gcc/ChangeLog:

2018-01-10  Kelvin Nilsen  <kelvin@gcc.gnu.org>

	* config/rs6000/rs6000-p8swap.c (rs6000_sum_of_two_registers_p):
	New function.
	(rs6000_quadword_masked_address_p): Likewise.
	(quad_aligned_load_p): Likewise.
	(quad_aligned_store_p): Likewise.
	(const_load_sequence_p): Add comment to describe the outer-most loop.
	(mimic_memory_attributes_and_flags): New function.
	(rs6000_gen_stvx): Likewise.
	(replace_swapped_aligned_store): Likewise.
	(rs6000_gen_lvx): Likewise.
	(replace_swapped_aligned_load): Likewise.
	(replace_swapped_load_constant): Capitalize argument name in
	comment describing this function.
	(rs6000_analyze_swaps): Add a third pass to search for vector loads
	and stores that access quad-word aligned addresses and replace
	with stvx or lvx instructions when appropriate.
	* config/rs6000/rs6000-protos.h (rs6000_sum_of_two_registers_p):
	New function prototype.
	(rs6000_quadword_masked_address_p): Likewise.
	(rs6000_gen_lvx): Likewise.
	(rs6000_gen_stvx): Likewise.
	* config/rs6000/vsx.md (*vsx_le_perm_load_<mode>): For modes
	VSX_D (V2DF, V2DI), modify this split to select lvx instruction
	when memory address is aligned.
	(*vsx_le_perm_load_<mode>): For modes VSX_W (V4SF, V4SI), modify
	this split to select lvx instruction when memory address is aligned.
	(*vsx_le_perm_load_v8hi): Modify this split to select lvx
	instruction when memory address is aligned.
	(*vsx_le_perm_load_v16qi): Likewise.
	(four unnamed splitters): Modify to select the stvx instruction
	when memory is aligned.

gcc/testsuite/ChangeLog:

2018-01-10  Kelvin Nilsen  <kelvin@gcc.gnu.org>

	* gcc.target/powerpc/pr48857.c: Modify dejagnu directives to look
	for lvx and stvx instead of lxvd2x and stxvd2x and require
	little-endian target.  Add comments.
	* gcc.target/powerpc/swaps-p8-28.c: Add functions for more
	comprehensive testing.
	* gcc.target/powerpc/swaps-p8-29.c: Likewise.
	* gcc.target/powerpc/swaps-p8-30.c: Likewise.
	* gcc.target/powerpc/swaps-p8-31.c: Likewise.
	* gcc.target/powerpc/swaps-p8-32.c: Likewise.
	* gcc.target/powerpc/swaps-p8-33.c: Likewise.
	* gcc.target/powerpc/swaps-p8-34.c: Likewise.
	* gcc.target/powerpc/swaps-p8-35.c: Likewise.
	* gcc.target/powerpc/swaps-p8-36.c: Likewise.
	* gcc.target/powerpc/swaps-p8-37.c: Likewise.
	* gcc.target/powerpc/swaps-p8-38.c: Likewise.
	* gcc.target/powerpc/swaps-p8-39.c: Likewise.
	* gcc.target/powerpc/swaps-p8-40.c: Likewise.
	* gcc.target/powerpc/swaps-p8-41.c: Likewise.
	* gcc.target/powerpc/swaps-p8-42.c: Likewise.
	* gcc.target/powerpc/swaps-p8-43.c: Likewise.
	* gcc.target/powerpc/swaps-p8-44.c: Likewise.
	* gcc.target/powerpc/swaps-p8-45.c: Likewise.
	* gcc.target/powerpc/vec-extract-2.c: Add comment and remove
	scan-assembler-not directives that forbid lvx and xxpermdi.
	* gcc.target/powerpc/vec-extract-3.c: Likewise.
	* gcc.target/powerpc/vec-extract-5.c: Likewise.
	* gcc.target/powerpc/vec-extract-6.c: Likewise.
	* gcc.target/powerpc/vec-extract-7.c: Likewise.
	* gcc.target/powerpc/vec-extract-8.c: Likewise.
	* gcc.target/powerpc/vec-extract-9.c: Likewise.
	* gcc.target/powerpc/vsx-vector-6-le.c: Change
	scan-assembler-times directives to reflect different numbers of
	expected xxlnor, xxlor, xvcmpgtdp, and xxland instructions.

libcpp/ChangeLog:

2018-01-10  Kelvin Nilsen  <kelvin@gcc.gnu.org>

	* lex.c (search_line_fast): Remove illegal coercion of an
	unaligned pointer value to vector pointer type and replace with
	use of __builtin_vec_vsx_ld () built-in function, which operates
	on unaligned pointer values.



git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@256656 138bc75d-0d04-0410-961f-82ee72b054a4

34 files changed, 3358 insertions, 146 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index bcc77eb28d9..dd1910df7f8 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,37 @@
+2018-01-10  Kelvin Nilsen  <kelvin@gcc.gnu.org>
+
+	* config/rs6000/rs6000-p8swap.c (rs6000_sum_of_two_registers_p):
+	New function.
+	(rs6000_quadword_masked_address_p): Likewise.
+	(quad_aligned_load_p): Likewise.
+	(quad_aligned_store_p): Likewise.
+	(const_load_sequence_p): Add comment to describe the outer-most loop.
+	(mimic_memory_attributes_and_flags): New function.
+	(rs6000_gen_stvx): Likewise.
+	(replace_swapped_aligned_store): Likewise.
+	(rs6000_gen_lvx): Likewise.
+	(replace_swapped_aligned_load): Likewise.
+	(replace_swapped_load_constant): Capitalize argument name in
+	comment describing this function.
+	(rs6000_analyze_swaps): Add a third pass to search for vector loads
+	and stores that access quad-word aligned addresses and replace
+	with stvx or lvx instructions when appropriate.
+	* config/rs6000/rs6000-protos.h (rs6000_sum_of_two_registers_p):
+	New function prototype.
+	(rs6000_quadword_masked_address_p): Likewise.
+	(rs6000_gen_lvx): Likewise.
+	(rs6000_gen_stvx): Likewise.
+	* config/rs6000/vsx.md (*vsx_le_perm_load_<mode>): For modes
+	VSX_D (V2DF, V2DI), modify this split to select lvx instruction
+	when memory address is aligned.
+	(*vsx_le_perm_load_<mode>): For modes VSX_W (V4SF, V4SI), modify
+	this split to select lvx instruction when memory address is aligned.
+	(*vsx_le_perm_load_v8hi): Modify this split to select lvx
+	instruction when memory address is aligned.
+	(*vsx_le_perm_load_v16qi): Likewise.
+	(four unnamed splitters): Modify to select the stvx instruction
+	when memory is aligned.
+
 2018-01-13  Jan Hubicka  <hubicka@ucw.cz>
 
 	* predict.c (determine_unlikely_bbs): Handle correctly BBs
diff --git a/gcc/config/rs6000/rs6000-p8swap.c b/gcc/config/rs6000/rs6000-p8swap.c
index cb88ffbb535..876f339a79e 100644
--- a/gcc/config/rs6000/rs6000-p8swap.c
+++ b/gcc/config/rs6000/rs6000-p8swap.c
@@ -328,6 +328,142 @@ insn_is_swap_p (rtx insn)
   return 1;
 }
 
+/* Return true iff EXPR represents the sum of two registers.  */
+bool
+rs6000_sum_of_two_registers_p (const_rtx expr)
+{
+  if (GET_CODE (expr) == PLUS)
+    {
+      const_rtx operand1 = XEXP (expr, 0);
+      const_rtx operand2 = XEXP (expr, 1);
+      return (REG_P (operand1) && REG_P (operand2));
+    }
+  return false;
+}
+
+/* Return true iff EXPR represents an address expression that masks off
+   the low-order 4 bits in the style of an lvx or stvx rtl pattern.  */
+bool
+rs6000_quadword_masked_address_p (const_rtx expr)
+{
+  if (GET_CODE (expr) == AND)
+    {
+      const_rtx operand1 = XEXP (expr, 0);
+      const_rtx operand2 = XEXP (expr, 1);
+      if ((REG_P (operand1) || rs6000_sum_of_two_registers_p (operand1))
+	  && CONST_SCALAR_INT_P (operand2) && INTVAL (operand2) == -16)
+	return true;
+    }
+  return false;
+}
+
+/* Return TRUE if INSN represents a swap of a swapped load from memory
+   and the memory address is quad-word aligned.  */
+static bool
+quad_aligned_load_p (swap_web_entry *insn_entry, rtx_insn *insn)
+{
+  unsigned uid = INSN_UID (insn);
+  if (!insn_entry[uid].is_swap || insn_entry[uid].is_load)
+    return false;
+
+  struct df_insn_info *insn_info = DF_INSN_INFO_GET (insn);
+
+  /* Since insn is known to represent a swap instruction, we know it
+     "uses" only one input variable.  */
+  df_ref use = DF_INSN_INFO_USES (insn_info);
+
+  /* Figure out where this input variable is defined.  */
+  struct df_link *def_link = DF_REF_CHAIN (use);
+
+  /* If there is no definition or the definition is artificial or there are
+     multiple definitions, punt.  */
+  if (!def_link || !def_link->ref || DF_REF_IS_ARTIFICIAL (def_link->ref)
+      || def_link->next)
+    return false;
+
+  rtx def_insn = DF_REF_INSN (def_link->ref);
+  unsigned uid2 = INSN_UID (def_insn);
+  /* We're looking for a load-with-swap insn.  If this is not that,
+     return false.  */
+  if (!insn_entry[uid2].is_load || !insn_entry[uid2].is_swap)
+    return false;
+
+  /* If the source of the rtl def is not a set from memory, return
+     false.  */
+  rtx body = PATTERN (def_insn);
+  if (GET_CODE (body) != SET
+      || GET_CODE (SET_SRC (body)) != VEC_SELECT
+      || GET_CODE (XEXP (SET_SRC (body), 0)) != MEM)
+    return false;
+
+  rtx mem = XEXP (SET_SRC (body), 0);
+  rtx base_reg = XEXP (mem, 0);
+  return ((REG_P (base_reg) || rs6000_sum_of_two_registers_p (base_reg))
+	  && MEM_ALIGN (mem) >= 128) ? true : false;
+}
+
+/* Return TRUE if INSN represents a store-with-swap of a swapped value
+   and the memory address is quad-word aligned.  */
+static bool
+quad_aligned_store_p (swap_web_entry *insn_entry, rtx_insn *insn)
+{
+  unsigned uid = INSN_UID (insn);
+  if (!insn_entry[uid].is_swap || !insn_entry[uid].is_store)
+    return false;
+
+  rtx body = PATTERN (insn);
+  rtx dest_address = XEXP (SET_DEST (body), 0);
+  rtx swap_reg = XEXP (SET_SRC (body), 0);
+
+  /* If the base address for the memory expression is not represented
+     by a single register and is not the sum of two registers, punt.  */
+  if (!REG_P (dest_address) && !rs6000_sum_of_two_registers_p (dest_address))
+    return false;
+
+  /* Confirm that the value to be stored is produced by a swap
+     instruction.  */
+  struct df_insn_info *insn_info = DF_INSN_INFO_GET (insn);
+  df_ref use;
+  FOR_EACH_INSN_INFO_USE (use, insn_info)
+    {
+      struct df_link *def_link = DF_REF_CHAIN (use);
+
+      /* If this is not the definition of the candidate swap register,
+	 then skip it.  I am interested in a different definition.  */
+      if (!rtx_equal_p (DF_REF_REG (use), swap_reg))
+	continue;
+
+      /* If there is no def or the def is artifical or there are
+	 multiple defs, punt.  */
+      if (!def_link || !def_link->ref || DF_REF_IS_ARTIFICIAL (def_link->ref)
+	  || def_link->next)
+	return false;
+
+      rtx def_insn = DF_REF_INSN (def_link->ref);
+      unsigned uid2 = INSN_UID (def_insn);
+
+      /* If this source value is not a simple swap, return false */
+      if (!insn_entry[uid2].is_swap || insn_entry[uid2].is_load
+	  || insn_entry[uid2].is_store)
+	return false;
+
+      /* I've processed the use that I care about, so break out of
+	 this loop.  */
+      break;
+    }
+
+  /* At this point, we know the source data comes from a swap.  The
+     remaining question is whether the memory address is aligned.  */
+  rtx set = single_set (insn);
+  if (set)
+    {
+      rtx dest = SET_DEST (set);
+      if (MEM_P (dest))
+	return (MEM_ALIGN (dest) >= 128);
+    }
+  return false;
+}
+
 /* Return 1 iff UID, known to reference a swap, is both fed by a load
    and a feeder of a store.  */
 static unsigned int
@@ -372,6 +508,9 @@ const_load_sequence_p (swap_web_entry *insn_entry, rtx insn)
 
