Hi!
On x86 (the only target with umulv4_optab) one can use mull; seto to check
for overflow instead of performing wider multiplication and performing
comparison on the high bits.
Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?
2020-05-05 Jakub Jelinek <ja...@redhat.com>
PR tree-optimization/94914
* match.pd ((((type)A * B) >> prec) != 0 to .MUL_OVERFLOW(A, B) != 0):
New simplification.
* gcc.target/i386/pr94914.c: New test.
--- gcc/match.pd.jj 2020-05-04 11:02:14.288865592 +0200
+++ gcc/match.pd 2020-05-04 12:15:33.220799388 +0200
@@ -4776,6 +4776,27 @@ (define_operator_list COND_TERNARY
(with { tree t = TREE_TYPE (@0), cpx = build_complex_type (t); }
(out (imagpart (IFN_MUL_OVERFLOW:cpx @0 @1)) { build_zero_cst (t); })))))
+/* Similarly, for unsigned operands, (((type) A * B) >> prec) != 0 where type
+ is at least twice as wide as type of A and B, simplify to
+ __builtin_mul_overflow (A, B, <unused>). */
+(for cmp (eq ne)
+ (simplify
+ (cmp (rshift (mult:s (convert@3 @0) (convert @1)) INTEGER_CST@2)
+ integer_zerop)
+ (if (INTEGRAL_TYPE_P (TREE_TYPE (@0))
+ && INTEGRAL_TYPE_P (TREE_TYPE (@3))
+ && TYPE_UNSIGNED (TREE_TYPE (@0))
+ && (TYPE_PRECISION (TREE_TYPE (@3))
+ >= 2 * TYPE_PRECISION (TREE_TYPE (@0)))
+ && tree_fits_uhwi_p (@2)
+ && tree_to_uhwi (@2) == TYPE_PRECISION (TREE_TYPE (@0))
+ && types_match (@0, @1)
+ && type_has_mode_precision_p (TREE_TYPE (@0))
+ && (optab_handler (umulv4_optab, TYPE_MODE (TREE_TYPE (@0)))
+ != CODE_FOR_nothing))
+ (with { tree t = TREE_TYPE (@0), cpx = build_complex_type (t); }
+ (cmp (imagpart (IFN_MUL_OVERFLOW:cpx @0 @1)) { build_zero_cst (t); })))))
+
/* 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
--- gcc/testsuite/gcc.target/i386/pr94914.c.jj 2020-05-04 12:58:04.435775670
+0200
+++ gcc/testsuite/gcc.target/i386/pr94914.c 2020-05-04 12:57:39.307152707
+0200
@@ -0,0 +1,17 @@
+/* PR tree-optimization/94914 */
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+/* { dg-final { scan-assembler "\tseto\t" } } */
+/* { dg-final { scan-assembler "\tsetno\t" } } */
+
+int
+foo (unsigned int x, unsigned int y)
+{
+ return (((unsigned long long)x * y) >> 32) != 0;
+}
+
+int
+bar (unsigned int x, unsigned int y)
+{
+ return (((unsigned long long)x * y) >> 32) == 0;
+}
Jakub
