code to check if ARG is a normal number. For the FP case we check + MIN_VALUE(ARG) <= ABS(ARG) > INF and for the INT value we check the exp and + mantissa bits. Returns a variable containing a boolean which has the result + of the check. + + SEQ is the buffer to use to emit the gimple instructions into. + LOC is the location to use during fold calls. */ +static tree +is_normal (gimple_seq *seq, tree arg, location_t loc) +{ + tree type = TREE_TYPE (arg); + + machine_mode mode = TYPE_MODE (type); + const real_format *format = REAL_MODE_FORMAT (mode); + const tree bool_type = boolean_type_node; + + + /* If not using optimized route then exit early. */ + if (!use_ieee_int_mode (arg)) + { + tree orig_arg = arg; + machine_mode orig_mode = mode; + if (TREE_CODE (arg) != SSA_NAME + && (TREE_ADDRESSABLE (arg) != 0 + || (TREE_CODE (arg) != PARM_DECL + && (!VAR_P (arg) || TREE_STATIC (arg))))) + orig_arg = save_expr (arg); + + /* Perform IBM extended format fixups if required. */ + bool is_ibm_extended = perform_ibm_extended_fixups (&arg, &mode, + &type, loc); + + REAL_VALUE_TYPE rinf, rmin; + tree arg_p = fold_build1_loc (loc, ABS_EXPR, type, arg); + + tree const islt_fn = builtin_decl_explicit (BUILT_IN_ISLESS); + tree const isgt_fn = builtin_decl_explicit (BUILT_IN_ISGREATER); + tree const isge_fn = builtin_decl_explicit (BUILT_IN_ISGREATEREQUAL); + + char buf[128]; + real_inf (&rinf); + get_min_float (REAL_MODE_FORMAT (orig_mode), buf, sizeof (buf)); + real_from_string (&rmin, buf); + + tree inf_exp = build_call_expr (islt_fn, 2, arg_p, + build_real (type, rinf)); + tree min_exp = build_real (type, rmin); + if (is_ibm_extended) + { + /* Testing the high end of the range is done just using + the high double, using the same test as isfinite(). + For the subnormal end of the range we first test the + high double, then if its magnitude is equal to the + limit of 0x1p-969, we test whether the low double is + non-zero and opposite sign to the high double. */ + tree gt_min = build_call_expr (isgt_fn, 2, arg_p, min_exp); + tree eq_min = fold_build2 (EQ_EXPR, integer_type_node, + arg_p, min_exp); + tree as_complex = build1 (VIEW_CONVERT_EXPR, + complex_double_type_node, orig_arg); + tree hi_dbl = build1 (REALPART_EXPR, type, as_complex); + tree lo_dbl = build1 (IMAGPART_EXPR, type, as_complex); + tree zero = build_real (type, dconst0); + tree hilt = build_call_expr (islt_fn, 2, hi_dbl, zero); + tree lolt = build_call_expr (islt_fn, 2, lo_dbl, zero); + tree logt = build_call_expr (isgt_fn, 2, lo_dbl, zero); + tree ok_lo = fold_build1 (TRUTH_NOT_EXPR, integer_type_node, + fold_build3 (COND_EXPR, + integer_type_node, + hilt, logt, lolt)); + eq_min = fold_build2 (TRUTH_ANDIF_EXPR, integer_type_node, + eq_min, ok_lo); + min_exp = fold_build2 (TRUTH_ORIF_EXPR, integer_type_node, + gt_min, eq_min); + } + else + { + min_exp = build_call_expr (isge_fn, 2, arg_p, min_exp); + } + + push_gimplify_context (); + gimplify_expr (&min_exp, seq, NULL, is_gimple_val, fb_either); + gimplify_expr (&inf_exp, seq, NULL, is_gimple_val, fb_either); + + tree res + = fold_build2_loc (loc, BIT_AND_EXPR, bool_type, + emit_tree_and_return_var (seq, + gimple_boolify (min_exp)), + emit_tree_and_return_var (seq, + gimple_boolify (inf_exp))); + pop_gimplify_context (NULL); + + return emit_tree_and_return_var (seq, res); + } + + const tree int_type = unsigned_type_node; + const int exp_bits = (GET_MODE_SIZE (mode) * BITS_PER_UNIT) - format->p; + const int exp_mask = (1 << exp_bits) - 1; + + /* Get the number reinterpreted as an integer. */ + tree int_arg = get_num_as_int (seq, arg, loc); + + /* Extract exp bits from the float, where we expect the exponent to be. + We create a new type because BIT_FIELD_REF does not allow you to + extract less bits than the precision of the storage variable. */ + tree exp_tmp + = fold_build3_loc (loc, BIT_FIELD_REF, + build_nonstandard_integer_type (exp_bits, true), + int_arg, + build_int_cstu (int_type, exp_bits), + build_int_cstu (int_type, format->p - 1)); + tree exp_bitfield = emit_tree_and_return_var (seq, exp_tmp); + + /* Re-interpret the extracted exponent bits as a 32 bit int. + This allows us to continue doing operations as int_type. */ + tree exp + = emit_tree_and_return_var (seq, fold_build1_loc (loc, NOP_EXPR, int_type, + exp_bitfield)); + + /* exp_mask & ~1. */ + tree mask_check + = fold_build2_loc (loc, BIT_AND_EXPR, int_type, + build_int_cstu (int_type, exp_mask), + fold_build1_loc (loc, BIT_NOT_EXPR, int_type, + build_int_cstu (int_type, 1))); + + /* (exp + 1) & mask_check. + Check to see if exp is not all 0 or all 1. */ + tree exp_check + = fold_build2_loc (loc, BIT_AND_EXPR, int_type, + emit_tree_and_return_var (seq, + fold_build2_loc (loc, PLUS_EXPR, int_type, exp, + build_int_cstu (int_type, 1))), + mask_check); + + tree res = fold_build2_loc (loc, NE_EXPR, boolean_type_node, + build_int_cstu (int_type, 0), + emit_tree_and_return_var (seq, exp_check)); + + return emit_tree_and_return_var (seq, res); +} + +/* Generates code to check if ARG is a zero. For both the FP and INT case we + check if ARG == 0 (modulo sign bit). Returns a variable containing a boolean + which has the result of the check. + + SEQ is the buffer to use to emit the gimple instructions into. + LOC is the location to use during fold calls. */ +static tree +is_zero (gimple_seq *seq, tree arg, location_t loc) +{ + tree type = TREE_TYPE (arg); + + /* If not using optimized route then exit early. */ + if (!use_ieee_int_mode (arg)) + { + machine_mode mode = TYPE_MODE (type); + /* Perform IBM extended format fixups if required. */ + perform_ibm_extended_fixups (&arg, &mode, &type, loc); + + tree