   struct df_insn_info *insn_info = DF_INSN_INFO_GET (insn);
   df_ref use;
+
+  /* Iterate over the definitions that are used by this insn.  Since
+     this is known to be a swap insn, expect only one used definnition.  */
   FOR_EACH_INSN_INFO_USE (use, insn_info)
     {
       struct df_link *def_link = DF_REF_CHAIN (use);
@@ -1353,7 +1492,326 @@ replace_swap_with_copy (swap_web_entry *insn_entry, unsigned i)
   insn->set_deleted ();
 }
 
-/* Given that swap_insn represents a swap of a load of a constant
+/* Make NEW_MEM_EXP's attributes and flags resemble those of
+   ORIGINAL_MEM_EXP.  */
+static void
+mimic_memory_attributes_and_flags (rtx new_mem_exp, const_rtx original_mem_exp)
+{
+  RTX_FLAG (new_mem_exp, jump) = RTX_FLAG (original_mem_exp, jump);
+  RTX_FLAG (new_mem_exp, call) = RTX_FLAG (original_mem_exp, call);
+  RTX_FLAG (new_mem_exp, unchanging) = RTX_FLAG (original_mem_exp, unchanging);
+  RTX_FLAG (new_mem_exp, volatil) = RTX_FLAG (original_mem_exp, volatil);
+  RTX_FLAG (new_mem_exp, frame_related) =
+    RTX_FLAG (original_mem_exp, frame_related);
+
+  /* The following fields may not be used with MEM subexpressions */
+  RTX_FLAG (new_mem_exp, in_struct) = RTX_FLAG (original_mem_exp, in_struct);
+  RTX_FLAG (new_mem_exp, return_val) = RTX_FLAG (original_mem_exp, return_val);
+
+  struct mem_attrs original_attrs = *get_mem_attrs(original_mem_exp);
+
+  alias_set_type set = original_attrs.alias;
+  set_mem_alias_set (new_mem_exp, set);
+
+  addr_space_t addrspace = original_attrs.addrspace;
+  set_mem_addr_space (new_mem_exp, addrspace);
+
+  unsigned int align = original_attrs.align;
+  set_mem_align (new_mem_exp, align);
+
+  tree expr = original_attrs.expr;
+  set_mem_expr (new_mem_exp, expr);
+
+  if (original_attrs.offset_known_p)
+    {
+      HOST_WIDE_INT offset = original_attrs.offset;
+      set_mem_offset (new_mem_exp, offset);
+    }
+  else
+    clear_mem_offset (new_mem_exp);
+
+  if (original_attrs.size_known_p)
+    {
+      HOST_WIDE_INT size = original_attrs.size;
+      set_mem_size (new_mem_exp, size);
+    }
+  else
+    clear_mem_size (new_mem_exp);
+}
+
+/* Generate an rtx expression to represent use of the stvx insn to store
+   the value represented by register SRC_EXP into the memory at address
+   DEST_EXP, with vector mode MODE.  */
+rtx
+rs6000_gen_stvx (enum machine_mode mode, rtx dest_exp, rtx src_exp)
+{
+  rtx memory_address = XEXP (dest_exp, 0);
+  rtx stvx;
+
+  if (rs6000_sum_of_two_registers_p (memory_address))
+    {
+      rtx op1, op2;
+      op1 = XEXP (memory_address, 0);
+      op2 = XEXP (memory_address, 1);
+      if (mode == V16QImode)
+	stvx = gen_altivec_stvx_v16qi_2op (src_exp, op1, op2);
+      else if (mode == V8HImode)
+	stvx = gen_altivec_stvx_v8hi_2op (src_exp, op1, op2);
+#ifdef HAVE_V8HFmode
+      else if (mode == V8HFmode)
+	stvx = gen_altivec_stvx_v8hf_2op (src_exp, op1, op2);
+#endif
+      else if (mode == V4SImode)
+	stvx = gen_altivec_stvx_v4si_2op (src_exp, op1, op2);
+      else if (mode == V4SFmode)
+	stvx = gen_altivec_stvx_v4sf_2op (src_exp, op1, op2);
+      else if (mode == V2DImode)
+	stvx = gen_altivec_stvx_v2di_2op (src_exp, op1, op2);
+      else if (mode == V2DFmode)
+	stvx = gen_altivec_stvx_v2df_2op (src_exp, op1, op2);
+      else if (mode == V1TImode)
+	stvx = gen_altivec_stvx_v1ti_2op (src_exp, op1, op2);
+      else
+	/* KFmode, TFmode, other modes not expected in this context.  */
+	gcc_unreachable ();
+    }
+  else				/* REG_P (memory_address) */
+    {
+      if (mode == V16QImode)
+	stvx = gen_altivec_stvx_v16qi_1op (src_exp, memory_address);
+      else if (mode == V8HImode)
+	stvx = gen_altivec_stvx_v8hi_1op (src_exp, memory_address);
+#ifdef HAVE_V8HFmode
+      else if (mode == V8HFmode)
+	stvx = gen_altivec_stvx_v8hf_1op (src_exp, memory_address);
+#endif
+      else if (mode == V4SImode)
+	stvx = gen_altivec_stvx_v4si_1op (src_exp, memory_address);
+      else if (mode == V4SFmode)
+	stvx = gen_altivec_stvx_v4sf_1op (src_exp, memory_address);
+      else if (mode == V2DImode)
+	stvx = gen_altivec_stvx_v2di_1op (src_exp, memory_address);
+      else if (mode == V2DFmode)
+	stvx = gen_altivec_stvx_v2df_1op (src_exp, memory_address);
+      else if (mode == V1TImode)
+	stvx = gen_altivec_stvx_v1ti_1op (src_exp, memory_address);
+      else
+	/* KFmode, TFmode, other modes not expected in this context.  */
+	gcc_unreachable ();
+    }
+
+  rtx new_mem_exp = SET_DEST (stvx);
+  mimic_memory_attributes_and_flags (new_mem_exp, dest_exp);
+  return stvx;
+}
+
+/* Given that STORE_INSN represents an aligned store-with-swap of a
+   swapped value, replace the store with an aligned store (without
+   swap) and replace the swap with a copy insn.  */
+static void
+replace_swapped_aligned_store (swap_web_entry *insn_entry,
+			       rtx_insn *store_insn)
+{
+  unsigned uid = INSN_UID (store_insn);
+  gcc_assert (insn_entry[uid].is_swap && insn_entry[uid].is_store);
+
+  rtx body = PATTERN (store_insn);
+  rtx dest_address = XEXP (SET_DEST (body), 0);
+  rtx swap_reg = XEXP (SET_SRC (body), 0);
+  gcc_assert (REG_P (dest_address)
+	      || rs6000_sum_of_two_registers_p (dest_address));
+
+  /* Find the swap instruction that provides the value to be stored by
+   * this store-with-swap instruction. */
+  struct df_insn_info *insn_info = DF_INSN_INFO_GET (store_insn);
+  df_ref use;
+  rtx_insn *swap_insn = NULL;
+  unsigned uid2 = 0;
+  FOR_EACH_INSN_INFO_USE (use, insn_info)
+    {
+      struct df_link *def_link = DF_REF_CHAIN (use);
+
+      /* if this is not the definition of the candidate swap register,
+	 then skip it.  I am only interested in the swap insnd.  */
+      if (!rtx_equal_p (DF_REF_REG (use), swap_reg))
+	continue;
+
+      /* If there is no def or the def is artifical or there are
+	 multiple defs, we should not be here.  */
+      gcc_assert (def_link && def_link->ref && !def_link->next
+		  && !DF_REF_IS_ARTIFICIAL (def_link->ref));
+
+      swap_insn = DF_REF_INSN (def_link->ref);
+      uid2 = INSN_UID (swap_insn);
+
+      /* If this source value is not a simple swap, we should not be here.  */
+      gcc_assert (insn_entry[uid2].is_swap && !insn_entry[uid2].is_load
+		  && !insn_entry[uid2].is_store);
+
+      /* We've processed the use we care about, so break out of
+	 this loop.  */
+      break;
+    }
+
+  /* At this point, swap_insn and uid2 represent the swap instruction
+     that feeds the store.  */
+  gcc_assert (swap_insn);
+  rtx set = single_set (store_insn);
+  gcc_assert (set);
+  rtx dest_exp = SET_DEST (set);
+  rtx src_exp = XEXP (SET_SRC (body), 0);
+  enum machine_mode mode = GET_MODE (dest_exp);
+  gcc_assert (MEM_P (dest_exp));
+  gcc_assert (MEM_ALIGN (dest_exp) >= 128);
+
+  /* Replace the copy with a new insn.  */
+  rtx stvx;
+  stvx = rs6000_gen_stvx (mode, dest_exp, src_exp);
+
+  rtx_insn *new_insn = emit_insn_before (stvx, store_insn);
+  rtx new_body = PATTERN (new_insn);
+
+  gcc_assert ((GET_CODE (new_body) == SET)
+	      && (GET_CODE (SET_DEST (new_body)) == MEM));
+
+  set_block_for_insn (new_insn, BLOCK_FOR_INSN (store_insn));
+  df_insn_rescan (new_insn);
+
+  df_insn_delete (store_insn);
+  remove_insn (store_insn);
+  store_insn->set_deleted ();
+
+  /* Replace the swap with a copy.  */
+  uid2 = INSN_UID (swap_insn);
+  mark_swaps_for_removal (insn_entry, uid2);
+  replace_swap_with_copy (insn_entry, uid2);
+}
+
+/* Generate an rtx expression to represent use of the lvx insn to load
+   from memory SRC_EXP into register DEST_EXP with vector mode MODE. */
+rtx
+rs6000_gen_lvx (enum machine_mode mode, rtx dest_exp, rtx src_exp)
+{
+  rtx memory_address = XEXP (src_exp, 0);
+  rtx lvx;
+
+  if (rs6000_sum_of_two_registers_p (memory_address))
+    {
+      rtx op1, op2;
+      op1 = XEXP (memory_address, 0);
+      op2 = XEXP (memory_address, 1);
+
+      if (mode == V16QImode)
+	lvx = gen_altivec_lvx_v16qi_2op (dest_exp, op1, op2);
+      else if (mode == V8HImode)
+	lvx = gen_altivec_lvx_v8hi_2op (dest_exp, op1, op2);
+#ifdef HAVE_V8HFmode
+      else if (mode == V8HFmode)
+	lvx = gen_altivec_lvx_v8hf_2op (dest_exp, op1, op2);
+#endif
+      else if (mode == V4SImode)
+	lvx = gen_altivec_lvx_v4si_2op (dest_exp, op1, op2);
+      else if (mode == V4SFmode)
+	lvx = gen_altivec_lvx_v4sf_2op (dest_exp, op1, op2);
+      else if (mode == V2DImode)
+	lvx = gen_altivec_lvx_v2di_2op (dest_exp, op1, op2);
+      else if (mode == V2DFmode)
+	lvx = gen_altivec_lvx_v2df_2op (dest_exp, op1, op2);
+      else if (mode == V1TImode)
+	lvx = gen_altivec_lvx_v1ti_2op (dest_exp, op1, op2);
+      else
+	/* KFmode, TFmode, other modes not expected in this context.  */
+	gcc_unreachable ();
+    }
+  else				/* REG_P (memory_address) */
+    {
+      if (mode == V16QImode)
+	lvx = gen_altivec_lvx_v16qi_1op (dest_exp, memory_address);
+      else if (mode == V8HImode)
+	lvx = gen_altivec_lvx_v8hi_1op (dest_exp, memory_address);
+#ifdef HAVE_V8HFmode
+      else if (mode == V8HFmode)
+	lvx = gen_altivec_lvx_v8hf_1op (dest_exp, memory_address);
+#endif
+      else if (mode == V4SImode)
+	lvx = gen_altivec_lvx_v4si_1op (dest_exp, memory_address);
+      else if (mode == V4SFmode)
+	lvx = gen_altivec_lvx_v4sf_1op (dest_exp, memory_address);
+      else if (mode == V2DImode)
+	lvx = gen_altivec_lvx_v2di_1op (dest_exp, memory_address);
+      else if (mode == V2DFmode)
+	lvx = gen_altivec_lvx_v2df_1op (dest_exp, memory_address);
+      else if (mode == V1TImode)
+	lvx = gen_altivec_lvx_v1ti_1op (dest_exp, memory_address);
+      else
+	/* KFmode, TFmode, other modes not expected in this context.  */
+	gcc_unreachable ();
+    }
+
+  rtx new_mem_exp = SET_SRC (lvx);
+  mimic_memory_attributes_and_flags (new_mem_exp, src_exp);
+
+  return lvx;
+}
+
+/* Given that SWAP_INSN represents a swap of an aligned
+   load-with-swap, replace the load with an aligned load (without
+   swap) and replace the swap with a copy insn.  */
+static void
+replace_swapped_aligned_load (swap_web_entry *insn_entry, rtx swap_insn)
+{
+  /* Find the load.  */
+  unsigned uid = INSN_UID (swap_insn);
+  /* Only call this if quad_aligned_load_p (swap_insn).  */
+  gcc_assert (insn_entry[uid].is_swap && !insn_entry[uid].is_load);
+  struct df_insn_info *insn_info = DF_INSN_INFO_GET (swap_insn);
+
+  /* Since insn is known to represent a swap instruction, we know it
+     "uses" only one input variable.  */
+  df_ref use = DF_INSN_INFO_USES (insn_info);
+
+  /* Figure out where this input variable is defined.  */
+  struct df_link *def_link = DF_REF_CHAIN (use);
+  gcc_assert (def_link && !def_link->next);
+  gcc_assert (def_link && def_link->ref &&
+	      !DF_REF_IS_ARTIFICIAL (def_link->ref) && !def_link->next);
+
+  rtx_insn *def_insn = DF_REF_INSN (def_link->ref);
+  unsigned uid2 = INSN_UID (def_insn);
+
+  /* We're expecting a load-with-swap insn.  */
+  gcc_assert (insn_entry[uid2].is_load && insn_entry[uid2].is_swap);
+
+  /* We expect this to be a set to memory, with source representing a
+     swap (indicated by code VEC_SELECT).  */
+  rtx body = PATTERN (def_insn);
+  gcc_assert ((GET_CODE (body) == SET)
+	      && (GET_CODE (SET_SRC (body)) == VEC_SELECT)
+	      && (GET_CODE (XEXP (SET_SRC (body), 0)) == MEM));
+
+  rtx src_exp = XEXP (SET_SRC (body), 0);
+  enum machine_mode mode = GET_MODE (src_exp);
+  rtx lvx = rs6000_gen_lvx (mode, SET_DEST (body), src_exp);
+
+  rtx_insn *new_insn = emit_insn_before (lvx, def_insn);
+  rtx new_body = PATTERN (new_insn);
+
+  gcc_assert ((GET_CODE (new_body) == SET)
+	      && (GET_CODE (SET_SRC (new_body)) == MEM));
+
+  set_block_for_insn (new_insn, BLOCK_FOR_INSN (def_insn));
+  df_insn_rescan (new_insn);
+
+  df_insn_delete (def_insn);
+  remove_insn (def_insn);
+  def_insn->set_deleted ();
+
+  /* Replace the swap with a copy.  */
+  mark_swaps_for_removal (insn_entry, uid);
+  replace_swap_with_copy (insn_entry, uid);
+}
+
+/* Given that SWAP_INSN represents a swap of a load of a constant
    vector value, replace with a single instruction that loads a
    swapped variant of the original constant.
 
