From dc87e1391c55c666c7ff39d4f0dea87666f25468 Mon Sep 17 00:00:00 2001
From: Richard Biener <rguenther@suse.de>
Date: Fri, 10 Feb 2023 11:07:30 +0100
Subject: [PATCH] tree-optimization/108724 - vectorized code getting piecewise
 expanded

This fixes an oversight to when removing the hard limits on using
generic vectors for the vectorizer to enable both SLP and BB
vectorization to use those.  The vectorizer relies on vector lowering
to expand plus, minus and negate to bit operations but vector
lowering has a hard limit on the minimum number of elements per
work item.  Vectorizer costs for the testcase at hand work out
to vectorize a loop with just two work items per vector and that
causes element wise expansion and spilling.

The fix for now is to re-instantiate the hard limit, matching what
vector lowering does.  For the future the way to go is to emit the
lowered sequence directly from the vectorizer instead.

	PR tree-optimization/108724
	* tree-vect-stmts.cc (vectorizable_operation): Avoid
	using word_mode vectors when vector lowering will
	decompose them to elementwise operations.

	* gcc.target/i386/pr108724.c: New testcase.
---
 gcc/testsuite/gcc.target/i386/pr108724.c | 15 +++++++++++++++
 gcc/tree-vect-stmts.cc                   | 14 ++++++++++++++
 2 files changed, 29 insertions(+)
 create mode 100644 gcc/testsuite/gcc.target/i386/pr108724.c

diff --git a/gcc/testsuite/gcc.target/i386/pr108724.c b/gcc/testsuite/gcc.target/i386/pr108724.c
new file mode 100644
index 0000000..c4e0e91
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr108724.c
@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -mno-sse" } */
+
+int a[16], b[16], c[16];
+void foo()
+{
+  for (int i = 0; i < 16; i++) {
+    a[i] = b[i] + c[i];
+  }
+}
+
+/* When this is vectorized this shouldn't be expanded piecewise again
+   which will result in spilling for the upper half access.  */
+
+/* { dg-final { scan-assembler-not "\\\[er\\\]sp" } } */
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index c86249a..09b5af6 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -6315,6 +6315,20 @@ vectorizable_operation (vec_info *vinfo,
       return false;
     }
 
+  /* ???  We should instead expand the operations here, instead of
+     relying on vector lowering which has this hard cap on the number
+     of vector elements below it performs elementwise operations.  */
+  if (using_emulated_vectors_p
+      && (code == PLUS_EXPR || code == MINUS_EXPR || code == NEGATE_EXPR)
+      && ((BITS_PER_WORD / vector_element_bits (vectype)) < 4
+	  || maybe_lt (nunits_out, 4U)))
+    {
+      if (dump_enabled_p ())
+	dump_printf (MSG_NOTE, "not using word mode for +- and less than "
+		     "four vector elements\n");
+      return false;
+    }
+
   int reduc_idx = STMT_VINFO_REDUC_IDX (stmt_info);
   vec_loop_masks *masks = (loop_vinfo ? &LOOP_VINFO_MASKS (loop_vinfo) : NULL);
   internal_fn cond_fn = get_conditional_internal_fn (code);
-- 
2.7.4