diff options
| -rw-r--r-- | gcc/builtins.cc | 277 | ||||
| -rw-r--r-- | gcc/builtins.def | 6 | ||||
| -rw-r--r-- | gcc/c-family/c-common.cc | 74 | ||||
| -rw-r--r-- | gcc/c-family/c-gimplify.cc | 22 | ||||
| -rw-r--r-- | gcc/c/c-typeck.cc | 18 | ||||
| -rw-r--r-- | gcc/cp/call.cc | 14 | ||||
| -rw-r--r-- | gcc/cp/cp-gimplify.cc | 4 | ||||
| -rw-r--r-- | gcc/doc/extend.texi | 42 | ||||
| -rw-r--r-- | gcc/fold-const-call.cc | 68 | ||||
| -rw-r--r-- | gcc/genmatch.cc | 66 | ||||
| -rw-r--r-- | gcc/gimple-lower-bitint.cc | 527 | ||||
| -rw-r--r-- | gcc/gimple-range-op.cc | 67 | ||||
| -rw-r--r-- | gcc/match.pd | 202 | ||||
| -rw-r--r-- | gcc/testsuite/c-c++-common/pr111309-1.c | 470 | ||||
| -rw-r--r-- | gcc/testsuite/c-c++-common/pr111309-2.c | 85 | ||||
| -rw-r--r-- | gcc/testsuite/gcc.dg/torture/bitint-43.c | 306 | ||||
| -rw-r--r-- | gcc/testsuite/gcc.dg/torture/bitint-44.c | 306 | ||||
| -rw-r--r-- | gcc/tree-ssa-forwprop.cc | 8 | ||||
| -rw-r--r-- | gcc/tree-ssa-loop-niter.cc | 10 | ||||
| -rw-r--r-- | gcc/tree-ssa-phiopt.cc | 66 | ||||
| -rw-r--r-- | gcc/tree-vect-patterns.cc | 65 | ||||
| -rw-r--r-- | gcc/tree-vect-stmts.cc | 16 |
22 files changed, 2576 insertions, 143 deletions
diff --git a/gcc/builtins.cc b/gcc/builtins.cc index cb90bd0..5ece0d2 100644 --- a/gcc/builtins.cc +++ b/gcc/builtins.cc @@ -9573,6 +9573,271 @@ fold_builtin_arith_overflow (location_t loc, enum built_in_function fcode, return build2_loc (loc, COMPOUND_EXPR, boolean_type_node, store, ovfres); } +/* Fold __builtin_{clz,ctz,clrsb,ffs,parity,popcount}g into corresponding + internal function. */ + +static tree +fold_builtin_bit_query (location_t loc, enum built_in_function fcode, + tree arg0, tree arg1) +{ + enum internal_fn ifn; + enum built_in_function fcodei, fcodel, fcodell; + tree arg0_type = TREE_TYPE (arg0); + tree cast_type = NULL_TREE; + int addend = 0; + + switch (fcode) + { + case BUILT_IN_CLZG: + if (arg1 && TREE_CODE (arg1) != INTEGER_CST) + return NULL_TREE; + ifn = IFN_CLZ; + fcodei = BUILT_IN_CLZ; + fcodel = BUILT_IN_CLZL; + fcodell = BUILT_IN_CLZLL; + break; + case BUILT_IN_CTZG: + if (arg1 && TREE_CODE (arg1) != INTEGER_CST) + return NULL_TREE; + ifn = IFN_CTZ; + fcodei = BUILT_IN_CTZ; + fcodel = BUILT_IN_CTZL; + fcodell = BUILT_IN_CTZLL; + break; + case BUILT_IN_CLRSBG: + ifn = IFN_CLRSB; + fcodei = BUILT_IN_CLRSB; + fcodel = BUILT_IN_CLRSBL; + fcodell = BUILT_IN_CLRSBLL; + break; + case BUILT_IN_FFSG: + ifn = IFN_FFS; + fcodei = BUILT_IN_FFS; + fcodel = BUILT_IN_FFSL; + fcodell = BUILT_IN_FFSLL; + break; + case BUILT_IN_PARITYG: + ifn = IFN_PARITY; + fcodei = BUILT_IN_PARITY; + fcodel = BUILT_IN_PARITYL; + fcodell = BUILT_IN_PARITYLL; + break; + case BUILT_IN_POPCOUNTG: + ifn = IFN_POPCOUNT; + fcodei = BUILT_IN_POPCOUNT; + fcodel = BUILT_IN_POPCOUNTL; + fcodell = BUILT_IN_POPCOUNTLL; + break; + default: + gcc_unreachable (); + } + + if (TYPE_PRECISION (arg0_type) + <= TYPE_PRECISION (long_long_unsigned_type_node)) + { + if (TYPE_PRECISION (arg0_type) <= TYPE_PRECISION (unsigned_type_node)) + + cast_type = (TYPE_UNSIGNED (arg0_type) + ? unsigned_type_node : integer_type_node); + else if (TYPE_PRECISION (arg0_type) + <= TYPE_PRECISION (long_unsigned_type_node)) + { + cast_type = (TYPE_UNSIGNED (arg0_type) + ? long_unsigned_type_node : long_integer_type_node); + fcodei = fcodel; + } + else + { + cast_type = (TYPE_UNSIGNED (arg0_type) + ? long_long_unsigned_type_node + : long_long_integer_type_node); + fcodei = fcodell; + } + } + else if (TYPE_PRECISION (arg0_type) <= MAX_FIXED_MODE_SIZE) + { + cast_type + = build_nonstandard_integer_type (MAX_FIXED_MODE_SIZE, + TYPE_UNSIGNED (arg0_type)); + gcc_assert (TYPE_PRECISION (cast_type) + == 2 * TYPE_PRECISION (long_long_unsigned_type_node)); + fcodei = END_BUILTINS; + } + else + fcodei = END_BUILTINS; + if (cast_type) + { + switch (fcode) + { + case BUILT_IN_CLZG: + case BUILT_IN_CLRSBG: + addend = TYPE_PRECISION (arg0_type) - TYPE_PRECISION (cast_type); + break; + default: + break; + } + arg0 = fold_convert (cast_type, arg0); + arg0_type = cast_type; + } + + if (arg1) + arg1 = fold_convert (integer_type_node, arg1); + + tree arg2 = arg1; + if (fcode == BUILT_IN_CLZG && addend) + { + if (arg1) + arg0 = save_expr (arg0); + arg2 = NULL_TREE; + } + tree call = NULL_TREE, tem; + if (TYPE_PRECISION (arg0_type) == MAX_FIXED_MODE_SIZE + && (TYPE_PRECISION (arg0_type) + == 2 * TYPE_PRECISION (long_long_unsigned_type_node))) + { + /* __int128 expansions using up to 2 long long builtins. */ + arg0 = save_expr (arg0); + tree type = (TYPE_UNSIGNED (arg0_type) + ? long_long_unsigned_type_node + : long_long_integer_type_node); + tree hi = fold_build2 (RSHIFT_EXPR, arg0_type, arg0, + build_int_cst (integer_type_node, + MAX_FIXED_MODE_SIZE / 2)); + hi = fold_convert (type, hi); + tree lo = fold_convert (type, arg0); + switch (fcode) + { + case BUILT_IN_CLZG: + call = fold_builtin_bit_query (loc, fcode, lo, NULL_TREE); + call = fold_build2 (PLUS_EXPR, integer_type_node, call, + build_int_cst (integer_type_node, + MAX_FIXED_MODE_SIZE / 2)); + if (arg2) + call = fold_build3 (COND_EXPR, integer_type_node, + fold_build2 (NE_EXPR, boolean_type_node, + lo, build_zero_cst (type)), + call, arg2); + call = fold_build3 (COND_EXPR, integer_type_node, + fold_build2 (NE_EXPR, boolean_type_node, + hi, build_zero_cst (type)), + fold_builtin_bit_query (loc, fcode, hi, + NULL_TREE), + call); + break; + case BUILT_IN_CTZG: + call = fold_builtin_bit_query (loc, fcode, hi, NULL_TREE); + call = fold_build2 (PLUS_EXPR, integer_type_node, call, + build_int_cst (integer_type_node, + MAX_FIXED_MODE_SIZE / 2)); + if (arg2) + call = fold_build3 (COND_EXPR, integer_type_node, + fold_build2 (NE_EXPR, boolean_type_node, + hi, build_zero_cst (type)), + call, arg2); + call = fold_build3 (COND_EXPR, integer_type_node, + fold_build2 (NE_EXPR, boolean_type_node, + lo, build_zero_cst (type)), + fold_builtin_bit_query (loc, fcode, lo, + NULL_TREE), + call); + break; + case BUILT_IN_CLRSBG: + tem = fold_builtin_bit_query (loc, fcode, lo, NULL_TREE); + tem = fold_build2 (PLUS_EXPR, integer_type_node, tem, + build_int_cst (integer_type_node, + MAX_FIXED_MODE_SIZE / 2)); + tem = fold_build3 (COND_EXPR, integer_type_node, + fold_build2 (LT_EXPR, boolean_type_node, + fold_build2 (BIT_XOR_EXPR, type, + lo, hi), + build_zero_cst (type)), + build_int_cst (integer_type_node, + MAX_FIXED_MODE_SIZE / 2 - 1), + tem); + call = fold_builtin_bit_query (loc, fcode, hi, NULL_TREE); + call = save_expr (call); + call = fold_build3 (COND_EXPR, integer_type_node, + fold_build2 (NE_EXPR, boolean_type_node, + call, + build_int_cst (integer_type_node, + MAX_FIXED_MODE_SIZE + / 2 - 1)), + call, tem); + break; + case BUILT_IN_FFSG: + call = fold_builtin_bit_query (loc, fcode, hi, NULL_TREE); + call = fold_build2 (PLUS_EXPR, integer_type_node, call, + build_int_cst (integer_type_node, + MAX_FIXED_MODE_SIZE / 2)); + call = fold_build3 (COND_EXPR, integer_type_node, + fold_build2 (NE_EXPR, boolean_type_node, + hi, build_zero_cst (type)), + call, integer_zero_node); + call = fold_build3 (COND_EXPR, integer_type_node, + fold_build2 (NE_EXPR, boolean_type_node, + lo, build_zero_cst (type)), + fold_builtin_bit_query (loc, fcode, lo, + NULL_TREE), + call); + break; + case BUILT_IN_PARITYG: + call = fold_builtin_bit_query (loc, fcode, + fold_build2 (BIT_XOR_EXPR, type, + lo, hi), NULL_TREE); + break; + case BUILT_IN_POPCOUNTG: + call = fold_build2 (PLUS_EXPR, integer_type_node, + fold_builtin_bit_query (loc, fcode, hi, + NULL_TREE), + fold_builtin_bit_query (loc, fcode, lo, + NULL_TREE)); + break; + default: + gcc_unreachable (); + } + } + else + { + /* Only keep second argument to IFN_CLZ/IFN_CTZ if it is the + value defined at zero during GIMPLE, or for large/huge _BitInt + (which are then lowered during bitint lowering). */ + if (arg2 && TREE_CODE (TREE_TYPE (arg0)) != BITINT_TYPE) + { + int val; + if (fcode == BUILT_IN_CLZG) + { + if (CLZ_DEFINED_VALUE_AT_ZERO (SCALAR_TYPE_MODE (arg0_type), + val) != 2 + || wi::to_widest (arg2) != val) + arg2 = NULL_TREE; + } + else if (CTZ_DEFINED_VALUE_AT_ZERO (SCALAR_TYPE_MODE (arg0_type), + val) != 2 + || wi::to_widest (arg2) != val) + arg2 = NULL_TREE; + if (!direct_internal_fn_supported_p (ifn, arg0_type, + OPTIMIZE_FOR_BOTH)) + arg2 = NULL_TREE; + } + if (fcodei == END_BUILTINS || arg2) + call = build_call_expr_internal_loc (loc, ifn, integer_type_node, + arg2 ? 2 : 1, arg0, arg2); + else + call = build_call_expr_loc (loc, builtin_decl_explicit (fcodei), 1, + arg0); + } + if (addend) + call = fold_build2 (PLUS_EXPR, integer_type_node, call, + build_int_cst (integer_type_node, addend)); + if (arg1 && arg2 == NULL_TREE) + call = fold_build3 (COND_EXPR, integer_type_node, + fold_build2 (NE_EXPR, boolean_type_node, + arg0, build_zero_cst (arg0_type)), + call, arg1); + + return call; +} + /* Fold __builtin_{add,sub}c{,l,ll} into pair of internal functions that return both result of arithmetics and overflowed boolean flag in a complex integer result. */ @@ -9824,6 +10089,14 @@ fold_builtin_1 (location_t loc, tree expr, tree fndecl, tree arg0) return build_empty_stmt (loc); break; + case BUILT_IN_CLZG: + case BUILT_IN_CTZG: + case BUILT_IN_CLRSBG: + case BUILT_IN_FFSG: + case BUILT_IN_PARITYG: + case BUILT_IN_POPCOUNTG: + return fold_builtin_bit_query (loc, fcode, arg0, NULL_TREE); + default: break; } @@ -9913,6 +10186,10 @@ fold_builtin_2 (location_t loc, tree expr, tree fndecl, tree arg0, tree arg1) case BUILT_IN_ATOMIC_IS_LOCK_FREE: return fold_builtin_atomic_is_lock_free (arg0, arg1); + case BUILT_IN_CLZG: + case BUILT_IN_CTZG: + return fold_builtin_bit_query (loc, fcode, arg0, arg1); + default: break; } diff --git a/gcc/builtins.def b/gcc/builtins.def index a6fdb22..33e6cad 100644 --- a/gcc/builtins.def +++ b/gcc/builtins.def @@ -962,15 +962,18 @@ DEF_GCC_BUILTIN (BUILT_IN_CLZ, "clz", BT_FN_INT_UINT, ATTR_CONST_NOTHROW_ DEF_GCC_BUILTIN (BUILT_IN_CLZIMAX, "clzimax", BT_FN_INT_UINTMAX, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_GCC_BUILTIN (BUILT_IN_CLZL, "clzl", BT_FN_INT_ULONG, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_GCC_BUILTIN (BUILT_IN_CLZLL, "clzll", BT_FN_INT_ULONGLONG, ATTR_CONST_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_CLZG, "clzg", BT_FN_INT_VAR, ATTR_CONST_NOTHROW_TYPEGENERIC_LEAF) DEF_GCC_BUILTIN (BUILT_IN_CONSTANT_P, "constant_p", BT_FN_INT_VAR, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_GCC_BUILTIN (BUILT_IN_CTZ, "ctz", BT_FN_INT_UINT, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_GCC_BUILTIN (BUILT_IN_CTZIMAX, "ctzimax", BT_FN_INT_UINTMAX, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_GCC_BUILTIN (BUILT_IN_CTZL, "ctzl", BT_FN_INT_ULONG, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_GCC_BUILTIN (BUILT_IN_CTZLL, "ctzll", BT_FN_INT_ULONGLONG, ATTR_CONST_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_CTZG, "ctzg", BT_FN_INT_VAR, ATTR_CONST_NOTHROW_TYPEGENERIC_LEAF) DEF_GCC_BUILTIN (BUILT_IN_CLRSB, "clrsb", BT_FN_INT_INT, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_GCC_BUILTIN (BUILT_IN_CLRSBIMAX, "clrsbimax", BT_FN_INT_INTMAX, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_GCC_BUILTIN (BUILT_IN_CLRSBL, "clrsbl", BT_FN_INT_LONG, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_GCC_BUILTIN (BUILT_IN_CLRSBLL, "clrsbll", BT_FN_INT_LONGLONG, ATTR_CONST_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_CLRSBG, "clrsbg", BT_FN_INT_VAR, ATTR_CONST_NOTHROW_TYPEGENERIC_LEAF) DEF_EXT_LIB_BUILTIN (BUILT_IN_DCGETTEXT, "dcgettext", BT_FN_STRING_CONST_STRING_CONST_STRING_INT, ATTR_FORMAT_ARG_2) DEF_EXT_LIB_BUILTIN (BUILT_IN_DGETTEXT, "dgettext", BT_FN_STRING_CONST_STRING_CONST_STRING, ATTR_FORMAT_ARG_2) DEF_GCC_BUILTIN (BUILT_IN_DWARF_CFA, "dwarf_cfa", BT_FN_PTR, ATTR_NULL) @@ -993,6 +996,7 @@ DEF_EXT_LIB_BUILTIN (BUILT_IN_FFS, "ffs", BT_FN_INT_INT, ATTR_CONST_NOTHROW_L DEF_EXT_LIB_BUILTIN (BUILT_IN_FFSIMAX, "ffsimax", BT_FN_INT_INTMAX, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_EXT_LIB_BUILTIN (BUILT_IN_FFSL, "ffsl", BT_FN_INT_LONG, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_EXT_LIB_BUILTIN (BUILT_IN_FFSLL, "ffsll", BT_FN_INT_LONGLONG, ATTR_CONST_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_FFSG, "ffsg", BT_FN_INT_VAR, ATTR_CONST_NOTHROW_TYPEGENERIC_LEAF) DEF_EXT_LIB_BUILTIN (BUILT_IN_FORK, "fork", BT_FN_PID, ATTR_NOTHROW_LIST) DEF_GCC_BUILTIN (BUILT_IN_FRAME_ADDRESS, "frame_address", BT_FN_PTR_UINT, ATTR_NULL) /* [trans-mem]: Adjust BUILT_IN_TM_FREE if BUILT_IN_FREE is changed. */ @@ -1041,10 +1045,12 @@ DEF_GCC_BUILTIN (BUILT_IN_PARITY, "parity", BT_FN_INT_UINT, ATTR_CONST_NO DEF_GCC_BUILTIN (BUILT_IN_PARITYIMAX, "parityimax", BT_FN_INT_UINTMAX, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_GCC_BUILTIN (BUILT_IN_PARITYL, "parityl", BT_FN_INT_ULONG, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_GCC_BUILTIN (BUILT_IN_PARITYLL, "parityll", BT_FN_INT_ULONGLONG, ATTR_CONST_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_PARITYG, "parityg", BT_FN_INT_VAR, ATTR_CONST_NOTHROW_TYPEGENERIC_LEAF) DEF_GCC_BUILTIN (BUILT_IN_POPCOUNT, "popcount", BT_FN_INT_UINT, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_GCC_BUILTIN (BUILT_IN_POPCOUNTIMAX, "popcountimax", BT_FN_INT_UINTMAX, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_GCC_BUILTIN (BUILT_IN_POPCOUNTL, "popcountl", BT_FN_INT_ULONG, ATTR_CONST_NOTHROW_LEAF_LIST) DEF_GCC_BUILTIN (BUILT_IN_POPCOUNTLL, "popcountll", BT_FN_INT_ULONGLONG, ATTR_CONST_NOTHROW_LEAF_LIST) +DEF_GCC_BUILTIN (BUILT_IN_POPCOUNTG, "popcountg", BT_FN_INT_VAR, ATTR_CONST_NOTHROW_TYPEGENERIC_LEAF) DEF_EXT_LIB_BUILTIN (BUILT_IN_POSIX_MEMALIGN, "posix_memalign", BT_FN_INT_PTRPTR_SIZE_SIZE, ATTR_NOTHROW_NONNULL_LEAF) DEF_GCC_BUILTIN (BUILT_IN_PREFETCH, "prefetch", BT_FN_VOID_CONST_PTR_VAR, ATTR_NOVOPS_LEAF_LIST) DEF_LIB_BUILTIN (BUILT_IN_REALLOC, "realloc", BT_FN_PTR_PTR_SIZE, ATTR_ALLOC_WARN_UNUSED_RESULT_SIZE_2_NOTHROW_LEAF_LIST) diff --git a/gcc/c-family/c-common.cc b/gcc/c-family/c-common.cc index 77faf17..a619429 100644 --- a/gcc/c-family/c-common.cc +++ b/gcc/c-family/c-common.cc @@ -6475,14 +6475,14 @@ check_builtin_function_arguments (location_t loc, vec<location_t> arg_loc, } if (TREE_CODE (TREE_TYPE (args[2])) == ENUMERAL_TYPE) { - error_at (ARG_LOCATION (2), "argument 3 in call to function " - "%qE has enumerated type", fndecl); + error_at (ARG_LOCATION (2), "argument %u in call to function " + "%qE has enumerated type", 3, fndecl); return false; } else if (TREE_CODE (TREE_TYPE (args[2])) == BOOLEAN_TYPE) { - error_at (ARG_LOCATION (2), "argument 3 in call to function " - "%qE has boolean type", fndecl); + error_at (ARG_LOCATION (2), "argument %u in call to function " + "%qE has boolean type", 3, fndecl); return false; } return true; @@ -6522,6 +6522,72 @@ check_builtin_function_arguments (location_t loc, vec<location_t> arg_loc, } return false; + case BUILT_IN_CLZG: + case BUILT_IN_CTZG: + case BUILT_IN_CLRSBG: + case BUILT_IN_FFSG: + case BUILT_IN_PARITYG: + case BUILT_IN_POPCOUNTG: + if (nargs == 2 + && (DECL_FUNCTION_CODE (fndecl) == BUILT_IN_CLZG + || DECL_FUNCTION_CODE (fndecl) == BUILT_IN_CTZG)) + { + if (!INTEGRAL_TYPE_P (TREE_TYPE (args[1]))) + { + error_at (ARG_LOCATION (1), "argument %u in call to function " + "%qE does not have integral type", 2, fndecl); + return false; + } + if ((TYPE_PRECISION (TREE_TYPE (args[1])) + > TYPE_PRECISION (integer_type_node)) + || (TYPE_PRECISION (TREE_TYPE (args[1])) + == TYPE_PRECISION (integer_type_node) + && TYPE_UNSIGNED (TREE_TYPE (args[1])))) + { + error_at (ARG_LOCATION (1), "argument %u in call to function " + "%qE does not have %<int%> type", 2, fndecl); + return false; + } + } + else if (!builtin_function_validate_nargs (loc, fndecl, nargs, 1)) + return false; + + if (!INTEGRAL_TYPE_P (TREE_TYPE (args[0]))) + { + error_at (ARG_LOCATION (0), "argument %u in call to function " + "%qE does not have integral type", 1, fndecl); + return false; + } + if (TREE_CODE (TREE_TYPE (args[0])) == ENUMERAL_TYPE) + { + error_at (ARG_LOCATION (0), "argument %u in call to function " + "%qE has enumerated type", 1, fndecl); + return false; + } + if (TREE_CODE (TREE_TYPE (args[0])) == BOOLEAN_TYPE) + { + error_at (ARG_LOCATION (0), "argument %u in call to function " + "%qE has boolean type", 1, fndecl); + return false; + } + if (DECL_FUNCTION_CODE (fndecl) == BUILT_IN_FFSG + || DECL_FUNCTION_CODE (fndecl) == BUILT_IN_CLRSBG) + { + if (TYPE_UNSIGNED (TREE_TYPE (args[0]))) + { + error_at (ARG_LOCATION (0), "argument 1 in call to function " + "%qE has unsigned type", fndecl); + return false; + } + } + else if (!TYPE_UNSIGNED (TREE_TYPE (args[0]))) + { + error_at (ARG_LOCATION (0), "argument 1 in call to function " + "%qE has signed type", fndecl); + return false; + } + return true; + default: return true; } diff --git a/gcc/c-family/c-gimplify.cc b/gcc/c-family/c-gimplify.cc index 17b0610..2f44e12 100644 --- a/gcc/c-family/c-gimplify.cc +++ b/gcc/c-family/c-gimplify.cc @@ -818,6 +818,28 @@ c_gimplify_expr (tree *expr_p, gimple_seq *pre_p ATTRIBUTE_UNUSED, break; } + case CALL_EXPR: + { + tree fndecl = get_callee_fndecl (*expr_p); + if (fndecl + && fndecl_built_in_p (fndecl, BUILT_IN_CLZG, BUILT_IN_CTZG) + && call_expr_nargs (*expr_p) == 2 + && TREE_CODE (CALL_EXPR_ARG (*expr_p, 1)) != INTEGER_CST) + { + tree a = save_expr (CALL_EXPR_ARG (*expr_p, 0)); + tree c = build_call_expr_loc (EXPR_LOCATION (*expr_p), + fndecl, 1, a); + *expr_p = build3_loc (EXPR_LOCATION (*expr_p), COND_EXPR, + integer_type_node, + build2_loc (EXPR_LOCATION (*expr_p), + NE_EXPR, boolean_type_node, a, + build_zero_cst (TREE_TYPE (a))), + c, CALL_EXPR_ARG (*expr_p, 1)); + return GS_OK; + } + break; + } + default:; } diff --git a/gcc/c/c-typeck.cc b/gcc/c/c-typeck.cc index 366ca88..1dbb447 100644 --- a/gcc/c/c-typeck.cc +++ b/gcc/c/c-typeck.cc @@ -3416,6 +3416,7 @@ convert_arguments (location_t loc, vec<location_t> arg_loc, tree typelist, && lookup_attribute ("type generic", TYPE_ATTRIBUTES (TREE_TYPE (fundecl))); bool type_generic_remove_excess_precision = false; bool type_generic_overflow_p = false; + bool type_generic_bit_query = false; tree selector; /* Change pointer to function to the function itself for @@ -3471,6 +3472,17 @@ convert_arguments (location_t loc, vec<location_t> arg_loc, tree typelist, type_generic_overflow_p = true; break; + case BUILT_IN_CLZG: + case BUILT_IN_CTZG: + case BUILT_IN_CLRSBG: + case BUILT_IN_FFSG: + case BUILT_IN_PARITYG: + case BUILT_IN_POPCOUNTG: + /* The first argument of these type-generic builtins + should not be promoted. */ + type_generic_bit_query = true; + break; + default: break; } @@ -3606,11 +3618,13 @@ convert_arguments (location_t loc, vec<location_t> arg_loc, tree typelist, } } else if ((excess_precision && !type_generic) - || (type_generic_overflow_p && parmnum == 2)) + || (type_generic_overflow_p && parmnum == 2) + || (type_generic_bit_query && parmnum == 0)) /* A "double" argument with excess precision being passed without a prototype or in variable arguments. The last argument of __builtin_*_overflow_p should not be - promoted. */ + promoted, similarly the first argument of + __builtin_{clz,ctz,clrsb,ffs,parity,popcount}g. */ parmval = convert (valtype, val); else if ((invalid_func_diag = targetm.calls.invalid_arg_for_unprototyped_fn (typelist, fundecl, val))) diff --git a/gcc/cp/call.cc b/gcc/cp/call.cc index 4516677..709fd74 100644 --- a/gcc/cp/call.cc +++ b/gcc/cp/call.cc @@ -9290,7 +9290,9 @@ convert_for_arg_passing (tree type, tree val, tsubst_flags_t complain) This is true for some builtins which don't act like normal functions. Return 2 if just decay_conversion and removal of excess precision should be done, 1 if just decay_conversion. Return 3 for special treatment of - the 3rd argument for __builtin_*_overflow_p. */ + the 3rd argument for __builtin_*_overflow_p. Return 4 for special + treatment of the 1st argument for + __builtin_{clz,ctz,clrsb,ffs,parity,popcount}g. */ int magic_varargs_p (tree fn) @@ -9317,6 +9319,14 @@ magic_varargs_p (tree fn) case BUILT_IN_FPCLASSIFY: return 2; + case BUILT_IN_CLZG: + case BUILT_IN_CTZG: + case BUILT_IN_CLRSBG: + case BUILT_IN_FFSG: + case BUILT_IN_PARITYG: + case BUILT_IN_POPCOUNTG: + return 4; + default: return lookup_attribute ("type generic", TYPE_ATTRIBUTES (TREE_TYPE (fn))) != 0; @@ -10122,7 +10132,7 @@ build_over_call (struct z_candidate *cand, int flags, tsubst_flags_t complain) for (; arg_index < vec_safe_length (args); ++arg_index) { tree a = (*args)[arg_index]; - if (magic == 3 && arg_index == 2) + if ((magic == 3 && arg_index == 2) || (magic == 4 && arg_index == 0)) { /* Do no conversions for certain magic varargs. */ a = mark_type_use (a); diff --git a/gcc/cp/cp-gimplify.cc b/gcc/cp/cp-gimplify.cc index 9375a11..795c811 100644 --- a/gcc/cp/cp-gimplify.cc +++ b/gcc/cp/cp-gimplify.cc @@ -771,6 +771,10 @@ cp_gimplify_expr (tree *expr_p, gimple_seq *pre_p, gimple_seq *post_p) default: break; } + else if (decl + && fndecl_built_in_p (decl, BUILT_IN_CLZG, BUILT_IN_CTZG)) + ret = (enum gimplify_status) c_gimplify_expr (expr_p, pre_p, + post_p); } break; diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi index 7cdfdf8..406ccc9 100644 --- a/gcc/doc/extend.texi +++ b/gcc/doc/extend.texi @@ -14960,6 +14960,48 @@ Similar to @code{__builtin_parity}, except the argument type is @code{unsigned long long}. @enddefbuiltin +@defbuiltin{int __builtin_ffsg (...)} +Similar to @code{__builtin_ffs}, except the argument is type-generic +signed integer (standard, extended or bit-precise). No integral argument +promotions are performed on the argument. +@enddefbuiltin + +@defbuiltin{int __builtin_clzg (...)} +Similar to @code{__builtin_clz}, except the argument is type-generic +unsigned integer (standard, extended or bit-precise) and there is +optional second argument with int type. No integral argument promotions +are performed on the first argument. If two arguments are specified, +and first argument is 0, the result is the second argument. If only +one argument is specified and it is 0, the result is undefined. +@enddefbuiltin + +@defbuiltin{int __builtin_ctzg (...)} +Similar to @code{__builtin_ctz}, except the argument is type-generic +unsigned integer (standard, extended or bit-precise) and there is +optional second argument with int type. No integral argument promotions +are performed on the first argument. If two arguments are specified, +and first argument is 0, the result is the second argument. If only +one argument is specified and it is 0, the result is undefined. +@enddefbuiltin + +@defbuiltin{int __builtin_clrsbg (...)} +Similar to @code{__builtin_clrsb}, except the argument is type-generic +signed integer (standard, extended or bit-precise). No integral argument +promotions are performed on the argument. +@enddefbuiltin + +@defbuiltin{int __builtin_popcountg (...)} +Similar to @code{__builtin_popcount}, except the argument is type-generic +unsigned integer (standard, extended or bit-precise). No integral argument +promotions are performed on the argument. +@enddefbuiltin + +@defbuiltin{int __builtin_parityg (...)} +Similar to @code{__builtin_parity}, except the argument is type-generic +unsigned integer (standard, extended or bit-precise). No integral argument +promotions are performed on the argument. +@enddefbuiltin + @defbuiltin{double __builtin_powi (double, int)} @defbuiltinx{float __builtin_powif (float, int)} @defbuiltinx{{long double} __builtin_powil (long double, int)} diff --git a/gcc/fold-const-call.cc b/gcc/fold-const-call.cc index 04be3d2..36f4ecc 100644 --- a/gcc/fold-const-call.cc +++ b/gcc/fold-const-call.cc @@ -27,7 +27,7 @@ along with GCC; see the file COPYING3. If not see #include "fold-const.h" #include "fold-const-call.h" #include "case-cfn-macros.h" -#include "tm.h" /* For C[LT]Z_DEFINED_AT_ZERO. */ +#include "tm.h" /* For C[LT]Z_DEFINED_VALUE_AT_ZERO. */ #include "builtins.h" #include "gimple-expr.h" #include "tree-vector-builder.h" @@ -1017,14 +1017,18 @@ fold_const_call_ss (wide_int *result, combined_fn fn, const wide_int_ref &arg, switch (fn) { CASE_CFN_FFS: + case CFN_BUILT_IN_FFSG: *result = wi::shwi (wi::ffs (arg), precision); return true; CASE_CFN_CLZ: + case CFN_BUILT_IN_CLZG: { int tmp; if (wi::ne_p (arg, 0)) tmp = wi::clz (arg); + else if (TREE_CODE (arg_type) == BITINT_TYPE) + tmp = TYPE_PRECISION (arg_type); else if (!CLZ_DEFINED_VALUE_AT_ZERO (SCALAR_INT_TYPE_MODE (arg_type), tmp)) tmp = TYPE_PRECISION (arg_type); @@ -1033,10 +1037,13 @@ fold_const_call_ss (wide_int *result, combined_fn fn, const wide_int_ref &arg, } CASE_CFN_CTZ: + case CFN_BUILT_IN_CTZG: { int tmp; if (wi::ne_p (arg, 0)) tmp = wi::ctz (arg); + else if (TREE_CODE (arg_type) == BITINT_TYPE) + tmp = TYPE_PRECISION (arg_type); else if (!CTZ_DEFINED_VALUE_AT_ZERO (SCALAR_INT_TYPE_MODE (arg_type), tmp)) tmp = TYPE_PRECISION (arg_type); @@ -1045,14 +1052,17 @@ fold_const_call_ss (wide_int *result, combined_fn fn, const wide_int_ref &arg, } CASE_CFN_CLRSB: + case CFN_BUILT_IN_CLRSBG: *result = wi::shwi (wi::clrsb (arg), precision); return true; CASE_CFN_POPCOUNT: + case CFN_BUILT_IN_POPCOUNTG: *result = wi::shwi (wi::popcount (arg), precision); return true; CASE_CFN_PARITY: + case CFN_BUILT_IN_PARITYG: *result = wi::shwi (wi::parity (arg), precision); return true; @@ -1531,6 +1541,49 @@ fold_const_call_sss (real_value *result, combined_fn fn, /* Try to evaluate: + *RESULT = FN (ARG0, ARG1) + + where ARG_TYPE is the type of ARG0 and PRECISION is the number of bits in + the result. Return true on success. */ + +static bool +fold_const_call_sss (wide_int *result, combined_fn fn, + const wide_int_ref &arg0, const wide_int_ref &arg1, + unsigned int precision, tree arg_type ATTRIBUTE_UNUSED) +{ + switch (fn) + { + case CFN_CLZ: + case CFN_BUILT_IN_CLZG: + { + int tmp; + if (wi::ne_p (arg0, 0)) + tmp = wi::clz (arg0); + else + tmp = arg1.to_shwi (); + *result = wi::shwi (tmp, precision); + return true; + } + + case CFN_CTZ: + case CFN_BUILT_IN_CTZG: + { + int tmp; + if (wi::ne_p (arg0, 0)) + tmp = wi::ctz (arg0); + else + tmp = arg1.to_shwi (); + *result = wi::shwi (tmp, precision); + return true; + } + + default: + return false; + } +} + +/* Try to evaluate: + RESULT = fn (ARG0, ARG1) where FORMAT is the format of the real and imaginary parts of RESULT @@ -1565,6 +1618,19 @@ fold_const_call_1 (combined_fn fn, tree type, tree arg0, tree arg1) machine_mode arg0_mode = TYPE_MODE (TREE_TYPE (arg0)); machine_mode arg1_mode = TYPE_MODE (TREE_TYPE (arg1)); + if (integer_cst_p (arg0) && integer_cst_p (arg1)) + { + if (SCALAR_INT_MODE_P (mode)) + { + wide_int result; + if (fold_const_call_sss (&result, fn, wi::to_wide (arg0), + wi::to_wide (arg1), TYPE_PRECISION (type), + TREE_TYPE (arg0))) + return wide_int_to_tree (type, result); + } + return NULL_TREE; + } + if (mode == arg0_mode && real_cst_p (arg0) && real_cst_p (arg1)) diff --git a/gcc/genmatch.cc b/gcc/genmatch.cc index 4572342..3488764 100644 --- a/gcc/genmatch.cc +++ b/gcc/genmatch.cc @@ -1896,8 +1896,14 @@ cmp_operand (operand *o1, operand *o2) { expr *e1 = static_cast<expr *>(o1); expr *e2 = static_cast<expr *>(o2); - return (e1->operation == e2->operation - && e1->is_generic == e2->is_generic); + if (e1->operation != e2->operation + || e1->is_generic != e2->is_generic) + return false; + if (e1->operation->kind == id_base::FN + /* For function calls also compare number of arguments. */ + && e1->ops.length () != e2->ops.length ()) + return false; + return true; } else return false; @@ -3071,6 +3077,26 @@ dt_operand::gen_generic_expr (FILE *f, int indent, const char *opname) return 0; } +/* Compare 2 fns or generic_fns vector entries for vector sorting. + Same operation entries with different number of arguments should + be adjacent. */ + +static int +fns_cmp (const void *p1, const void *p2) +{ + dt_operand *op1 = *(dt_operand *const *) p1; + dt_operand *op2 = *(dt_operand *const *) p2; + expr *e1 = as_a <expr *> (op1->op); + expr *e2 = as_a <expr *> (op2->op); + id_base *b1 = e1->operation; + id_base *b2 = e2->operation; + if (b1->hashval < b2->hashval) + return -1; + if (b1->hashval > b2->hashval) + return 1; + return strcmp (b1->id, b2->id); +} + /* Generate matching code for the children of the decision tree node. */ void @@ -3144,6 +3170,8 @@ dt_node::gen_kids (FILE *f, int indent, bool gimple, int depth) Like DT_TRUE, DT_MATCH serves as a barrier as it can cause dependent matches to get out-of-order. Generate code now for what we have collected sofar. */ + fns.qsort (fns_cmp); + generic_fns.qsort (fns_cmp); gen_kids_1 (f, indent, gimple, depth, gimple_exprs, generic_exprs, fns, generic_fns, preds, others); /* And output the true operand itself. */ @@ -3160,6 +3188,8 @@ dt_node::gen_kids (FILE *f, int indent, bool gimple, int depth) } /* Generate code for the remains. */ + fns.qsort (fns_cmp); + generic_fns.qsort (fns_cmp); gen_kids_1 (f, indent, gimple, depth, gimple_exprs, generic_exprs, fns, generic_fns, preds, others); } @@ -3257,14 +3287,21 @@ dt_node::gen_kids_1 (FILE *f, int indent, bool gimple, int depth, indent += 4; fprintf_indent (f, indent, "{\n"); + id_base *last_op = NULL; for (unsigned i = 0; i < fns_len; ++i) { expr *e = as_a <expr *>(fns[i]->op); - if (user_id *u = dyn_cast <user_id *> (e->operation)) - for (auto id : u->substitutes) - fprintf_indent (f, indent, "case %s:\n", id->id); - else - fprintf_indent (f, indent, "case %s:\n", e->operation->id); + if (e->operation != last_op) + { + if (i) + fprintf_indent (f, indent, " break;\n"); + if (user_id *u = dyn_cast <user_id *> (e->operation)) + for (auto id : u->substitutes) + fprintf_indent (f, indent, "case %s:\n", id->id); + else + fprintf_indent (f, indent, "case %s:\n", e->operation->id); + } + last_op = e->operation; /* We need to be defensive against bogus prototypes allowing calls with not enough arguments. */ fprintf_indent (f, indent, @@ -3273,9 +3310,9 @@ dt_node::gen_kids_1 (FILE *f, int indent, bool gimple, int depth, fprintf_indent (f, indent, " {\n"); fns[i]->gen (f, indent + 6, true, depth); fprintf_indent (f, indent, " }\n"); - fprintf_indent (f, indent, " break;\n"); } + fprintf_indent (f, indent, " break;\n"); fprintf_indent (f, indent, "default:;\n"); fprintf_indent (f, indent, "}\n"); indent -= 4; @@ -3335,18 +3372,25 @@ dt_node::gen_kids_1 (FILE *f, int indent, bool gimple, int depth, " {\n"); indent += 4; + id_base *last_op = NULL; for (unsigned j = 0; j < generic_fns.length (); ++j) { expr *e = as_a <expr *>(generic_fns[j]->op); gcc_assert (e->operation->kind == id_base::FN); - fprintf_indent (f, indent, "case %s:\n", e->operation->id); + if (e->operation != last_op) + { + if (j) + fprintf_indent (f, indent, " break;\n"); + fprintf_indent (f, indent, "case %s:\n", e->operation->id); + } + last_op = e->operation; fprintf_indent (f, indent, " if (call_expr_nargs (%s) == %d)\n" " {\n", kid_opname, e->ops.length ()); generic_fns[j]->gen (f, indent + 6, false, depth); - fprintf_indent (f, indent, " }\n" - " break;\n"); + fprintf_indent (f, indent, " }\n"); } + fprintf_indent (f, indent, " break;\n"); fprintf_indent (f, indent, "default:;\n"); indent -= 4; diff --git a/gcc/gimple-lower-bitint.cc b/gcc/gimple-lower-bitint.cc index 6655859..c429cb2 100644 --- a/gcc/gimple-lower-bitint.cc +++ b/gcc/gimple-lower-bitint.cc @@ -427,6 +427,7 @@ struct bitint_large_huge void lower_mul_overflow (tree, gimple *); void lower_cplxpart_stmt (tree, gimple *); void lower_complexexpr_stmt (gimple *); + void lower_bit_query (gimple *); void lower_call (tree, gimple *); void lower_asm (gimple *); void lower_stmt (gimple *); @@ -4455,6 +4456,524 @@ bitint_large_huge::lower_complexexpr_stmt (gimple *stmt) insert_before (g); } +/* Lower a .{CLZ,CTZ,CLRSB,FFS,PARITY,POPCOUNT} call with one large/huge _BitInt + argument. */ + +void +bitint_large_huge::lower_bit_query (gimple *stmt) +{ + tree arg0 = gimple_call_arg (stmt, 0); + tree arg1 = (gimple_call_num_args (stmt) == 2 + ? gimple_call_arg (stmt, 1) : NULL_TREE); + tree lhs = gimple_call_lhs (stmt); + gimple *g; + + if (!lhs) + { + gimple_stmt_iterator gsi = gsi_for_stmt (stmt); + gsi_remove (&gsi, true); + return; + } + tree type = TREE_TYPE (arg0); + gcc_assert (TREE_CODE (type) == BITINT_TYPE); + bitint_prec_kind kind = bitint_precision_kind (type); + gcc_assert (kind >= bitint_prec_large); + enum internal_fn ifn = gimple_call_internal_fn (stmt); + enum built_in_function fcode = END_BUILTINS; + gcc_assert (TYPE_PRECISION (unsigned_type_node) == limb_prec + || TYPE_PRECISION (long_unsigned_type_node) == limb_prec + || TYPE_PRECISION (long_long_unsigned_type_node) == limb_prec); + switch (ifn) + { + case IFN_CLZ: + if (TYPE_PRECISION (unsigned_type_node) == limb_prec) + fcode = BUILT_IN_CLZ; + else if (TYPE_PRECISION (long_unsigned_type_node) == limb_prec) + fcode = BUILT_IN_CLZL; + else + fcode = BUILT_IN_CLZLL; + break; + case IFN_FFS: + /* .FFS (X) is .CTZ (X, -1) + 1, though under the hood + we don't add the addend at the end. */ + arg1 = integer_zero_node; + /* FALLTHRU */ + case IFN_CTZ: + if (TYPE_PRECISION (unsigned_type_node) == limb_prec) + fcode = BUILT_IN_CTZ; + else if (TYPE_PRECISION (long_unsigned_type_node) == limb_prec) + fcode = BUILT_IN_CTZL; + else + fcode = BUILT_IN_CTZLL; + m_upwards = true; + break; + case IFN_CLRSB: + if (TYPE_PRECISION (unsigned_type_node) == limb_prec) + fcode = BUILT_IN_CLRSB; + else if (TYPE_PRECISION (long_unsigned_type_node) == limb_prec) + fcode = BUILT_IN_CLRSBL; + else + fcode = BUILT_IN_CLRSBLL; + break; + case IFN_PARITY: + if (TYPE_PRECISION (unsigned_type_node) == limb_prec) + fcode = BUILT_IN_PARITY; + else if (TYPE_PRECISION (long_unsigned_type_node) == limb_prec) + fcode = BUILT_IN_PARITYL; + else + fcode = BUILT_IN_PARITYLL; + m_upwards = true; + break; + case IFN_POPCOUNT: + if (TYPE_PRECISION (unsigned_type_node) == limb_prec) + fcode = BUILT_IN_POPCOUNT; + else if (TYPE_PRECISION (long_unsigned_type_node) == limb_prec) + fcode = BUILT_IN_POPCOUNTL; + else + fcode = BUILT_IN_POPCOUNTLL; + m_upwards = true; + break; + default: + gcc_unreachable (); + } + tree fndecl = builtin_decl_explicit (fcode), res = NULL_TREE; + unsigned cnt = 0, rem = 0, end = 0, prec = TYPE_PRECISION (type); + struct bq_details { edge e; tree val, addend; } *bqp = NULL; + basic_block edge_bb = NULL; + if (m_upwards) + { + tree idx = NULL_TREE, idx_first = NULL_TREE, idx_next = NULL_TREE; + if (kind == bitint_prec_large) + cnt = CEIL (prec, limb_prec); + else + { + rem = (prec % (2 * limb_prec)); + end = (prec - rem) / limb_prec; + cnt = 2 + CEIL (rem, limb_prec); + idx = idx_first = create_loop (size_zero_node, &idx_next); + } + + if (ifn == IFN_CTZ || ifn == IFN_FFS) + { + gimple_stmt_iterator gsi = gsi_for_stmt (stmt); + gsi_prev (&gsi); + edge e = split_block (gsi_bb (gsi), gsi_stmt (gsi)); + edge_bb = e->src; + if (kind == bitint_prec_large) + { + m_gsi = gsi_last_bb (edge_bb); + if (!gsi_end_p (m_gsi)) + gsi_next (&m_gsi); + } + bqp = XALLOCAVEC (struct bq_details, cnt); + } + else + m_after_stmt = stmt; + if (kind != bitint_prec_large) + m_upwards_2limb = end; + + for (unsigned i = 0; i < cnt; i++) + { + m_data_cnt = 0; + if (kind == bitint_prec_large) + idx = size_int (i); + else if (i >= 2) + idx = size_int (end + (i > 2)); + + tree rhs1 = handle_operand (arg0, idx); + if (!useless_type_conversion_p (m_limb_type, TREE_TYPE (rhs1))) + { + if (!TYPE_UNSIGNED (TREE_TYPE (rhs1))) + rhs1 = add_cast (unsigned_type_for (TREE_TYPE (rhs1)), rhs1); + rhs1 = add_cast (m_limb_type, rhs1); + } + + tree in, out, tem; + if (ifn == IFN_PARITY) + in = prepare_data_in_out (build_zero_cst (m_limb_type), idx, &out); + else if (ifn == IFN_FFS) + in = prepare_data_in_out (integer_one_node, idx, &out); + else + in = prepare_data_in_out (integer_zero_node, idx, &out); + + switch (ifn) + { + case IFN_CTZ: + case IFN_FFS: + g = gimple_build_cond (NE_EXPR, rhs1, + build_zero_cst (m_limb_type), + NULL_TREE, NULL_TREE); + insert_before (g); + edge e1, e2; + e1 = split_block (gsi_bb (m_gsi), g); + e1->flags = EDGE_FALSE_VALUE; + e2 = make_edge (e1->src, gimple_bb (stmt), EDGE_TRUE_VALUE); + e1->probability = profile_probability::unlikely (); + e2->probability = e1->probability.invert (); + if (i == 0) + set_immediate_dominator (CDI_DOMINATORS, e2->dest, e2->src); + m_gsi = gsi_after_labels (e1->dest); + bqp[i].e = e2; + bqp[i].val = rhs1; + if (tree_fits_uhwi_p (idx)) + bqp[i].addend + = build_int_cst (integer_type_node, + tree_to_uhwi (idx) * limb_prec + + (ifn == IFN_FFS)); + else + { + bqp[i].addend = in; + if (i == 1) + res = out; + else + res = make_ssa_name (integer_type_node); + g = gimple_build_assign (res, PLUS_EXPR, in, + build_int_cst (integer_type_node, + limb_prec)); + insert_before (g); + m_data[m_data_cnt] = res; + } + break; + case IFN_PARITY: + if (!integer_zerop (in)) + { + if (kind == bitint_prec_huge && i == 1) + res = out; + else + res = make_ssa_name (m_limb_type); + g = gimple_build_assign (res, BIT_XOR_EXPR, in, rhs1); + insert_before (g); + } + else + res = rhs1; + m_data[m_data_cnt] = res; + break; + case IFN_POPCOUNT: + g = gimple_build_call (fndecl, 1, rhs1); + tem = make_ssa_name (integer_type_node); + gimple_call_set_lhs (g, tem); + insert_before (g); + if (!integer_zerop (in)) + { + if (kind == bitint_prec_huge && i == 1) + res = out; + else + res = make_ssa_name (integer_type_node); + g = gimple_build_assign (res, PLUS_EXPR, in, tem); + insert_before (g); + } + else + res = tem; + m_data[m_data_cnt] = res; + break; + default: + gcc_unreachable (); + } + + m_first = false; + if (kind == bitint_prec_huge && i <= 1) + { + if (i == 0) + { + idx = make_ssa_name (sizetype); + g = gimple_build_assign (idx, PLUS_EXPR, idx_first, + size_one_node); + insert_before (g); + } + else + { + g = gimple_build_assign (idx_next, PLUS_EXPR, idx_first, + size_int (2)); + insert_before (g); + g = gimple_build_cond (NE_EXPR, idx_next, size_int (end), + NULL_TREE, NULL_TREE); + insert_before (g); + if (ifn == IFN_CTZ || ifn == IFN_FFS) + m_gsi = gsi_after_labels (edge_bb); + else + m_gsi = gsi_for_stmt (stmt); + } + } + } + } + else + { + tree idx = NULL_TREE, idx_next = NULL_TREE, first = NULL_TREE; + int sub_one = 0; + if (kind == bitint_prec_large) + cnt = CEIL (prec, limb_prec); + else + { + rem = prec % limb_prec; + if (rem == 0 && (!TYPE_UNSIGNED (type) || ifn == IFN_CLRSB)) + rem = limb_prec; + end = (prec - rem) / limb_prec; + cnt = 1 + (rem != 0); + if (ifn == IFN_CLRSB) + sub_one = 1; + } + + gimple_stmt_iterator gsi = gsi_for_stmt (stmt); + gsi_prev (&gsi); + edge e = split_block (gsi_bb (gsi), gsi_stmt (gsi)); + edge_bb = e->src; + m_gsi = gsi_last_bb (edge_bb); + if (!gsi_end_p (m_gsi)) + gsi_next (&m_gsi); + + if (ifn == IFN_CLZ) + bqp = XALLOCAVEC (struct bq_details, cnt); + else + { + gsi = gsi_for_stmt (stmt); + gsi_prev (&gsi); + e = split_block (gsi_bb (gsi), gsi_stmt (gsi)); + edge_bb = e->src; + bqp = XALLOCAVEC (struct bq_details, 2 * cnt); + } + + for (unsigned i = 0; i < cnt; i++) + { + m_data_cnt = 0; + if (kind == bitint_prec_large) + idx = size_int (cnt - i - 1); + else if (i == cnt - 1) + idx = create_loop (size_int (end - 1), &idx_next); + else + idx = size_int (end); + + tree rhs1 = handle_operand (arg0, idx); + if (!useless_type_conversion_p (m_limb_type, TREE_TYPE (rhs1))) + { + if (ifn == IFN_CLZ && !TYPE_UNSIGNED (TREE_TYPE (rhs1))) + rhs1 = add_cast (unsigned_type_for (TREE_TYPE (rhs1)), rhs1); + else if (ifn == IFN_CLRSB && TYPE_UNSIGNED (TREE_TYPE (rhs1))) + rhs1 = add_cast (signed_type_for (TREE_TYPE (rhs1)), rhs1); + rhs1 = add_cast (m_limb_type, rhs1); + } + + if (ifn == IFN_CLZ) + { + g = gimple_build_cond (NE_EXPR, rhs1, + build_zero_cst (m_limb_type), + NULL_TREE, NULL_TREE); + insert_before (g); + edge e1 = split_block (gsi_bb (m_gsi), g); + e1->flags = EDGE_FALSE_VALUE; + edge e2 = make_edge (e1->src, gimple_bb (stmt), EDGE_TRUE_VALUE); + e1->probability = profile_probability::unlikely (); + e2->probability = e1->probability.invert (); + if (i == 0) + set_immediate_dominator (CDI_DOMINATORS, e2->dest, e2->src); + m_gsi = gsi_after_labels (e1->dest); + bqp[i].e = e2; + bqp[i].val = rhs1; + } + else + { + if (i == 0) + { + first = rhs1; + g = gimple_build_assign (make_ssa_name (m_limb_type), + PLUS_EXPR, rhs1, + build_int_cst (m_limb_type, 1)); + insert_before (g); + g = gimple_build_cond (GT_EXPR, gimple_assign_lhs (g), + build_int_cst (m_limb_type, 1), + NULL_TREE, NULL_TREE); + insert_before (g); + } + else + { + g = gimple_build_assign (make_ssa_name (m_limb_type), + BIT_XOR_EXPR, rhs1, first); + insert_before (g); + tree stype = signed_type_for (m_limb_type); + g = gimple_build_cond (LT_EXPR, + add_cast (stype, + gimple_assign_lhs (g)), + build_zero_cst (stype), + NULL_TREE, NULL_TREE); + insert_before (g); + edge e1 = split_block (gsi_bb (m_gsi), g); + e1->flags = EDGE_FALSE_VALUE; + edge e2 = make_edge (e1->src, gimple_bb (stmt), + EDGE_TRUE_VALUE); + e1->probability = profile_probability::unlikely (); + e2->probability = e1->probability.invert (); + if (i == 1) + set_immediate_dominator (CDI_DOMINATORS, e2->dest, + e2->src); + m_gsi = gsi_after_labels (e1->dest); + bqp[2 * i].e = e2; + g = gimple_build_cond (NE_EXPR, rhs1, first, + NULL_TREE, NULL_TREE); + insert_before (g); + } + edge e1 = split_block (gsi_bb (m_gsi), g); + e1->flags = EDGE_FALSE_VALUE; + edge e2 = make_edge (e1->src, edge_bb, EDGE_TRUE_VALUE); + e1->probability = profile_probability::unlikely (); + e2->probability = e1->probability.invert (); + if (i == 0) + set_immediate_dominator (CDI_DOMINATORS, e2->dest, e2->src); + m_gsi = gsi_after_labels (e1->dest); + bqp[2 * i + 1].e = e2; + bqp[i].val = rhs1; + } + if (tree_fits_uhwi_p (idx)) + bqp[i].addend + = build_int_cst (integer_type_node, + (int) prec + - (((int) tree_to_uhwi (idx) + 1) + * limb_prec) - sub_one); + else + { + tree in, out; + in = build_int_cst (integer_type_node, rem - sub_one); + m_first = true; + in = prepare_data_in_out (in, idx, &out); + out = m_data[m_data_cnt + 1]; + bqp[i].addend = in; + g = gimple_build_assign (out, PLUS_EXPR, in, + build_int_cst (integer_type_node, + limb_prec)); + insert_before (g); + m_data[m_data_cnt] = out; + } + + m_first = false; + if (kind == bitint_prec_huge && i == cnt - 1) + { + g = gimple_build_assign (idx_next, PLUS_EXPR, idx, + size_int (-1)); + insert_before (g); + g = gimple_build_cond (NE_EXPR, idx, size_zero_node, + NULL_TREE, NULL_TREE); + insert_before (g); + edge true_edge, false_edge; + extract_true_false_edges_from_block (gsi_bb (m_gsi), + &true_edge, &false_edge); + m_gsi = gsi_after_labels (false_edge->dest); + } + } + } + switch (ifn) + { + case IFN_CLZ: + case IFN_CTZ: + case IFN_FFS: + gphi *phi1, *phi2, *phi3; + basic_block bb; + bb = gsi_bb (m_gsi); + remove_edge (find_edge (bb, gimple_bb (stmt))); + phi1 = create_phi_node (make_ssa_name (m_limb_type), + gimple_bb (stmt)); + phi2 = create_phi_node (make_ssa_name (integer_type_node), + gimple_bb (stmt)); + for (unsigned i = 0; i < cnt; i++) + { + add_phi_arg (phi1, bqp[i].val, bqp[i].e, UNKNOWN_LOCATION); + add_phi_arg (phi2, bqp[i].addend, bqp[i].e, UNKNOWN_LOCATION); + } + if (arg1 == NULL_TREE) + { + g = gimple_build_builtin_unreachable (m_loc); + insert_before (g); + } + m_gsi = gsi_for_stmt (stmt); + g = gimple_build_call (fndecl, 1, gimple_phi_result (phi1)); + gimple_call_set_lhs (g, make_ssa_name (integer_type_node)); + insert_before (g); + if (arg1 == NULL_TREE) + g = gimple_build_assign (lhs, PLUS_EXPR, + gimple_phi_result (phi2), + gimple_call_lhs (g)); + else + { + g = gimple_build_assign (make_ssa_name (integer_type_node), + PLUS_EXPR, gimple_phi_result (phi2), + gimple_call_lhs (g)); + insert_before (g); + edge e1 = split_block (gimple_bb (stmt), g); + edge e2 = make_edge (bb, e1->dest, EDGE_FALLTHRU); + e2->probability = profile_probability::always (); + set_immediate_dominator (CDI_DOMINATORS, e1->dest, + get_immediate_dominator (CDI_DOMINATORS, + e1->src)); + phi3 = create_phi_node (make_ssa_name (integer_type_node), e1->dest); + add_phi_arg (phi3, gimple_assign_lhs (g), e1, UNKNOWN_LOCATION); + add_phi_arg (phi3, arg1, e2, UNKNOWN_LOCATION); + m_gsi = gsi_for_stmt (stmt); + g = gimple_build_assign (lhs, gimple_phi_result (phi3)); + } + gsi_replace (&m_gsi, g, true); + break; + case IFN_CLRSB: + bb = gsi_bb (m_gsi); + remove_edge (find_edge (bb, edge_bb)); + edge e; + e = make_edge (bb, gimple_bb (stmt), EDGE_FALLTHRU); + e->probability = profile_probability::always (); + set_immediate_dominator (CDI_DOMINATORS, gimple_bb (stmt), + get_immediate_dominator (CDI_DOMINATORS, + edge_bb)); + phi1 = create_phi_node (make_ssa_name (m_limb_type), + edge_bb); + phi2 = create_phi_node (make_ssa_name (integer_type_node), + edge_bb); + phi3 = create_phi_node (make_ssa_name (integer_type_node), + gimple_bb (stmt)); + for (unsigned i = 0; i < cnt; i++) + { + add_phi_arg (phi1, bqp[i].val, bqp[2 * i + 1].e, UNKNOWN_LOCATION); + add_phi_arg (phi2, bqp[i].addend, bqp[2 * i + 1].e, + UNKNOWN_LOCATION); + tree a = bqp[i].addend; + if (i && kind == bitint_prec_large) + a = int_const_binop (PLUS_EXPR, a, integer_minus_one_node); + if (i) + add_phi_arg (phi3, a, bqp[2 * i].e, UNKNOWN_LOCATION); + } + add_phi_arg (phi3, build_int_cst (integer_type_node, prec - 1), e, + UNKNOWN_LOCATION); + m_gsi = gsi_after_labels (edge_bb); + g = gimple_build_call (fndecl, 1, + add_cast (signed_type_for (m_limb_type), + gimple_phi_result (phi1))); + gimple_call_set_lhs (g, make_ssa_name (integer_type_node)); + insert_before (g); + g = gimple_build_assign (make_ssa_name (integer_type_node), + PLUS_EXPR, gimple_call_lhs (g), + gimple_phi_result (phi2)); + insert_before (g); + if (kind != bitint_prec_large) + { + g = gimple_build_assign (make_ssa_name (integer_type_node), + PLUS_EXPR, gimple_assign_lhs (g), + integer_one_node); + insert_before (g); + } + add_phi_arg (phi3, gimple_assign_lhs (g), + find_edge (edge_bb, gimple_bb (stmt)), UNKNOWN_LOCATION); + m_gsi = gsi_for_stmt (stmt); + g = gimple_build_assign (lhs, gimple_phi_result (phi3)); + gsi_replace (&m_gsi, g, true); + break; + case IFN_PARITY: + g = gimple_build_call (fndecl, 1, res); + gimple_call_set_lhs (g, lhs); + gsi_replace (&m_gsi, g, true); + break; + case IFN_POPCOUNT: + g = gimple_build_assign (lhs, res); + gsi_replace (&m_gsi, g, true); + break; + default: + gcc_unreachable (); + } +} + /* Lower a call statement with one or more large/huge _BitInt arguments or large/huge _BitInt return value. */ @@ -4476,6 +4995,14 @@ bitint_large_huge::lower_call (tree obj, gimple *stmt) case IFN_UBSAN_CHECK_MUL: lower_mul_overflow (obj, stmt); return; + case IFN_CLZ: + case IFN_CTZ: + case IFN_CLRSB: + case IFN_FFS: + case IFN_PARITY: + case IFN_POPCOUNT: + lower_bit_query (stmt); + return; default: break; } diff --git a/gcc/gimple-range-op.cc b/gcc/gimple-range-op.cc index 67b3c3d..26c42da 100644 --- a/gcc/gimple-range-op.cc +++ b/gcc/gimple-range-op.cc @@ -908,39 +908,34 @@ public: cfn_clz (bool internal) { m_gimple_call_internal_p = internal; } using range_operator::fold_range; virtual bool fold_range (irange &r, tree type, const irange &lh, - const irange &, relation_trio) const; + const irange &rh, relation_trio) const; private: bool m_gimple_call_internal_p; } op_cfn_clz (false), op_cfn_clz_internal (true); bool cfn_clz::fold_range (irange &r, tree type, const irange &lh, - const irange &, relation_trio) const + const irange &rh, relation_trio) const { // __builtin_c[lt]z* return [0, prec-1], except when the // argument is 0, but that is undefined behavior. // // For __builtin_c[lt]z* consider argument of 0 always undefined - // behavior, for internal fns depending on C?Z_DEFINED_VALUE_AT_ZERO. + // behavior, for internal fns likewise, unless it has 2 arguments, + // then the second argument is the value at zero. if (lh.undefined_p ()) return false; int prec = TYPE_PRECISION (lh.type ()); int mini = 0; int maxi = prec - 1; - int zerov = 0; - scalar_int_mode mode = SCALAR_INT_TYPE_MODE (lh.type ()); if (m_gimple_call_internal_p) { - if (optab_handler (clz_optab, mode) != CODE_FOR_nothing - && CLZ_DEFINED_VALUE_AT_ZERO (mode, zerov) == 2) - { - // Only handle the single common value. - if (zerov == prec) - maxi = prec; - else - // Magic value to give up, unless we can prove arg is non-zero. - mini = -2; - } + // Only handle the single common value. + if (rh.lower_bound () == prec) + maxi = prec; + else + // Magic value to give up, unless we can prove arg is non-zero. + mini = -2; } // From clz of minimum we can compute result maximum. @@ -985,37 +980,31 @@ public: cfn_ctz (bool internal) { m_gimple_call_internal_p = internal; } using range_operator::fold_range; virtual bool fold_range (irange &r, tree type, const irange &lh, - const irange &, relation_trio) const; + const irange &rh, relation_trio) const; private: bool m_gimple_call_internal_p; } op_cfn_ctz (false), op_cfn_ctz_internal (true); bool cfn_ctz::fold_range (irange &r, tree type, const irange &lh, - const irange &, relation_trio) const + const irange &rh, relation_trio) const { if (lh.undefined_p ()) return false; int prec = TYPE_PRECISION (lh.type ()); int mini = 0; int maxi = prec - 1; - int zerov = 0; - scalar_int_mode mode = SCALAR_INT_TYPE_MODE (lh.type ()); if (m_gimple_call_internal_p) { - if (optab_handler (ctz_optab, mode) != CODE_FOR_nothing - && CTZ_DEFINED_VALUE_AT_ZERO (mode, zerov) == 2) - { - // Handle only the two common values. - if (zerov == -1) - mini = -1; - else if (zerov == prec) - maxi = prec; - else - // Magic value to give up, unless we can prove arg is non-zero. - mini = -2; - } + // Handle only the two common values. + if (rh.lower_bound () == -1) + mini = -1; + else if (rh.lower_bound () == prec) + maxi = prec; + else + // Magic value to give up, unless we can prove arg is non-zero. + mini = -2; } // If arg is non-zero, then use [0, prec - 1]. if (!range_includes_zero_p (&lh)) @@ -1288,16 +1277,24 @@ gimple_range_op_handler::maybe_builtin_call () CASE_CFN_CLZ: m_op1 = gimple_call_arg (call, 0); - if (gimple_call_internal_p (call)) - m_operator = &op_cfn_clz_internal; + if (gimple_call_internal_p (call) + && gimple_call_num_args (call) == 2) + { + m_op2 = gimple_call_arg (call, 1); + m_operator = &op_cfn_clz_internal; + } else m_operator = &op_cfn_clz; break; CASE_CFN_CTZ: m_op1 = gimple_call_arg (call, 0); - if (gimple_call_internal_p (call)) - m_operator = &op_cfn_ctz_internal; + if (gimple_call_internal_p (call) + && gimple_call_num_args (call) == 2) + { + m_op2 = gimple_call_arg (call, 1); + m_operator = &op_cfn_ctz_internal; + } else m_operator = &op_cfn_ctz; break; diff --git a/gcc/match.pd b/gcc/match.pd index 281c6c0..59791f4 100644 --- a/gcc/match.pd +++ b/gcc/match.pd @@ -8536,31 +8536,34 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) (op (clz:s@2 @0) INTEGER_CST@1) (if (integer_zerop (@1) && single_use (@2)) /* clz(X) == 0 is (int)X < 0 and clz(X) != 0 is (int)X >= 0. */ - (with { tree type0 = TREE_TYPE (@0); - tree stype = signed_type_for (type0); - HOST_WIDE_INT val = 0; - /* Punt on hypothetical weird targets. */ - if (clz == CFN_CLZ - && CLZ_DEFINED_VALUE_AT_ZERO (SCALAR_TYPE_MODE (type0), - val) == 2 - && val == 0) - stype = NULL_TREE; - } - (if (stype) - (cmp (convert:stype @0) { build_zero_cst (stype); }))) + (with { tree stype = signed_type_for (TREE_TYPE (@0)); } + (cmp (convert:stype @0) { build_zero_cst (stype); })) /* clz(X) == (prec-1) is X == 1 and clz(X) != (prec-1) is X != 1. */ - (with { bool ok = true; - HOST_WIDE_INT val = 0; - tree type0 = TREE_TYPE (@0); - /* Punt on hypothetical weird targets. */ - if (clz == CFN_CLZ - && CLZ_DEFINED_VALUE_AT_ZERO (SCALAR_TYPE_MODE (type0), - val) == 2 - && val == TYPE_PRECISION (type0) - 1) - ok = false; - } - (if (ok && wi::to_wide (@1) == (TYPE_PRECISION (type0) - 1)) - (op @0 { build_one_cst (type0); }))))))) + (if (wi::to_wide (@1) == TYPE_PRECISION (TREE_TYPE (@0)) - 1) + (op @0 { build_one_cst (TREE_TYPE (@0)); })))))) +(for op (eq ne) + cmp (lt ge) + (simplify + (op (IFN_CLZ:s@2 @0 @3) INTEGER_CST@1) + (if (integer_zerop (@1) && single_use (@2)) + /* clz(X) == 0 is (int)X < 0 and clz(X) != 0 is (int)X >= 0. */ + (with { tree type0 = TREE_TYPE (@0); + tree stype = signed_type_for (TREE_TYPE (@0)); + /* Punt if clz(0) == 0. */ + if (integer_zerop (@3)) + stype = NULL_TREE; + } + (if (stype) + (cmp (convert:stype @0) { build_zero_cst (stype); }))) + /* clz(X) == (prec-1) is X == 1 and clz(X) != (prec-1) is X != 1. */ + (with { bool ok = true; + tree type0 = TREE_TYPE (@0); + /* Punt if clz(0) == prec - 1. */ + if (wi::to_widest (@3) == TYPE_PRECISION (type0) - 1) + ok = false; + } + (if (ok && wi::to_wide (@1) == (TYPE_PRECISION (type0) - 1)) + (op @0 { build_one_cst (type0); })))))) /* CTZ simplifications. */ (for ctz (CTZ) @@ -8585,22 +8588,14 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) val++; } } - bool zero_res = false; - HOST_WIDE_INT zero_val = 0; tree type0 = TREE_TYPE (@0); int prec = TYPE_PRECISION (type0); - if (ctz == CFN_CTZ - && CTZ_DEFINED_VALUE_AT_ZERO (SCALAR_TYPE_MODE (type0), - zero_val) == 2) - zero_res = true; } - (if (val <= 0) - (if (ok && (!zero_res || zero_val >= val)) - { constant_boolean_node (cmp == EQ_EXPR ? true : false, type); }) - (if (val >= prec) - (if (ok && (!zero_res || zero_val < val)) - { constant_boolean_node (cmp == EQ_EXPR ? false : true, type); }) - (if (ok && (!zero_res || zero_val < 0 || zero_val >= prec)) + (if (ok && prec <= MAX_FIXED_MODE_SIZE) + (if (val <= 0) + { constant_boolean_node (cmp == EQ_EXPR ? true : false, type); } + (if (val >= prec) + { constant_boolean_node (cmp == EQ_EXPR ? false : true, type); } (cmp (bit_and @0 { wide_int_to_tree (type0, wi::mask (val, false, prec)); }) { build_zero_cst (type0); }))))))) @@ -8608,19 +8603,68 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) (simplify /* __builtin_ctz (x) == C -> (x & ((1 << (C + 1)) - 1)) == (1 << C). */ (op (ctz:s @0) INTEGER_CST@1) - (with { bool zero_res = false; - HOST_WIDE_INT zero_val = 0; - tree type0 = TREE_TYPE (@0); + (with { tree type0 = TREE_TYPE (@0); int prec = TYPE_PRECISION (type0); - if (ctz == CFN_CTZ - && CTZ_DEFINED_VALUE_AT_ZERO (SCALAR_TYPE_MODE (type0), - zero_val) == 2) - zero_res = true; } + (if (prec <= MAX_FIXED_MODE_SIZE) + (if (tree_int_cst_sgn (@1) < 0 || wi::to_widest (@1) >= prec) + { constant_boolean_node (op == EQ_EXPR ? false : true, type); } + (op (bit_and @0 { wide_int_to_tree (type0, + wi::mask (tree_to_uhwi (@1) + 1, + false, prec)); }) + { wide_int_to_tree (type0, + wi::shifted_mask (tree_to_uhwi (@1), 1, + false, prec)); }))))))) +(for op (ge gt le lt) + cmp (eq eq ne ne) + (simplify + /* __builtin_ctz (x) >= C -> (x & ((1 << C) - 1)) == 0. */ + (op (IFN_CTZ:s @0 @2) INTEGER_CST@1) + (with { bool ok = true; + HOST_WIDE_INT val = 0; + if (!tree_fits_shwi_p (@1)) + ok = false; + else + { + val = tree_to_shwi (@1); + /* Canonicalize to >= or <. */ + if (op == GT_EXPR || op == LE_EXPR) + { + if (val == HOST_WIDE_INT_MAX) + ok = false; + else + val++; + } + } + HOST_WIDE_INT zero_val = tree_to_shwi (@2); + tree type0 = TREE_TYPE (@0); + int prec = TYPE_PRECISION (type0); + if (prec > MAX_FIXED_MODE_SIZE) + ok = false; + } + (if (val <= 0) + (if (ok && zero_val >= val) + { constant_boolean_node (cmp == EQ_EXPR ? true : false, type); }) + (if (val >= prec) + (if (ok && zero_val < val) + { constant_boolean_node (cmp == EQ_EXPR ? false : true, type); }) + (if (ok && (zero_val < 0 || zero_val >= prec)) + (cmp (bit_and @0 { wide_int_to_tree (type0, + wi::mask (val, false, prec)); }) + { build_zero_cst (type0); }))))))) +(for op (eq ne) + (simplify + /* __builtin_ctz (x) == C -> (x & ((1 << (C + 1)) - 1)) == (1 << C). */ + (op (IFN_CTZ:s @0 @2) INTEGER_CST@1) + (with { HOST_WIDE_INT zero_val = tree_to_shwi (@2); + tree type0 = TREE_TYPE (@0); + int prec = TYPE_PRECISION (type0); + } + (if (prec <= MAX_FIXED_MODE_SIZE) (if (tree_int_cst_sgn (@1) < 0 || wi::to_widest (@1) >= prec) - (if (!zero_res || zero_val != wi::to_widest (@1)) + (if (zero_val != wi::to_widest (@1)) { constant_boolean_node (op == EQ_EXPR ? false : true, type); }) - (if (!zero_res || zero_val < 0 || zero_val >= prec) + (if (zero_val < 0 || zero_val >= prec) (op (bit_and @0 { wide_int_to_tree (type0, wi::mask (tree_to_uhwi (@1) + 1, false, prec)); }) @@ -8757,13 +8801,38 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) (cond (ne @0 integer_zerop@1) (func (convert?@3 @0)) INTEGER_CST@2) (with { int val; internal_fn ifn = IFN_LAST; - if (direct_internal_fn_supported_p (IFN_CLZ, type, OPTIMIZE_FOR_BOTH) - && CLZ_DEFINED_VALUE_AT_ZERO (SCALAR_INT_TYPE_MODE (type), - val) == 2) + if (TREE_CODE (TREE_TYPE (@3)) == BITINT_TYPE) + { + if (tree_fits_shwi_p (@2)) + { + HOST_WIDE_INT valw = tree_to_shwi (@2); + if ((int) valw == valw) + { + val = valw; + ifn = IFN_CLZ; + } + } + } + else if (direct_internal_fn_supported_p (IFN_CLZ, TREE_TYPE (@3), + OPTIMIZE_FOR_BOTH) + && CLZ_DEFINED_VALUE_AT_ZERO + (SCALAR_INT_TYPE_MODE (TREE_TYPE (@3)), val) == 2) ifn = IFN_CLZ; } (if (ifn == IFN_CLZ && wi::to_widest (@2) == val) - (IFN_CLZ @3))))) + (IFN_CLZ @3 @2))))) +(simplify + (cond (ne @0 integer_zerop@1) (IFN_CLZ (convert?@3 @0) INTEGER_CST@2) @2) + (with { int val; + internal_fn ifn = IFN_LAST; + if (TREE_CODE (TREE_TYPE (@3)) == BITINT_TYPE) + ifn = IFN_CLZ; + else if (direct_internal_fn_supported_p (IFN_CLZ, TREE_TYPE (@3), + OPTIMIZE_FOR_BOTH)) + ifn = IFN_CLZ; + } + (if (ifn == IFN_CLZ) + (IFN_CLZ @3 @2)))) /* a != 0 ? CTZ(a) : CST -> .CTZ(a) where CST is the result of the internal function for 0. */ (for func (CTZ) @@ -8771,13 +8840,38 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) (cond (ne @0 integer_zerop@1) (func (convert?