@@ -2144,8 +2602,17 @@ rs6000_analyze_swaps (function *fun)
   /* Clean up.  */
   free (insn_entry);
 
-  /* Use additional pass over rtl to replace swap(load(vector constant))
-     with load(swapped vector constant). */
+  /* Use a second pass over rtl to detect that certain vector values
+     fetched from or stored to memory on quad-word aligned addresses
+     can use lvx/stvx without swaps.  */
+
+  /* First, rebuild ud chains.  */
+  df_remove_problem (df_chain);
+  df_process_deferred_rescans ();
+  df_set_flags (DF_RD_PRUNE_DEAD_DEFS);
+  df_chain_add_problem (DF_UD_CHAIN);
+  df_analyze ();
+
   swap_web_entry *pass2_insn_entry;
   pass2_insn_entry = XCNEWVEC (swap_web_entry, get_max_uid ());
 
@@ -2174,13 +2641,69 @@ rs6000_analyze_swaps (function *fun)
     if (pass2_insn_entry[i].is_swap && !pass2_insn_entry[i].is_load
 	&& !pass2_insn_entry[i].is_store)
       {
-	insn = pass2_insn_entry[i].insn;
-	if (const_load_sequence_p (pass2_insn_entry, insn))
-	  replace_swapped_load_constant (pass2_insn_entry, insn);
+	/* Replace swap of aligned load-swap with aligned unswapped
+	   load.  */
+	rtx_insn *rtx_insn = pass2_insn_entry[i].insn;
+	if (quad_aligned_load_p (pass2_insn_entry, rtx_insn))
+	  replace_swapped_aligned_load (pass2_insn_entry, rtx_insn);
+      }
+    else if (pass2_insn_entry[i].is_swap && pass2_insn_entry[i].is_store)
+      {
+	/* Replace aligned store-swap of swapped value with aligned
+	   unswapped store.  */
+	rtx_insn *rtx_insn = pass2_insn_entry[i].insn;
+	if (quad_aligned_store_p (pass2_insn_entry, rtx_insn))
+	  replace_swapped_aligned_store (pass2_insn_entry, rtx_insn);
       }
 
   /* Clean up.  */
   free (pass2_insn_entry);
+
+  /* Use a third pass over rtl to replace swap(load(vector constant))
+     with load(swapped vector constant).  */
+
+  /* First, rebuild ud chains.  */
+  df_remove_problem (df_chain);
+  df_process_deferred_rescans ();
+  df_set_flags (DF_RD_PRUNE_DEAD_DEFS);
+  df_chain_add_problem (DF_UD_CHAIN);
+  df_analyze ();
+
+  swap_web_entry *pass3_insn_entry;
+  pass3_insn_entry = XCNEWVEC (swap_web_entry, get_max_uid ());
+
+  /* Walk the insns to gather basic data.  */
+  FOR_ALL_BB_FN (bb, fun)
+    FOR_BB_INSNS_SAFE (bb, insn, curr_insn)
+    {
+      unsigned int uid = INSN_UID (insn);
+      if (NONDEBUG_INSN_P (insn))
+	{
+	  pass3_insn_entry[uid].insn = insn;
+
+	  pass3_insn_entry[uid].is_relevant = 1;
+	  pass3_insn_entry[uid].is_load = insn_is_load_p (insn);
+	  pass3_insn_entry[uid].is_store = insn_is_store_p (insn);
+
+	  /* Determine if this is a doubleword swap.  If not,
+	     determine whether it can legally be swapped.  */
+	  if (insn_is_swap_p (insn))
+	    pass3_insn_entry[uid].is_swap = 1;
+	}
+    }
+
+  e = get_max_uid ();
+  for (unsigned i = 0; i < e; ++i)
+    if (pass3_insn_entry[i].is_swap && !pass3_insn_entry[i].is_load
+	&& !pass3_insn_entry[i].is_store)
+      {
+	insn = pass3_insn_entry[i].insn;
+	if (const_load_sequence_p (pass3_insn_entry, insn))
+	  replace_swapped_load_constant (pass3_insn_entry, insn);
+      }
+
+  /* Clean up.  */
+  free (pass3_insn_entry);
   return 0;
 }
 
diff --git a/gcc/config/rs6000/rs6000-protos.h b/gcc/config/rs6000/rs6000-protos.h
index 1f96005c010..9c6c9a61c15 100644
--- a/gcc/config/rs6000/rs6000-protos.h
+++ b/gcc/config/rs6000/rs6000-protos.h
@@ -254,5 +254,9 @@ namespace gcc { class context; }
 class rtl_opt_pass;
 
 extern rtl_opt_pass *make_pass_analyze_swaps (gcc::context *);
+extern bool rs6000_sum_of_two_registers_p (const_rtx expr);
+extern bool rs6000_quadword_masked_address_p (const_rtx exp);
+extern rtx rs6000_gen_lvx (enum machine_mode, rtx, rtx);
+extern rtx rs6000_gen_stvx (enum machine_mode, rtx, rtx);
 
