diff mbox series

Fix PR92818

Message ID nycvar.YFH.7.76.1912051214160.5566@zhemvz.fhfr.qr
State New
Headers show
Series Fix PR92818 | expand

Commit Message

Richard Biener Dec. 5, 2019, 11:15 a.m. UTC 
The following fixes a typo in the vec_perm to bit_insert pattern
and adjusts forwprop heuristic to make it trigger.  This improves
code-gen for the testcase back to a simple movhpd like we emitted
with GCC 9.

Bootstrap / regtest running on x86_64-unknown-linux-gnu.

Richard.

2019-12-05  Richard Biener  <rguenther@suse.de>

	PR middle-end/92818
	* tree-ssa-forwprop.c (simplify_vector_constructor): Improve
	heuristics on what don't care element to choose.
	* match.pd (VEC_PERM_EXPR -> BIT_INSERT_EXPR): Fix typo.

	* gcc.target/i386/pr92818.c: New testcase.
diff mbox series

Patch

Index: gcc/tree-ssa-forwprop.c
===================================================================
--- gcc/tree-ssa-forwprop.c	(revision 278992)
+++ gcc/tree-ssa-forwprop.c	(working copy)
@@ -2265,9 +2265,12 @@  simplify_vector_constructor (gimple_stmt
 	sel.quick_push (elts[i].second + elts[i].first * refnelts);
       /* And fill the tail with "something".  It's really don't care,
          and ideally we'd allow VEC_PERM to have a smaller destination
-	 vector.  */
+	 vector.  As heuristic try to preserve a uniform orig[0] which
+	 facilitates later pattern-matching VEC_PERM_EXPR to a
+	 BIT_INSERT_EXPR.  */
       for (; i < refnelts; ++i)
-	sel.quick_push (i - elts.length ());
+	sel.quick_push ((elts[0].second == 0 && elts[0].first == 0
+			 ? 0 : refnelts) + i);
       vec_perm_indices indices (sel, orig[1] ? 2 : 1, refnelts);
       if (!can_vec_perm_const_p (TYPE_MODE (perm_type), indices))
 	return false;
Index: gcc/match.pd
===================================================================
--- gcc/match.pd	(revision 278992)
+++ gcc/match.pd	(working copy)
@@ -6049,7 +6049,7 @@  (define_operator_list COND_TERNARY
 		    break;
 		if (at < encoded_nelts && sel.series_p (at + 1, 1, at + 1, 1))
 		  {
-		    if (known_lt (at, nelts))
+		    if (known_lt (poly_uint64 (sel[at]), nelts))
 		      ins = fold_read_from_vector (cop0, sel[at]);
 		    else
 		      ins = fold_read_from_vector (cop1, sel[at] - nelts);
Index: gcc/testsuite/gcc.target/i386/pr92818.c
===================================================================
--- gcc/testsuite/gcc.target/i386/pr92818.c	(nonexistent)
+++ gcc/testsuite/gcc.target/i386/pr92818.c	(working copy)
@@ -0,0 +1,14 @@ 
+/* { dg-do compile } */
+/* { dg-options "-O -mavx2 -fdump-tree-forwprop1" } */
+
+typedef double v4df __attribute__((vector_size (32)));
+typedef double v2df __attribute__((vector_size (16)));
+
+v2df
+bar (v4df x, double *p)
+{
+  return (v2df) { x[0], *p };
+}
+
+/* { dg-final { scan-tree-dump "BIT_INSERT_EXPR" "forwprop1" } } */
+/* { dg-final { scan-assembler "movhpd" } } */