From 28131dfe443772ac5e625914cc341f5be9f8bbc7 Mon Sep 17 00:00:00 2001
From: Richard Earnshaw <rearnsha@arm.com>
Date: Thu, 29 Nov 2012 17:51:40 +0000
Subject: re PR target/55073 (Wrong Neon code generation at -O2 caused by
 -fschedule-insns)

	PR target/55073
	* arm/neon.md (neon_vtrn<mode>_internal): Split into expand
	and insn patterns.  Re-order insn arguments to tie inputs to
	outputs.
	(neon_vzip<mode>_internal): Likewise.
	(neon_vuzp<mode>_internal): Likewise.

	* gcc.target/arm/pr55073.C: New test.

From-SVN: r193943
---
 gcc/config/arm/neon.md | 69 +++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 54 insertions(+), 15 deletions(-)

(limited to 'gcc/config/arm')

diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md
index 8f84795334b..0822049a3e9 100644
--- a/gcc/config/arm/neon.md
+++ b/gcc/config/arm/neon.md
@@ -4411,16 +4411,29 @@
   [(set_attr "neon_type" "neon_bp_3cycle")]
 )
 
-(define_insn "neon_vtrn<mode>_internal"
+(define_expand "neon_vtrn<mode>_internal"
+  [(parallel
+    [(set (match_operand:VDQW 0 "s_register_operand" "")
+	  (unspec:VDQW [(match_operand:VDQW 1 "s_register_operand" "")
+			(match_operand:VDQW 2 "s_register_operand" "")]
+	   UNSPEC_VTRN1))
+     (set (match_operand:VDQW 3 "s_register_operand" "")
+          (unspec:VDQW [(match_dup 1) (match_dup 2)] UNSPEC_VTRN2))])]
+  "TARGET_NEON"
+  ""
+)
+
+;; Note: Different operand numbering to handle tied registers correctly.
+(define_insn "*neon_vtrn<mode>_insn"
   [(set (match_operand:VDQW 0 "s_register_operand" "=w")
         (unspec:VDQW [(match_operand:VDQW 1 "s_register_operand" "0")
-                      (match_operand:VDQW 2 "s_register_operand" "w")]
+                      (match_operand:VDQW 3 "s_register_operand" "2")]
                      UNSPEC_VTRN1))
-   (set (match_operand:VDQW 3 "s_register_operand" "=2")
-         (unspec:VDQW [(match_dup 1) (match_dup 2)]
+   (set (match_operand:VDQW 2 "s_register_operand" "=w")
+         (unspec:VDQW [(match_dup 1) (match_dup 3)]
                      UNSPEC_VTRN2))]
   "TARGET_NEON"
-  "vtrn.<V_sz_elem>\t%<V_reg>0, %<V_reg>3"
+  "vtrn.<V_sz_elem>\t%<V_reg>0, %<V_reg>2"
   [(set (attr "neon_type")
       (if_then_else (match_test "<Is_d_reg>")
                     (const_string "neon_bp_simple")
@@ -4438,16 +4451,29 @@
   DONE;
 })
 
-(define_insn "neon_vzip<mode>_internal"
+(define_expand "neon_vzip<mode>_internal"
+  [(parallel
+    [(set (match_operand:VDQW 0 "s_register_operand" "")
+	  (unspec:VDQW [(match_operand:VDQW 1 "s_register_operand" "")
+	  	        (match_operand:VDQW 2 "s_register_operand" "")]
+		       UNSPEC_VZIP1))
+    (set (match_operand:VDQW 3 "s_register_operand" "")
+	 (unspec:VDQW [(match_dup 1) (match_dup 2)] UNSPEC_VZIP2))])]
+  "TARGET_NEON"
+  ""
+)
+
+;; Note: Different operand numbering to handle tied registers correctly.
+(define_insn "*neon_vzip<mode>_insn"
   [(set (match_operand:VDQW 0 "s_register_operand" "=w")
         (unspec:VDQW [(match_operand:VDQW 1 "s_register_operand" "0")
-                      (match_operand:VDQW 2 "s_register_operand" "w")]
+                      (match_operand:VDQW 3 "s_register_operand" "2")]
                      UNSPEC_VZIP1))
-   (set (match_operand:VDQW 3 "s_register_operand" "=2")
-        (unspec:VDQW [(match_dup 1) (match_dup 2)]
+   (set (match_operand:VDQW 2 "s_register_operand" "=w")
+        (unspec:VDQW [(match_dup 1) (match_dup 3)]
                      UNSPEC_VZIP2))]
   "TARGET_NEON"
-  "vzip.<V_sz_elem>\t%<V_reg>0, %<V_reg>3"
+  "vzip.<V_sz_elem>\t%<V_reg>0, %<V_reg>2"
   [(set (attr "neon_type")
       (if_then_else (match_test "<Is_d_reg>")
                     (const_string "neon_bp_simple")
@@ -4465,16 +4491,29 @@
   DONE;
 })
 
-(define_insn "neon_vuzp<mode>_internal"
+(define_expand "neon_vuzp<mode>_internal"
+  [(parallel
+    [(set (match_operand:VDQW 0 "s_register_operand" "")
+	  (unspec:VDQW [(match_operand:VDQW 1 "s_register_operand" "")
+			(match_operand:VDQW 2 "s_register_operand" "")]
+	   UNSPEC_VUZP1))
+     (set (match_operand:VDQW 3 "s_register_operand" "")
+	  (unspec:VDQW [(match_dup 1) (match_dup 2)] UNSPEC_VUZP2))])]
+  "TARGET_NEON"
+  ""
+)
+
+;; Note: Different operand numbering to handle tied registers correctly.
+(define_insn "*neon_vuzp<mode>_insn"
   [(set (match_operand:VDQW 0 "s_register_operand" "=w")
         (unspec:VDQW [(match_operand:VDQW 1 "s_register_operand" "0")
-                      (match_operand:VDQW 2 "s_register_operand" "w")]
+                      (match_operand:VDQW 3 "s_register_operand" "2")]
                      UNSPEC_VUZP1))
-   (set (match_operand:VDQW 3 "s_register_operand" "=2")
-        (unspec:VDQW [(match_dup 1) (match_dup 2)]
+   (set (match_operand:VDQW 2 "s_register_operand" "=w")
+        (unspec:VDQW [(match_dup 1) (match_dup 3)]
                      UNSPEC_VUZP2))]
   "TARGET_NEON"
-  "vuzp.<V_sz_elem>\t%<V_reg>0, %<V_reg>3"
+  "vuzp.<V_sz_elem>\t%<V_reg>0, %<V_reg>2"
   [(set (attr "neon_type")
       (if_then_else (match_test "<Is_d_reg>")
                     (const_string "neon_bp_simple")
-- 
cgit v1.2.1