[gcc(refs/users/meissner/heads/work082)] Improve vsx_extract_<mode>

[Michael Meissner <meissner@gcc.gnu.org>]

https://gcc.gnu.org/g:dccdb5e79c21b11a6a2080ec91ae69a3d6a183d3

commit dccdb5e79c21b11a6a2080ec91ae69a3d6a183d3
Author: Michael Meissner <meissner@linux.ibm.com>
Date:   Wed Mar 23 19:32:02 2022 -0400

    Improve vsx_extract_<mode>
    
    In looking at PR target/99293, I noticed that the code in
    vsx_extract_<mode> could be improved.
    
    When the element being extracted is the element in the upper 64-bits, we
    should do an insn_split to convert this to a simple move.  This would
    allow the post reload passes to eliminate the move completely.
    
    The insn type attribute was incorrect in that it used "mfvsr" instead of
    "vecperm" when a xxpermdi would be generated.  Also, when a "mvfsrld"
    would be generated, the type should be "mfvsr".
    
    2022-03-23   Michael Meissner  <meissner@linux.ibm.com>
    
    gcc/
            PR target/99392
            * config/rs6000/rs6000.md (vsx_extract_<mode>): Split extracts
            that are just a move to being a move insn.  Use the correct insn
            type for the alternatives.
            (insn splitter for vsx_extract_<mode>): Add new splitter.

Diff:
---
 gcc/config/rs6000/vsx.md | 32 ++++++++++++++------------------
 1 file changed, 14 insertions(+), 18 deletions(-)

diff --git a/gcc/config/rs6000/vsx.md b/gcc/config/rs6000/vsx.md
index 75b85409cd8..a3e6e324d33 100644
--- a/gcc/config/rs6000/vsx.md
+++ b/gcc/config/rs6000/vsx.md
@@ -3417,23 +3417,7 @@
   gcc_assert (VSX_REGNO_P (op1_regno));
 
   if (element == VECTOR_ELEMENT_SCALAR_64BIT)
-    {
-      if (op0_regno == op1_regno)
-	return ASM_COMMENT_START " vec_extract to same register";
-
-      else if (INT_REGNO_P (op0_regno) && TARGET_DIRECT_MOVE
-	       && TARGET_POWERPC64)
-	return "mfvsrd %0,%x1";
-
-      else if (FP_REGNO_P (op0_regno) && FP_REGNO_P (op1_regno))
-	return "fmr %0,%1";
-
-      else if (VSX_REGNO_P (op0_regno))
-	return "xxlor %x0,%x1,%x1";
-
-      else
-	gcc_unreachable ();
-    }
+    return "#";
 
   else if (element == VECTOR_ELEMENT_MFVSRLD_64BIT && INT_REGNO_P (op0_regno)
 	   && TARGET_P9_VECTOR && TARGET_POWERPC64 && TARGET_DIRECT_MOVE)
@@ -3451,9 +3435,21 @@
   else
     gcc_unreachable ();
 }
-  [(set_attr "type" "veclogical,mfvsr,mfvsr,vecperm")
+  [(set_attr "type" "vecsimple,vecperm,mfvsr,mfvsr")
    (set_attr "isa" "*,*,p8v,p9v")])
 
+;; Convert extracting the element in the upper 64-bit bits to just a move.
+(define_split
+  [(set (match_operand:<VS_scalar> 0 "gpc_reg_operand")
+	(vec_select:<VS_scalar>
+	 (match_operand:VSX_D 1 "gpc_reg_operand")
+	 (parallel [(match_operand:QI 2 "vsx_scalar_64bit")])))]
+  "VECTOR_MEM_VSX_P (<MODE>mode) && reload_completed"
+  [(set (match_dup 0) (match_dup 3))]
+{
+  operands[3] = gen_rtx_REG (<VS_scalar>mode, reg_or_subregno (operands[1]));
+})
+
 ;; Optimize extracting a single scalar element from memory.
 (define_insn_and_split "*vsx_extract_<P:mode>_<VSX_D:mode>_load"
   [(set (match_operand:<VS_scalar> 0 "register_operand" "=wa,wr")