rs6000-string.c (expand_block_move): Don't use unaligned vsx and avoid lxvd2x/stxvd2x.

2019-01-03  Aaron Sawdey  <acsawdey@linux.ibm.com>

	* config/rs6000/rs6000-string.c (expand_block_move): Don't use
	unaligned vsx and avoid lxvd2x/stxvd2x.
	(gen_lvx_v4si_move): New function.

From-SVN: r267562

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 40b1fdf..5a15470 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,9 @@
+2019-01-03  Aaron Sawdey  <acsawdey@linux.ibm.com>
+
+       * config/rs6000/rs6000-string.c (expand_block_move): Don't use
+       unaligned vsx and avoid lxvd2x/stxvd2x.
+       (gen_lvx_v4si_move): New function.
+
 2019-01-03  Tom de Vries  <tdevries@suse.de>
 
        * config/nvptx/nvptx.c (MACH_VECTOR_LENGTH, MACH_MAX_WORKERS): Define.

diff --git a/gcc/config/rs6000/rs6000-string.c b/gcc/config/rs6000/rs6000-string.c
index f370397..37e19ed 100644 (file)
--- a/gcc/config/rs6000/rs6000-string.c
+++ b/gcc/config/rs6000/rs6000-string.c
@@ -2669,6 +2669,25 @@ expand_strn_compare (rtx operands[], int no_length)
   return true;
 }
 
+/* Generate loads and stores for a move of v4si mode using lvx/stvx.
+   This uses altivec_{l,st}vx_<mode>_internal which use unspecs to
+   keep combine from changing what instruction gets used.
+
+   DEST is the destination for the data.
+   SRC is the source of the data for the move.  */
+
+static rtx
+gen_lvx_v4si_move (rtx dest, rtx src)
+{
+  gcc_assert (MEM_P (dest) ^ MEM_P (src));
+  gcc_assert (GET_MODE (dest) == V4SImode && GET_MODE (src) == V4SImode);
+
+  if (MEM_P (dest))
+    return gen_altivec_stvx_v4si_internal (dest, src);
+  else 
+    return gen_altivec_lvx_v4si_internal (dest, src);
+}
+
 /* Expand a block move operation, and return 1 if successful.  Return 0
    if we should let the compiler generate normal code.
 
@@ -2721,11 +2740,11 @@ expand_block_move (rtx operands[])
 
       /* Altivec first, since it will be faster than a string move
         when it applies, and usually not significantly larger.  */
-      if (TARGET_ALTIVEC && bytes >= 16 && (TARGET_EFFICIENT_UNALIGNED_VSX || align >= 128))
+      if (TARGET_ALTIVEC && bytes >= 16 && align >= 128)
        {
          move_bytes = 16;
          mode = V4SImode;
-         gen_func.mov = gen_movv4si;
+         gen_func.mov = gen_lvx_v4si_move;
        }
       else if (bytes >= 8 && TARGET_POWERPC64
               && (align >= 64 || !STRICT_ALIGNMENT))