 #endif  /* rs6000-protos.h */
diff --git a/gcc/config/rs6000/vsx.md b/gcc/config/rs6000/vsx.md
index e0d76b1e382..6762a00beaa 100644
--- a/gcc/config/rs6000/vsx.md
+++ b/gcc/config/rs6000/vsx.md
@@ -434,7 +434,7 @@
         (match_operand:VSX_D 1 "indexed_or_indirect_operand" "Z"))]
   "!BYTES_BIG_ENDIAN && TARGET_VSX && !TARGET_P9_VECTOR"
   "#"
-  "!BYTES_BIG_ENDIAN && TARGET_VSX && !TARGET_P9_VECTOR"
+  "&& 1"
   [(set (match_dup 2)
         (vec_select:<MODE>
           (match_dup 1)
@@ -445,6 +445,33 @@
           (parallel [(const_int 1) (const_int 0)])))]
   "
 {
+  rtx mem = operands[1];
+
+  /* Don't apply the swap optimization if we've already performed register
+     allocation and the hard register destination is not in the altivec
+     range.  */
+  if ((MEM_ALIGN (mem) >= 128)
+      && ((reg_or_subregno (operands[0]) >= FIRST_PSEUDO_REGISTER)
+	  || ALTIVEC_REGNO_P (reg_or_subregno (operands[0]))))
+    {
+      rtx mem_address = XEXP (mem, 0);
+      enum machine_mode mode = GET_MODE (mem);
+
+      if (REG_P (mem_address) || rs6000_sum_of_two_registers_p (mem_address))
+        {
+	  /* Replace the source memory address with masked address.  */
+          rtx lvx_set_expr = rs6000_gen_lvx (mode, operands[0], mem);
+	  emit_insn (lvx_set_expr);
+	  DONE;
+        }
+      else if (rs6000_quadword_masked_address_p (mem_address))
+        {
+	  /* This rtl is already in the form that matches lvx
+	     instruction, so leave it alone.  */
+	  DONE;
+        }
+      /* Otherwise, fall through to transform into a swapping load.  */
+    }
   operands[2] = can_create_pseudo_p () ? gen_reg_rtx_and_attrs (operands[0])
                                        : operands[0];
 }
@@ -457,7 +484,7 @@
         (match_operand:VSX_W 1 "indexed_or_indirect_operand" "Z"))]
   "!BYTES_BIG_ENDIAN && TARGET_VSX && !TARGET_P9_VECTOR"
   "#"
-  "!BYTES_BIG_ENDIAN && TARGET_VSX && !TARGET_P9_VECTOR"
+  "&& 1"
   [(set (match_dup 2)
         (vec_select:<MODE>
           (match_dup 1)
@@ -470,6 +497,33 @@
                      (const_int 0) (const_int 1)])))]
   "
 {
+  rtx mem = operands[1];
+
+  /* Don't apply the swap optimization if we've already performed register
+     allocation and the hard register destination is not in the altivec
+     range.  */
+  if ((MEM_ALIGN (mem) >= 128)
+      && ((REGNO(operands[0]) >= FIRST_PSEUDO_REGISTER)
+	  || ALTIVEC_REGNO_P (REGNO(operands[0]))))
+    {
+      rtx mem_address = XEXP (mem, 0);
+      enum machine_mode mode = GET_MODE (mem);
+
+      if (REG_P (mem_address) || rs6000_sum_of_two_registers_p (mem_address))
+        {
+	  /* Replace the source memory address with masked address.  */
+          rtx lvx_set_expr = rs6000_gen_lvx (mode, operands[0], mem);
+	  emit_insn (lvx_set_expr);
+	  DONE;
+        }
+      else if (rs6000_quadword_masked_address_p (mem_address))
+        {
+	  /* This rtl is already in the form that matches lvx
+	     instruction, so leave it alone.  */
+	  DONE;
+        }
+      /* Otherwise, fall through to transform into a swapping load.  */
+    }
   operands[2] = can_create_pseudo_p () ? gen_reg_rtx_and_attrs (operands[0])
                                        : operands[0];
 }
@@ -482,7 +536,7 @@
         (match_operand:V8HI 1 "indexed_or_indirect_operand" "Z"))]
   "!BYTES_BIG_ENDIAN && TARGET_VSX && !TARGET_P9_VECTOR"
   "#"
-  "!BYTES_BIG_ENDIAN && TARGET_VSX && !TARGET_P9_VECTOR"
+  "&& 1"
   [(set (match_dup 2)
         (vec_select:V8HI
           (match_dup 1)
@@ -499,6 +553,33 @@
                      (const_int 2) (const_int 3)])))]
   "
 {
+  rtx mem = operands[1];
+
+  /* Don't apply the swap optimization if we've already performed register
+     allocation and the hard register destination is not in the altivec
+     range.  */
+  if ((MEM_ALIGN (mem) >= 128)
+      && ((REGNO(operands[0]) >= FIRST_PSEUDO_REGISTER)
+	  || ALTIVEC_REGNO_P (REGNO(operands[0]))))
+    {
+      rtx mem_address = XEXP (mem, 0);
+      enum machine_mode mode = GET_MODE (mem);
+
+      if (REG_P (mem_address) || rs6000_sum_of_two_registers_p (mem_address))
+        {
+	  /* Replace the source memory address with masked address.  */
+	  rtx lvx_set_expr = rs6000_gen_lvx (mode, operands[0], mem);
+	  emit_insn (lvx_set_expr);
+	  DONE;
+        }
+      else if (rs6000_quadword_masked_address_p (mem_address))
+        {
+	  /* This rtl is already in the form that matches lvx
+	     instruction, so leave it alone.  */
+	  DONE;
+        }
+      /* Otherwise, fall through to transform into a swapping load.  */
+    }
   operands[2] = can_create_pseudo_p () ? gen_reg_rtx_and_attrs (operands[0])
                                        : operands[0];
 }
@@ -511,7 +592,7 @@
         (match_operand:V16QI 1 "indexed_or_indirect_operand" "Z"))]
   "!BYTES_BIG_ENDIAN && TARGET_VSX && !TARGET_P9_VECTOR"
   "#"
-  "!BYTES_BIG_ENDIAN && TARGET_VSX && !TARGET_P9_VECTOR"
+  "&& 1"
   [(set (match_dup 2)
         (vec_select:V16QI
           (match_dup 1)
@@ -536,6 +617,33 @@
                      (const_int 6) (const_int 7)])))]
   "
 {
+  rtx mem = operands[1];
+
+  /* Don't apply the swap optimization if we've already performed register
+     allocation and the hard register destination is not in the altivec
+     range.  */
+  if ((MEM_ALIGN (mem) >= 128)
+      && ((REGNO(operands[0]) >= FIRST_PSEUDO_REGISTER)
+	  || ALTIVEC_REGNO_P (REGNO(operands[0]))))
+    {
+      rtx mem_address = XEXP (mem, 0);
+      enum machine_mode mode = GET_MODE (mem);
+
+      if (REG_P (mem_address) || rs6000_sum_of_two_registers_p (mem_address))
+        {
+	  /* Replace the source memory address with masked address.  */
+	  rtx lvx_set_expr = rs6000_gen_lvx (mode, operands[0], mem);
+	  emit_insn (lvx_set_expr);
+	  DONE;
+        }
+      else if (rs6000_quadword_masked_address_p (mem_address))
+        {
+	  /* This rtl is already in the form that matches lvx
+	     instruction, so leave it alone.  */
+	  DONE;
+        }
+      /* Otherwise, fall through to transform into a swapping load.  */
+    }
   operands[2] = can_create_pseudo_p () ? gen_reg_rtx_and_attrs (operands[0])
                                        : operands[0];
 }
@@ -564,6 +672,31 @@
           (match_dup 2)
           (parallel [(const_int 1) (const_int 0)])))]
 {
+  rtx mem = operands[0];
+
+  /* Don't apply the swap optimization if we've already performed register
+     allocation and the hard register source is not in the altivec range.  */
+  if ((MEM_ALIGN (mem) >= 128)
+      && ((reg_or_subregno (operands[1]) >= FIRST_PSEUDO_REGISTER)
+          || ALTIVEC_REGNO_P (reg_or_subregno (operands[1]))))
+    {
+      rtx mem_address = XEXP (mem, 0);
+      enum machine_mode mode = GET_MODE (mem);
+      if (REG_P (mem_address) || rs6000_sum_of_two_registers_p (mem_address))
+	{
+	  rtx stvx_set_expr = rs6000_gen_stvx (mode, mem, operands[1]);
+	  emit_insn (stvx_set_expr);
+	  DONE;
+	}
+      else if (rs6000_quadword_masked_address_p (mem_address))
+	{
+	  /* This rtl is already in the form that matches stvx instruction,
+	     so leave it alone.  */
+	  DONE;
+	}
+      /* Otherwise, fall through to transform into a swapping store.  */
+    }
+
   operands[2] = can_create_pseudo_p () ? gen_reg_rtx_and_attrs (operands[1]) 
                                        : operands[1];
 })
@@ -611,6 +744,31 @@
           (parallel [(const_int 2) (const_int 3)
 	             (const_int 0) (const_int 1)])))]
 {
+  rtx mem = operands[0];
+
+  /* Don't apply the swap optimization if we've already performed register
+     allocation and the hard register source is not in the altivec range.  */
+  if ((MEM_ALIGN (mem) >= 128)
+      && ((reg_or_subregno (operands[1]) >= FIRST_PSEUDO_REGISTER)
+          || ALTIVEC_REGNO_P (reg_or_subregno (operands[1]))))
+    {
+      rtx mem_address = XEXP (mem, 0);
+      enum machine_mode mode = GET_MODE (mem);
+      if (REG_P (mem_address) || rs6000_sum_of_two_registers_p (mem_address))
+	{
+	  rtx stvx_set_expr = rs6000_gen_stvx (mode, mem, operands[1]);
+	  emit_insn (stvx_set_expr);
+	  DONE;
+	}
+      else if (rs6000_quadword_masked_address_p (mem_address))
+	{
+	  /* This rtl is already in the form that matches stvx instruction,
+	     so leave it alone.  */
+	  DONE;
+	}
+      /* Otherwise, fall through to transform into a swapping store.  */
+    }
+
   operands[2] = can_create_pseudo_p () ? gen_reg_rtx_and_attrs (operands[1]) 
                                        : operands[1];
 })
@@ -665,6 +823,31 @@
                      (const_int 0) (const_int 1)
                      (const_int 2) (const_int 3)])))]
 {
+  rtx mem = operands[0];
+
+  /* Don't apply the swap optimization if we've already performed register
+     allocation and the hard register source is not in the altivec range.  */
+  if ((MEM_ALIGN (mem) >= 128)
+      && ((reg_or_subregno (operands[1]) >= FIRST_PSEUDO_REGISTER)
+          || ALTIVEC_REGNO_P (reg_or_subregno (operands[1]))))
+    {
+      rtx mem_address = XEXP (mem, 0);
+      enum machine_mode mode = GET_MODE (mem);
+      if (REG_P (mem_address) || rs6000_sum_of_two_registers_p (mem_address))
+	{
+	  rtx stvx_set_expr = rs6000_gen_stvx (mode, mem, operands[1]);
+	  emit_insn (stvx_set_expr);
+	  DONE;
+	}
+      else if (rs6000_quadword_masked_address_p (mem_address))
+	{
+	  /* This rtl is already in the form that matches stvx instruction,
+	     so leave it alone.  */
+	  DONE;
+	}
+      /* Otherwise, fall through to transform into a swapping store.  */
+    }
+
   operands[2] = can_create_pseudo_p () ? gen_reg_rtx_and_attrs (operands[1]) 
                                        : operands[1];
 })
@@ -733,6 +916,31 @@
                      (const_int 4) (const_int 5)
                      (const_int 6) (const_int 7)])))]
 {
+  rtx mem = operands[0];
+
+  /* Don't apply the swap optimization if we've already performed register
+     allocation and the hard register source is not in the altivec range.  */
+  if ((MEM_ALIGN (mem) >= 128)
+      && ((reg_or_subregno (operands[1]) >= FIRST_PSEUDO_REGISTER)
+          || ALTIVEC_REGNO_P (reg_or_subregno (operands[1]))))
+    {
+      rtx mem_address = XEXP (mem, 0);
+      enum machine_mode mode = GET_MODE (mem);
+      if (REG_P (mem_address) || rs6000_sum_of_two_registers_p (mem_address))
+	{
+	  rtx stvx_set_expr = rs6000_gen_stvx (mode, mem, operands[1]);
+	  emit_insn (stvx_set_expr);
+	  DONE;
+	}
+      else if (rs6000_quadword_masked_address_p (mem_address))
+	{
+	  /* This rtl is already in the form that matches stvx instruction,
+	     so leave it alone.  */
+	  DONE;
+	}
+      /* Otherwise, fall through to transform into a swapping store.  */
+    }
+
   operands[2] = can_create_pseudo_p () ? gen_reg_rtx_and_attrs (operands[1]) 
                                        : operands[1];
 })
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 612489f4cf2..f2976406a5f 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,39 @@
+2018-01-10  Kelvin Nilsen  <kelvin@gcc.gnu.org>
+
+	* gcc.target/powerpc/pr48857.c: Modify dejagnu directives to look
+	for lvx and stvx instead of lxvd2x and stxvd2x and require
+	little-endian target.  Add comments.
+	* gcc.target/powerpc/swaps-p8-28.c: Add functions for more
+	comprehensive testing.
+	* gcc.target/powerpc/swaps-p8-29.c: Likewise.
+	* gcc.target/powerpc/swaps-p8-30.c: Likewise.
+	* gcc.target/powerpc/swaps-p8-31.c: Likewise.
+	* gcc.target/powerpc/swaps-p8-32.c: Likewise.
+	* gcc.target/powerpc/swaps-p8-33.c: Likewise.
+	* gcc.target/powerpc/swaps-p8-34.c: Likewise.
+	* gcc.target/powerpc/swaps-p8-35.c: Likewise.
+	* gcc.target/powerpc/swaps-p8-36.c: Likewise.
+	* gcc.target/powerpc/swaps-p8-37.c: Likewise.
+	* gcc.target/powerpc/swaps-p8-38.c: Likewise.
+	* gcc.target/powerpc/swaps-p8-39.c: Likewise.
+	* gcc.target/powerpc/swaps-p8-40.c: Likewise.
+	* gcc.target/powerpc/swaps-p8-41.c: Likewise.
+	* gcc.target/powerpc/swaps-p8-42.c: Likewise.
+	* gcc.target/powerpc/swaps-p8-43.c: Likewise.
+	* gcc.target/powerpc/swaps-p8-44.c: Likewise.
+	* gcc.target/powerpc/swaps-p8-45.c: Likewise.
+	* gcc.target/powerpc/vec-extract-2.c: Add comment and remove
+	scan-assembler-not directives that forbid lvx and xxpermdi.
+	* gcc.target/powerpc/vec-extract-3.c: Likewise.
+	* gcc.target/powerpc/vec-extract-5.c: Likewise.
+	* gcc.target/powerpc/vec-extract-6.c: Likewise.
+	* gcc.target/powerpc/vec-extract-7.c: Likewise.
+	* gcc.target/powerpc/vec-extract-8.c: Likewise.
+	* gcc.target/powerpc/vec-extract-9.c: Likewise.
+	* gcc.target/powerpc/vsx-vector-6-le.c: Change
+	scan-assembler-times directives to reflect different numbers of
+	expected xxlnor, xxlor, xvcmpgtdp, and xxland instructions.
+
 2018-01-13  Richard Sandiford  <richard.sandiford@linaro.org>
 	    Alan Hayward  <alan.hayward@arm.com>
 	    David Sherwood  <david.sherwood@arm.com>
diff --git a/gcc/testsuite/gcc.target/powerpc/pr48857.c b/gcc/testsuite/gcc.target/powerpc/pr48857.c
index 25f14b71331..2a391282ee2 100644
--- a/gcc/testsuite/gcc.target/powerpc/pr48857.c
+++ b/gcc/testsuite/gcc.target/powerpc/pr48857.c
@@ -1,10 +1,13 @@
-/* { dg-do compile { target { powerpc*-*-* } } } */
+/* Expected instruction selection as characterized by
+   scan-assembler-times directives below is only relevant to
+   little-endian targets.  */
+/* { dg-do compile { target { powerpc64le-*-* } } } */
 /* { dg-skip-if "" { powerpc*-*-darwin* } } */
 /* { dg-require-effective-target powerpc_vsx_ok } */
 /* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power7" } } */
 /* { dg-options "-O2 -mcpu=power7 -mabi=altivec" } */
-/* { dg-final { scan-assembler-times "lxvd2x" 1 } } */
-/* { dg-final { scan-assembler-times "stxvd2x" 1 } } */
+/* { dg-final { scan-assembler-times "lvx" 1 } } */
+/* { dg-final { scan-assembler-times "stvx" 1 } } */
 /* { dg-final { scan-assembler-not "ld" } } */
 /* { dg-final { scan-assembler-not "lwz" } } */
 /* { dg-final { scan-assembler-not "stw" } } */
@@ -15,12 +18,19 @@ typedef vector long long v2di_type;
 v2di_type
 return_v2di (v2di_type *ptr)
 {
-  return *ptr;		/* should generate lxvd2x 34,0,3.  */
+  /* As of pr48857, should generate lxvd2x 34,0,3
+     followed by xxpermdi 34,34,34,2.  Subsequent optimization
+     recognizes that ptr refers to an aligned vector and replaces
+     this with lvx 2,0,3.  */
+  return *ptr;
 }
 
