Dear all,
Here's my patch for PR120265. Bootstrapped and tested on aarch64 that it
causes no regressions. I also added a testcase. I'd be grateful
if you could commit it.
Otherwise, feedback to improve it is welcome.
Many thanks
MCCCS
From 1e901c3fa5c8cc3e55d4f1715b4aae4ae3d66714 Mon Sep 17 00:00:00 2001
From: MCCCS <mc...@gmx.com>
Date: Thu, 15 May 2025 09:16:49 +0100
Subject: [PATCH] tree-optimization/120265 - Optimize modular counters
This PR is about replacing trunc_mod with with a
simpler expression given the bounds of variables.
PR tree-optimization/120265
* match.pd:
X % M -> X for X in 0 to M-1
X % M -> (X == M) ? 0 : X for X in 0 to M
X % M -> (X >= M) ? (X - M) : X for X in 0 to 2*M-1.
* gcc.dg/pr120265.c. New testcase.
---
gcc/match.pd | 27 ++++++++++++++++++++
gcc/testsuite/gcc.dg/pr120265.c | 44 +++++++++++++++++++++++++++++++++
2 files changed, 71 insertions(+)
create mode 100644 gcc/testsuite/gcc.dg/pr120265.c
diff --git a/gcc/match.pd b/gcc/match.pd
index 79485f9678a..bd8950b4e10 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -5602,6 +5602,33 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
optab_vector)))
(eq (trunc_mod @0 @1) { build_zero_cst (TREE_TYPE (@0)); })))
+#if GIMPLE
+/* X % M -> X for X in 0 to M-1. */
+/* X % M -> (X == M) ? 0 : X for X in 0 to M. */
+/* X % M -> (X >= M) ? (X - M) : X for X in 0 to 2*M-1. */
+(simplify
+ (trunc_mod @0 @1)
+ (with { int_range_max vr0, vr1; }
+ (if (get_range_query (cfun)->range_of_expr (vr0, @0)
+ && get_range_query (cfun)->range_of_expr (vr1, @1)
+ && !vr0.undefined_p ()
+ && !vr1.undefined_p ()
+ && !integer_zerop (@1)
+ && (TYPE_UNSIGNED (type)
+ || (vr0.nonnegative_p () && vr1.nonnegative_p ())))
+ (with
+ { wide_int twice = 2 * vr1.lower_bound (); }
+ (switch
+ (if (wi::gtu_p (vr1.lower_bound (), vr0.upper_bound ()))
+ @0)
+ (if (wi::geu_p (vr1.lower_bound (), vr0.upper_bound ()))
+ (cond (eq @0 @1)
+ { build_zero_cst (type); }
+ @0))
+ (if (wi::gtu_p (twice, vr0.upper_bound ()))
+ (cond (ge @0 @1) (minus @0 @1) @0)))))))
+#endif
+
/* ((X /[ex] C1) +- C2) * (C1 * C3) --> (X * C3) +- (C1 * C2 * C3). */
(for op (plus minus)
(simplify
diff --git a/gcc/testsuite/gcc.dg/pr120265.c b/gcc/testsuite/gcc.dg/pr120265.c
new file mode 100644
index 00000000000..2634af36226
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/pr120265.c
@@ -0,0 +1,44 @@
+/* { dg-do compile } */
+/* { dg-options "-O -fdump-tree-optimized" } */
+__attribute__((noipa)) void g(int r)
+{
+ (void) r;
+}
+
+int x;
+
+void a(void)
+{
+ unsigned m = 0;
+ for(int i = 0; i < 300; i++)
+ {
+ m++;
+ m %= 600;
+ g(m);
+ }
+}
+
+void b(void)
+{
+ unsigned m = 0;
+ for(int i = 0; i < x; i++)
+ {
+ m++;
+ m %= 600;
+ g(m);
+ }
+}
+
+void c(void)
+{
+ unsigned m = 0;
+ for(int i = 0; i < x; i++)
+ {
+ m += 7;
+ m %= 600;
+ g(m);
+ }
+}
+
+/* { dg-final { scan-tree-dump-not "% 600" "optimized" } } */
+
--
2.45.2