res = fold_build2_loc (loc, EQ_EXPR, boolean_type_node, arg, + build_real (type, dconst0)); + return emit_tree_and_return_var (seq, res); + } + + const HOST_WIDE_INT type_width = TYPE_PRECISION (type); + + tree int_arg_type = build_nonstandard_integer_type (type_width, true); + + /* Get the number reinterpreted as an integer. + Shift left to remove the sign. */ + tree int_arg + = fold_build2_loc (loc, LSHIFT_EXPR, int_arg_type, + get_num_as_int (seq, arg, loc), + build_int_cstu (int_arg_type, 1)); + + /* num << 1 == 0. + This checks to see if the number is zero. */ + tree zero_check + = fold_build2_loc (loc, EQ_EXPR, boolean_type_node, + build_int_cstu (int_arg_type, 0), + emit_tree_and_return_var (seq, int_arg)); + + return emit_tree_and_return_var (seq, zero_check); +} + +/* Generates code to check if ARG is a subnormal number. In the FP case we test + fabs (ARG) != 0 && fabs (ARG) < MIN_VALUE (ARG) and in the INT case we check + the exp and mantissa bits on ARG. Returns a variable containing a boolean + which has the result of the check. + + SEQ is the buffer to use to emit the gimple instructions into. + LOC is the location to use during fold calls. */ +static tree +is_subnormal (gimple_seq *seq, tree arg, location_t loc) +{ + const tree bool_type = boolean_type_node; + + tree type = TREE_TYPE (arg); + + machine_mode mode = TYPE_MODE (type); + const real_format *format = REAL_MODE_FORMAT (mode); + const HOST_WIDE_INT type_width = TYPE_PRECISION (type); + + tree int_arg_type = build_nonstandard_integer_type (type_width, true); + + /* If not using optimized route then exit early. */ + if (!use_ieee_int_mode (arg)) + { + tree const islt_fn = builtin_decl_explicit (BUILT_IN_ISLESS); + tree const isgt_fn = builtin_decl_explicit (BUILT_IN_ISGREATER); + + tree arg_p + = emit_tree_and_return_var (seq, fold_build1_loc (loc, ABS_EXPR, type, + arg)); + REAL_VALUE_TYPE r; + char buf[128]; + get_min_float (REAL_MODE_FORMAT (mode), buf, sizeof (buf)); + real_from_string (&r, buf); + tree subnorm = build_call_expr (islt_fn, 2, arg_p, build_real (type, r)); + + tree zero = build_call_expr (isgt_fn, 2, arg_p, + build_real (type, dconst0)); + + push_gimplify_context (); + gimplify_expr (&subnorm, seq, NULL, is_gimple_val, fb_either); + gimplify_expr (&zero, seq, NULL, is_gimple_val, fb_either); + + tree res + = fold_build2_loc (loc, BIT_AND_EXPR, bool_type, + emit_tree_and_return_var (seq, + gimple_boolify (subnorm)), + emit_tree_and_return_var (seq, + gimple_boolify (zero))); + pop_gimplify_context (NULL); + + return emit_tree_and_return_var (seq, res); + } + + /* Get the number reinterpreted as an integer. + Shift left to remove the sign. */ + tree int_arg + = fold_build2_loc (loc, LSHIFT_EXPR, int_arg_type, + get_num_as_int (seq, arg, loc), + build_int_cstu (int_arg_type, 1)); + + /* Check for a zero exponent and non-zero mantissa. + This can be done with two comparisons by first apply a + removing the sign bit and checking if the value is larger + than the mantissa mask. */ + + /* This creates a mask to be used to check the mantissa value in the shifted + integer representation of the fpnum. */ + tree significant_bit = build_int_cstu (int_arg_type, format->p - 1); + tree mantissa_mask + = fold_build2_loc (loc, MINUS_EXPR, int_arg_type, + fold_build2_loc (loc, LSHIFT_EXPR, int_arg_type, + build_int_cstu (int_arg_type, 2), + significant_bit), + build_int_cstu (int_arg_type, 1)); + + /* Check if exponent is zero and mantissa is not. */ + tree subnorm_cond_tmp + = fold_build2_loc (loc, LE_EXPR, bool_type, + emit_tree_and_return_var (seq, int_arg), + mantissa_mask); + + tree subnorm_cond = emit_tree_and_return_var (seq, subnorm_cond_tmp); + + tree zero_cond + = fold_build2_loc (loc, GT_EXPR, boolean_type_node, + emit_tree_and_return_var (seq, int_arg), + build_int_cstu (int_arg_type, 0)); + + tree subnorm_check + = fold_build2_loc (loc, BIT_AND_EXPR, boolean_type_node, + emit_tree_and_return_var (seq, subnorm_cond), + emit_tree_and_return_var (seq, zero_cond)); + + return emit_tree_and_return_var (seq, subnorm_check); +} + +/* Generates code to check if ARG is an infinity. In the FP case we test + FABS(ARG) == INF and in the INT case we check the bits on the exp and + mantissa. Returns a variable containing a boolean which has the result + of the check. + + SEQ is the buffer to use to emit the gimple instructions into. + LOC is the location to use during fold calls. */ +static tree +is_infinity (gimple_seq *seq, tree arg, location_t loc) +{ + tree type = TREE_TYPE (arg); + + machine_mode mode = TYPE_MODE (type); + const tree bool_type = boolean_type_node; + + if (!HONOR_INFINITIES (mode)) + { + return build_int_cst (bool_type, false); + } + + /* If not using optimized route then exit early. */ + if (!use_ieee_int_mode (arg)) + { + /* Perform IBM extended format fixups if required. */ + perform_ibm_extended_fixups (&arg, &mode, &type, loc); + + tree arg_p + = emit_tree_and_return_var (seq, fold_build1_loc (loc, ABS_EXPR, type, + arg)); + REAL_VALUE_TYPE r; + real_inf (&r); + tree res = fold_build2_loc (loc, EQ_EXPR, bool_type, arg_p, + build_real (type, r)); + + return emit_tree_and_return_var (seq, res); + } + + const real_format *format = REAL_MODE_FORMAT (mode); + const HOST_WIDE_INT type_width = TYPE_PRECISION (type); + + tree int_arg_type = build_nonstandard_integer_type (type_width, true); + + /* This creates a mask to be used to check the exp value in the shifted + integer representation of the fpnum. */ + const int exp_bits = (GET_MODE_SIZE (mode) * BITS_PER_UNIT) - format->p; + gcc_assert (format->p > 0); + + tree significant_bit = build_int_cstu (int_arg_type, format->p); + tree exp_mask + = fold_build2_loc (loc, MINUS_EXPR, int_arg_type, + fold_build2_loc (loc, LSHIFT_EXPR, int_arg_type, + build_int_cstu (int_arg_type, 2), + build_int_cstu (int_arg_type, + exp_bits - 1)), + build_int_cstu (int_arg_type, 1)); + + /* Get the number reinterpreted as an integer. + Shift left to remove the sign. */ + tree int_arg + = fold_build2_loc (loc, LSHIFT_EXPR, int_arg_type, + get_num_as_int (seq, arg, loc), + build_int_cstu (int_arg_type, 1)); + + /* This mask checks to see if the exp has all bits set and mantissa no + bits set. */ + tree inf_mask + = fold_build2_loc (loc, LSHIFT_EXPR, int_arg_type, + exp_mask, significant_bit); + + /* Check if exponent has all bits set and mantissa is 0. */ + tree inf_check + = emit_tree_and_return_var(seq, + fold_build2_loc (loc, EQ_EXPR, bool_type, + emit_tree_and_return_var(seq, int_arg), + inf_mask)); + + return emit_tree_and_return_var (seq, inf_check); +} + +/* Generates code to check if ARG is a finite number. In the FP case we check + if FABS(ARG) <= MAX_VALUE(ARG) and in the INT case we check the exp and + mantissa bits. Returns a variable containing a boolean which has the result + of the check. + + SEQ is the buffer to use to emit the gimple instructions into. + LOC is the location to use during fold calls. */ +static tree +is_finite (gimple_seq *seq, tree arg, location_t loc) +{ + tree type = TREE_TYPE (arg); + + machine_mode mode = TYPE_MODE (type); + const tree bool_type = boolean_type_node; + + if (!HONOR_NANS (arg) && !HONOR_INFINITIES (arg)) + { + return build_int_cst (bool_type, true); + } + + /* If not using optimized route then exit early. */ + if (!use_ieee_int_mode (arg)) + { + + /* Perform IBM extended format fixups if required. */ + perform_ibm_extended_fixups (&arg, &mode, &type, loc); + + tree const isle_fn = builtin_decl_explicit (BUILT_IN_ISLESSEQUAL); + + tree arg_p + = emit_tree_and_return_var (seq, fold_build1_loc (loc, ABS_EXPR, type, + arg)); + REAL_VALUE_TYPE rmax; + char buf[128]; + get_max_float (REAL_MODE_FORMAT (mode), buf, sizeof (buf)); + real_from_string (&rmax, buf); + + tree res = build_call_expr (isle_fn, 2, arg_p, build_real (type, rmax)); + + push_gimplify_context (); + gimplify_expr (&res, seq, NULL, is_gimple_val, fb_either); + pop_gimplify_context (NULL); + + return emit_tree_and_return_var (seq, gimple_boolify(res)); + } + + const real_format *format = REAL_MODE_FORMAT (mode); + const HOST_WIDE_INT type_width = TYPE_PRECISION (type); + + tree int_arg_type = build_nonstandard_integer_type (type_width, true); + + /* This creates a mask to be used to check the exp value in the shifted + integer representation of the fpnum. */ + const int exp_bits = (GET_MODE_SIZE (mode) * BITS_PER_UNIT) - format->p; + gcc_assert (format->p > 0); + + tree significant_bit = build_int_cstu (int_arg_type, format->p); + tree exp_mask + = fold_build2_loc (loc, MINUS_EXPR, int_arg_type, + fold_build2_loc (loc, LSHIFT_EXPR, int_arg_type, + build_int_cstu (int_arg_type, 2), + build_int_cstu (int_arg_type, + exp_bits - 1)), + build_int_cstu (int_arg_type, 1)); + + /* Get the number reinterpreted as an integer. + Shift left to remove the sign. */ + tree int_arg + = fold_build2_loc (loc, LSHIFT_EXPR, int_arg_type, + get_num_as_int (seq, arg, loc), + build_int_cstu (int_arg_type, 1)); + + /* This mask checks to see if the exp has all bits set and mantissa no + bits set. */ + tree inf_mask + = fold_build2_loc (loc, LSHIFT_EXPR, int_arg_type, + exp_mask, significant_bit); + + /* Check if exponent has all bits set and mantissa is 0. */ + tree inf_check_tmp + = fold_build2_loc (loc, LT_EXPR, bool_type, + emit_tree_and_return_var (seq, int_arg), + inf_mask); + + tree inf_check = emit_tree_and_return_var (seq, inf_check_tmp); + + return emit_tree_and_return_var (seq, inf_check); +} + +/* Generates code to check if ARG is a NaN. In the FP case we simply check if + ARG != ARG and in the INT case we check the bits in the exp and mantissa. + Returns a variable containing a boolean which has the result of the check. + + SEQ is the buffer to use to emit the gimple instructions into. + LOC is the location to use during fold calls. */ +static tree +is_nan (gimple_seq *seq, tree arg, location_t loc) +{ + tree type = TREE_TYPE (arg); + + machine_mode mode = TYPE_MODE (type); + const tree bool_type = boolean_type_node; + + if (!HONOR_NANS (mode)) + { + return build_int_cst (bool_type, false); + } + + const real_format *format = REAL_MODE_FORMAT (mode); + + /* If not using optimized route then exit early. */ + if (!use_ieee_int_mode (arg)) + { + /* Perform IBM extended format fixups if required. */ + perform_ibm_extended_fixups (&arg, &mode, &type, loc); + + tree arg_p + = emit_tree_and_return_var (seq, fold_build1_loc (loc, ABS_EXPR, type, + arg)); + tree res + = fold_build2_loc (loc, UNORDERED_EXPR, bool_type,arg_p, arg_p); + + return emit_tree_and_return_var (seq, res); + } + + const HOST_WIDE_INT type_width = TYPE_PRECISION (type); + tree int_arg_type = build_nonstandard_integer_type (type_width, true); + + /* This creates a mask to be used to check the exp value in the shifted + integer representation of the fpnum. */ + const int exp_bits = (GET_MODE_SIZE (mode) * BITS_PER_UNIT) - format->p; + tree significant_bit = build_int_cstu (int_arg_type, format->p); + tree exp_mask + = fold_build2_loc (loc, MINUS_EXPR, int_arg_type, + fold_build2_loc (loc, LSHIFT_EXPR, int_arg_type, + build_int_cstu (int_arg_type, 2), + build_int_cstu (int_arg_type, + exp_bits - 1)), + build_int_cstu (int_arg_type, 1)); + + /* Get the number reinterpreted as an integer. + Shift