 void
 pass_v2di (v2di_type arg, v2di_type *ptr)
 {
-  *ptr = arg;		/* should generate stxvd2x 34,0,{3,5}.  */
+  /* As of pr48857, should generate xxpermdi 34,34,34,2 followed by
+     stxvd2x 34,0,5.  Subsequent optimization recognizes that ptr
+     refers to an aligned vector and replaces this with stvx 2,0,5.  */
+  *ptr = arg;
 }
 
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-28.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-28.c
index 4ab2bc3db77..03309d716fe 100644
--- a/gcc/testsuite/gcc.target/powerpc/swaps-p8-28.c
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-28.c
@@ -12,10 +12,100 @@ vector char y = { 0, 1, 2, 3,
 		  8, 9, 10, 11,
 		  12, 13, 14, 15 };
 
+vector char x, z;
+
 vector char
 foo (void)
 {
-  return y;
+  return y;			/* Remove 1 swap and use lvx.  */
+}
+
+vector char
+foo1 (void)
+{
+  x = y;			/* Remove 2 redundant swaps here.  */
+  return x;			/* Remove 1 swap and use lvx.  */
+}
+
+void __attribute__ ((noinline))
+fill_local (vector char *vp)
+{
+  *vp = x;			/* Remove 2 redundant swaps here.  */
+}
+
+/* Test aligned load from local.  */
+vector char
+foo2 (void)
+{
+  vector char v;
+
+  /* Need to be clever here because v will normally reside in a
+     register rather than memory.  */
+  fill_local (&v);
+  return v;			/* Remove 1 swap and use lvx.  */
+}
+
+
+/* Test aligned load from pointer.  */
+vector char
+foo3 (vector char *arg)
+{
+  return *arg;			/* Remove 1 swap and use lvx.  */
+}
+
+/* In this structure, the compiler should insert padding to assure
+   that a_vector is properly aligned.  */
+struct bar {
+  char a_field;
+  vector char a_vector;
+};
+
+vector char
+foo4 (struct bar *bp)
+{
+  return bp->a_vector;		/* Remove 1 swap and use lvx.  */
+}
+
+/* Test aligned store to global.  */
+void
+baz (vector char arg)
+{
+  x = arg;			/* Remove 1 swap and use stvx.  */
+}
+
+void __attribute__ ((noinline))
+copy_local (vector char *arg)
+{
+  x = *arg;			/* Remove 2 redundant swaps.  */
+}
+
+
+/* Test aligned store to local.  */
+void
+baz1 (vector char arg)
+{
+  vector char v;
+
+  /* Need cleverness, because v will normally reside in a register
+     rather than memory.  */
+  v = arg;			/* Aligned store to local: remove 1
+				   swap and use stvx.  */
+  copy_local (&v);
+}
+
+/* Test aligned store to pointer.  */
+void
+baz2 (vector char *arg1, vector char arg2)
+{
+  /* Assume arg2 resides in register.  */
+  *arg1 = arg2;			/* Remove 1 swap and use stvx.  */
+}
+
+void
+baz3 (struct bar *bp, vector char v)
+{
+  /* Assume v resides in register.  */
+  bp->a_vector = v;		/* Remove 1 swap and use stvx.  */
 }
 
