diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 13ade946690..f59ab8485ae 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,11 @@
+2015-04-22  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>
+
+	* config/rs6000/rs6000.c (rtx_is_swappable_p): Commentary
+	adjustments.
+	(insn_is_swappable_p): Return 1 for a convert from double to
+	single precision when all of its uses are splats of BE element
+	zero.
+
 2015-04-23  Kugan Vivekanandarajah  <kuganv@linaro.org>
 
 	* ira-costs.c (record_operand_costs): Fix typo (remove redundant code).
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index b55dae2c37b..77f6a869929 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -34245,7 +34245,8 @@ rtx_is_swappable_p (rtx op, unsigned int *special)
 	   order-dependent element, so additional fixup code would be
 	   needed to make those work.  Vector set and non-immediate-form
 	   vector splat are element-order sensitive.  A few of these
-	   cases might be workable with special handling if required.  */
+	   cases might be workable with special handling if required.
+	   Adding cost modeling would be appropriate in some cases.  */
 	int val = XINT (op, 1);
 	switch (val)
 	  {
@@ -34284,12 +34285,6 @@ rtx_is_swappable_p (rtx op, unsigned int *special)
 	  case UNSPEC_VUPKLPX:
 	  case UNSPEC_VUPKLS_V4SF:
 	  case UNSPEC_VUPKLU_V4SF:
-	  /* The following could be handled as an idiom with XXSPLTW.
-	     These place a scalar in BE element zero, but the XXSPLTW
-	     will currently expect it in BE element 2 in a swapped
-	     region.  When one of these feeds an XXSPLTW with no other
-	     defs/uses either way, we can avoid the lane change for
-	     XXSPLTW and things will be correct.  TBD.  */
 	  case UNSPEC_VSX_CVDPSPN:
 	  case UNSPEC_VSX_CVSPDP:
 	  case UNSPEC_VSX_CVSPDPN:
@@ -34380,6 +34375,36 @@ insn_is_swappable_p (swap_web_entry *insn_entry, rtx insn,
 	return 0;
     }
 
+  /* A convert to single precision can be left as is provided that
+     all of its uses are in xxspltw instructions that splat BE element
+     zero.  */
+  if (GET_CODE (body) == SET
+      && GET_CODE (SET_SRC (body)) == UNSPEC
+      && XINT (SET_SRC (body), 1) == UNSPEC_VSX_CVDPSPN)
+    {
+      df_ref def;
+      struct df_insn_info *insn_info = DF_INSN_INFO_GET (insn);
+
+      FOR_EACH_INSN_INFO_DEF (def, insn_info)
+	{
+	  struct df_link *link = DF_REF_CHAIN (def);
+	  if (!link)
+	    return 0;
+
+	  for (; link; link = link->next) {
+	    rtx use_insn = DF_REF_INSN (link->ref);
+	    rtx use_body = PATTERN (use_insn);
+	    if (GET_CODE (use_body) != SET
+		|| GET_CODE (SET_SRC (use_body)) != UNSPEC
+		|| XINT (SET_SRC (use_body), 1) != UNSPEC_VSX_XXSPLTW
+		|| XEXP (XEXP (SET_SRC (use_body), 0), 1) != const0_rtx)
+	      return 0;
+	  }
+	}
+
+      return 1;
+    }
+
   /* Otherwise check the operands for vector lane violations.  */
   return rtx_is_swappable_p (body, special);
 }
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 0b45415afd9..d0e53773c8b 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,7 @@
+2015-04-22  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>
+
+	* gcc.target/powerpc/swaps-p8-18.c: New test.
+
 2015-04-22  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>
 
 	PR target/65456
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-18.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-18.c
new file mode 100644
index 00000000000..c55f527d420
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-18.c
@@ -0,0 +1,35 @@
+/* { dg-do compile { target { powerpc64le-*-* } } } */
+/* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power8" } } */
+/* { dg-options "-mcpu=power8 -O3" } */
+/* { dg-final { scan-assembler-not "xxpermdi" } } */
+
+/* This is a test for a specific convert-splat permute removal.  */
+
+void compute (float*, float*, float*, int, int);
+double test (void);
+double gorp;
+
+int main (void)
+{
+  float X[10000], Y[256], Z[2000];
+  int i;
+  for (i = 0; i < 2500; i++)
+    compute (X, Y, Z, 256, 2000);
+  gorp = test ();
+}
+
+void compute(float *X, float *Y, float *Z, int m, int n)
+{
+  int i, j;
+  float w, *x, *y;
+
+  for (i = 0; i < n; i++)
+    {
+      w = 0.0;
+      x = X++;
+      y = Y;
+      for (j = 0; j < m; j++)
+	w += (*x++) * (*y++);
+      Z[i] = w;
+    }
+}