left to remove the sign. */ + tree int_arg + = fold_build2_loc (loc, LSHIFT_EXPR, int_arg_type, + get_num_as_int (seq, arg, loc), + build_int_cstu (int_arg_type, 1)); + + /* This mask checks to see if the exp has all bits set and mantissa no + bits set. */ + tree inf_mask + = fold_build2_loc (loc, LSHIFT_EXPR, int_arg_type, + exp_mask, significant_bit); + + /* Check if exponent has all bits set and mantissa is not 0. */ + tree nan_check + = emit_tree_and_return_var(seq, + fold_build2_loc (loc, GT_EXPR, bool_type, + emit_tree_and_return_var(seq, int_arg), + inf_mask)); + + return emit_tree_and_return_var (seq, nan_check); +} + +/* Validates a single argument from the arguments list CALL at position INDEX. + The extracted parameter is compared against the expected type CODE. + + A boolean is returned indicating if the parameter exist and if of the + expected type. */ +static bool +gimple_validate_arg (gimple* call, int index, enum tree_code code) +{ + const tree arg = gimple_call_arg (call, index); + if (!arg) + return false; + else if (code == POINTER_TYPE) + return POINTER_TYPE_P (TREE_TYPE (arg)); + else if (code == INTEGER_TYPE) + return INTEGRAL_TYPE_P (TREE_TYPE (arg)); + return code == TREE_CODE (TREE_TYPE (arg)); +} + +/* Lowers calls to __builtin_fpclassify to + fpclassify (x) -> + isnormal(x) ? FP_NORMAL : + iszero (x) ? FP_ZERO : + isnan (x) ? FP_NAN : + isinfinite (x) ? FP_INFINITE : + FP_SUBNORMAL. + + The code may use integer arithmentic if it decides + that the produced assembly would be faster. This can only be done + for numbers that are similar to IEEE-754 in format. + + This builtin will generate code to return the appropriate floating + point classification depending on the value of the floating point + number passed in. The possible return values must be supplied as + int arguments to the call in the following order: FP_NAN, FP_INFINITE, + FP_NORMAL, FP_SUBNORMAL and FP_ZERO. The ellipses is for exactly + one floating point argument which is "type generic". + + GSI is the gimple iterator containing the fpclassify call to lower. + The call will be expanded and replaced inline in the given GSI. */ +static void +lower_builtin_fpclassify (gimple_stmt_iterator *gsi) +{ + gimple *call = gsi_stmt (*gsi); + location_t loc = gimple_location (call); + + /* Verify the required arguments in the original call. */ + if (gimple_call_num_args (call) != 6 + || !gimple_validate_arg (call, 0, INTEGER_TYPE) + || !gimple_validate_arg (call, 1, INTEGER_TYPE) + || !gimple_validate_arg (call, 2, INTEGER_TYPE) + || !gimple_validate_arg (call, 3, INTEGER_TYPE) + || !gimple_validate_arg (call, 4, INTEGER_TYPE) + || !gimple_validate_arg (call, 5, REAL_TYPE)) + return; + + /* Collect the arguments from the call. */ + tree fp_nan = gimple_call_arg (call, 0); + tree fp_infinite = gimple_call_arg (call, 1); + tree fp_normal = gimple_call_arg (call, 2); + tree fp_subnormal = gimple_call_arg (call, 3); + tree fp_zero = gimple_call_arg (call, 4); + tree arg = gimple_call_arg (call, 5); + + gimple_seq body = NULL; + + /* Create label to jump to to exit. */ + tree done_label = create_artificial_label (UNKNOWN_LOCATION); + tree dest; + tree orig_dest = dest = gimple_call_lhs (call); + if (orig_dest && TREE_CODE (orig_dest) == SSA_NAME) + dest = create_tmp_reg (TREE_TYPE (orig_dest)); + + emit_tree_cond (&body, dest, done_label, + is_normal (&body, arg, loc), fp_normal); + emit_tree_cond (&body, dest, done_label, + is_zero (&body, arg, loc), fp_zero); + emit_tree_cond (&body, dest, done_label, + is_nan (&body, arg, loc), fp_nan); + emit_tree_cond (&body, dest, done_label, + is_infinity (&body, arg, loc), fp_infinite); + + /* And finally, emit the default case if nothing else matches. + This replaces the call to is_subnormal. */ + gimple_seq_add_stmt (&body, gimple_build_assign (dest, fp_subnormal)); + gimple_seq_add_stmt (&body, gimple_build_label (done_label)); + + /* Build orig_dest = dest if necessary. */ + if (dest != orig_dest) + { + gimple_seq_add_stmt (&body, gimple_build_assign (orig_dest, dest)); + } + + gsi_insert_seq_before (gsi, body, GSI_SAME_STMT); + + + /* Remove the call to __builtin_fpclassify. */ + gsi_remove (gsi, false); +} + +/* Generic wrapper for the is_nan, is_normal, is_subnormal, is_zero, etc. + All these functions have the same setup. The wrapper validates the parameter + and also creates the branches and labels required to properly invoke. + This has been generalize and the function to call is passed as argument FNDECL. + + GSI is the gimple iterator containing the fpclassify call to lower. + The call will be expanded and replaced inline in the given GSI. */ +static void +gen_call_fp_builtin (gimple_stmt_iterator *gsi, + tree (*fndecl)(gimple_seq *, tree, location_t)) +{ + gimple *call = gsi_stmt (*gsi); + location_t loc = gimple_location (call); + + /* Verify the required arguments in the original call. */ + if (gimple_call_num_args (call) != 1 + || !gimple_validate_arg (call, 0, REAL_TYPE)) + return; + + tree arg = gimple_call_arg (call, 0); + gimple_seq body = NULL; + + /* Create label to jump to to exit. */ + tree done_label = create_artificial_label (UNKNOWN_LOCATION); + tree dest; + tree orig_dest = dest = gimple_call_lhs (call); + tree type = TREE_TYPE (orig_dest); + if (orig_dest && TREE_CODE (orig_dest) == SSA_NAME) + dest = create_tmp_reg (type); + + tree t_true = build_int_cst (type, true); + tree t_false = build_int_cst (type, false); + + emit_tree_cond (&body, dest, done_label, + fndecl (&body, arg, loc), t_true); + + /* And finally, emit the default case if nothing else matches. + This replaces the call to false. */ + gimple_seq_add_stmt (&body, gimple_build_assign (dest, t_false)); + gimple_seq_add_stmt (&body, gimple_build_label (done_label)); + + /* Build orig_dest = dest if necessary. */ + if (dest != orig_dest) + { + gimple_seq_add_stmt (&body, gimple_build_assign (orig_dest, dest)); + } + + gsi_insert_seq_before (gsi, body, GSI_SAME_STMT); + + /* Remove the call to the builtin. */ + gsi_remove (gsi, false); +} + +/* Lower and expand calls to __builtin_isnan in GSI. */ +static void +lower_builtin_isnan (gimple_stmt_iterator *gsi) +{ + gen_call_fp_builtin (gsi, &is_nan); +} + +/* Lower and expand calls to __builtin_isinfinite in GSI. */ +static void +lower_builtin_isinfinite (gimple_stmt_iterator *gsi) +{ + gen_call_fp_builtin (gsi, &is_infinity); +} + +/* Lower and expand calls to __builtin_isnormal in GSI. */ +static void +lower_builtin_isnormal (gimple_stmt_iterator *gsi) +{ + gen_call_fp_builtin (gsi, &is_normal); +} + +/* Lower and expand calls to __builtin_iszero in GSI. */ +static void +lower_builtin_iszero (gimple_stmt_iterator *gsi) +{ + gen_call_fp_builtin (gsi, &is_zero); +} + +/* Lower and expand calls to __builtin_issubnormal in GSI. */ +static void +lower_builtin_issubnormal (gimple_stmt_iterator *gsi) +{ + gen_call_fp_builtin (gsi, &is_subnormal); +} + +/* Lower and expand calls to __builtin_isfinite in GSI. */ +static void +lower_builtin_isfinite (gimple_stmt_iterator *gsi) +{ + gen_call_fp_builtin (gsi, &is_finite); +} + /* Lower calls to posix_memalign to res = posix_memalign (ptr, align, size); if (res == 0) diff --git a/gcc/real.c b/gcc/real.c index a5671b2865b..4b4635ff913 100644 --- a/gcc/real.c +++ b/gcc/real.c @@ -3052,6 +3052,7 @@ const struct real_format ieee_single_format = true, true, false, + true, "ieee_single" }; @@ -3075,6 +3076,7 @@ const struct real_format mips_single_format = true, false, true, + true, "mips_single" }; @@ -3098,6 +3100,7 @@ const struct real_format motorola_single_format = true, true, true, + true, "motorola_single" }; @@ -3132,6 +3135,7 @@ const struct real_format spu_single_format = true, false, false, + false, "spu_single" }; @@ -3343,6 +3347,7 @@ const struct real_format ieee_double_format = true, true, false, + true, "ieee_double" }; @@ -3366,6 +3371,7 @@ const struct real_format mips_double_format = true, false, true, + true, "mips_double" }; @@ -3389,6 +3395,7 @@ const struct real_format motorola_double_format = true, true, true, + true, "motorola_double" }; @@ -3735,6 +3742,7 @@ const struct real_format ieee_extended_motorola_format = true, true, true, + false, "ieee_extended_motorola" }; @@ -3758,6 +3766,7 @@ const struct real_format ieee_extended_intel_96_format = true, true, false, + false, "ieee_extended_intel_96" }; @@ -3781,6 +3790,7 @@ const struct real_format ieee_extended_intel_128_format = true, true, false, + false, "ieee_extended_intel_128" }; @@ -3806,6 +3816,7 @@ const struct real_format ieee_extended_intel_96_round_53_format = true, true, false, + false, "ieee_extended_intel_96_round_53" }; @@ -3896,6 +3907,7 @@ const struct real_format ibm_extended_format = true, true, false, + false, "ibm_extended" }; @@ -3919,6 +3931,7 @@ const struct real_format mips_extended_format = true, false, true, + false, "mips_extended" }; @@ -4184,6 +4197,7 @@ const struct real_format ieee_quad_format = true, true, false, + true, "ieee_quad" }; @@ -4207,6 +4221,7 @@ const struct real_format mips_quad_format = true, false, true, + true, "mips_quad" }; @@ -4509,6 +4524,7 @@ const struct real_format vax_f_format = false, false, false, + false, "vax_f" }; @@ -4532,6 +4548,7 @@ const struct real_format vax_d_format = false, false, false, + false, "vax_d" }; @@ -4555,6 +4572,7 @@ const struct real_format vax_g_format = false, false, false, + false, "vax_g" }; @@ -4633,6 +4651,7 @@ const struct real_format decimal_single_format = true, true, false, + false, "decimal_single" }; @@ -4657,6 +4676,7 @@ const struct real_format decimal_double_format = true, true, false, + false, "decimal_double" }; @@ -4681,6 +4701,7 @@ const struct real_format decimal_quad_format = true, true, false, + false, "decimal_quad" }; @@ -4820,6 +4841,7 @@ const struct real_format ieee_half_format = true, true, false, + true, "ieee_half" }; @@ -4846,6 +4868,7 @@ const struct real_format arm_half_format = true, false, false, + false, "arm_half" }; @@ -4893,6 +4916,7 @@ const struct real_format real_internal_format = true, true, false, + false, "real_internal" }; @@ -5080,6 +5104,16 @@ get_max_float (const struct real_format *fmt, char *buf, size_t len) gcc_assert (strlen (buf) < len); } +/* Write into BUF the minimum negative representable finite floating-point + number, x, such that b**(x-1) is normalized. + BUF must be large enough to contain the result. */ +void +get_min_float (const struct real_format *fmt, char *buf, size_t len) +{ + sprintf (buf, "0x1p%d", fmt->emin - 1); + gcc_assert (strlen (buf) < len); +} + /* True if mode M has a NaN representation and the treatment of NaN operands is important. */ diff --git a/gcc/real.h b/gcc/real.h index e7248e30fa5..67fa7932e88 100644 --- a/gcc/real.h +++ b/gcc/real.h @@ -161,6 +161,19 @@ struct real_format bool has_signed_zero; bool qnan_msb_set; bool canonical_nan_lsbs_set; + + /* This flag indicates whether the format is suitable for the optimized + code paths for the __builtin_fpclassify function and friends. For + this, the format must be a base 2 representation with the sign bit as + the most-significant bit followed by (exp <= 32) exponent bits + followed by the mantissa bits. It must be possible to interpret the + bits of the floating-point representation as an integer. NaNs and + INFs (if available) must be represented by the same schema used by + IEEE 754. (NaNs must be represented by an exponent with all bits 1, + any mantissa except all bits 0 and any sign bit. +INF and -INF must be + represented by an exponent with all bits 1, a mantissa with all bits 0 and + a sign bit of 0 and 1 respectively.) */ + bool is_binary_ieee_compatible; const char *name; }; @@ -511,6 +524,11 @@ extern bool real_isinteger (const REAL_VALUE_TYPE *, HOST_WIDE_INT *); float string. BUF must be large enough to contain the result. */ extern void get_max_float (const struct real_format *, char *, size_t); +/* Write into BUF the smallest positive normalized number x, + such that b**(x-1) is normalized. BUF must be large enough + to contain the result. */ +extern void get_min_float (const struct real_format *, char *, size_t); + #ifndef GENERATOR_FILE /* real related routines. */ extern wide_int real_to_integer (const REAL_VALUE_TYPE *, bool *, int); diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index 52a0854bb1f..3899e20dedd 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,3 +1,20 @@ +2017-06-08 Tamar Christina + + * gcc.target/aarch64/builtin-fpclassify.c: New codegen test. + * gcc.dg/fold-notunord.c: Removed. + * gcc.dg/torture/floatn-tg-4.h: Add tests for iszero and issubnormal. + * gcc.dg/torture/float128-tg-4.c: Likewise. + * gcc.dg/torture/float128x-tg-4: Likewise. + * gcc.dg/torture/float16-tg-4.c: Likewise. + * gcc.dg/torture/float32-tg-4.c: Likewise. + * gcc.dg/torture/float32x-tg-4.c: Likewise. + * gcc.dg/torture/float64-tg-4.c: Likewise. + * gcc.dg/torture/float64x-tg-4.c: Likewise. + * gcc.dg/pr28796-1.c: Add -O2. + * gcc.dg/builtins-43.c: Check lower instead of gimple. + * gcc.dg/tg-tests.h: Add iszero and issubnormal. + * gcc.dg/pr77925.c: Add to test safe cases. + 2017-06-08 Richard Biener PR tree-optimization/80928 diff --git a/gcc/testsuite/gcc.dg/builtins-43.c b/gcc/testsuite/gcc.dg/builtins-43.c index f7c318edf08..5d41c28aef8 100644 --- a/gcc/testsuite/gcc.dg/builtins-43.c +++ b/gcc/testsuite/gcc.dg/builtins-43.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-O1 -fno-trapping-math -fno-finite-math-only -fdump-tree-gimple -fdump-tree-optimized" } */ +/* { dg-options "-O1 -fno-trapping-math -fno-finite-math-only -fdump-tree-lower -fdump-tree-optimized" } */ extern void f(int); extern void link_error (); @@ -51,7 +51,7 @@ main () /* Check that all instances of __builtin_isnan were folded. */ -/* { dg-final { scan-tree-dump-times "isnan" 0 "gimple" } } */ +/* { dg-final { scan-tree-dump-times "isnan" 0 "lower" } } */ /* Check that all instances of link_error were subject to DCE. */ /* { dg-final { scan-tree-dump-times "link_error" 0 "optimized" } } */ diff --git a/gcc/testsuite/gcc.dg/fold-notunord.c b/gcc/testsuite/gcc.dg/fold-notunord.c deleted file mode 100644 index ca345154ac2..00000000000 --- a/gcc/testsuite/gcc.dg/fold-notunord.c +++ /dev/null @@ -1,9 +0,0 @@ -/* { dg-do compile } */ -/* { dg-options "-O -ftrapping-math -fdump-tree-optimized" } */ - -int f (double d) -{ - return !__builtin_isnan (d); -} - -/* { dg-final { scan-tree-dump " ord " "optimized" } } */ diff --git a/gcc/testsuite/gcc.dg/pr28796-1.c b/gcc/testsuite/gcc.dg/pr28796-1.c index 077118a2988..a57b4e350af 100644 --- a/gcc/testsuite/gcc.dg/pr28796-1.c +++ b/gcc/testsuite/gcc.dg/pr28796-1.c @@ -1,5 +1,5 @@ /* { dg-do link } */ -/* { dg-options "-ffinite-math-only" } */ +/* { dg-options "-ffinite-math-only -O2" } */ extern void link_error(void); diff --git a/gcc/testsuite/gcc.dg/pr77925.c b/gcc/testsuite/gcc.dg/pr77925.c new file mode 100644 index 00000000000..f92518b59af --- /dev/null +++ b/gcc/testsuite/gcc.dg/pr77925.c @@ -0,0 +1,11 @@ +/* { dg-do run } */ +/* { dg-options "-O2" } */ +/* { dg-add-options ieee } */ +/* { dg-skip-if "No Inf/NaN support" { spu-*-* } } */ + +#include "tg-tests.h" + +int main(void) +{ + return main_tests (); +} diff --git a/gcc/testsuite/gcc.dg/tg-tests.h b/gcc/testsuite/gcc.dg/tg-tests.h index 0cf1f645258..134bc825275 100644 --- a/gcc/testsuite/gcc.dg/tg-tests.h +++ b/gcc/testsuite/gcc.dg/tg-tests.h @@ -11,6 +11,7 @@ void __attribute__ ((__noinline__)) foo_1 (float f, double d, long double ld, int res_unord, int res_isnan, int res_isinf, int res_isinf_sign, int res_isfin, int res_isnorm, + int res_iszero, int res_issubnorm, int res_signbit, int classification) { if (__builtin_isunordered (f, 0) != res_unord) @@ -80,6 +81,29 @@ foo_1 (float f, double d, long double ld, if (__builtin_finitel (ld) != res_isfin) __builtin_abort (); +/* On CPUs which flush denormals to zero these tests can never work one + denormals for the floating point version of the implementation. The integer + versions would work fine but we can't detect which version we have here. */ +#ifdef UNSAFE +if (!res_issubnorm) { +#endif + if (__builtin_iszero (f) != res_iszero) + __builtin_abort (); + if (__builtin_iszero (d) != res_iszero) + __builtin_abort (); + if (__builtin_iszero (ld) != res_iszero) + __builtin_abort (); + + if (__builtin_issubnormal (f) != res_issubnorm) + __builtin_abort (); + if (__builtin_issubnormal (d) != res_issubnorm) + __builtin_abort (); + if (__builtin_issubnormal (ld) != res_issubnorm) + __builtin_abort (); +#ifdef UNSAFE +} +#endif + /* Sign bit of zeros and nans is not preserved in unsafe math mode. */ #ifdef UNSAFE if (!res_isnan && f != 0 && d != 0 && ld != 0) @@ -115,12 +139,13 @@ foo_1 (float f, double d, long double ld, void __attribute__ ((__noinline__)) foo (float f, double d, long double ld, int res_unord, int res_isnan, int res_isinf, - int res_isfin, int res_isnorm, int classification) + int res_isfin, int