 int
@@ -24,6 +114,47 @@ main (int argc, char *argv[])
   vector char fetched_value = foo ();
   if (fetched_value[0] != 0 || fetched_value[15] != 15)
     abort ();
-  else
-    return 0;
+
+  fetched_value = foo1 ();
+  if (fetched_value[1] != 1 || fetched_value[14] != 14)
+    abort ();
+
+  fetched_value = foo2 ();
+  if (fetched_value[2] != 2 || fetched_value[13] != 13)
+    abort ();
+
+  fetched_value = foo3 (&x);
+  if (fetched_value[3] != 3 || fetched_value[12] != 12)
+    abort ();
+
+  struct bar a_struct;
+  a_struct.a_vector = x;	/* Remove 2 redundant swaps.  */
+  fetched_value = foo4 (&a_struct);
+  if (fetched_value[4] != 4 || fetched_value[11] != 11)
+    abort ();
+
+  for (int i = 0; i < 16; i++)
+    z[i] = 15 - i;
+
+  baz (z);
+  if (x[0] != 15 || x[15] != 0)
+    abort ();
+
+  vector char source = { 8, 7, 6, 5, 4, 3, 2, 1,
+			 0, 9, 10, 11, 12, 13, 14, 15 };
+
+  baz1 (source);
+  if (x[3] != 5 || x[8] != 0)
+    abort ();
+
+  vector char dest;
+  baz2 (&dest, source);
+  if (dest[4] != 4 || dest[1] != 7)
+    abort ();
+
+  baz3 (&a_struct, source);
+  if (a_struct.a_vector[7] != 1 || a_struct.a_vector[15] != 15)
+    abort ();
+
+  return 0;
 }
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-29.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-29.c
index d2025dfbafc..943f4e732ed 100644
--- a/gcc/testsuite/gcc.target/powerpc/swaps-p8-29.c
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-29.c
@@ -12,10 +12,100 @@ const vector char y = { 0, 1, 2, 3,
 			8, 9, 10, 11,
 			12, 13, 14, 15 };
 
+vector char x, z;
+
 vector char
 foo (void)
 {
-  return y;
+  return y;			/* Remove 1 swap and use lvx.  */
+}
+
+vector char
+foo1 (void)
+{
+  x = y;			/* Remove 2 redundant swaps here.  */
+  return x;			/* Remove 1 swap and use lvx.  */
+}
+
+void __attribute__ ((noinline))
+fill_local (vector char *vp)
+{
+  *vp = x;			/* Remove 2 redundant swaps here.  */
+}
+
+/* Test aligned load from local.  */
+vector char
+foo2 (void)
+{
+  vector char v;
+
+  /* Need to be clever here because v will normally reside in a
+     register rather than memory.  */
+  fill_local (&v);
+  return v;			/* Remove 1 swap and use lvx.  */
+}
+
+
+/* Test aligned load from pointer.  */
+vector char
+foo3 (vector char *arg)
+{
+  return *arg;			/* Remove 1 swap and use lvx.  */
+}
+
+/* In this structure, the compiler should insert padding to assure
+   that a_vector is properly aligned.  */
+struct bar {
+  char a_field;
+  vector char a_vector;
+};
+
+vector char
+foo4 (struct bar *bp)
+{
+  return bp->a_vector;		/* Remove 1 swap and use lvx.  */
+}
+
+/* Test aligned store to global.  */
+void
+baz (vector char arg)
+{
+  x = arg;			/* Remove 1 swap and use stvx.  */
+}
+
+void __attribute__ ((noinline))
+copy_local (vector char *arg)
+{
+  x = *arg;			/* Remove 2 redundant swaps.  */
+}
+
+
+/* Test aligned store to local.  */
+void
+baz1 (vector char arg)
+{
+  vector char v;
+
+  /* Need cleverness, because v will normally reside in a register
+     rather than memory.  */
+  v = arg;			/* Aligned store to local: remove 1
+				   swap and use stvx.  */
+  copy_local (&v);
+}
+
+/* Test aligned store to pointer.  */
+void
+baz2 (vector char *arg1, vector char arg2)
+{
+  /* Assume arg2 resides in register.  */
+  *arg1 = arg2;			/* Remove 1 swap and use stvx.  */
+}
+
+void
+baz3 (struct bar *bp, vector char v)
+{
+  /* Assume v resides in register.  */
+  bp->a_vector = v;		/* Remove 1 swap and use stvx.  */
 }
 
 int
@@ -24,6 +114,47 @@ main (int argc, char *argv[])
   vector char fetched_value = foo ();
   if (fetched_value[0] != 0 || fetched_value[15] != 15)
     abort ();
-  else
-    return 0;
+
+  fetched_value = foo1 ();
+  if (fetched_value[1] != 1 || fetched_value[14] != 14)
+    abort ();
+
+  fetched_value = foo2 ();
+  if (fetched_value[2] != 2 || fetched_value[13] != 13)
+    abort ();
+
+  fetched_value = foo3 (&x);
+  if (fetched_value[3] != 3 || fetched_value[12] != 12)
+    abort ();
+
+  struct bar a_struct;
+  a_struct.a_vector = x;	/* Remove 2 redundant swaps.  */
+  fetched_value = foo4 (&a_struct);
+  if (fetched_value[4] != 4 || fetched_value[11] != 11)
+    abort ();
+
+  for (int i = 0; i < 16; i++)
+    z[i] = 15 - i;
+
+  baz (z);
+  if (x[0] != 15 || x[15] != 0)
+    abort ();
+
+  vector char source = { 8, 7, 6, 5, 4, 3, 2, 1,
+			 0, 9, 10, 11, 12, 13, 14, 15 };
+
+  baz1 (source);
+  if (x[3] != 5 || x[8] != 0)
+    abort ();
+
+  vector char dest;
+  baz2 (&dest, source);
+  if (dest[4] != 4 || dest[1] != 7)
+    abort ();
+
+  baz3 (&a_struct, source);
+  if (a_struct.a_vector[7] != 1 || a_struct.a_vector[15] != 15)
+    abort ();
+
+  return 0;
 }
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-30.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-30.c
index 9421dbbb156..eddecf570c8 100644
--- a/gcc/testsuite/gcc.target/powerpc/swaps-p8-30.c
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-30.c
@@ -2,8 +2,12 @@
 /* { dg-require-effective-target powerpc_p8vector_ok } */
 /* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power8" } } */
 /* { dg-options "-mcpu=power8 -O3 " } */
-/* { dg-final { scan-assembler-not "xxpermdi" } } */
-/* { dg-final { scan-assembler-not "xxswapd" } } */
+
+/* Previous versions of this test required that the assembler does not
+   contain xxpermdi or xxswapd.  However, with the more sophisticated
+   code generation used today, it is now possible that xxpermdi (aka
+   xxswapd) show up without being part of a lxvd2x or stxvd2x
+   sequence.  */
 
 #include <altivec.h>
 
@@ -14,10 +18,100 @@ const vector char y = { 0, 1, 2, 3,
 			8, 9, 10, 11,
 			12, 13, 14, 15 };
 
+vector char x, z;
+
 vector char
 foo (void)
 {
-  return y;
+  return y;			/* Remove 1 swap and use lvx.  */
+}
+
+vector char
+foo1 (void)
+{
+  x = y;			/* Remove 2 redundant swaps here.  */
+  return x;			/* Remove 1 swap and use lvx.  */
+}
+
+void __attribute__ ((noinline))
+fill_local (vector char *vp)
+{
+  *vp = x;			/* Remove 2 redundant swaps here.  */
+}
+
+/* Test aligned load from local.  */
+vector char
+foo2 (void)
+{
+  vector char v;
+
+  /* Need to be clever here because v will normally reside in a
+     register rather than memory.  */
+  fill_local (&v);
+  return v;			/* Remove 1 swap and use lvx.  */
+}
+
+
+/* Test aligned load from pointer.  */
+vector char
+foo3 (vector char *arg)
+{
+  return *arg;			/* Remove 1 swap and use lvx.  */
+}
+
+/* In this structure, the compiler should insert padding to assure
+   that a_vector is properly aligned.  */
+struct bar {
+  char a_field;
+  vector char a_vector;
+};
+
+vector char
+foo4 (struct bar *bp)
+{
+  return bp->a_vector;		/* Remove 1 swap and use lvx.  */
+}
+
+/* Test aligned store to global.  */
+void
+baz (vector char arg)
+{
+  x = arg;			/* Remove 1 swap and use stvx.  */
+}
+
+void __attribute__ ((noinline))
+copy_local (vector char *arg)
+{
+  x = *arg;			/* Remove 2 redundant swaps.  */
+}
+
+
+/* Test aligned store to local.  */
+void
+baz1 (vector char arg)
+{
+  vector char v;
+
+  /* Need cleverness, because v will normally reside in a register
+     rather than memory.  */
+  v = arg;			/* Aligned store to local: remove 1
+				   swap and use stvx.  */
+  copy_local (&v);
+}
+
+/* Test aligned store to pointer.  */
+void
+baz2 (vector char *arg1, vector char arg2)
+{
+  /* Assume arg2 resides in register.  */
+  *arg1 = arg2;			/* Remove 1 swap and use stvx.  */
+}
+
+void
+baz3 (struct bar *bp, vector char v)
+{
+  /* Assume v resides in register.  */
+  bp->a_vector = v;		/* Remove 1 swap and use stvx.  */
 }
 
 int
@@ -26,6 +120,47 @@ main (int argc, char *argv[])
   vector char fetched_value = foo ();
   if (fetched_value[0] != 0 || fetched_value[15] != 15)
     abort ();
-  else
-    return 0;
+
+  fetched_value = foo1 ();
+  if (fetched_value[1] != 1 || fetched_value[14] != 14)
+    abort ();
+
+  fetched_value = foo2 ();
+  if (fetched_value[2] != 2 || fetched_value[13] != 13)
+    abort ();
+
+  fetched_value = foo3 (&x);
+  if (fetched_value[3] != 3 || fetched_value[12] != 12)
+    abort ();
+
+  struct bar a_struct;
+  a_struct.a_vector = x;	/* Remove 2 redundant swaps.  */
+  fetched_value = foo4 (&a_struct);
+  if (fetched_value[4] != 4 || fetched_value[11] != 11)
+    abort ();
+
+  for (int i = 0; i < 16; i++)
+    z[i] = 15 - i;
+
+  baz (z);
+  if (x[0] != 15 || x[15] != 0)
+    abort ();
+
+  vector char source = { 8, 7, 6, 5, 4, 3, 2, 1,
+			 0, 9, 10, 11, 12, 13, 14, 15 };
+
+  baz1 (source);
+  if (x[3] != 5 || x[8] != 0)
+    abort ();
+
+  vector char dest;
+  baz2 (&dest, source);
+  if (dest[4] != 4 || dest[1] != 7)
+    abort ();
+
+  baz3 (&a_struct, source);
+  if (a_struct.a_vector[7] != 1 || a_struct.a_vector[15] != 15)
+    abort ();
+
+  return 0;
 }
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-31.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-31.c
index a3c2f8240be..976a9cffdb2 100644
--- a/gcc/testsuite/gcc.target/powerpc/swaps-p8-31.c
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-31.c
@@ -7,21 +7,150 @@
 
 extern void abort (void);
 
