[gcc r12-6402] tree-optimization/100359 - restore unroll at -O3

[gcc r12-6402] tree-optimization/100359 - restore unroll at -O3

[Richard Biener]

https://gcc.gnu.org/g:92e114d66e93d60dcef97c66cddbae38b657d768

commit r12-6402-g92e114d66e93d60dcef97c66cddbae38b657d768
Author: Richard Biener <rguenther@suse.de>
Date:   Wed Jan 5 16:29:53 2022 +0100

    tree-optimization/100359 - restore unroll at -O3
    
    This fixes a mistake done with r8-5008 when introducing
    allow_peel to the unroll code.  The intent was to allow
    peeling that doesn't grow code but the result was that
    with -O3 and UL_ALL this wasn't done.  The following
    instantiates the desired effect by adjusting ul to UL_NO_GROWTH
    if peeling is not allowed.
    
    2022-01-05  Richard Biener  <rguenther@suse.de>
    
            PR tree-optimization/100359
            * tree-ssa-loop-ivcanon.c (try_unroll_loop_completely):
            Allow non-growing peeling with !allow_peel and UL_ALL.
    
            * gcc.dg/tree-ssa/pr100359.c: New testcase.

Diff:
---
 gcc/testsuite/gcc.dg/tree-ssa/pr100359.c | 31 +++++++++++++++++++++++++++++++
 gcc/tree-ssa-loop-ivcanon.c              |  6 +++++-
 2 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr100359.c b/gcc/testsuite/gcc.dg/tree-ssa/pr100359.c
new file mode 100644
index 00000000000..29243522caa
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr100359.c
@@ -0,0 +1,31 @@
+/* { dg-do link } */
+/* { dg-options "-O3 -fdump-tree-cunrolli-optimized" } */
+
+extern void foo(void);
+static int b, f, *a = &b;
+int **c = &a;
+static void d() {
+  int g, h;
+  for (f = 0; f < 1; f++) {
+    int *i = &b;
+    {
+      int *j[3], **k = &a;
+      for (g = 0; g < 3; g++)
+        for (h = 0; h < 1; h++)
+          j[g] = &b;
+      *k = j[0];
+    }
+    *c = i;
+  }
+}
+int main() {
+  d();
+  *a = 0;
+  if (**c)
+    foo();
+  return 0;
+}
+
+/* Verify that we unroll the inner loop early even with -O3.  */
+/* { dg-final { scan-tree-dump "loop with 1 iterations completely unrolled" "cunrolli" } }  */
+/* { dg-final { scan-tree-dump "loop with 3 iterations completely unrolled" "cunrolli" } }  */
diff --git a/gcc/tree-ssa-loop-ivcanon.c b/gcc/tree-ssa-loop-ivcanon.c
index 4f1e3537f05..e2ac2044741 100644
--- a/gcc/tree-ssa-loop-ivcanon.c
+++ b/gcc/tree-ssa-loop-ivcanon.c
@@ -720,7 +720,7 @@ try_unroll_loop_completely (class loop *loop,
     exit = NULL;
 
   /* See if we can improve our estimate by using recorded loop bounds.  */
-  if ((allow_peel || maxiter == 0 || ul == UL_NO_GROWTH)
+  if ((maxiter == 0 || ul != UL_SINGLE_ITER)
       && maxiter >= 0
       && (!n_unroll_found || (unsigned HOST_WIDE_INT)maxiter < n_unroll))
     {
@@ -729,6 +729,10 @@ try_unroll_loop_completely (class loop *loop,
       /* Loop terminates before the IV variable test, so we cannot
 	 remove it in the last iteration.  */
       edge_to_cancel = NULL;
+      /* If we do not allow peeling and we iterate just allow cases
+	 that do not grow code.  */
+      if (!allow_peel && maxiter != 0)
+	ul = UL_NO_GROWTH;
     }
 
   if (!n_unroll_found)