@3 @0)) INTEGER_CST@2) (with { int val; internal_fn ifn = IFN_LAST; - if (direct_internal_fn_supported_p (IFN_CTZ, type, OPTIMIZE_FOR_BOTH) - && CTZ_DEFINED_VALUE_AT_ZERO (SCALAR_INT_TYPE_MODE (type), - val) == 2) + if (TREE_CODE (TREE_TYPE (@3)) == BITINT_TYPE) + { + if (tree_fits_shwi_p (@2)) + { + HOST_WIDE_INT valw = tree_to_shwi (@2); + if ((int) valw == valw) + { + val = valw; + ifn = IFN_CTZ; + } + } + } + else if (direct_internal_fn_supported_p (IFN_CTZ, TREE_TYPE (@3), + OPTIMIZE_FOR_BOTH) + && CTZ_DEFINED_VALUE_AT_ZERO + (SCALAR_INT_TYPE_MODE (TREE_TYPE (@3)), val) == 2) ifn = IFN_CTZ; } (if (ifn == IFN_CTZ && wi::to_widest (@2) == val) - (IFN_CTZ @3))))) + (IFN_CTZ @3 @2))))) +(simplify + (cond (ne @0 integer_zerop@1) (IFN_CTZ (convert?@3 @0) INTEGER_CST@2) @2) + (with { int val; + internal_fn ifn = IFN_LAST; + if (TREE_CODE (TREE_TYPE (@3)) == BITINT_TYPE) + ifn = IFN_CTZ; + else if (direct_internal_fn_supported_p (IFN_CTZ, TREE_TYPE (@3), + OPTIMIZE_FOR_BOTH)) + ifn = IFN_CTZ; + } + (if (ifn == IFN_CTZ) + (IFN_CTZ @3 @2)))) #endif /* Common POPCOUNT/PARITY simplifications. */ diff --git a/gcc/testsuite/c-c++-common/pr111309-1.c b/gcc/testsuite/c-c++-common/pr111309-1.c new file mode 100644 index 0000000..fdf3bf1 --- /dev/null +++ b/gcc/testsuite/c-c++-common/pr111309-1.c @@ -0,0 +1,470 @@ +/* PR c/111309 */ +/* { dg-do run } */ +/* { dg-options "-O2" } */ + +__attribute__((noipa)) int +clzc (unsigned char x) +{ + return __builtin_clzg (x); +} + +__attribute__((noipa)) int +clzc2 (unsigned char x, int y) +{ + return __builtin_clzg (x, y); +} + +__attribute__((noipa)) int +clzs (unsigned short x) +{ + return __builtin_clzg (x); +} + +__attribute__((noipa)) int +clzs2 (unsigned short x) +{ + return __builtin_clzg (x, -2); +} + +__attribute__((noipa)) int +clzi (unsigned int x) +{ + return __builtin_clzg (x); +} + +__attribute__((noipa)) int +clzi2 (unsigned int x, int y) +{ + return __builtin_clzg (x, y); +} + +__attribute__((noipa)) int +clzl (unsigned long x) +{ + return __builtin_clzg (x); +} + +__attribute__((noipa)) int +clzl2 (unsigned long x) +{ + return __builtin_clzg (x, -1); +} + +__attribute__((noipa)) int +clzL (unsigned long long x) +{ + return __builtin_clzg (x); +} + +__attribute__((noipa)) int +clzL2 (unsigned long long x, int y) +{ + return __builtin_clzg (x, y); +} + +#ifdef __SIZEOF_INT128__ +__attribute__((noipa)) int +clzI (unsigned __int128 x) +{ + return __builtin_clzg (x); +} + +__attribute__((noipa)) int +clzI2 (unsigned __int128 x, int y) +{ + return __builtin_clzg (x, y); +} +#endif + +__attribute__((noipa)) int +ctzc (unsigned char x) +{ + return __builtin_ctzg (x); +} + +__attribute__((noipa)) int +ctzc2 (unsigned char x, int y) +{ + return __builtin_ctzg (x, y); +} + +__attribute__((noipa)) int +ctzs (unsigned short x) +{ + return __builtin_ctzg (x); +} + +__attribute__((noipa)) int +ctzs2 (unsigned short x, int y) +{ + return __builtin_ctzg (x, y); +} + +__attribute__((noipa)) int +ctzi (unsigned int x) +{ + return __builtin_ctzg (x); +} + +__attribute__((noipa)) int +ctzi2 (unsigned int x, int y) +{ + return __builtin_ctzg (x, y); +} + +__attribute__((noipa)) int +ctzl (unsigned long x) +{ + return __builtin_ctzg (x); +} + +__attribute__((noipa)) int +ctzl2 (unsigned long x, int y) +{ + return __builtin_ctzg (x, y); +} + +__attribute__((noipa)) int +ctzL (unsigned long long x) +{ + return __builtin_ctzg (x); +} + +__attribute__((noipa)) int +ctzL2 (unsigned long long x, int y) +{ + return __builtin_ctzg (x, y); +} + +#ifdef __SIZEOF_INT128__ +__attribute__((noipa)) int +ctzI (unsigned __int128 x) +{ + return __builtin_ctzg (x); +} + +__attribute__((noipa)) int +ctzI2 (unsigned __int128 x) +{ + return __builtin_ctzg (x, __SIZEOF_INT128__ * __CHAR_BIT__); +} +#endif + +__attribute__((noipa)) int +clrsbc (signed char x) +{ + return __builtin_clrsbg (x); +} + +__attribute__((noipa)) int +clrsbs (signed short x) +{ + return __builtin_clrsbg (x); +} + +__attribute__((noipa)) int +clrsbi (signed int x) +{ + return __builtin_clrsbg (x); +} + +__attribute__((noipa)) int +clrsbl (signed long x) +{ + return __builtin_clrsbg (x); +} + +__attribute__((noipa)) int +clrsbL (signed long long x) +{ + return __builtin_clrsbg (x); +} + +#ifdef __SIZEOF_INT128__ +__attribute__((noipa)) int +clrsbI (signed __int128 x) +{ + return __builtin_clrsbg (x); +} +#endif + +__attribute__((noipa)) int +ffsc (signed char x) +{ + return __builtin_ffsg (x); +} + +__attribute__((noipa)) int +ffss (signed short x) +{ + return __builtin_ffsg (x); +} + +__attribute__((noipa)) int +ffsi (signed int x) +{ + return __builtin_ffsg (x); +} + +__attribute__((noipa)) int +ffsl (signed long x) +{ + return __builtin_ffsg (x); +} + +__attribute__((noipa)) int +ffsL (signed long long x) +{ + return __builtin_ffsg (x); +} + +#ifdef __SIZEOF_INT128__ +__attribute__((noipa)) int +ffsI (signed __int128 x) +{ + return __builtin_ffsg (x); +} +#endif + +__attribute__((noipa)) int +parityc (unsigned char x) +{ + return __builtin_parityg (x); +} + +__attribute__((noipa)) int +paritys (unsigned short x) +{ + return __builtin_parityg (x); +} + +__attribute__((noipa)) int +parityi (unsigned int x) +{ + return __builtin_parityg (x); +} + +__attribute__((noipa)) int +parityl (unsigned long x) +{ + return __builtin_parityg (x); +} + +__attribute__((noipa)) int +parityL (unsigned long long x) +{ + return __builtin_parityg (x); +} + +#ifdef __SIZEOF_INT128__ +__attribute__((noipa)) int +parityI (unsigned __int128 x) +{ + return __builtin_parityg (x); +} +#endif + +__attribute__((noipa)) int +popcountc (unsigned char x) +{ + return __builtin_popcountg (x); +} + +__attribute__((noipa)) int +popcounts (unsigned short x) +{ + return __builtin_popcountg (x); +} + +__attribute__((noipa)) int +popcounti (unsigned int x) +{ + return __builtin_popcountg (x); +} + +__attribute__((noipa)) int +popcountl (unsigned long x) +{ + return __builtin_popcountg (x); +} + +__attribute__((noipa)) int +popcountL (unsigned long long x) +{ + return __builtin_popcountg (x); +} + +#ifdef __SIZEOF_INT128__ +__attribute__((noipa)) int +popcountI (unsigned __int128 x) +{ + return __builtin_popcountg (x); +} +#endif + +int +main () +{ + if (__builtin_clzg ((unsigned char) 1) != __CHAR_BIT__ - 1 + || __builtin_clzg ((unsigned short) 2, -2) != __SIZEOF_SHORT__ * __CHAR_BIT__ - 2 + || __builtin_clzg (0U, 42) != 42 + || __builtin_clzg (0U, -1) != -1 + || __builtin_clzg (1U) != __SIZEOF_INT__ * __CHAR_BIT__ - 1 + || __builtin_clzg (2UL, -1) != __SIZEOF_LONG__ * __CHAR_BIT__ - 2 + || __builtin_clzg (5ULL) != __SIZEOF_LONG_LONG__ * __CHAR_BIT__ - 3 +#ifdef __SIZEOF_INT128__ + || __builtin_clzg ((unsigned __int128) 9) != __SIZEOF_INT128__ * __CHAR_BIT__ - 4 +#endif + || __builtin_clzg (~0U, -5) != 0 + || __builtin_clzg (~0ULL >> 2) != 2 + || __builtin_ctzg ((unsigned char) 1) != 0 + || __builtin_ctzg ((unsigned short) 28) != 2 + || __builtin_ctzg (0U, 32) != 32 + || __builtin_ctzg (0U, -42) != -42 + || __builtin_ctzg (1U) != 0 + || __builtin_ctzg (16UL, -1) != 4 + || __builtin_ctzg (5ULL << 52, 0) != 52 +#ifdef __SIZEOF_INT128__ + || __builtin_ctzg (((unsigned __int128) 9) << 72) != 72 +#endif + || __builtin_clrsbg ((signed char) 0) != __CHAR_BIT__ - 1 + || __builtin_clrsbg ((signed short) -1) != __SIZEOF_SHORT__ * __CHAR_BIT__ - 1 + || __builtin_clrsbg (0) != __SIZEOF_INT__ * __CHAR_BIT__ - 1 + || __builtin_clrsbg (-1L) != __SIZEOF_LONG__ * __CHAR_BIT__ - 1 + || __builtin_clrsbg (0LL) != __SIZEOF_LONG_LONG__ * __CHAR_BIT__ - 1 +#ifdef __SIZEOF_INT128__ + || __builtin_clrsbg ((__int128) -1) != __SIZEOF_INT128__ * __CHAR_BIT__ - 1 +#endif + || __builtin_clrsbg (0x1afb) != __SIZEOF_INT__ * __CHAR_BIT__ - 14 + || __builtin_clrsbg (-2) != __SIZEOF_INT__ * __CHAR_BIT__ - 2 + || __builtin_clrsbg (1L) != __SIZEOF_LONG__ * __CHAR_BIT__ - 2 + || __builtin_clrsbg (-4LL) != __SIZEOF_LONG_LONG__ * __CHAR_BIT__ - 3 + || __builtin_ffsg ((signed char) 0) != 0 + || __builtin_ffsg ((signed short) 0) != 0 + || __builtin_ffsg (0) != 0 + || __builtin_ffsg (0L) != 0 + || __builtin_ffsg (0LL) != 0 +#ifdef __SIZEOF_INT128__ + || __builtin_ffsg ((__int128) 0) != 0 +#endif + || __builtin_ffsg ((signed char) 4) != 3 + || __builtin_ffsg ((signed short) 8) != 4 + || __builtin_ffsg (1) != 1 + || __builtin_ffsg (2L) != 2 + || __builtin_ffsg (28LL) != 3 + || __builtin_parityg ((unsigned char) 1) != 1 + || __builtin_parityg ((unsigned short) 2) != 1 + || __builtin_parityg (0U) != 0 + || __builtin_parityg (3U) != 0 + || __builtin_parityg (0UL) != 0 + || __builtin_parityg (7UL) != 1 + || __builtin_parityg (0ULL) != 0 +#ifdef __SIZEOF_INT128__ + || __builtin_parityg ((unsigned __int128) 0) != 0 +#endif + || __builtin_parityg ((unsigned char) ~0U) != 0 + || __builtin_parityg ((unsigned short) ~0U) != 0 + || __builtin_parityg (~0U) != 0 + || __builtin_parityg (~0UL) != 0 + || __builtin_parityg (~0ULL) != 0 +#ifdef __SIZEOF_INT128__ + || __builtin_parityg (~(unsigned __int128) 0) != 0 +#endif + || __builtin_popcountg (0U) != 0 + || __builtin_popcountg (0UL) != 0 + || __builtin_popcountg (0ULL) != 0 +#ifdef __SIZEOF_INT128__ + || __builtin_popcountg ((unsigned __int128) 0) != 0 +#endif + || __builtin_popcountg ((unsigned char) ~0U) != __CHAR_BIT__ + || __builtin_popcountg ((unsigned short) ~0U) != __SIZEOF_SHORT__ * __CHAR_BIT__ + || __builtin_popcountg (~0U) != __SIZEOF_INT__ * __CHAR_BIT__ + || __builtin_popcountg (~0UL) != __SIZEOF_LONG__ * __CHAR_BIT__ + || __builtin_popcountg (~0ULL) != __SIZEOF_LONG_LONG__ * __CHAR_BIT__ +#ifdef __SIZEOF_INT128__ + || __builtin_popcountg (~(unsigned __int128) 0) != __SIZEOF_INT128__ * __CHAR_BIT__ +#endif + || 0) + __builtin_abort (); + if (clzc (1) != __CHAR_BIT__ - 1 + || clzs2 (2) != __SIZEOF_SHORT__ * __CHAR_BIT__ - 2 + || clzi2 (0U, 42) != 42 + || clzi2 (0U, -1) != -1 + || clzi (1U) != __SIZEOF_INT__ * __CHAR_BIT__ - 1 + || clzl2 (2UL) != __SIZEOF_LONG__ * __CHAR_BIT__ - 2 + || clzL (5ULL) != __SIZEOF_LONG_LONG__ * __CHAR_BIT__ - 3 +#ifdef __SIZEOF_INT128__ + || clzI ((unsigned __int128) 9) != __SIZEOF_INT128__ * __CHAR_BIT__ - 4 +#endif + || clzi2 (~0U, -5) != 0 + || clzL (~0ULL >> 2) != 2 + || ctzc (1) != 0 + || ctzs (28) != 2 + || ctzi2 (0U, 32) != 32 + || ctzi2 (0U, -42) != -42 + || ctzi (1U) != 0 + || ctzl2 (16UL, -1) != 4 + || ctzL2 (5ULL << 52, 0) != 52 +#ifdef __SIZEOF_INT128__ + || ctzI (((unsigned __int128) 9) << 72) != 72 +#endif + || clrsbc (0) != __CHAR_BIT__ - 1 + || clrsbs (-1) != __SIZEOF_SHORT__ * __CHAR_BIT__ - 1 + || clrsbi (0) != __SIZEOF_INT__ * __CHAR_BIT__ - 1 + || clrsbl (-1L) != __SIZEOF_LONG__ * __CHAR_BIT__ - 1 + || clrsbL (0LL) != __SIZEOF_LONG_LONG__ * __CHAR_BIT__ - 1 +#ifdef __SIZEOF_INT128__ + || clrsbI (-1) != __SIZEOF_INT128__ * __CHAR_BIT__ - 1 +#endif + || clrsbi (0x1afb) != __SIZEOF_INT__ * __CHAR_BIT__ - 14 + || clrsbi (-2) != __SIZEOF_INT__ * __CHAR_BIT__ - 2 + || clrsbl (1L) != __SIZEOF_LONG__ * __CHAR_BIT__ - 2 + || clrsbL (-4LL) != __SIZEOF_LONG_LONG__ * __CHAR_BIT__ - 3 + || ffsc (0) != 0 + || ffss (0) != 0 + || ffsi (0) != 0 + || ffsl (0L) != 0 + || ffsL (0LL) != 0 +#ifdef __SIZEOF_INT128__ + || ffsI (0) != 0 +#endif + || ffsc (4) != 3 + || ffss (8) != 4 + || ffsi (1) != 1 + || ffsl (2L) != 2 + || ffsL (28LL) != 3 + || parityc (1) != 1 + || paritys (2) != 1 + || parityi (0U) != 0 + || parityi (3U) != 0 + || parityl (0UL) != 0 + || parityl (7UL) != 1 + || parityL (0ULL) != 0 +#ifdef __SIZEOF_INT128__ + || parityI (0) != 0 +#endif + || parityc ((unsigned char) ~0U) != 0 + || paritys ((unsigned short) ~0U) != 0 + || parityi (~0U) != 0 + || parityl (~0UL) != 0 + || parityL (~0ULL) != 0 +#ifdef __SIZEOF_INT128__ + || parityI (~(unsigned __int128) 0) != 0 +#endif + || popcounti (0U) != 0 + || popcountl (0UL) != 0 + || popcountL (0ULL) != 0 +#ifdef __SIZEOF_INT128__ + || popcountI (0) != 0 +#endif + || popcountc ((unsigned char) ~0U) != __CHAR_BIT__ + || popcounts ((unsigned short) ~0U) != __SIZEOF_SHORT__ * __CHAR_BIT__ + || popcounti (~0U) != __SIZEOF_INT__ * __CHAR_BIT__ + || popcountl (~0UL) != __SIZEOF_LONG__ * __CHAR_BIT__ + || popcountL (~0ULL) != __SIZEOF_LONG_LONG__ * __CHAR_BIT__ +#ifdef __SIZEOF_INT128__ + || popcountI (~(unsigned __int128) 0) != __SIZEOF_INT128__ * __CHAR_BIT__ +#endif + || 0) + __builtin_abort (); +} diff --git a/gcc/testsuite/c-c++-common/pr111309-2.c b/gcc/testsuite/c-c++-common/pr111309-2.c new file mode 100644 index 0000000..535208b --- /dev/null +++ b/gcc/testsuite/c-c++-common/pr111309-2.c @@ -0,0 +1,85 @@ +/* PR c/111309 */ +/* { dg-do compile } */ +/* { dg-additional-options "-std=c99" { target c } } */ + +#ifndef __cplusplus +#define bool _Bool +#define true ((_Bool) 1) +#define false ((_Bool) 0) +#endif + +void +foo (void) +{ + enum E { E0 = 0 }; + struct S { int s; } s; + __builtin_clzg (); /* { dg-error "too few arguments" } */ + __builtin_clzg (0U, 1, 2); /* { dg-error "too many arguments" } */ + __builtin_clzg (0); /* { dg-error "has signed type" } */ + __builtin_clzg (0.0); /* { dg-error "does not have integral type" } */ + __builtin_clzg (s); /* { dg-error "does not have integral type" } */ + __builtin_clzg (true); /* { dg-error "has boolean type" } */ + __builtin_clzg (E0); /* { dg-error "has signed type" "" { target c } } */ + /* { dg-error "has enumerated type" "" { target c++ } .-1 } */ + __builtin_clzg (0, 0); /* { dg-error "has signed type" } */ + __builtin_clzg (0.0, 0); /* { dg-error "does not have integral type" } */ + __builtin_clzg (s, 0); /* { dg-error "does not have integral type" } */ + __builtin_clzg (true, 0); /* { dg-error "has boolean type" } */ + __builtin_clzg (E0, 0); /* { dg-error "has signed type" "" { target c } } */ + /* { dg-error "has enumerated type" "" { target c++ } .-1 } */ + __builtin_clzg (0U, 2.0); /* { dg-error "does not have integral type" } */ + __builtin_clzg (0U, s); /* { dg-error "does not have integral type" } */ + __builtin_clzg (0U, 2LL); /* { dg-error "does not have 'int' type" } */ + __builtin_clzg (0U, 2U); /* { dg-error "does not have 'int' type" } */ + __builtin_clzg (0U, true); + __builtin_clzg (0U, E0); /* { dg-error "does not have 'int' type" "" { target c++ } } */ + __builtin_ctzg (); /* { dg-error "too few arguments" } */ + __builtin_ctzg (0U, 1, 2); /* { dg-error "too many arguments" } */ + __builtin_ctzg (0); /* { dg-error "has signed type" } */ + __builtin_ctzg (0.0); /* { dg-error "does not have integral type" } */ + __builtin_ctzg (s); /* { dg-error "does not have integral type" } */ + __builtin_ctzg (true); /* { dg-error "has boolean type" } */ + __builtin_ctzg (E0); /* { dg-error "has signed type" "" { target c } } */ + /* { dg-error "has enumerated type" "" { target c++ } .