-vector short y = { 0, 1, 2, 3,
-		   4, 5, 6, 7 };
+vector short x;
+vector short y = { 0, 1, 2, 3, 4, 5, 6, 7 };
+vector short z;
 
 vector short
 foo (void)
 {
-  return y;
+  return y;			/* Remove 1 swap and use lvx.  */
+}
+
+vector short
+foo1 (void)
+{
+  x = y;			/* Remove 2 redundant swaps here.  */
+  return x;			/* Remove 1 swap and use lvx.  */
+}
+
+void __attribute__ ((noinline))
+fill_local (vector short *vp)
+{
+  *vp = x;			/* Remove 2 redundant swaps here.  */
+}
+
+/* Test aligned load from local.  */
+vector short
+foo2 (void)
+{
+  vector short v;
+
+  /* Need to be clever here because v will normally reside in a
+     register rather than memory.  */
+  fill_local (&v);
+  return v;			/* Remove 1 swap and use lvx.  */
+}
+
+
+/* Test aligned load from pointer.  */
+vector short
+foo3 (vector short *arg)
+{
+  return *arg;			/* Remove 1 swap and use lvx.  */
+}
+
+/* In this structure, the compiler should insert padding to assure
+   that a_vector is properly aligned.  */
+struct bar {
+  short a_field;
+  vector short a_vector;
+};
+
+vector short
+foo4 (struct bar *bp)
+{
+  return bp->a_vector;		/* Remove 1 swap and use lvx.  */
+}
+
+/* Test aligned store to global.  */
+void
+baz (vector short arg)
+{
+  x = arg;			/* Remove 1 swap and use stvx.  */
+}
+
+void __attribute__ ((noinline))
+copy_local (vector short *arg)
+{
+  x = *arg;			/* Remove 2 redundant swaps.  */
+}
+
+
+/* Test aligned store to local.  */
+void
+baz1 (vector short arg)
+{
+  vector short v;
+
+  /* Need cleverness, because v will normally reside in a register
+     rather than memory.  */
+  v = arg;			/* Aligned store to local: remove 1
+				   swap and use stvx.  */
+  copy_local (&v);
+}
+
+/* Test aligned store to pointer.  */
+void
+baz2 (vector short *arg1, vector short arg2)
+{
+  /* Assume arg2 resides in register.  */
+  *arg1 = arg2;			/* Remove 1 swap and use stvx.  */
+}
+
+void
+baz3 (struct bar *bp, vector short v)
+{
+  /* Assume v resides in register.  */
+  bp->a_vector = v;		/* Remove 1 swap and use stvx.  */
 }
 
 int
-main (int argc, char *argv[])
+main (int argc, short *argv[])
 {
   vector short fetched_value = foo ();
   if (fetched_value[0] != 0 || fetched_value[7] != 7)
     abort ();
-  else
-    return 0;
+
+  fetched_value = foo1 ();
+  if (fetched_value[1] != 1 || fetched_value[6] != 6)
+    abort ();
+
+  fetched_value = foo2 ();
+  if (fetched_value[2] != 2 || fetched_value[5] != 5)
+    abort ();
+
+  fetched_value = foo3 (&x);
+  if (fetched_value[3] != 3 || fetched_value[4] != 4)
+    abort ();
+
+  struct bar a_struct;
+  a_struct.a_vector = x;	/* Remove 2 redundant swaps.  */
+  fetched_value = foo4 (&a_struct);
+  if (fetched_value[4] != 4 || fetched_value[3] != 3)
+    abort ();
+
+  for (int i = 0; i < 8; i++)
+    z[i] = 7 - i;
+
+  baz (z);
+  if (x[0] != 7 || x[7] != 0)
+    abort ();
+
+  vector short source = { 8, 7, 6, 5, 4, 3, 2, 1 };
+
+  baz1 (source);
+  if (x[3] != 5 || x[7] != 1)
+    abort ();
+
+  vector short dest;
+  baz2 (&dest, source);
+  if (dest[4] != 4 || dest[1] != 7)
+    abort ();
+
+  baz3 (&a_struct, source);
+  if (a_struct.a_vector[7] != 1 || a_struct.a_vector[5] != 3)
+    abort ();
+
+  return 0;
 }
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-32.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-32.c
index 57b76ecf7fc..98d5c62dab9 100644
--- a/gcc/testsuite/gcc.target/powerpc/swaps-p8-32.c
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-32.c
@@ -7,21 +7,150 @@
 
 extern void abort (void);
 
-const vector short y = { 0, 1, 2, 3,
-			 4, 5, 6, 7 };
+vector short x;
+const vector short y = { 0, 1, 2, 3, 4, 5, 6, 7 };
+vector short z;
 
 vector short
 foo (void)
 {
-  return y;
+  return y;			/* Remove 1 swap and use lvx.  */
+}
+
+vector short
+foo1 (void)
+{
+  x = y;			/* Remove 2 redundant swaps here.  */
+  return x;			/* Remove 1 swap and use lvx.  */
+}
+
+void __attribute__ ((noinline))
+fill_local (vector short *vp)
+{
+  *vp = x;			/* Remove 2 redundant swaps here.  */
+}
+
+/* Test aligned load from local.  */
+vector short
+foo2 (void)
+{
+  vector short v;
+
+  /* Need to be clever here because v will normally reside in a
+     register rather than memory.  */
+  fill_local (&v);
+  return v;			/* Remove 1 swap and use lvx.  */
+}
+
+
+/* Test aligned load from pointer.  */
+vector short
+foo3 (vector short *arg)
+{
+  return *arg;			/* Remove 1 swap and use lvx.  */
+}
+
+/* In this structure, the compiler should insert padding to assure
+   that a_vector is properly aligned.  */
+struct bar {
+  short a_field;
+  vector short a_vector;
+};
+
+vector short
+foo4 (struct bar *bp)
+{
+  return bp->a_vector;		/* Remove 1 swap and use lvx.  */
+}
+
+/* Test aligned store to global.  */
+void
+baz (vector short arg)
+{
+  x = arg;			/* Remove 1 swap and use stvx.  */
+}
+
+void __attribute__ ((noinline))
+copy_local (vector short *arg)
+{
+  x = *arg;			/* Remove 2 redundant swaps.  */
+}
+
+
+/* Test aligned store to local.  */
+void
+baz1 (vector short arg)
+{
+  vector short v;
+
+  /* Need cleverness, because v will normally reside in a register
+     rather than memory.  */
+  v = arg;			/* Aligned store to local: remove 1
+				   swap and use stvx.  */
+  copy_local (&v);
+}
+
+/* Test aligned store to pointer.  */
+void
+baz2 (vector short *arg1, vector short arg2)
+{
+  /* Assume arg2 resides in register.  */
+  *arg1 = arg2;			/* Remove 1 swap and use stvx.  */
+}
+
+void
+baz3 (struct bar *bp, vector short v)
+{
+  /* Assume v resides in register.  */
+  bp->a_vector = v;		/* Remove 1 swap and use stvx.  */
 }
 
 int
-main (int argc, char *argv[])
+main (int argc, short *argv[])
 {
   vector short fetched_value = foo ();
   if (fetched_value[0] != 0 || fetched_value[7] != 7)
     abort ();
-  else
-    return 0;
+
+  fetched_value = foo1 ();
+  if (fetched_value[1] != 1 || fetched_value[6] != 6)
+    abort ();
+
+  fetched_value = foo2 ();
+  if (fetched_value[2] != 2 || fetched_value[5] != 5)
+    abort ();
+
+  fetched_value = foo3 (&x);
+  if (fetched_value[3] != 3 || fetched_value[4] != 4)
+    abort ();
+
+  struct bar a_struct;
+  a_struct.a_vector = x;	/* Remove 2 redundant swaps.  */
+  fetched_value = foo4 (&a_struct);
+  if (fetched_value[4] != 4 || fetched_value[3] != 3)
+    abort ();
+
+  for (int i = 0; i < 8; i++)
+    z[i] = 7 - i;
+
+  baz (z);
+  if (x[0] != 7 || x[7] != 0)
+    abort ();
+
+  vector short source = { 8, 7, 6, 5, 4, 3, 2, 1 };
+
+  baz1 (source);
+  if (x[3] != 5 || x[7] != 1)
+    abort ();
+
+  vector short dest;
+  baz2 (&dest, source);
+  if (dest[4] != 4 || dest[1] != 7)
+    abort ();
+
+  baz3 (&a_struct, source);
+  if (a_struct.a_vector[7] != 1 || a_struct.a_vector[5] != 3)
+    abort ();
+
+  return 0;
 }
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-33.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-33.c
index 2289be468ec..4e189d8a82b 100644
--- a/gcc/testsuite/gcc.target/powerpc/swaps-p8-33.c
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-33.c
@@ -2,28 +2,161 @@
 /* { dg-require-effective-target powerpc_p8vector_ok } */
 /* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power8" } } */
 /* { dg-options "-mcpu=power8 -O3 " } */
-/* { dg-final { scan-assembler-not "xxpermdi" } } */
-/* { dg-final { scan-assembler-not "xxswapd" } } */
+
+/* Previous versions of this test required that the assembler does not
+   contain xxpermdi or xxswapd.  However, with the more sophisticated
+   code generation used today, it is now possible that xxpermdi (aka
+   xxswapd) show up without being part of a lxvd2x or stxvd2x
+   sequence.  */
 
 #include <altivec.h>
 
 extern void abort (void);
 
