[gcc r12-7326] Implement constant-folding simplifications of reductions.

[Roger Sayle]

https://gcc.gnu.org/g:2ef0e75d0bbc80bc06a0a39135e3564f907e39c8

commit r12-7326-g2ef0e75d0bbc80bc06a0a39135e3564f907e39c8
Author: Roger Sayle <roger@nextmovesoftware.com>
Date:   Tue Feb 22 12:32:22 2022 +0000

    Implement constant-folding simplifications of reductions.
    
    This patch addresses a code quality regression in GCC 12 by implementing
    some constant folding/simplification transformations for REDUC_PLUS_EXPR
    in match.pd.  The motivating example is gcc.dg/vect/pr89440.c which with
    -O2 -ffast-math (with vectorization now enabled) gets optimized to:
    
    float f (float x)
    {
      vector(4) float vect_x_14.11;
      vector(4) float _2;
      float _32;
    
      _2 = {x_9(D), 0.0, 0.0, 0.0};
      vect_x_14.11_29 = _2 + { 1.0e+1, 2.6e+1, 4.2e+1, 5.8e+1 };
      _32 = .REDUC_PLUS (vect_x_14.11_29); [tail call]
      return _32;
    }
    
    With these proposed new transformations, we can simplify the
    above code even further.
    
    float f (float x)
    {
      float _32;
      _32 = x_9(D) + 1.36e+2;
      return _32;
    }
    
    [which happens to match what we'd produce with -fno-tree-vectorize,
    and with GCC 11].
    
    2022-02-22  Roger Sayle  <roger@nextmovesoftware.com>
                Richard Biener  <rguenther@suse.de>
    
    gcc/ChangeLog
            * fold-const.cc (ctor_single_nonzero_element): New function to
            return the single non-zero element of a (vector) constructor.
            * fold-const.h (ctor_single_nonzero_element): Prototype here.
            * match.pd (reduc (constructor@0)): Simplify reductions of a
            constructor containing a single non-zero element.
            (reduc (@0 op VECTOR_CST) ->  (reduc @0) op CONST): Simplify
            reductions of vector operations of the same operator with
            constant vector operands.
    
    gcc/testsuite/ChangeLog
            * gcc.dg/fold-reduc-1.c: New test case.

Diff:
---
 gcc/fold-const.cc                   | 20 ++++++++++++++++++++
 gcc/fold-const.h                    |  1 +
 gcc/match.pd                        | 18 ++++++++++++++++++
 gcc/testsuite/gcc.dg/fold-reduc-1.c | 19 +++++++++++++++++++
 4 files changed, 58 insertions(+)

diff --git a/gcc/fold-const.cc b/gcc/fold-const.cc
index 7b21240ba76..39a5a52958d 100644
--- a/gcc/fold-const.cc
+++ b/gcc/fold-const.cc
@@ -16792,6 +16792,26 @@ address_compare (tree_code code, tree type, tree op0, tree op1,
   return equal;
 }
 
+/* Return the single non-zero element of a CONSTRUCTOR or NULL_TREE.  */
+tree
+ctor_single_nonzero_element (const_tree t)
+{
+  unsigned HOST_WIDE_INT idx;
+  constructor_elt *ce;
+  tree elt = NULL_TREE;
+
+  if (TREE_CODE (t) != CONSTRUCTOR)
+    return NULL_TREE;
+  for (idx = 0; vec_safe_iterate (CONSTRUCTOR_ELTS (t), idx, &ce); idx++)
+    if (!integer_zerop (ce->value) && !real_zerop (ce->value))
+      {
+	if (elt)
+	  return NULL_TREE;
+	elt = ce->value;
+      }
+  return elt;
+}
+
 #if CHECKING_P
 
 namespace selftest {
diff --git a/gcc/fold-const.h b/gcc/fold-const.h
index 926c775e696..a4ff55418a5 100644
--- a/gcc/fold-const.h
+++ b/gcc/fold-const.h
@@ -225,6 +225,7 @@ extern const char *c_getstr (tree);
 extern wide_int tree_nonzero_bits (const_tree);
 extern int address_compare (tree_code, tree, tree, tree, tree &, tree &,
 			    poly_int64 &, poly_int64 &, bool);
+extern tree ctor_single_nonzero_element (const_tree);
 
 /* Return OFF converted to a pointer offset type suitable as offset for
    POINTER_PLUS_EXPR.  Use location LOC for this conversion.  */
diff --git a/gcc/match.pd b/gcc/match.pd
index 8b6f22f1065..cad61848daa 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -7532,6 +7532,24 @@ and,
        (BIT_FIELD_REF:elt_type @0 { size; } { pos; })
        { elt; })))))))
 
+/* Fold reduction of a single nonzero element constructor.  */
+(for reduc (IFN_REDUC_PLUS IFN_REDUC_IOR IFN_REDUC_XOR)
+  (simplify (reduc (CONSTRUCTOR@0))
+    (with { tree ctor = (TREE_CODE (@0) == SSA_NAME
+			 ? gimple_assign_rhs1 (SSA_NAME_DEF_STMT (@0)) : @0);
+	    tree elt = ctor_single_nonzero_element (ctor); }
+      (if (elt
+	   && !HONOR_SNANS (type)
+	   && !HONOR_SIGNED_ZEROS (type))
+	{ elt; }))))
+
+/* Fold REDUC (@0 op VECTOR_CST) as REDUC (@0) op REDUC (VECTOR_CST).  */
+(for reduc (IFN_REDUC_PLUS IFN_REDUC_MAX IFN_REDUC_MIN IFN_REDUC_FMAX
+	    IFN_REDUC_FMIN IFN_REDUC_AND IFN_REDUC_IOR IFN_REDUC_XOR)
+     op (plus max min IFN_FMAX IFN_FMIN bit_and bit_ior bit_xor)
+  (simplify (reduc (op @0 VECTOR_CST@1))
+    (op (reduc:type @0) (reduc:type @1))))
+
 (simplify
  (vec_perm @0 @1 VECTOR_CST@2)
  (with
diff --git a/gcc/testsuite/gcc.dg/fold-reduc-1.c b/gcc/testsuite/gcc.dg/fold-reduc-1.c
new file mode 100644
index 00000000000..c8360b0fc7d
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/fold-reduc-1.c
@@ -0,0 +1,19 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ffast-math -fdump-tree-optimized" } */
+float foo (float x)
+{
+ int i;
+ float j;
+ float a = 0;
+ for (i = 0; i < 4; ++i)
+   {
+     for (j = 0; j < 4; ++j)
+       {
+         a += 1;
+         x += a;
+       }
+   }
+ return x;
+}
+
+/* { dg-final { scan-tree-dump-not "REDUC_PLUS" "optimized"} } */