-1 } */ + __builtin_ctzg (0, 0); /* { dg-error "has signed type" } */ + __builtin_ctzg (0.0, 0); /* { dg-error "does not have integral type" } */ + __builtin_ctzg (s, 0); /* { dg-error "does not have integral type" } */ + __builtin_ctzg (true, 0); /* { dg-error "has boolean type" } */ + __builtin_ctzg (E0, 0); /* { dg-error "has signed type" "" { target c } } */ + /* { dg-error "has enumerated type" "" { target c++ } .-1 } */ + __builtin_ctzg (0U, 2.0); /* { dg-error "does not have integral type" } */ + __builtin_ctzg (0U, 2LL); /* { dg-error "does not have 'int' type" } */ + __builtin_ctzg (0U, 2U); /* { dg-error "does not have 'int' type" } */ + __builtin_ctzg (0U, true); + __builtin_ctzg (0U, E0); /* { dg-error "does not have 'int' type" "" { target c++ } } */ + __builtin_clrsbg (); /* { dg-error "too few arguments" } */ + __builtin_clrsbg (0, 1); /* { dg-error "too many arguments" } */ + __builtin_clrsbg (0U); /* { dg-error "has unsigned type" } */ + __builtin_clrsbg (0.0); /* { dg-error "does not have integral type" } */ + __builtin_clrsbg (s); /* { dg-error "does not have integral type" } */ + __builtin_clrsbg (true); /* { dg-error "has boolean type" } */ + __builtin_clrsbg (E0); /* { dg-error "has enumerated type" "" { target c++ } } */ + __builtin_ffsg (); /* { dg-error "too few arguments" } */ + __builtin_ffsg (0, 1); /* { dg-error "too many arguments" } */ + __builtin_ffsg (0U); /* { dg-error "has unsigned type" } */ + __builtin_ffsg (0.0); /* { dg-error "does not have integral type" } */ + __builtin_ffsg (s); /* { dg-error "does not have integral type" } */ + __builtin_ffsg (true); /* { dg-error "has boolean type" } */ + __builtin_ffsg (E0); /* { dg-error "has enumerated type" "" { target c++ } } */ + __builtin_parityg (); /* { dg-error "too few arguments" } */ + __builtin_parityg (0U, 1); /* { dg-error "too many arguments" } */ + __builtin_parityg (0); /* { dg-error "has signed type" } */ + __builtin_parityg (0.0); /* { dg-error "does not have integral type" } */ + __builtin_parityg (s); /* { dg-error "does not have integral type" } */ + __builtin_parityg (true); /* { dg-error "has boolean type" } */ + __builtin_parityg (E0); /* { dg-error "has signed type" "" { target c } } */ + /* { dg-error "has enumerated type" "" { target c++ } .-1 } */ + __builtin_popcountg (); /* { dg-error "too few arguments" } */ + __builtin_popcountg (0U, 1); /* { dg-error "too many arguments" } */ + __builtin_popcountg (0); /* { dg-error "has signed type" } */ + __builtin_popcountg (0.0); /* { dg-error "does not have integral type" } */ + __builtin_popcountg (s); /* { dg-error "does not have integral type" } */ + __builtin_popcountg (true); /* { dg-error "has boolean type" } */ + __builtin_popcountg (E0); /* { dg-error "has signed type" "" { target c } } */ + /* { dg-error "has enumerated type" "" { target c++ } .-1 } */ +} diff --git a/gcc/testsuite/gcc.dg/torture/bitint-43.c b/gcc/testsuite/gcc.dg/torture/bitint-43.c new file mode 100644 index 0000000..4265bff --- /dev/null +++ b/gcc/testsuite/gcc.dg/torture/bitint-43.c @@ -0,0 +1,306 @@ +/* PR c/111309 */ +/* { dg-do run { target bitint } } */ +/* { dg-options "-std=c2x -pedantic-errors" } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "-flto" } { "" } } */ + +#if __BITINT_MAXWIDTH__ >= 156 +__attribute__((noipa)) int +clz156 (unsigned _BitInt(156) x) +{ + return __builtin_clzg (x); +} + +__attribute__((noipa)) int +clzd156 (unsigned _BitInt(156) x) +{ + return __builtin_clzg (x, __builtin_popcountg ((typeof (x)) ~(typeof (x)) 0)); +} + +__attribute__((noipa)) int +clzD156 (unsigned _BitInt(156) x, int y) +{ + return __builtin_clzg (x, y); +} + +__attribute__((noipa)) int +ctz156 (unsigned _BitInt(156) x) +{ + return __builtin_ctzg (x); +} + +__attribute__((noipa)) int +ctzd156 (unsigned _BitInt(156) x) +{ + return __builtin_ctzg (x, __builtin_popcountg ((typeof (x)) ~(typeof (x)) 0)); +} + +__attribute__((noipa)) int +ctzD156 (unsigned _BitInt(156) x, int y) +{ + return __builtin_ctzg (x, y); +} + +__attribute__((noipa)) int +clrsb156 (_BitInt(156) x) +{ + return __builtin_clrsbg (x); +} + +__attribute__((noipa)) int +ffs156 (_BitInt(156) x) +{ + return __builtin_ffsg (x); +} + +__attribute__((noipa)) int +parity156 (unsigned _BitInt(156) x) +{ + return __builtin_parityg (x); +} + +__attribute__((noipa)) int +popcount156 (unsigned _BitInt(156) x) +{ + return __builtin_popcountg (x); +} +#endif + +#if __BITINT_MAXWIDTH__ >= 192 +__attribute__((noipa)) int +clz192 (unsigned _BitInt(192) x) +{ + return __builtin_clzg (x); +} + +__attribute__((noipa)) int +clzd192 (unsigned _BitInt(192) x) +{ + return __builtin_clzg (x, __builtin_popcountg ((typeof (x)) ~(typeof (x)) 0)); +} + +__attribute__((noipa)) int +clzD192 (unsigned _BitInt(192) x, int y) +{ + return __builtin_clzg (x, y); +} + +__attribute__((noipa)) int +ctz192 (unsigned _BitInt(192) x) +{ + return __builtin_ctzg (x); +} + +__attribute__((noipa)) int +ctzd192 (unsigned _BitInt(192) x) +{ + return __builtin_ctzg (x, __builtin_popcountg ((typeof (x)) ~(typeof (x)) 0)); +} + +__attribute__((noipa)) int +ctzD192 (unsigned _BitInt(192) x, int y) +{ + return __builtin_ctzg (x, y); +} + +__attribute__((noipa)) int +clrsb192 (_BitInt(192) x) +{ + return __builtin_clrsbg (x); +} + +__attribute__((noipa)) int +ffs192 (_BitInt(192) x) +{ + return __builtin_ffsg (x); +} + +__attribute__((noipa)) int +parity192 (unsigned _BitInt(192) x) +{ + return __builtin_parityg (x); +} + +__attribute__((noipa)) int +popcount192 (unsigned _BitInt(192) x) +{ + return __builtin_popcountg (x); +} +#endif + +int +main () +{ +#if __BITINT_MAXWIDTH__ >= 156 + if (clzd156 (0) != 156 + || clzD156 (0, -1) != -1 + || ctzd156 (0) != 156 + || ctzD156 (0, 42) != 42 + || clrsb156 (0) != 156 - 1 + || ffs156 (0) != 0 + || parity156 (0) != 0 + || popcount156 (0) != 0 + || __builtin_clzg ((unsigned _BitInt(156)) 0, 156 + 32) != 156 + 32 + || __builtin_ctzg ((unsigned _BitInt(156)) 0, 156) != 156 + || __builtin_clrsbg ((_BitInt(156)) 0) != 156 - 1 + || __builtin_ffsg ((_BitInt(156)) 0) != 0 + || __builtin_parityg ((unsigned _BitInt(156)) 0) != 0 + || __builtin_popcountg ((unsigned _BitInt(156)) 0) != 0) + __builtin_abort (); + if (clz156 (-1) != 0 + || clzd156 (-1) != 0 + || clzD156 (-1, 0) != 0 + || ctz156 (-1) != 0 + || ctzd156 (-1) != 0 + || ctzD156 (-1, 17) != 0 + || clrsb156 (-1) != 156 - 1 + || ffs156 (-1) != 1 + || parity156 (-1) != 0 + || popcount156 (-1) != 156 + || __builtin_clzg ((unsigned _BitInt(156)) -1) != 0 + || __builtin_clzg ((unsigned _BitInt(156)) -1, 156 + 32) != 0 + || __builtin_ctzg ((unsigned _BitInt(156)) -1) != 0 + || __builtin_ctzg ((unsigned _BitInt(156)) -1, 156) != 0 + || __builtin_clrsbg ((_BitInt(156)) -1) != 156 - 1 + || __builtin_ffsg ((_BitInt(156)) -1) != 1 + || __builtin_parityg ((unsigned _BitInt(156)) -1) != 0 + || __builtin_popcountg ((unsigned _BitInt(156)) -1) != 156) + __builtin_abort (); + if (clz156 (((unsigned _BitInt(156)) -1) >> 24) != 24 + || clz156 (((unsigned _BitInt(156)) -1) >> 79) != 79 + || clz156 (1) != 156 - 1 + || clzd156 (((unsigned _BitInt(156)) -1) >> 139) != 139 + || clzd156 (2) != 156 - 2 + || ctz156 (((unsigned _BitInt(156)) -1) << 42) != 42 + || ctz156 (((unsigned _BitInt(156)) -1) << 57) != 57 + || ctz156 (0x4000000000000000000000uwb) != 86 + || ctzd156 (((unsigned _BitInt(156)) -1) << 149) != 149 + || ctzd156 (2) != 1 + || clrsb156 ((unsigned _BitInt(156 - 4)) -1) != 3 + || clrsb156 ((unsigned _BitInt(156 - 28)) -1) != 27 + || clrsb156 ((unsigned _BitInt(156 - 29)) -1) != 28 + || clrsb156 (~(unsigned _BitInt(156)) (unsigned _BitInt(156 - 68)) -1) != 67 + || clrsb156 (~(unsigned _BitInt(156)) (unsigned _BitInt(156 - 92)) -1) != 91 + || clrsb156 (~(unsigned _BitInt(156)) (unsigned _BitInt(156 - 93)) -1) != 92 + || ffs156 (((unsigned _BitInt(156)) -1) << 42) != 43 + || ffs156 (((unsigned _BitInt(156)) -1) << 57) != 58 + || ffs156 (0x4000000000000000000000uwb) != 87 + || ffs156 (((unsigned _BitInt(156)) -1) << 149) != 150 + || ffs156 (2) != 2 + || __builtin_clzg (((unsigned _BitInt(156)) -1) >> 24) != 24 + || __builtin_clzg (((unsigned _BitInt(156)) -1) >> 79) != 79 + || __builtin_clzg ((unsigned _BitInt(156)) 1) != 156 - 1 + || __builtin_clzg (((unsigned _BitInt(156)) -1) >> 139, 156) != 139 + || __builtin_clzg ((unsigned _BitInt(156)) 2, 156) != 156 - 2 + || __builtin_ctzg (((unsigned _BitInt(156)) -1) << 42) != 42 + || __builtin_ctzg (((unsigned _BitInt(156)) -1) << 57) != 57 + || __builtin_ctzg ((unsigned _BitInt(156)) 0x4000000000000000000000uwb) != 86 + || __builtin_ctzg (((unsigned _BitInt(156)) -1) << 149, 156) != 149 + || __builtin_ctzg ((unsigned _BitInt(156)) 2, 156) != 1 + || __builtin_clrsbg ((_BitInt(156)) (unsigned _BitInt(156 - 4)) -1) != 3 + || __builtin_clrsbg ((_BitInt(156)) (unsigned _BitInt(156 - 28)) -1) != 27 + || __builtin_clrsbg ((_BitInt(156)) (unsigned _BitInt(156 - 29)) -1) != 28 + || __builtin_clrsbg ((_BitInt(156)) ~(unsigned _BitInt(156)) (unsigned _BitInt(156 - 68)) -1) != 67 + || __builtin_clrsbg ((_BitInt(156)) ~(unsigned _BitInt(156)) (unsigned _BitInt(156 - 92)) -1) != 91 + || __builtin_clrsbg ((_BitInt(156)) ~(unsigned _BitInt(156)) (unsigned _BitInt(156 - 93)) -1) != 92 + || __builtin_ffsg ((_BitInt(156)) (((unsigned _BitInt(156)) -1) << 42)) != 43 + || __builtin_ffsg ((_BitInt(156)) (((unsigned _BitInt(156)) -1) << 57)) != 58 + || __builtin_ffsg ((_BitInt(156)) 0x4000000000000000000000uwb) != 87 + || __builtin_ffsg ((_BitInt(156)) (((unsigned _BitInt(156)) -1) << 149)) != 150 + || __builtin_ffsg ((_BitInt(156)) 2) != 2) + __builtin_abort (); + if (parity156 (23008250258685373142923325827291949461178444434uwb) != __builtin_parityg (23008250258685373142923325827291949461178444434uwb) + || parity156 (41771568792516301628132437740665810252917251244uwb) != __builtin_parityg (41771568792516301628132437740665810252917251244uwb) + || parity156 (5107402473866766219120283991834936835726115452uwb) != __builtin_parityg (5107402473866766219120283991834936835726115452uwb) + || popcount156 (50353291748276374580944955711958129678996395562uwb) != __builtin_popcountg (50353291748276374580944955711958129678996395562uwb) + || popcount156 (29091263616891212550063067166307725491211684496uwb) != __builtin_popcountg (29091263616891212550063067166307725491211684496uwb) + || popcount156 (64973284306583205619384799873110935608793072026uwb) != __builtin_popcountg (64973284306583205619384799873110935608793072026uwb)) + __builtin_abort (); +#endif +#if __BITINT_MAXWIDTH__ >= 192 + if (clzd192 (0) != 192 + || clzD192 (0, 42) != 42 + || ctzd192 (0) != 192 + || ctzD192 (0, -1) != -1 + || clrsb192 (0) != 192 - 1 + || ffs192 (0) != 0 + || parity192 (0) != 0 + || popcount192 (0) != 0 + || __builtin_clzg ((unsigned _BitInt(192)) 0, 192 + 32) != 192 + 32 + || __builtin_ctzg ((unsigned _BitInt(192)) 0, 192) != 192 + || __builtin_clrsbg ((_BitInt(192)) 0) != 192 - 1 + || __builtin_ffsg ((_BitInt(192)) 0) != 0 + || __builtin_parityg ((unsigned _BitInt(192)) 0) != 0 + || __builtin_popcountg ((unsigned _BitInt(192)) 0) != 0) + __builtin_abort (); + if (clz192 (-1) != 0 + || clzd192 (-1) != 0 + || clzD192 (-1, 15) != 0 + || ctz192 (-1) != 0 + || ctzd192 (-1) != 0 + || ctzD192 (-1, -57) != 0 + || clrsb192 (-1) != 192 - 1 + || ffs192 (-1) != 1 + || parity192 (-1) != 0 + || popcount192 (-1) != 192 + || __builtin_clzg ((unsigned _BitInt(192)) -1) != 0 + || __builtin_clzg ((unsigned _BitInt(192)) -1, 192 + 32) != 0 + || __builtin_ctzg ((unsigned _BitInt(192)) -1) != 0 + || __builtin_ctzg ((unsigned _BitInt(192)) -1, 192) != 0 + || __builtin_clrsbg ((_BitInt(192)) -1) != 192 - 1 + || __builtin_ffsg ((_BitInt(192)) -1) != 1 + || __builtin_parityg ((unsigned _BitInt(192)) -1) != 0 + || __builtin_popcountg ((unsigned _BitInt(192)) -1) != 192) + __builtin_abort (); + if (clz192 (((unsigned _BitInt(192)) -1) >> 24) != 24 + || clz192 (((unsigned _BitInt(192)) -1) >> 79) != 79 + || clz192 (1) != 192 - 1 + || clzd192 (((unsigned _BitInt(192)) -1) >> 139) != 139 + || clzd192 (2) != 192 - 2 + || ctz192 (((unsigned _BitInt(192)) -1) << 42) != 42 + || ctz192 (((unsigned _BitInt(192)) -1) << 57) != 57 + || ctz192 (0x4000000000000000000000uwb) != 86 + || ctzd192 (((unsigned _BitInt(192)) -1) << 149) != 149 + || ctzd192 (2) != 1 + || clrsb192 ((unsigned _BitInt(192 - 4)) -1) != 3 + || clrsb192 ((unsigned _BitInt(192 - 28)) -1) != 27 + || clrsb192 ((unsigned _BitInt(192 - 29)) -1) != 28 + || clrsb192 (~(unsigned _BitInt(192)) (unsigned _BitInt(192 - 68)) -1) != 67 + || clrsb192 (~(unsigned _BitInt(192)) (unsigned _BitInt(192 - 92)) -1) != 91 + || clrsb192 (~(unsigned _BitInt(192)) (unsigned _BitInt(192 - 93)) -1) != 92 + || ffs192 (((unsigned _BitInt(192)) -1) << 42) != 43 + || ffs192 (((unsigned _BitInt(192)) -1) << 57) != 58 + || ffs192 (0x4000000000000000000000uwb) != 87 + || ffs192 (((unsigned _BitInt(192)) -1) << 149) != 150 + || ffs192 (2) != 2 + || __builtin_clzg (((unsigned _BitInt(192)) -1) >> 24) != 24 + || __builtin_clzg (((unsigned _BitInt(192)) -1) >> 79) != 79 + || __builtin_clzg ((unsigned _BitInt(192)) 1) != 192 - 1 + || __builtin_clzg (((unsigned _BitInt(192)) -1) >> 139, 192) != 139 + || __builtin_clzg ((unsigned _BitInt(192)) 2, 192) != 192 - 2 + || __builtin_ctzg (((unsigned _BitInt(192)) -1) << 42) != 42 + || __builtin_ctzg (((unsigned _BitInt(192)) -1) << 57) != 57 + || __builtin_ctzg ((unsigned _BitInt(192)) 0x4000000000000000000000uwb) != 86 + || __builtin_ctzg (((unsigned _BitInt(192)) -1) << 149, 192) != 149 + || __builtin_ctzg ((unsigned _BitInt(192)) 2, 192) != 1 + || __builtin_clrsbg ((_BitInt(192)) (unsigned _BitInt(192 - 4)) -1) != 3 + || __builtin_clrsbg ((_BitInt(192)) (unsigned _BitInt(192 - 28)) -1) != 27 + || __builtin_clrsbg ((_BitInt(192)) (unsigned _BitInt(192 - 29)) -1) != 28 + || __builtin_clrsbg ((_BitInt(192)) ~(unsigned _BitInt(192)) (unsigned _BitInt(192 - 68)) -1) != 67 + || __builtin_clrsbg ((_BitInt(192)) ~(unsigned _BitInt(192)) (unsigned _BitInt(192 - 92)) -1) != 91 + || __builtin_clrsbg ((_BitInt(192)) ~(unsigned _BitInt(192)) (unsigned _BitInt(192 - 93)) -1) != 92 + || __builtin_ffsg ((_BitInt(192)) (((unsigned _BitInt(192)) -1) << 42)) != 43 + || __builtin_ffsg ((_BitInt(192)) (((unsigned _BitInt(192)) -1) << 57)) != 58 + || __builtin_ffsg ((_BitInt(192)) 0x4000000000000000000000uwb) != 87 + || __builtin_ffsg ((_BitInt(192)) (((unsigned _BitInt(192)) -1) << 149)) != 150 + || __builtin_ffsg ((_BitInt(192)) 2) != 2) + __builtin_abort (); + if (parity192 (4692147078159863499615754634965484598760535154638668598762uwb) != __builtin_parityg (4692147078159863499615754634965484598760535154638668598762uwb) + || parity192 (1669461228546917627909935444501097256112222796898845183538uwb) != __builtin_parityg (1669461228546917627909935444501097256112222796898845183538uwb) + || parity192 (5107402473866766219120283991834936835726115452uwb) != __builtin_parityg (5107402473866766219120283991834936835726115452uwb) + || popcount192 (4033871057575185619108386380181511734118888391160164588976uwb) != __builtin_popcountg (4033871057575185619108386380181511734118888391160164588976uwb) + || popcount192 (58124766715713711628758119849579188845074973856704521119uwb) != __builtin_popcountg (58124766715713711628758119849579188845074973856704521119uwb) + || popcount192 (289948065236269174335700831610076764076947650072787325852uwb) != __builtin_popcountg (289948065236269174335700831610076764076947650072787325852uwb)) + __builtin_abort (); +#endif +} diff --git a/gcc/testsuite/gcc.dg/torture/bitint-44.c b/gcc/testsuite/gcc.dg/torture/bitint-44.c new file mode 100644 index 0000000..938c0e9 --- /dev/null +++ b/gcc/testsuite/gcc.dg/torture/bitint-44.c @@ -0,0 +1,306 @@ +/* PR c/111309 */ +/* { dg-do run { target bitint } } */ +/* { dg-options "-std=c2x -pedantic-errors" } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "-flto" } { "" } } */ + +#if __BITINT_MAXWIDTH__ >= 512 +__attribute__((noipa)) int +clz512 (unsigned _BitInt(512) x) +{ + return __builtin_clzg (x); +} + +__attribute__((noipa)) int +clzd512 (unsigned _BitInt(512) x) +{ + return __builtin_clzg (x, __builtin_popcountg ((typeof (x)) ~(typeof (x)) 0)); +} + +__attribute__((noipa)) int +clzD512 (unsigned _BitInt(512) x, int y) +{ + return __builtin_clzg (x, y); +} + +__attribute__((noipa)) int +ctz512 (unsigned _BitInt(512) x) +{ + return __builtin_ctzg (x); +} + +__attribute__((noipa)) int +ctzd512 (unsigned _BitInt(512) x) +{ + return __builtin_ctzg (x, __builtin_popcountg ((typeof (x)) ~(typeof (x)) 0)); +} + +__attribute__((noipa)) int +ctzD512 (unsigned _BitInt(512) x, int y) +{ + return __builtin_ctzg (x, y); +} + +__attribute__((noipa)) int +clrsb512 (_BitInt(512) x) +{ + return __builtin_clrsbg (x); +} + +__attribute__((noipa)) int +ffs512 (_BitInt(512) x) +{ + return __builtin_ffsg (x); +} + +__attribute__((noipa)) int +parity512 (unsigned _BitInt(512) x) +{ + return __builtin_parityg (x); +} + +__attribute__((noipa)) int +popcount512 (unsigned _BitInt(512) x) +{ + return __builtin_popcountg (x); +} +#endif + +#if __BITINT_MAXWIDTH__ >= 523 +__attribute__((noipa)) int +clz523 (unsigned _BitInt(523) x) +{ + return __builtin_clzg (x); +} + +__attribute__((noipa)) int +clzd523 (unsigned _BitInt(523) x) +{ + return __builtin_clzg (x, __builtin_popcountg ((typeof (x)) ~(typeof (x)) 0)); +} + +__attribute__((noipa)) int +clzD523 (unsigned _BitInt(523) x, int y) +{ + return __builtin_clzg (x, y); +} + +__attribute__((noipa)) int +ctz523 (unsigned _BitInt(523) x) +{ + return __builtin_ctzg (x); +} + +__attribute__((noipa)) int +ctzd523 (unsigned _BitInt(523) x) +{ + return __builtin_ctzg (x, __builtin_popcountg ((typeof (x)) ~(typeof (x)) 0)); +} + +__attribute__((noipa)) int +ctzD523 (unsigned _BitInt(523) x, int y) +{ + return __builtin_ctzg (x, y); +} + +__attribute__((noipa)) int +clrsb523 (_BitInt(523) x) +{ + return __builtin_clrsbg (x); +} + +__attribute__((noipa)) int +ffs523 (_BitInt(523) x) +{ + return __builtin_ffsg (x); +} + +__attribute__((noipa)) int +parity523 (unsigned _BitInt(523) x) +{ + return __builtin_parityg (x); +} + +__attribute__((noipa)) int +popcount523 (unsigned _BitInt(523) x) +{ + return __builtin_popcountg (x); +} +#endif + +int +main () +{ +#if __BITINT_MAXWIDTH__ >= 512 + if (clzd512 (0) != 512 + || clzD512 (0, -1) != -1 + || ctzd512 (0) != 512 + || ctzD512 (0, 42) != 42 + || clrsb512 (0) != 512 - 1 + || ffs512 (0) != 0 + || parity512 (0) != 0 + || popcount512 (0) != 0 + || __builtin_clzg ((unsigned _BitInt(512)) 0, 512 + 32) != 512 + 32 + || __builtin_ctzg ((unsigned _BitInt(512)) 0, 512) != 512 + || __builtin_clrsbg ((_BitInt(512)) 0) != 512 - 1 + || __builtin_ffsg ((_BitInt(512)) 0) != 0 + || __builtin_parityg ((unsigned _BitInt(512)) 0) != 0 + || __builtin_popcountg ((unsigned _BitInt(512)) 0) != 0) + __builtin_abort (); + if (clz512 (-1) != 0 + || clzd512 (-1) != 0 + || clzD512 (-1, 0) != 0 + || ctz512 (-1) != 0 + || ctzd512 (-1) != 0 + || ctzD512 (-1, 17) != 0 + || clrsb512 (-1) != 512 - 1 + || ffs512 (-1) != 1 + || parity512 (-1) != 0 + || popcount512 (-1) != 512 + || __builtin_clzg ((unsigned _BitInt(512)) -1) != 0 + || __builtin_clzg ((unsigned _BitInt(512)) -1, 512 + 32) != 0 + || __builtin_ctzg ((unsigned _BitInt(512)) -1) != 0 + || __builtin_ctzg ((unsigned _BitInt(512)) -1, 512) != 0 + || __builtin_clrsbg ((_BitInt(512)) -1) != 512 - 1 + || __builtin_ffsg ((_BitInt(512)) -1) != 1 + || __builtin_parityg ((unsigned _BitInt(512)) -1) != 0 + || __builtin_popcountg ((unsigned _BitInt(512)) -1) != 512) + __builtin_abort (); + if (clz512 (((unsigned _BitInt(512)) -1) >> 24) != 24 + || clz512 (((unsigned _BitInt(512)) -1) >> 79) != 79 + || clz512 (1) != 512 - 1 + || clzd512 (((unsigned _BitInt(512)) -1) >> 139) != 139 + || clzd512 (2) != 512 - 2 + || ctz512 (((unsigned _BitInt(512)) -1) << 42) != 42 + || ctz512 (((unsigned _BitInt(512)) -1) << 57) != 57 + || ctz512 (0x4000000000000000000000uwb) != 86 + || ctzd512 (((unsigned _BitInt(512)) -1) << 149) != 149 + || ctzd512 (2) != 1 + || clrsb512 ((unsigned _BitInt(512 - 4)) -1) != 3 + || clrsb512 ((unsigned _BitInt(512 - 28)) -1) != 27 + || clrsb512 ((unsigned _BitInt(512 - 29)) -1) != 28 + || clrsb512 (~(unsigned _BitInt(512)) (unsigned _BitInt(512 - 68)) -1) != 67 + || clrsb512 (~(unsigned _BitInt(512)) (unsigned _BitInt(512 - 92)) -1) != 91 + || clrsb512 (~(unsigned _BitInt(512)) (unsigned _BitInt(512 - 93)) -1) != 92 + || ffs512 (((unsigned _BitInt(512)) -1) << 42) != 43 + || ffs512 (((unsigned _BitInt(512)) -1) << 57) != 58 + || ffs512 (0x4000000000000000000000uwb) != 87 + || ffs512 (((unsigned _BitInt(512)) -1) << 149) != 150 + || ffs512 (2) != 2 + || __builtin_clzg (((unsigned _BitInt(512)) -1) >> 24) != 24 + || __builtin_clzg (((unsigned _BitInt(512)) -1) >> 79) != 79 + || __builtin_clzg ((unsigned _BitInt(512)) 1) != 512 - 1 + || __builtin_clzg (((unsigned _BitInt(512)) -1) >> 139, 512) != 139 + || __builtin_clzg ((unsigned _BitInt(512)) 2, 512) != 512 - 2 + || __builtin_ctzg (((unsigned _BitInt(512)) -1) << 42) != 42 + || __builtin_ctzg (((unsigned _BitInt(512)) -1) << 57) != 57 + || __builtin_ctzg ((unsigned _BitInt(512)) 0x4000000000000000000000uwb) != 86 + || __builtin_ctzg (((unsigned _BitInt(512)) -1) << 149, 512) != 149 + || __builtin_ctzg ((unsigned _BitInt(512)) 2, 512) != 1 + || __builtin_clrsbg ((_BitInt(512)) (unsigned _BitInt(512 - 4)) -1) != 3 + || __builtin_clrsbg ((_BitInt(512)) (unsigned _BitInt(512 - 28)) -1) != 27 + || __builtin_clrsbg ((_BitInt(512)) (unsigned _BitInt(512 - 29)) -1) != 28 + || __builtin_clrsbg ((_BitInt(512)) ~(unsigned _BitInt(512)) (unsigned _BitInt(512 - 68)) -1) != 67 + || __builtin_clrsbg ((_BitInt(512)) ~(unsigned _BitInt(512)) (unsigned _BitInt(512 - 92)) -1) != 91 + || __builtin_clrsbg ((_BitInt(512)) ~(unsigned _BitInt(512)) (unsigned _BitInt(512 - 93)) -1) != 92 + || __builtin_ffsg ((_BitInt(512)) (((unsigned _BitInt(512)) -1) << 42)) != 43 + || __builtin_ffsg ((_BitInt(512)) (((unsigned _BitInt(512)) -1) << 57)) != 58 + || __builtin_ffsg ((_BitInt(512)) 0x4000000000000000000000uwb) != 87 + || __builtin_ffsg ((_BitInt(512)) (((unsigned _BitInt(512)) -1) << 149)) != 150 + || __builtin_ffsg ((_BitInt(512)) 2) != 2) + __builtin_abort (); + if (parity512 (8278593062772967967574644592392030907507244457324713380127157444008480135136016412791369421272159911061801023217823646324038055629840240503699995274750141uwb) != __builtin_parityg (8278593062772967967574644592392030907507244457324713380127157444008480135136016412791369421272159911061801023217823646324038055629840240503699995274750141uwb) + || parity512 (663951521760319802637316646127146913163123967584512032007606686578544864655291546789196279408181546344880831465704154822174055168766759305688225967189384uwb) != __builtin_parityg (663951521760319802637316646127146913163123967584512032007606686578544864655291546789196279408181546344880831465704154822174055168766759305688225967189384uwb) + || parity512 (8114152627481936575035564712656624361256533214211179387274127464949371919139038942819974113641465089580051998523156404968195970853124179018281296621919217uwb) != __builtin_parityg (8114152627481936575035564712656624361256533214211179387274127464949371919139038942819974113641465089580051998523156404968195970853124179018281296621919217uwb) + || popcount512 (697171368046392901434470580443928282938585745214587494987284546386421344865289735592202298494880955572094546861862007016154025065165834164941207378563932uwb) != __builtin_popcountg (697171368046392901434470580443928282938585745214587494987284546386421344865289735592202298494880955572094546861862007016154025065165834164941207378563932uwb) + || popcount512 (12625357869391866487124235043239209385173615631331705015179232007319637649427586947822360147798041278948617160703315666047585702906648747835331939389354450uwb) != __builtin_popcountg (12625357869391866487124235043239209385173615631331705015179232007319637649427586947822360147798041278948617160703315666047585702906648747835331939389354450uwb) + || popcount512 (12989863959706456104163426941303698078341934896544520782734564901708926112239778316241786242633862403309192697330635825122310265805838908726925342761646021uwb) != __builtin_popcountg (12989863959706456104163426941303698078341934896544520782734564901708926112239778316241786242633862403309192697330635825122310265805838908726925342761646021uwb)) + __builtin_abort (); +#endif +#if __BITINT_MAXWIDTH__ >= 523 + if (clzd523 (0) != 523 + || clzD523 (0, 42) != 42 + || ctzd523 (0) != 523 + || ctzD523 (0, -1) != -1 + || clrsb523 (0) != 523 - 1 + || ffs523 (0) != 0 + || parity523 (0) != 0 + || popcount523 (0) != 0 + || __builtin_clzg ((unsigned _BitInt(523)) 0, 523 + 32) != 523 + 32 + || __builtin_ctzg ((unsigned _BitInt(523)) 0, 523) != 523 + || __builtin_clrsbg ((_BitInt(523)) 0) != 523 - 1 + || __builtin_ffsg ((_BitInt(523)) 0) != 0 + || __builtin_parityg ((unsigned _BitInt(523)) 0) != 0 + || __builtin_popcountg ((unsigned _BitInt(523)) 0) != 0) + __builtin_abort (); + if (clz523 (-1) != 0 + || clzd523 (-1) != 0 + || clzD523 (-1, 15) != 0 + || ctz523 (-1) != 0 + || ctzd523 (-1) != 0 + || ctzD523 (-1, -57) != 0 + || clrsb523 (-1) != 523 - 1 + || ffs523 (-1) != 1 + || parity523 (-1) != 1 + || popcount523 (-1) != 523 + || __builtin_clzg ((unsigned _BitInt(523)) -1) != 0 + || __builtin_clzg ((unsigned _BitInt(523)) -1, 523 + 32) != 0 + || __builtin_ctzg ((unsigned _BitInt(523)) -1) != 0 + || __builtin_ctzg ((unsigned _BitInt(523)) -1, 523) != 0 + || __builtin_clrsbg ((_BitInt(523)) -1) != 523 - 1 + || __builtin_ffsg ((_BitInt(523)) -1) != 1 + || __builtin_parityg ((unsigned _BitInt(523)) -1) != 1 + || __builtin_popcountg ((unsigned _BitInt(523)) -1) != 523) + __builtin_abort (); + if (clz523 (((unsigned _BitInt(523)) -1) >> 24) != 24 + || clz523 (((unsigned _BitInt(523)) -1) >> 79) != 79 + || clz523 (1) != 523 - 1 + || clzd523 (((unsigned _BitInt(523)) -1) >> 139) != 139 + || clzd523 (2) != 523 - 2 + || ctz523 (((unsigned _BitInt(523)) -1) << 42) != 42 + || ctz523 (((unsigned _BitInt(523)) -1) << 57) != 57 + || ctz523 (0x4000000000000000000000uwb) != 86 + || ctzd523 (((unsigned _BitInt(523)) -1) << 149) != 149 + || ctzd523 (2) != 1 + || clrsb523 ((unsigned _BitInt(523 - 4)) -1) != 3 + || clrsb523 ((unsigned _BitInt(523 - 28)) -1) != 27 + || clrsb523 ((unsigned _BitInt(523 - 29)) -1) != 28 + || clrsb523 (~(unsigned _BitInt(523)) (unsigned _BitInt(523 - 68)) -1) != 67 + || clrsb523 (~(unsigned _BitInt(523)) (unsigned _BitInt(523 - 92)) -1) != 91 + || clrsb523 (~(unsigned _BitInt(523)) (unsigned _BitInt(523 - 93)) -1) != 92 + || ffs523 (((unsigned _BitInt(523)) -1) << 42) != 43 + || ffs523 (((unsigned _BitInt(523)) -1) << 57) != 58 + || ffs523 (0x4000000000000000000000uwb) != 87 + || ffs523 (((unsigned _BitInt(523)) -1) << 149) != 150 + || ffs523 (2) != 2 + || __builtin_clzg (((unsigned _BitInt(523)) -1) >> 24) != 24 + || __builtin_clzg (((unsigned _BitInt(523)) -1) >> 79) != 79 + || __builtin_clzg ((unsigned _BitInt(523)) 1) != 523 - 1 + || __builtin_clzg (((unsigned _BitInt(523)) -1) >> 139, 523) != 139 + || __builtin_clzg ((unsigned _BitInt(523)) 2, 523) != 523 - 2 + || __builtin_ctzg (((unsigned _BitInt(523)) -1) << 42) != 42 + || __builtin_ctzg (((unsigned _BitInt(523)) -1) << 57) != 57 + || __builtin_ctzg ((unsigned _BitInt(523)) 0x4000000000000000000000uwb) != 86 + || __builtin_ctzg (((unsigned _BitInt(523)) -1) << 149, 523) != 149 + || __builtin_ctzg ((unsigned _BitInt(523)) 2, 523) != 1 + || __builtin_clrsbg ((_BitInt(523)) (unsigned _BitInt(523 - 4)) -1) != 3 + || __builtin_clrsbg ((_BitInt(523)) (unsigned _BitInt(523 - 28)) -1) != 27 + || __builtin_clrsbg ((_BitInt(523)) (unsigned _BitInt(523 - 29)) -1) != 28 + || __builtin_clrsbg ((_BitInt(523)) ~(unsigned _BitInt(523)) (unsigned _BitInt(523 - 68)) -1) != 67 + || __builtin_clrsbg ((_BitInt(523)) ~(unsigned _BitInt(523)) (unsigned _BitInt(523 - 92)) -1) != 91 + || __builtin_clrsbg ((_BitInt(523)) ~(unsigned _BitInt(523)) (unsigned _BitInt(523 - 93)) -1) != 92 + || __builtin_ffsg ((_BitInt(523)) (((unsigned _BitInt(523)) -1) << 42)) != 43 + || __builtin_ffsg ((_BitInt(523)) (((unsigned _BitInt(523)) -1) << 57)) != 58 + || __builtin_ffsg ((_BitInt(523)) 0x4000000000000000000000uwb) != 87 + || __builtin_ffsg ((_BitInt(523)) (((unsigned _BitInt(523)) -1) << 149)) != 150 + || __builtin_ffsg ((_BitInt(523)) 2) != 2) + __builtin_abort (); + if (parity523 (14226628251091586975416900831427560438504550751597528218770815297642064445318137709184907300499591292677456563377096100346699421879373024906380724757049700104uwb) != __builtin_parityg (14226628251091586975416900831427560438504550751597528218770815297642064445318137709184907300499591292677456563377096100346699421879373024906380724757049700104uwb) + || parity523 (20688958227123188226117538663818621034852702121556301239818743230005799574164516085541310491875153692467123662601853835357822935286851364843928714141587045255uwb) != __builtin_parityg (20688958227123188226117538663818621034852702121556301239818743230005799574164516085541310491875153692467123662601853835357822935286851364843928714141587045255uwb) + || parity523 (8927708174664018648856542263215989788443763271738485875573765922613438023117960552135374015673598803453205044464280019640319125968982118836809392169156450404uwb) != __builtin_parityg (8927708174664018648856542263215989788443763271738485875573765922613438023117960552135374015673598803453205044464280019640319125968982118836809392169156450404uwb) + || popcount523 (27178327344587654457581274852432957423537947348354896748701960885269035920194935311522194372418922852798513401240689173265979378157685169921449935364246334672uwb) != __builtin_popcountg (27178327344587654457581274852432957423537947348354896748701960885269035920194935311522194372418922852798513401240689173265979378157685169921449935364246334672uwb) + || popcount523 (5307736750284212829931201546806718535860789684371772688568780952567669490917265125893664418036905110148872995350655890585853451175740907670080602411287166989uwb) != __builtin_popcountg (5307736750284212829931201546806718535860789684371772688568780952567669490917265125893664418036905110148872995350655890585853451175740907670080602411287166989uwb) + || popcount523 (21261096432069432668470452941790780841888331284195411465624030283325239673941548816191698556934198698768393659379577567450765073013688585051560340496749593370uwb) != __builtin_popcountg (21261096432069432668470452941790780841888331284195411465624030283325239673941548816191698556934198698768393659379577567450765073013688585051560340496749593370uwb)) + __builtin_abort (); +#endif +} diff --git a/gcc/tree-ssa-forwprop.cc b/gcc/tree-ssa-forwprop.cc index d4e9202..d39dfc1 100644 --- a/gcc/tree-ssa-forwprop.cc +++ b/gcc/tree-ssa-forwprop.cc @@ -2381,6 +2381,7 @@ simplify_count_trailing_zeroes (gimple_stmt_iterator *gsi) HOST_WIDE_INT type_size = tree_to_shwi (TYPE_SIZE (type)); bool zero_ok = CTZ_DEFINED_VALUE_AT_ZERO (SCALAR_INT_TYPE_MODE (type), ctz_val) == 2; + int nargs = 2; /* If the input value can't be zero, don't special case ctz (0). */ if (tree_expr_nonzero_p (res_ops[0])) @@ -2388,6 +2389,7 @@ simplify_count_trailing_zeroes (gimple_stmt_iterator *gsi) zero_ok = true; zero_val = 0; ctz_val = 0; + nargs = 1; } /* Skip if there is no value defined at zero, or if we can't easily @@ -2399,7 +2401,11 @@ simplify_count_trailing_zeroes (gimple_stmt_iterator *gsi) gimple_seq seq = NULL; gimple *g; - gcall *call = gimple_build_call_internal (IFN_CTZ, 1, res_ops[0]); + gcall *call + = gimple_build_call_internal (IFN_CTZ, nargs, res_ops[0], + nargs == 1 ? NULL_TREE + : build_int_cst (integer_type_node, + ctz_val)); gimple_set_location (call, gimple_location (stmt)); gimple_set_lhs (call, make_ssa_name (integer_type_node)); gimple_seq_add_stmt (&seq, call); diff --git a/gcc/tree-ssa-loop-niter.cc b/gcc/tree-ssa-loop-niter.cc index 718582a..2098bef 100644 --- a/gcc/tree-ssa-loop-niter.cc +++ b/gcc/tree-ssa-loop-niter.cc @@ -2235,14 +2235,18 @@ build_cltz_expr (tree src, bool leading, bool define_at_zero) tree call; if (use_ifn) { - call = build_call_expr_internal_loc (UNKNOWN_LOCATION, ifn, - integer_type_node, 1, src); int val; int optab_defined_at_zero = (leading ? CLZ_DEFINED_VALUE_AT_ZERO (SCALAR_INT_TYPE_MODE (utype), val) : CTZ_DEFINED_VALUE_AT_ZERO (SCALAR_INT_TYPE_MODE (utype), val)); - if (define_at_zero && !(optab_defined_at_zero == 2 && val == prec)) + tree arg2 = NULL_TREE; + if (define_at_zero && optab_defined_at_zero == 2 && val == prec) + arg2 = build_int_cst (integer_type_node, val); + call = build_call_expr_internal_loc (UNKNOWN_LOCATION, ifn, + integer_type_node, arg2 ? 2 : 1, + src, arg2); + if (define_at_zero && arg2 == NULL_TREE) { tree is_zero = fold_build2 (NE_EXPR, boolean_type_node, src, build_zero_cst (TREE_TYPE (src))); diff --git a/gcc/tree-ssa-phiopt.cc b/gcc/tree-ssa-phiopt.cc index bb55a4f..ac80517 100644 --- a/gcc/tree-ssa-phiopt.cc +++ b/gcc/tree-ssa-phiopt.cc @@ -2863,18 +2863,26 @@ cond_removal_in_builtin_zero_pattern (basic_block cond_bb, } /* Check that we have a popcount/clz/ctz builtin. */ - if (!is_gimple_call (call) || gimple_call_num_args (call) != 1) + if (!is_gimple_call (call)) return false; - arg = gimple_call_arg (call, 0); lhs = gimple_get_lhs (call); if (lhs == NULL_TREE) return false; combined_fn cfn = gimple_call_combined_fn (call); + if (gimple_call_num_args (call) != 1 + && (gimple_call_num_args (call) != 2 + || cfn == CFN_CLZ + || cfn == CFN_CTZ)) + return false; + + arg = gimple_call_arg (call, 0); + internal_fn ifn = IFN_LAST; int val = 0; + bool any_val = false; switch (cfn) { case CFN_BUILT_IN_BSWAP16: @@ -2889,6 +2897,23 @@ cond_removal_in_builtin_zero_pattern (basic_block cond_bb, if (INTEGRAL_TYPE_P (TREE_TYPE (arg))) { tree type = TREE_TYPE (arg); + if (TREE_CODE (type) == BITINT_TYPE) + { + if (gimple_call_num_args (call) == 1) + { + any_val = true; + ifn = IFN_CLZ; + break; + } + if (!tree_fits_shwi_p (gimple_call_arg (call, 1))) + return false; + HOST_WIDE_INT at_zero = tree_to_shwi (gimple_call_arg (call, 1)); + if ((int) at_zero != at_zero) + return false; + ifn = IFN_CLZ; + val = at_zero; + break; + } if (direct_internal_fn_supported_p (IFN_CLZ, type, OPTIMIZE_FOR_BOTH) && CLZ_DEFINED_VALUE_AT_ZERO (SCALAR_INT_TYPE_MODE (type), val) == 2) @@ -2902,6 +2927,23 @@ cond_removal_in_builtin_zero_pattern (basic_block cond_bb, if (INTEGRAL_TYPE_P (TREE_TYPE (arg))) { tree type = TREE_TYPE (arg); + if (TREE_CODE (type) == BITINT_TYPE) + { + if (gimple_call_num_args (call) == 1) + { + any_val = true; + ifn = IFN_CTZ; + break; + } + if (!tree_fits_shwi_p (gimple_call_arg (call, 1))) + return false; + HOST_WIDE_INT at_zero = tree_to_shwi (gimple_call_arg (call, 1)); + if ((int) at_zero != at_zero) + return false; + ifn = IFN_CTZ; + val = at_zero; + break; + } if (direct_internal_fn_supported_p (IFN_CTZ, type, OPTIMIZE_FOR_BOTH) && CTZ_DEFINED_VALUE_AT_ZERO (SCALAR_INT_TYPE_MODE (type), val) == 2) @@ -2960,8 +3002,18 @@ cond_removal_in_builtin_zero_pattern (basic_block cond_bb, /* Check PHI arguments. */ if (lhs != arg0 - || TREE_CODE (arg1) != INTEGER_CST - || wi::to_wide (arg1) != val) + || TREE_CODE (arg1) != INTEGER_CST) + return false; + if (any_val) + { + if (!tree_fits_shwi_p (arg1)) + return false; + HOST_WIDE_INT at_zero = tree_to_shwi (arg1); + if ((int) at_zero != at_zero) + return false; + val = at_zero; + } + else if (wi::to_wide (arg1) != val) return false; /* And insert the popcount/clz/ctz builtin and cast stmt before the @@ -2974,13 +3026,15 @@ cond_removal_in_builtin_zero_pattern (basic_block cond_bb, reset_flow_sensitive_info (gimple_get_lhs (cast)); } gsi_from = gsi_for_stmt (call); - if (ifn == IFN_LAST || gimple_call_internal_p (call)) + if (ifn == IFN_LAST + || (gimple_call_internal_p (call) && gimple_call_num_args (call) == 2)) gsi_move_before (&gsi_from, &gsi); else { /* For __builtin_c[lt]z* force .C[LT]Z ifn, because only the latter is well defined at zero. */ - call = gimple_build_call_internal (ifn, 1, gimple_call_arg (call, 0)); + call = gimple_build_call_internal (ifn, 2, gimple_call_arg (call, 0), + build_int_cst (integer_type_node, val)); gimple_call_set_lhs (call, lhs); gsi_insert_before (&gsi, call, GSI_SAME_STMT); gsi_remove (&gsi_from, true); diff --git a/gcc/tree-vect-patterns.cc b/gcc/tree-vect-patterns.cc index 6b6b412..7debe7f 100644 --- a/gcc/tree-vect-patterns.cc +++ b/gcc/tree-vect-patterns.cc @@ -1818,7 +1818,7 @@ vect_recog_ctz_ffs_pattern (vec_info *vinfo, stmt_vec_info stmt_vinfo, tree new_var; internal_fn ifn = IFN_LAST, ifnnew = IFN_LAST; bool defined_at_zero = true, defined_at_zero_new = false; - int val = 0, val_new = 0; + int val = 0, val_new = 0, val_cmp = 0; int prec; int sub = 0, add = 0; location_t loc; @@ -1826,7 +1826,8 @@ vect_recog_ctz_ffs_pattern (vec_info *vinfo, stmt_vec_info stmt_vinfo, if (!is_gimple_call (call_stmt)) return NULL; - if (gimple_call_num_args (call_stmt) != 1) + if (gimple_call_num_args (call_stmt) != 1 + && gimple_call_num_args (call_stmt) != 2) return NULL; rhs_oprnd = gimple_call_arg (call_stmt, 0); @@ -1846,9 +1847,10 @@ vect_recog_ctz_ffs_pattern (vec_info *vinfo, stmt_vec_info stmt_vinfo, CASE_CFN_CTZ: ifn = IFN_CTZ; if (!gimple_call_internal_p (call_stmt) - || CTZ_DEFINED_VALUE_AT_ZERO (SCALAR_INT_TYPE_MODE (rhs_type), - val) != 2) + || gimple_call_num_args (call_stmt) != 2) defined_at_zero = false; + else + val = tree_to_shwi (gimple_call_arg (call_stmt, 1)); break; CASE_CFN_FFS: ifn = IFN_FFS; @@ -1907,6 +1909,7 @@ vect_recog_ctz_ffs_pattern (vec_info *vinfo, stmt_vec_info stmt_vinfo, vect_pattern_detected ("vec_recog_ctz_ffs_pattern", call_stmt); + val_cmp = val_new; if ((ifnnew == IFN_CLZ && defined_at_zero && defined_at_zero_new @@ -1918,7 +1921,7 @@ vect_recog_ctz_ffs_pattern (vec_info *vinfo, stmt_vec_info stmt_vinfo, .CTZ (X) = .POPCOUNT ((X - 1) & ~X). */ if (ifnnew == IFN_CLZ) sub = prec; - val_new = prec; + val_cmp = prec; if (!TYPE_UNSIGNED (rhs_type)) { @@ -1955,7 +1958,7 @@ vect_recog_ctz_ffs_pattern (vec_info *vinfo, stmt_vec_info stmt_vinfo, /* .CTZ (X) = (PREC - 1) - .CLZ (X & -X) .FFS (X) = PREC - .CLZ (X & -X). */ sub = prec - (ifn == IFN_CTZ); - val_new = sub - val_new; + val_cmp = sub - val_new; tree neg = vect_recog_temp_ssa_var (rhs_type, NULL); pattern_stmt = gimple_build_assign (neg, NEGATE_EXPR, rhs_oprnd); @@ -1974,7 +1977,7 @@ vect_recog_ctz_ffs_pattern (vec_info *vinfo, stmt_vec_info stmt_vinfo, /* .CTZ (X) = PREC - .POPCOUNT (X | -X) .FFS (X) = (PREC + 1) - .POPCOUNT (X | -X). */ sub = prec + (ifn == IFN_FFS); - val_new = sub; + val_cmp = sub; tree neg = vect_recog_temp_ssa_var (rhs_type, NULL); pattern_stmt = gimple_build_assign (neg, NEGATE_EXPR, rhs_oprnd); @@ -1992,12 +1995,18 @@ vect_recog_ctz_ffs_pattern (vec_info *vinfo, stmt_vec_info stmt_vinfo, { /* .FFS (X) = .CTZ (X) + 1. */ add = 1; - val_new++; + val_cmp++; } /* Create B = .IFNNEW (A). */ new_var = vect_recog_temp_ssa_var (lhs_type, NULL); - pattern_stmt = gimple_build_call_internal (ifnnew, 1, rhs_oprnd); + if ((ifnnew == IFN_CLZ || ifnnew == IFN_CTZ) && defined_at_zero_new) + pattern_stmt + = gimple_build_call_internal (ifnnew, 2, rhs_oprnd, + build_int_cst (integer_type_node, + val_new)); + else + pattern_stmt = gimple_build_call_internal (ifnnew, 1, rhs_oprnd); gimple_call_set_lhs (pattern_stmt, new_var); gimple_set_location (pattern_stmt, loc); *type_out = vec_type; @@ -2023,7 +2032,7 @@ vect_recog_ctz_ffs_pattern (vec_info *vinfo, stmt_vec_info stmt_vinfo, } if (defined_at_zero - && (!defined_at_zero_new || val != val_new)) + && (!defined_at_zero_new || val != val_cmp)) { append_pattern_def_seq (vinfo, stmt_vinfo, pattern_stmt, vec_type); tree ret_var = vect_recog_temp_ssa_var (lhs_type, NULL); @@ -2143,7 +2152,8 @@ vect_recog_popcount_clz_ctz_ffs_pattern (vec_info *vinfo, return NULL; } - if (gimple_call_num_args (call_stmt) != 1) + if (gimple_call_num_args (call_stmt) != 1 + && gimple_call_num_args (call_stmt) != 2) return NULL; rhs_oprnd = gimple_call_arg (call_stmt, 0); @@ -2181,17 +2191,14 @@ vect_recog_popcount_clz_ctz_ffs_pattern (vec_info *vinfo, return NULL; addend = (TYPE_PRECISION (TREE_TYPE (rhs_oprnd)) - TYPE_PRECISION (lhs_type)); - if (gimple_call_internal_p (call_stmt)) + if (gimple_call_internal_p (call_stmt) + && gimple_call_num_args (call_stmt) == 2) { int val1, val2; - int d1 - = CLZ_DEFINED_VALUE_AT_ZERO - (SCALAR_INT_TYPE_MODE (TREE_TYPE (rhs_oprnd)), val1); + val1 = tree_to_shwi (gimple_call_arg (call_stmt, 1)); int d2 = CLZ_DEFINED_VALUE_AT_ZERO (SCALAR_INT_TYPE_MODE (lhs_type), val2); - if (d1 != 2) - break; if (d2 != 2 || val1 != val2 + addend) return NULL; } @@ -2200,17 +2207,14 @@ vect_recog_popcount_clz_ctz_ffs_pattern (vec_info *vinfo, /* ctzll (x) == ctz (x) for unsigned or signed x != 0, so ok if it is undefined at zero or if it matches also for the defined value there. */ - if (gimple_call_internal_p (call_stmt)) + if (gimple_call_internal_p (call_stmt) + && gimple_call_num_args (call_stmt) == 2) { int val1, val2; - int d1 - = CTZ_DEFINED_VALUE_AT_ZERO - (SCALAR_INT_TYPE_MODE (TREE_TYPE (rhs_oprnd)), val1); + val1 = tree_to_shwi (gimple_call_arg (call_stmt, 1)); int d2 = CTZ_DEFINED_VALUE_AT_ZERO (SCALAR_INT_TYPE_MODE (lhs_type), val2); - if (d1 != 2) - break; if (d2 != 2 || val1 != val2) return NULL; } @@ -2260,7 +2264,20 @@ vect_recog_popcount_clz_ctz_ffs_pattern (vec_info *vinfo, /* Create B = .POPCOUNT (A). */ new_var = vect_recog_temp_ssa_var (lhs_type, NULL); - pattern_stmt = gimple_build_call_internal (ifn, 1, unprom_diff.op); + tree arg2 = NULL_TREE; + int val; + if (ifn == IFN_CLZ + && CLZ_DEFINED_VALUE_AT_ZERO (SCALAR_INT_TYPE_MODE (lhs_type), + val) == 2) + arg2 = build_int_cst (integer_type_node, val); + else if (ifn == IFN_CTZ + && CTZ_DEFINED_VALUE_AT_ZERO (SCALAR_INT_TYPE_MODE (lhs_type), + val) == 2) + arg2 = build_int_cst (integer_type_node, val); + if (arg2) + pattern_stmt = gimple_build_call_internal (ifn, 2, unprom_diff.op, arg2); + else + pattern_stmt = gimple_build_call_internal (ifn, 1, unprom_diff.op); gimple_call_set_lhs (pattern_stmt, new_var); gimple_set_location (pattern_stmt, gimple_location (last_stmt)); *type_out = vec_type; diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc index ee89f47..96e4a6cf 100644 --- a/gcc/tree-vect-stmts.cc +++ b/gcc/tree-vect-stmts.cc @@ -3115,6 +3115,7 @@ vectorizable_call (vec_info *vinfo, enum { NARROW, NONE, WIDEN } modifier; size_t i, nargs; tree lhs; + tree clz_ctz_arg1 = NULL_TREE; if (!STMT_VINFO_RELEVANT_P (stmt_info) && !bb_vinfo) return false; @@ -3160,6 +3161,14 @@ vectorizable_call (vec_info *vinfo, nargs = 0; rhs_type = unsigned_type_node; } + /* Similarly pretend IFN_CLZ and IFN_CTZ only has one argument, the second + argument just says whether it is well-defined at zero or not and what + value should be returned for it. */ + if ((cfn == CFN_CLZ || cfn == CFN_CTZ) && nargs == 2) + { + nargs = 1; + clz_ctz_arg1 = gimple_call_arg (stmt, 1); + } int mask_opno = -1; if (internal_fn_p (cfn)) @@ -3425,6 +3434,8 @@ vectorizable_call (vec_info *vinfo, ifn = cond_fn; vect_nargs += 2; } + if (clz_ctz_arg1) + ++vect_nargs; if (modifier == NONE || ifn != IFN_LAST) { @@ -3462,6 +3473,9 @@ vectorizable_call (vec_info *vinfo, } if (masked_loop_p && reduc_idx >= 0) vargs[varg++] = vargs[reduc_idx + 1]; + if (clz_ctz_arg1) + vargs[varg++] = clz_ctz_arg1; + gimple *new_stmt; if (modifier == NARROW) { @@ -3548,6 +3562,8 @@ vectorizable_call (vec_info *vinfo, } if (masked_loop_p && reduc_idx >= 0) vargs[varg++] = vargs[reduc_idx + 1]; + if (clz_ctz_arg1) + vargs[varg++] = clz_ctz_arg1; if (len_opno >= 0 && len_loop_p) { |