From: Richard Biener <rguenther@suse.de>
Date: Tue, 23 May 2023 13:12:33 +0000 (+0200)
Subject: Account for vector splat GPR->XMM move cost
X-Git-Tag: basepoints/gcc-15~9002
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=f504b70eb0fc1339322960041a85606df4547897;p=thirdparty%2Fgcc.git

Account for vector splat GPR->XMM move cost

The following also accounts for a GPR->XMM move cost for splat
operations and properly guards eliding the cost when moving from
memory only for SSE4.1 or HImode or larger operands.  This
doesn't fix the PR fully yet.

	PR target/109944
	* config/i386/i386.cc (ix86_vector_costs::add_stmt_cost):
	For vector construction or splats apply GPR->XMM move
	costing.  QImode memory can be handled directly only
	with SSE4.1 pinsrb.
---

diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index 2710c6dfc568..271fbd4e5d87 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -23690,7 +23690,7 @@ ix86_vector_costs::add_stmt_cost (int count, vect_cost_for_stmt kind,
       stmt_cost = ix86_builtin_vectorization_cost (kind, vectype, misalign);
       stmt_cost *= (TYPE_VECTOR_SUBPARTS (vectype) + 1);
     }
-  else if (kind == vec_construct
+  else if ((kind == vec_construct || kind == scalar_to_vec)
 	   && node
 	   && SLP_TREE_DEF_TYPE (node) == vect_external_def
 	   && INTEGRAL_TYPE_P (TREE_TYPE (vectype)))
@@ -23723,7 +23723,9 @@ ix86_vector_costs::add_stmt_cost (int count, vect_cost_for_stmt kind,
 	     Likewise with a BIT_FIELD_REF extracting from a vector
 	     register we can hope to avoid using a GPR.  */
 	  if (!is_gimple_assign (def)
-	      || (!gimple_assign_load_p (def)
+	      || ((!gimple_assign_load_p (def)
+		   || (!TARGET_SSE4_1
+		       && GET_MODE_SIZE (TYPE_MODE (TREE_TYPE (op))) == 1))
 		  && (gimple_assign_rhs_code (def) != BIT_FIELD_REF
 		      || !VECTOR_TYPE_P (TREE_TYPE
 				(TREE_OPERAND (gimple_assign_rhs1 (def), 0))))))