res_isnorm, int res_iszero, + int res_issubnorm, int classification) { - foo_1 (f, d, ld, res_unord, res_isnan, res_isinf, res_isinf, res_isfin, res_isnorm, 0, classification); + foo_1 (f, d, ld, res_unord, res_isnan, res_isinf, res_isinf, res_isfin, res_isnorm, res_iszero, res_issubnorm, 0, classification); /* Try all the values negated as well. All will have the sign bit set, except for the nan. */ - foo_1 (-f, -d, -ld, res_unord, res_isnan, res_isinf, -res_isinf, res_isfin, res_isnorm, 1, classification); + foo_1 (-f, -d, -ld, res_unord, res_isnan, res_isinf, -res_isinf, res_isfin, res_isnorm, res_iszero, res_issubnorm, 1, classification); } int __attribute__ ((__noinline__)) @@ -132,35 +157,35 @@ main_tests (void) /* Test NaN. */ f = __builtin_nanf(""); d = __builtin_nan(""); ld = __builtin_nanl(""); - foo(f, d, ld, /*unord=*/ 1, /*isnan=*/ 1, /*isinf=*/ 0, /*isfin=*/ 0, /*isnorm=*/ 0, FP_NAN); + foo(f, d, ld, /*unord=*/ 1, /*isnan=*/ 1, /*isinf=*/ 0, /*isfin=*/ 0, /*isnorm=*/ 0, /*iszero=*/0, /*issubnorm=*/0, FP_NAN); /* Test infinity. */ f = __builtin_inff(); d = __builtin_inf(); ld = __builtin_infl(); - foo(f, d, ld, /*unord=*/ 0, /*isnan=*/ 0, /*isinf=*/ 1, /*isfin=*/ 0, /*isnorm=*/ 0, FP_INFINITE); + foo(f, d, ld, /*unord=*/ 0, /*isnan=*/ 0, /*isinf=*/ 1, /*isfin=*/ 0, /*isnorm=*/ 0, /*iszero=*/0, /*issubnorm=*/0, FP_INFINITE); /* Test zero. */ f = 0; d = 0; ld = 0; - foo(f, d, ld, /*unord=*/ 0, /*isnan=*/ 0, /*isinf=*/ 0, /*isfin=*/ 1, /*isnorm=*/ 0, FP_ZERO); + foo(f, d, ld, /*unord=*/ 0, /*isnan=*/ 0, /*isinf=*/ 0, /*isfin=*/ 1, /*isnorm=*/ 0, /*iszero=*/1, /*issubnorm=*/0, FP_ZERO); /* Test one. */ f = 1; d = 1; ld = 1; - foo(f, d, ld, /*unord=*/ 0, /*isnan=*/ 0, /*isinf=*/ 0, /*isfin=*/ 1, /*isnorm=*/ 1, FP_NORMAL); + foo(f, d, ld, /*unord=*/ 0, /*isnan=*/ 0, /*isinf=*/ 0, /*isfin=*/ 1, /*isnorm=*/ 1, /*iszero=*/0, /*issubnorm=*/0, FP_NORMAL); /* Test minimum values. */ f = __FLT_MIN__; d = __DBL_MIN__; ld = __LDBL_MIN__; - foo(f, d, ld, /*unord=*/ 0, /*isnan=*/ 0, /*isinf=*/ 0, /*isfin=*/ 1, /*isnorm=*/ 1, FP_NORMAL); + foo(f, d, ld, /*unord=*/ 0, /*isnan=*/ 0, /*isinf=*/ 0, /*isfin=*/ 1, /*isnorm=*/ 1, /*iszero=*/0, /*issubnorm=*/0, FP_NORMAL); /* Test subnormal values. */ f = __FLT_MIN__/2; d = __DBL_MIN__/2; ld = __LDBL_MIN__/2; - foo(f, d, ld, /*unord=*/ 0, /*isnan=*/ 0, /*isinf=*/ 0, /*isfin=*/ 1, /*isnorm=*/ 0, FP_SUBNORMAL); + foo(f, d, ld, /*unord=*/ 0, /*isnan=*/ 0, /*isinf=*/ 0, /*isfin=*/ 1, /*isnorm=*/ 0, /*iszero=*/0, /*issubnorm=*/1, FP_SUBNORMAL); /* Test maximum values. */ f = __FLT_MAX__; d = __DBL_MAX__; ld = __LDBL_MAX__; - foo(f, d, ld, /*unord=*/ 0, /*isnan=*/ 0, /*isinf=*/ 0, /*isfin=*/ 1, /*isnorm=*/ 1, FP_NORMAL); + foo(f, d, ld, /*unord=*/ 0, /*isnan=*/ 0, /*isinf=*/ 0, /*isfin=*/ 1, /*isnorm=*/ 1, /*iszero=*/0, /*issubnorm=*/0, FP_NORMAL); /* Test overflow values. */ f = __FLT_MAX__*2; d = __DBL_MAX__*2; ld = __LDBL_MAX__*2; - foo(f, d, ld, /*unord=*/ 0, /*isnan=*/ 0, /*isinf=*/ 1, /*isfin=*/ 0, /*isnorm=*/ 0, FP_INFINITE); + foo(f, d, ld, /*unord=*/ 0, /*isnan=*/ 0, /*isinf=*/ 1, /*isfin=*/ 0, /*isnorm=*/ 0, /*iszero=*/0, /*issubnorm=*/0, FP_INFINITE); return 0; } diff --git a/gcc/testsuite/gcc.dg/torture/float128-tg-4.c b/gcc/testsuite/gcc.dg/torture/float128-tg-4.c new file mode 100644 index 00000000000..ec9d3ad41e2 --- /dev/null +++ b/gcc/testsuite/gcc.dg/torture/float128-tg-4.c @@ -0,0 +1,11 @@ +/* Test _Float128 type-generic built-in functions: __builtin_iszero, + __builtin_issubnormal. */ +/* { dg-do run } */ +/* { dg-options "" } */ +/* { dg-add-options float128 } */ +/* { dg-add-options ieee } */ +/* { dg-require-effective-target float128_runtime } */ + +#define WIDTH 128 +#define EXT 0 +#include "floatn-tg-4.h" diff --git a/gcc/testsuite/gcc.dg/torture/float128x-tg-4.c b/gcc/testsuite/gcc.dg/torture/float128x-tg-4.c new file mode 100644 index 00000000000..0ede8617167 --- /dev/null +++ b/gcc/testsuite/gcc.dg/torture/float128x-tg-4.c @@ -0,0 +1,11 @@ +/* Test _Float128x type-generic built-in functions: __builtin_iszero, + __builtin_issubnormal. */ +/* { dg-do run } */ +/* { dg-options "" } */ +/* { dg-add-options float128x } */ +/* { dg-add-options ieee } */ +/* { dg-require-effective-target float128x_runtime } */ + +#define WIDTH 128 +#define EXT 1 +#include "floatn-tg-4.h" diff --git a/gcc/testsuite/gcc.dg/torture/float16-tg-4.c b/gcc/testsuite/gcc.dg/torture/float16-tg-4.c new file mode 100644 index 00000000000..007c4c224ea --- /dev/null +++ b/gcc/testsuite/gcc.dg/torture/float16-tg-4.c @@ -0,0 +1,11 @@ +/* Test _Float16 type-generic built-in functions: __builtin_iszero, + __builtin_issubnormal. */ +/* { dg-do run } */ +/* { dg-options "" } */ +/* { dg-add-options float16 } */ +/* { dg-add-options ieee } */ +/* { dg-require-effective-target float16_runtime } */ + +#define WIDTH 16 +#define EXT 0 +#include "floatn-tg-4.h" diff --git a/gcc/testsuite/gcc.dg/torture/float32-tg-4.c b/gcc/testsuite/gcc.dg/torture/float32-tg-4.c new file mode 100644 index 00000000000..c7f8353da2c --- /dev/null +++ b/gcc/testsuite/gcc.dg/torture/float32-tg-4.c @@ -0,0 +1,11 @@ +/* Test _Float32 type-generic built-in functions: __builtin_f__builtin_iszero, + __builtin_issubnormal. */ +/* { dg-do run } */ +/* { dg-options "" } */ +/* { dg-add-options float32 } */ +/* { dg-add-options ieee } */ +/* { dg-require-effective-target float32_runtime } */ + +#define WIDTH 32 +#define EXT 0 +#include "floatn-tg-4.h" diff --git a/gcc/testsuite/gcc.dg/torture/float32x-tg-4.c b/gcc/testsuite/gcc.dg/torture/float32x-tg-4.c new file mode 100644 index 00000000000..0d7a592920a --- /dev/null +++ b/gcc/testsuite/gcc.dg/torture/float32x-tg-4.c @@ -0,0 +1,11 @@ +/* Test _Float32x type-generic built-in functions: __builtin_iszero, + __builtin_issubnormal. */ +/* { dg-do run } */ +/* { dg-options "" } */ +/* { dg-add-options float32x } */ +/* { dg-add-options ieee } */ +/* { dg-require-effective-target float32x_runtime } */ + +#define WIDTH 32 +#define EXT 1 +#include "floatn-tg-4.h" diff --git a/gcc/testsuite/gcc.dg/torture/float64-tg-4.c b/gcc/testsuite/gcc.dg/torture/float64-tg-4.c new file mode 100644 index 00000000000..bb25a22a68e --- /dev/null +++ b/gcc/testsuite/gcc.dg/torture/float64-tg-4.c @@ -0,0 +1,11 @@ +/* Test _Float64 type-generic built-in functions: __builtin_iszero, + __builtin_issubnormal */ +/* { dg-do run } */ +/* { dg-options "" } */ +/* { dg-add-options float64 } */ +/* { dg-add-options ieee } */ +/* { dg-require-effective-target float64_runtime } */ + +#define WIDTH 64 +#define EXT 0 +#include "floatn-tg-4.h" diff --git a/gcc/testsuite/gcc.dg/torture/float64x-tg-4.c b/gcc/testsuite/gcc.dg/torture/float64x-tg-4.c new file mode 100644 index 00000000000..82305d916b8 --- /dev/null +++ b/gcc/testsuite/gcc.dg/torture/float64x-tg-4.c @@ -0,0 +1,11 @@ +/* Test _Float64x type-generic built-in functions: __builtin_iszero, + __builtin_issubnormal. */ +/* { dg-do run } */ +/* { dg-options "" } */ +/* { dg-add-options float64x } */ +/* { dg-add-options ieee } */ +/* { dg-require-effective-target float64x_runtime } */ + +#define WIDTH 64 +#define EXT 1 +#include "floatn-tg-4.h" diff --git a/gcc/testsuite/gcc.dg/torture/floatn-tg-4.h b/gcc/testsuite/gcc.dg/torture/floatn-tg-4.h new file mode 100644 index 00000000000..aa3448c090c --- /dev/null +++ b/gcc/testsuite/gcc.dg/torture/floatn-tg-4.h @@ -0,0 +1,99 @@ +/* Tests for _FloatN / _FloatNx types: compile and execution tests for + type-generic built-in functions: __builtin_iszero, __builtin_issubnormal. + Before including this file, define WIDTH as the value N; define EXT to 1 + for _FloatNx and 0 for _FloatN. */ + +#define __STDC_WANT_IEC_60559_TYPES_EXT__ +#include + +#define CONCATX(X, Y) X ## Y +#define CONCAT(X, Y) CONCATX (X, Y) +#define CONCAT3(X, Y, Z) CONCAT (CONCAT (X, Y), Z) +#define CONCAT4(W, X, Y, Z) CONCAT (CONCAT (CONCAT (W, X), Y), Z) + +#if EXT +# define TYPE CONCAT3 (_Float, WIDTH, x) +# define CST(C) CONCAT4 (C, f, WIDTH, x) +# define MAX CONCAT3 (FLT, WIDTH, X_MAX) +# define MIN CONCAT3 (FLT, WIDTH, X_MIN) +# define TRUE_MIN CONCAT3 (FLT, WIDTH, X_TRUE_MIN) +#else +# define TYPE CONCAT (_Float, WIDTH) +# define CST(C) CONCAT3 (C, f, WIDTH) +# define MAX CONCAT3 (FLT, WIDTH, _MAX) +# define MIN CONCAT3 (FLT, WIDTH, _MIN) +# define TRUE_MIN CONCAT3 (FLT, WIDTH, _TRUE_MIN) +#endif + +extern void exit (int); +extern void abort (void); + +volatile TYPE inf = __builtin_inf (), nanval = __builtin_nan (""); +volatile TYPE neginf = -__builtin_inf (), negnanval = -__builtin_nan (""); +volatile TYPE zero = CST (0.0), negzero = -CST (0.0), one = CST (1.0); +volatile TYPE max = MAX, negmax = -MAX, min = MIN, negmin = -MIN; +volatile TYPE true_min = TRUE_MIN, negtrue_min = -TRUE_MIN; +volatile TYPE sub_norm = MIN / 2.0; + +int +main (void) +{ + if (__builtin_iszero (inf) == 1) + abort (); + if (__builtin_iszero (nanval) == 1) + abort (); + if (__builtin_iszero (neginf) == 1) + abort (); + if (__builtin_iszero (negnanval) == 1) + abort (); + if (__builtin_iszero (zero) != 1) + abort (); + if (__builtin_iszero (negzero) != 1) + abort (); + if (__builtin_iszero (one) == 1) + abort (); + if (__builtin_iszero (max) == 1) + abort (); + if (__builtin_iszero (negmax) == 1) + abort (); + if (__builtin_iszero (min) == 1) + abort (); + if (__builtin_iszero (negmin) == 1) + abort (); + if (__builtin_iszero (true_min) == 1) + abort (); + if (__builtin_iszero (negtrue_min) == 1) + abort (); + if (__builtin_iszero (sub_norm) == 1) + abort (); + + if (__builtin_issubnormal (inf) == 1) + abort (); + if (__builtin_issubnormal (nanval) == 1) + abort (); + if (__builtin_issubnormal (neginf) == 1) + abort (); + if (__builtin_issubnormal (negnanval) == 1) + abort (); + if (__builtin_issubnormal (zero) == 1) + abort (); + if (__builtin_issubnormal (negzero) == 1) + abort (); + if (__builtin_issubnormal (one) == 1) + abort (); + if (__builtin_issubnormal (max) == 1) + abort (); + if (__builtin_issubnormal (negmax) == 1) + abort (); + if (__builtin_issubnormal (min) == 1) + abort (); + if (__builtin_issubnormal (negmin) == 1) + abort (); + if (__builtin_issubnormal (true_min) != 1) + abort (); + if (__builtin_issubnormal (negtrue_min) != 1) + abort (); + if (__builtin_issubnormal (sub_norm) != 1) + abort (); + exit (0); +} diff --git a/gcc/testsuite/gcc.target/aarch64/builtin-fpclassify.c b/gcc/testsuite/gcc.target/aarch64/builtin-fpclassify.c new file mode 100644 index 00000000000..3a1bf956bfc --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/builtin-fpclassify.c @@ -0,0 +1,22 @@ +/* This file checks the code generation for the new __builtin_fpclassify. + because checking the exact assembly isn't very useful, we'll just be checking + for the presence of certain instructions and the omition of others. */ +/* { dg-options "-O2" } */ +/* { dg-do compile } */ +/* { dg-final { scan-assembler-not "\[ \t\]?fabs\[ \t\]?" } } */ +/* { dg-final { scan-assembler-not "\[ \t\]?fcmp\[ \t\]?" } } */ +/* { dg-final { scan-assembler-not "\[ \t\]?fcmpe\[ \t\]?" } } */ +/* { dg-final { scan-assembler "\[ \t\]?ubfx\[ \t\]?" } } */ + +#include +#include + +/* + fp_nan = args[0]; + fp_infinite = args[1]; + fp_normal = args[2]; + fp_subnormal = args[3]; + fp_zero = args[4]; +*/ + +int f(double x) { return __builtin_fpclassify(0, 1, 4, 3, 2, x); } -- 2.30.2