From: Roger Sayle <roger@nextmovesoftware.com>
Date: Tue, 24 May 2022 14:15:12 +0000 (+0100)
Subject: PR tree-optimization/105668: Provide vcond_mask_v1tiv1ti pattern.
X-Git-Tag: basepoints/gcc-14~6468
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=793f847ba7dbe7638f1c27178868edbefd3a8108;p=thirdparty%2Fgcc.git

PR tree-optimization/105668: Provide vcond_mask_v1tiv1ti pattern.

This patch is an alternate/supplementary fix to PR tree-optimization/105668
that provides a vcond_mask_v1titi optab/define_expand to the i386 backend.
An undocumented feature/bug of GCC's vectorization is that any target that
provides a vec_cmpeq<mode><mode> has to also provide a matching
vcond_mask<mode><mode>.  This backend patch preserves the status quo,
rather than fixes the underlying problem.

One aspect of this clean-up is that ix86_expand_sse_movcc provides
fallback implementations using pand/pandn/por that effectively make
V2DImode and V1TImode vcond_mask available on any TARGET_SSE2, not
just TARGET_SSE4_2.  This allows a simplification as V2DI mode can
be handled by using a VI_128 mode iterator instead of a VI124_128
mode iterator, and instead this define_expand is effectively renamed
to provide a V1TImode vcond_mask expander (as V1TI isn't in VI_128).

2022-05-24  Roger Sayle  <roger@nextmovesoftware.com>

gcc/ChangeLog
	PR tree-optimization/105668
	* config/i386/i386-expand.cc (ix86_expand_sse_movcc): Support
	V1TImode, just like V2DImode.
	* config/i386/sse.md (vcond_mask_<mode><sseintvecmodelower>):
	Use VI_128 mode iterator instead of VI124_128 to include V2DI.
	(vcond_mask_v2div2di): Delete.
	(vcond_mask_v1tiv1ti): New define_expand.

gcc/testsuite/ChangeLog
	PR tree-optimization/105668
	* gcc.target/i386/pr105668.c: New test case.
---

diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc
index 1460bcc87a2..e3bd661470b 100644
--- a/gcc/config/i386/i386-expand.cc
+++ b/gcc/config/i386/i386-expand.cc
@@ -4026,6 +4026,7 @@ ix86_expand_sse_movcc (rtx dest, rtx cmp, rtx op_true, rtx op_false)
     case E_V8HFmode:
     case E_V4SImode:
     case E_V2DImode:
+    case E_V1TImode:
       if (TARGET_SSE4_1)
 	{
 	  gen = gen_sse4_1_pblendvb;
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 191371b1081..f261ff60d1c 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -4579,10 +4579,10 @@
 })
 
 (define_expand "vcond_mask_<mode><sseintvecmodelower>"
-  [(set (match_operand:VI124_128 0 "register_operand")
-	(vec_merge:VI124_128
-	  (match_operand:VI124_128 1 "vector_operand")
-	  (match_operand:VI124_128 2 "nonimm_or_0_operand")
+  [(set (match_operand:VI_128 0 "register_operand")
+	(vec_merge:VI_128
+	  (match_operand:VI_128 1 "vector_operand")
+	  (match_operand:VI_128 2 "nonimm_or_0_operand")
 	  (match_operand:<sseintvecmode> 3 "register_operand")))]
   "TARGET_SSE2"
 {
@@ -4591,13 +4591,13 @@
   DONE;
 })
 
-(define_expand "vcond_mask_v2div2di"
-  [(set (match_operand:V2DI 0 "register_operand")
-	(vec_merge:V2DI
-	  (match_operand:V2DI 1 "vector_operand")
-	  (match_operand:V2DI 2 "nonimm_or_0_operand")
-	  (match_operand:V2DI 3 "register_operand")))]
-  "TARGET_SSE4_2"
+(define_expand "vcond_mask_v1tiv1ti"
+  [(set (match_operand:V1TI 0 "register_operand")
+	(vec_merge:V1TI
+	  (match_operand:V1TI 1 "vector_operand")
+	  (match_operand:V1TI 2 "nonimm_or_0_operand")
+	  (match_operand:V1TI 3 "register_operand")))]
+  "TARGET_SSE2"
 {
   ix86_expand_sse_movcc (operands[0], operands[3],
 			 operands[1], operands[2]);
diff --git a/gcc/testsuite/gcc.target/i386/pr105668.c b/gcc/testsuite/gcc.target/i386/pr105668.c
new file mode 100644
index 00000000000..359c2b677a3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr105668.c
@@ -0,0 +1,16 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O -ftracer -fno-tree-fre" } */
+
+typedef __int128 __attribute__((__vector_size__ (16))) V;
+
+int i;
+
+V
+foo (_Complex float f)
+{
+  (void) __builtin_atanhf (i);
+  V v = i != (V) { };
+  i ^= f && 8;
+  v %= 5;
+  return v;
+}