[gcc(refs/users/meissner/heads/dmf009)] Improve 64->128 bit zero extension on PowerPC

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

https://gcc.gnu.org/g:46018d188b594f6bd8950ce95affa9f796b90c5b

commit 46018d188b594f6bd8950ce95affa9f796b90c5b
Author: Michael Meissner <meissner@linux.ibm.com>
Date:   Mon Feb 27 17:35:39 2023 -0500

    Improve 64->128 bit zero extension on PowerPC
    
    2023-02-17   Michael Meissner  <meissner@linux.ibm.com>
    
    gcc/
    
            PR target/108958
            * gcc/config/rs6000.md (zero_extendditi2): New insn.
            * ChangeLog.meissner: Update.

Diff:
---
 gcc/ChangeLog.meissner      | 11 ++++++++++
 gcc/config/rs6000/rs6000.md | 52 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 63 insertions(+)

diff --git a/gcc/ChangeLog.meissner b/gcc/ChangeLog.meissner
index 35b2df668c8..355548204e2 100644
--- a/gcc/ChangeLog.meissner
+++ b/gcc/ChangeLog.meissner
@@ -1,3 +1,14 @@
+==================== dmf009 branch, patch #20 ====================
+
+Improve 64->128 bit zero extension on PowerPC
+
+2023-02-17   Michael Meissner  <meissner@linux.ibm.com>
+
+gcc/
+
+	PR target/108958
+	* gcc/config/rs6000.md (zero_extendditi2): New insn.
+
 ==================== work109 branch, patch #17 ====================
 
 Add saturating subtract built-ins.
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index ddb8a6abfca..d23045590c7 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -996,6 +996,58 @@
    (set_attr "dot" "yes")
    (set_attr "length" "4,8")])
 
+(define_insn_and_split "zero_extendditi2"
+  [(set (match_operand:TI 0 "gpc_reg_operand" "=r,r,wa,wa,wa")
+	(zero_extend:TI
+	 (match_operand:DI 1 "reg_or_mem_operand" "r,m,b,Z,wa")))
+   (clobber (match_scratch:DI 2 "=&X,X,X,X,wa"))]
+  "TARGET_POWERPC64 && TARGET_P9_VECTOR"
+  "@
+   #
+   #
+   mtvsrdd %x0,0,%1
+   lxvrdx %x0,%y1
+   #"
+  "&& reload_completed
+   && (int_reg_operand (operands[0], TImode)
+       || (vsx_register_operand (operands[0], TImode)
+	   && vsx_register_operand (operands[1], DImode)))"
+  [(set (match_dup 2) (match_dup 1))
+   (set (match_dup 3) (const_int 0))]
+{
+  rtx dest = operands[0];
+  rtx src = operands[1];
+
+  /* If we are converting a VSX DImode to VSX TImode, we need to move the upper
+     64-bits (DImode) to the lower 64-bits.  We can't just do a xxpermdi
+     instruction to swap the two 64-bit words, because can't rely on the bottom
+     64-bits of the VSX register being 0.  Instead we create a 0 and do the
+     xxpermdi operation to combine the two registers.  */
+  if (vsx_register_operand (dest, TImode)
+      && vsx_register_operand (src, DImode))
+    {
+      rtx tmp = operands[2];
+      emit_move_insn (tmp, const0_rtx);
+
+      rtx hi = tmp;
+      rtx lo = src;
+      if (!BYTES_BIG_ENDIAN)
+	std::swap (hi, lo);
+
+      rtx dest_v2di = gen_rtx_REG (V2DImode, reg_or_subregno (dest));
+      emit_insn (gen_vsx_concat_v2di (dest_v2di, hi, lo));
+      DONE;
+    }
+
+  /* If we are zero extending to a GPR register either from a GPR register,
+     a VSX register or from memory, do the zero extend operation to the
+     lower DI register, and set the upper DI register to 0.  */
+  operands[2] = gen_lowpart (DImode, dest);
+  operands[3] = gen_highpart (DImode, dest);
+}
+  [(set_attr "type" "*,load,vecexts,vecload,vecperm")
+   (set_attr "isa" "*,*,p9v,p10,*")
+   (set_attr "length" "8,8,*,*,8")])
 
 (define_insn "extendqi<mode>2"
   [(set (match_operand:EXTQI 0 "gpc_reg_operand" "=r,?*v")