From cf78d8411d00e21c30512d2af895e70d38bbfb77 Mon Sep 17 00:00:00 2001 From: Jakub Jelinek Date: Wed, 1 Jun 2022 17:54:39 +0200 Subject: [PATCH] match.pd: Optimize __builtin_mul_overflow_p (x, cst, (utype)0) to x > ~(utype)0 / cst [PR30314] A comparison with a constant is most likely always faster than .MUL_OVERFLOW from which we only check whether it overflowed and not the multiplication result, and even if not, it is simpler operation on GIMPLE and even if a target exists where such multiplications with overflow checking are cheaper than comparisons, because comparisons are so much more common than overflow checking multiplications, it would be nice if it simply arranged for comparisons to be emitted like those multiplications on its own... 2022-06-01 Jakub Jelinek PR middle-end/30314 * match.pd (__builtin_mul_overflow_p (x, cst, (utype) 0) -> x > ~(utype)0 / cst): New simplification. * gcc.dg/tree-ssa/pr30314.c: New test. --- gcc/match.pd | 11 +++++++++++ gcc/testsuite/gcc.dg/tree-ssa/pr30314.c | 18 ++++++++++++++++++ 2 files changed, 29 insertions(+) create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr30314.c diff --git a/gcc/match.pd b/gcc/match.pd index 88c6c41..2d3ffc4 100644 --- a/gcc/match.pd +++ b/gcc/match.pd @@ -5969,6 +5969,17 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) && (!TYPE_UNSIGNED (TREE_TYPE (@2)) || TYPE_UNSIGNED (TREE_TYPE (@0)))) (ovf @1 @0)))) +/* Optimize __builtin_mul_overflow_p (x, cst, (utype) 0) if all 3 types + are unsigned to x > (umax / cst). */ +(simplify + (imagpart (IFN_MUL_OVERFLOW:cs@2 @0 integer_nonzerop@1)) + (if (INTEGRAL_TYPE_P (TREE_TYPE (@0)) + && TYPE_UNSIGNED (TREE_TYPE (@0)) + && TYPE_MAX_VALUE (TREE_TYPE (@0)) + && types_match (TREE_TYPE (@0), TREE_TYPE (TREE_TYPE (@2))) + && int_fits_type_p (@1, TREE_TYPE (@0))) + (convert (gt @0 (trunc_div! { TYPE_MAX_VALUE (TREE_TYPE (@0)); } @1))))) + /* Simplification of math builtins. These rules must all be optimizations as well as IL simplifications. If there is a possibility that the new form could be a pessimization, the rule should go in the canonicalization diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr30314.c b/gcc/testsuite/gcc.dg/tree-ssa/pr30314.c new file mode 100644 index 0000000..91388af --- /dev/null +++ b/gcc/testsuite/gcc.dg/tree-ssa/pr30314.c @@ -0,0 +1,18 @@ +/* PR middle-end/30314 */ +/* { dg-do compile } */ +/* { dg-options "-O2 -fdump-tree-optimized" } */ +/* { dg-final { scan-tree-dump-not "\.MUL_OVERFLOW " "optimized" } } */ +/* { dg-final { scan-tree-dump " > 122713351" "optimized" { target int32 } } } */ +/* { dg-final { scan-tree-dump " > 527049830677415760" "optimized" { target lp64 } } } */ + +int +foo (unsigned int x) +{ + return __builtin_mul_overflow_p (x, 35U, 0U); +} + +int +bar (unsigned long int x) +{ + return __builtin_mul_overflow_p (x, 35UL, 0UL); +} -- 2.7.4