rs6000-protos.h (expand_block_move): Change prototype.

2019-10-02  Aaron Sawdey <acsawdey@linux.ibm.com>

	* config/rs6000/rs6000-protos.h (expand_block_move): Change prototype.
	* config/rs6000/rs6000-string.c (expand_block_move): Add
	might_overlap parm.
	* config/rs6000/rs6000.md (movmemsi): Add new pattern.
	(cpymemsi): Add might_overlap parm to expand_block_move() call.

From-SVN: r276462

4 files changed, 51 insertions, 34 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index fe14577..5dc5331 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,5 +1,13 @@
 2019-10-02  Aaron Sawdey <acsawdey@linux.ibm.com>
 
+	* config/rs6000/rs6000-protos.h (expand_block_move): Change prototype.
+	* config/rs6000/rs6000-string.c (expand_block_move): Add
+	might_overlap parm.
+	* config/rs6000/rs6000.md (movmemsi): Add new pattern.
+	(cpymemsi): Add might_overlap parm to expand_block_move() call.
+
+2019-10-02  Aaron Sawdey <acsawdey@linux.ibm.com>
+
 	* builtins.c (expand_builtin_memory_copy_args): Add might_overlap parm.
 	(expand_builtin_memcpy): Use might_overlap parm.
 	(expand_builtin_mempcpy_args): Use might_overlap parm.
diff --git a/gcc/config/rs6000/rs6000-protos.h b/gcc/config/rs6000/rs6000-protos.h
index c51b768..08dd88c 100644
--- a/gcc/config/rs6000/rs6000-protos.h
+++ b/gcc/config/rs6000/rs6000-protos.h
@@ -69,7 +69,7 @@ extern void rs6000_generate_float2_code (bool, rtx, rtx, rtx);
 extern void rs6000_generate_float2_double_code (rtx, rtx, rtx);
 extern void rs6000_generate_vsigned2_code (bool, rtx, rtx, rtx);
 extern int expand_block_clear (rtx[]);
-extern int expand_block_move (rtx[]);
+extern int expand_block_move (rtx[], bool);
 extern bool expand_block_compare (rtx[]);
 extern bool expand_strn_compare (rtx[], int);
 extern bool rs6000_is_valid_mask (rtx, int *, int *, machine_mode);
diff --git a/gcc/config/rs6000/rs6000-string.c b/gcc/config/rs6000/rs6000-string.c
index b939185..3bc359e 100644
--- a/gcc/config/rs6000/rs6000-string.c
+++ b/gcc/config/rs6000/rs6000-string.c
@@ -2719,7 +2719,7 @@ gen_lvx_v4si_move (rtx dest, rtx src)
 #define MAX_MOVE_REG 4
 
 int
-expand_block_move (rtx operands[])
+expand_block_move (rtx operands[], bool might_overlap)
 {
   rtx orig_dest = operands[0];
   rtx orig_src	= operands[1];
@@ -2730,6 +2730,7 @@ expand_block_move (rtx operands[])
   int bytes;
   int offset;
   int move_bytes;
+  rtx loads[MAX_MOVE_REG];
   rtx stores[MAX_MOVE_REG];
   int num_reg = 0;
 
@@ -2817,47 +2818,35 @@ expand_block_move (rtx operands[])
 	  gen_func.mov = gen_movqi;
 	}
 
+      /* Mode is always set to something other than BLKmode by one of the 
+	 cases of the if statement above.  */
+      gcc_assert (mode != BLKmode);
+
       src = adjust_address (orig_src, mode, offset);
       dest = adjust_address (orig_dest, mode, offset);
 
-      if (mode != BLKmode)
-	{
-	  rtx tmp_reg = gen_reg_rtx (mode);
+      rtx tmp_reg = gen_reg_rtx (mode);
+      
+      loads[num_reg]    = (*gen_func.mov) (tmp_reg, src);
+      stores[num_reg++] = (*gen_func.mov) (dest, tmp_reg);
 
-	  emit_insn ((*gen_func.mov) (tmp_reg, src));
-	  stores[num_reg++] = (*gen_func.mov) (dest, tmp_reg);
-	}
+      /* If we didn't succeed in doing it in one pass, we can't do it in the 
+	 might_overlap case.  Bail out and return failure.  */
+      if (might_overlap && num_reg >= MAX_MOVE_REG
+	  && bytes > move_bytes)
+	return 0;
 
-      if (mode == BLKmode || num_reg >= MAX_MOVE_REG || bytes == move_bytes)
+      /* Emit loads and stores saved up.  */
+      if (num_reg >= MAX_MOVE_REG || bytes == move_bytes)
 	{
 	  int i;
 	  for (i = 0; i < num_reg; i++)
+	    emit_insn (loads[i]);
+	  for (i = 0; i < num_reg; i++)
 	    emit_insn (stores[i]);
 	  num_reg = 0;
 	}
-
-      if (mode == BLKmode)
-	{
-	  /* Move the address into scratch registers.  The movmemsi
-	     patterns require zero offset.  */
-	  if (!REG_P (XEXP (src, 0)))
-	    {
-	      rtx src_reg = copy_addr_to_reg (XEXP (src, 0));
-	      src = replace_equiv_address (src, src_reg);
-	    }
-	  set_mem_size (src, move_bytes);
-
-	  if (!REG_P (XEXP (dest, 0)))
-	    {
-	      rtx dest_reg = copy_addr_to_reg (XEXP (dest, 0));
-	      dest = replace_equiv_address (dest, dest_reg);
-	    }
-	  set_mem_size (dest, move_bytes);
-
-	  emit_insn ((*gen_func.movmemsi) (dest, src,
-					   GEN_INT (move_bytes & 31),
-					   align_rtx));
-	}
+	
     }
 
   return 1;
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index 4f27f13..2dca269 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -9107,7 +9107,7 @@
     FAIL;
 })
 
-;; String/block move insn.
+;; String/block copy insn (source and destination must not overlap).
 ;; Argument 0 is the destination
 ;; Argument 1 is the source
 ;; Argument 2 is the length
@@ -9120,11 +9120,31 @@
 	      (use (match_operand:SI 3 ""))])]
   ""
 {
-  if (expand_block_move (operands))
+  if (expand_block_move (operands, false))
     DONE;
   else
     FAIL;
 })
+
+;; String/block move insn (source and destination may overlap).
+;; Argument 0 is the destination
+;; Argument 1 is the source
+;; Argument 2 is the length
+;; Argument 3 is the alignment
+
+(define_expand "movmemsi"
+  [(parallel [(set (match_operand:BLK 0 "")
+		   (match_operand:BLK 1 ""))
+	      (use (match_operand:SI 2 ""))
+	      (use (match_operand:SI 3 ""))])]
+  ""
+{
+  if (expand_block_move (operands, true))
+    DONE;
+  else
+    FAIL;
+})
+
 
 ;; Define insns that do load or store with update.  Some of these we can
 ;; get by using pre-decrement or pre-increment, but the hardware can also