-const vector short y = { 0, 1, 2, 3,
-			 4, 5, 6, 7 };
+vector short x;
+const vector short y = { 0, 1, 2, 3, 4, 5, 6, 7 };
+vector short z;
 
 vector short
 foo (void)
 {
-  return y;
+  return y;			/* Remove 1 swap and use lvx.  */
+}
+
+vector short
+foo1 (void)
+{
+  x = y;			/* Remove 2 redundant swaps here.  */
+  return x;			/* Remove 1 swap and use lvx.  */
+}
+
+void __attribute__ ((noinline))
+fill_local (vector short *vp)
+{
+  *vp = x;			/* Remove 2 redundant swaps here.  */
+}
+
+/* Test aligned load from local.  */
+vector short
+foo2 (void)
+{
+  vector short v;
+
+  /* Need to be clever here because v will normally reside in a
+     register rather than memory.  */
+  fill_local (&v);
+  return v;			/* Remove 1 swap and use lvx.  */
+}
+
+
+/* Test aligned load from pointer.  */
+vector short
+foo3 (vector short *arg)
+{
+  return *arg;			/* Remove 1 swap and use lvx.  */
+}
+
+/* In this structure, the compiler should insert padding to assure
+   that a_vector is properly aligned.  */
+struct bar {
+  short a_field;
+  vector short a_vector;
+};
+
+vector short
+foo4 (struct bar *bp)
+{
+  return bp->a_vector;		/* Remove 1 swap and use lvx.  */
+}
+
+/* Test aligned store to global.  */
+void
+baz (vector short arg)
+{
+  x = arg;			/* Remove 1 swap and use stvx.  */
+}
+
+void __attribute__ ((noinline))
+copy_local (vector short *arg)
+{
+  x = *arg;			/* Remove 2 redundant swaps.  */
+}
+
+
+/* Test aligned store to local.  */
+void
+baz1 (vector short arg)
+{
+  vector short v;
+
+  /* Need cleverness, because v will normally reside in a register
+     rather than memory.  */
+  v = arg;			/* Aligned store to local: remove 1
+				   swap and use stvx.  */
+  copy_local (&v);
+}
+
+/* Test aligned store to pointer.  */
+void
+baz2 (vector short *arg1, vector short arg2)
+{
+  /* Assume arg2 resides in register.  */
+  *arg1 = arg2;			/* Remove 1 swap and use stvx.  */
+}
+
+void
+baz3 (struct bar *bp, vector short v)
+{
+  /* Assume v resides in register.  */
+  bp->a_vector = v;		/* Remove 1 swap and use stvx.  */
 }
 
 int
-main (int argc, char *argv[])
+main (int argc, short *argv[])
 {
   vector short fetched_value = foo ();
-  if (fetched_value[0] != 0 || fetched_value[15] != 15)
+  if (fetched_value[0] != 0 || fetched_value[7] != 7)
+    abort ();
+
+  fetched_value = foo1 ();
+  if (fetched_value[1] != 1 || fetched_value[6] != 6)
     abort ();
-  else
-    return 0;
+
+  fetched_value = foo2 ();
+  if (fetched_value[2] != 2 || fetched_value[5] != 5)
+    abort ();
+
+  fetched_value = foo3 (&x);
+  if (fetched_value[3] != 3 || fetched_value[4] != 4)
+    abort ();
+
+  struct bar a_struct;
+  a_struct.a_vector = x;	/* Remove 2 redundant swaps.  */
+  fetched_value = foo4 (&a_struct);
+  if (fetched_value[4] != 4 || fetched_value[3] != 3)
+    abort ();
+
+  for (int i = 0; i < 8; i++)
+    z[i] = 7 - i;
+
+  baz (z);
+  if (x[0] != 7 || x[7] != 0)
+    abort ();
+
+  vector short source = { 8, 7, 6, 5, 4, 3, 2, 1 };
+
+  baz1 (source);
+  if (x[3] != 5 || x[7] != 1)
+    abort ();
+
+  vector short dest;
+  baz2 (&dest, source);
+  if (dest[4] != 4 || dest[1] != 7)
+    abort ();
+
+  baz3 (&a_struct, source);
+  if (a_struct.a_vector[7] != 1 || a_struct.a_vector[5] != 3)
+    abort ();
+
+  return 0;
 }
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-34.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-34.c
index a7ddb01864a..8ee9795b9a5 100644
--- a/gcc/testsuite/gcc.target/powerpc/swaps-p8-34.c
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-34.c
@@ -7,20 +7,152 @@
 
 extern void abort (void);
 
+vector int x;
 vector int y = { 0, 1, 2, 3 };
+vector int z;
 
 vector int
 foo (void)
 {
-  return y;
+  return y;			/* Remove 1 swap and use lvx.  */
+}
+
+vector int
+foo1 (void)
+{
+  x = y;			/* Remove 2 redundant swaps here.  */
+  return x;			/* Remove 1 swap and use lvx.  */
+}
+
+void __attribute__ ((noinline))
+fill_local (vector int *vp)
+{
+  *vp = x;			/* Remove 2 redundant swaps here.  */
+}
+
+/* Test aligned load from local.  */
+vector int
+foo2 (void)
+{
+  vector int v;
+
+  /* Need to be clever here because v will normally reside in a
+     register rather than memory.  */
+  fill_local (&v);
+  return v;			/* Remove 1 swap and use lvx.  */
+}
+
+
+/* Test aligned load from pointer.  */
+vector int
+foo3 (vector int *arg)
+{
+  return *arg;			/* Remove 1 swap and use lvx.  */
+}
+
+/* In this structure, the compiler should insert padding to assure
+   that a_vector is properly aligned.  */
+struct bar {
+  short a_field;
+  vector int a_vector;
+};
+
+vector int
+foo4 (struct bar *bp)
+{
+  return bp->a_vector;		/* Remove 1 swap and use lvx.  */
+}
+
+/* Test aligned store to global.  */
+void
+baz (vector int arg)
+{
+  x = arg;			/* Remove 1 swap and use stvx.  */
+}
+
+void __attribute__ ((noinline))
+copy_local (vector int *arg)
+{
+  x = *arg;			/* Remove 2 redundant swaps.  */
+}
+
+
+/* Test aligned store to local.  */
+void
+baz1 (vector int arg)
+{
+  vector int v;
+
+  /* Need cleverness, because v will normally reside in a register
+     rather than memory.  */
+  v = arg;			/* Aligned store to local: remove 1
+				   swap and use stvx.  */
+  copy_local (&v);
+}
+
+/* Test aligned store to pointer.  */
+void
+baz2 (vector int *arg1, vector int arg2)
+{
+  /* Assume arg2 resides in register.  */
+  *arg1 = arg2;			/* Remove 1 swap and use stvx.  */
+}
+
+void
+baz3 (struct bar *bp, vector int v)
+{
+  /* Assume v resides in register.  */
+  bp->a_vector = v;		/* Remove 1 swap and use stvx.  */
 }
 
 int
-main (int argc, char *argv[])
+main (int argc, int *argv[])
 {
   vector int fetched_value = foo ();
   if (fetched_value[0] != 0 || fetched_value[3] != 3)
     abort ();
-  else
-    return 0;
+
+  fetched_value = foo1 ();
+  if (fetched_value[1] != 1 || fetched_value[2] != 2)
+    abort ();
+
+  fetched_value = foo2 ();
+  if (fetched_value[2] != 2 || fetched_value[1] != 1)
+    abort ();
+
+  fetched_value = foo3 (&x);
+  if (fetched_value[3] != 3 || fetched_value[0] != 0)
+    abort ();
+
+  struct bar a_struct;
+  a_struct.a_vector = x;	/* Remove 2 redundant swaps.  */
+  fetched_value = foo4 (&a_struct);
+  if (fetched_value[2] != 2 || fetched_value[3] != 3)
+    abort ();
+
+  z[0] = 7;
+  z[1] = 6;
+  z[2] = 5;
+  z[3] = 4;
+
+  baz (z);
+  if (x[0] != 7 || x[3] != 4)
+    abort ();
+
+  vector int source = { 8, 7, 6, 5 };
+
+  baz1 (source);
+  if (x[2] != 6 || x[1] != 7)
+    abort ();
+
+  vector int dest;
+  baz2 (&dest, source);
+  if (dest[0] != 8 || dest[1] != 7)
+    abort ();
+
+  baz3 (&a_struct, source);
+  if (a_struct.a_vector[3] != 5 || a_struct.a_vector[0] != 8)
+    abort ();
+
+  return 0;
 }
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-35.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-35.c
index da98e90e2c3..13f2ea745bd 100644
--- a/gcc/testsuite/gcc.target/powerpc/swaps-p8-35.c
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-35.c
@@ -7,20 +7,152 @@
 
 extern void abort (void);
 
+vector int x;
 const vector int y = { 0, 1, 2, 3 };
+vector int z;
 
 vector int
 foo (void)
 {
-  return y;
+  return y;			/* Remove 1 swap and use lvx.  */
+}
+
+vector int
+foo1 (void)
+{
+  x = y;			/* Remove 2 redundant swaps here.  */
+  return x;			/* Remove 1 swap and use lvx.  */
+}
+
+void __attribute__ ((noinline))
+fill_local (vector int *vp)
+{
+  *vp = x;			/* Remove 2 redundant swaps here.  */
+}
+
+/* Test aligned load from local.  */
+vector int
+foo2 (void)
+{
+  vector int v;
+
+  /* Need to be clever here because v will normally reside in a
+     register rather than memory.  */
+  fill_local (&v);
+  return v;			/* Remove 1 swap and use lvx.  */
+}
+
+
+/* Test aligned load from pointer.  */
+vector int
+foo3 (vector int *arg)
+{
+  return *arg;			/* Remove 1 swap and use lvx.  */
+}
+
+/* In this structure, the compiler should insert padding to assure
+   that a_vector is properly aligned.  */
+struct bar {
+  short a_field;
+  vector int a_vector;
+};
+
+vector int
+foo4 (struct bar *bp)
+{
+  return bp->a_vector;		/* Remove 1 swap and use lvx.  */
+}
+
+/* Test aligned store to global.  */
+void
+baz (vector int arg)
+{
+  x = arg;			/* Remove 1 swap and use stvx.  */
+}
+
+void __attribute__ ((noinline))
+copy_local (vector int *arg)
+{
+  x = *arg;			/* Remove 2 redundant swaps.  */
+}
+
+
+/* Test aligned store to local.  */
+void
+baz1 (vector int arg)
+{
+  vector int v;
+
+  /* Need cleverness, because v will normally reside in a register
+     rather than memory.  */
+  v = arg;			/* Aligned store to local: remove 1
+				   swap and use stvx.  */
+  copy_local (&v);
+}
+
+/* Test aligned store to pointer.  */
+void
+baz2 (vector int *arg1, vector int arg2)
+{
+  /* Assume arg2 resides in register.  */
+  *arg1 = arg2;			/* Remove 1 swap and use stvx.  */
+}
+
+void
+baz3 (struct bar *bp, vector int v)
+{
+  /* Assume v resides in register.  */
+  bp->a_vector = v;		/* Remove 1 swap and use stvx.  */
 }
 
 int
-main (int argc, char *argv[])
+main (int argc, int *argv[])
 {
   vector int fetched_value = foo ();
   if (fetched_value[0] != 0 || fetched_value[3] != 3)
     abort ();
-  else
-    return 0;
+
+  fetched_value = foo1 ();
+  if (fetched_value[1] != 1 || fetched_value[2] != 2)
+    abort ();
+
+  fetched_value = foo2 ();
+  if (fetched_value[2] != 2 || fetched_value[1] != 1)
+    abort ();
+
+  fetched_value = foo3 (&x);
+  if (fetched_value[3] != 3 || fetched_value[0] != 0)
+    abort ();
+
+  struct bar a_struct;
+  a_struct.a_vector = x;	/* Remove 2 redundant swaps.  */
+  fetched_value = foo4 (&a_struct);
+  if (fetched_value[2] != 2 || fetched_value[3] != 3)
+    abort ();
+
+  z[0] = 7;
+  z[1] = 6;
+  z[2] = 5;
+  z[3] = 4;
+
+  baz (z);
+  if (x[0] != 7 || x[3] != 4)
+    abort ();
+
+  vector int source = { 8, 7, 6, 5 };
+
+  baz1 (source);
+  if (x[2] != 6 || x[1] != 7)
+    abort ();
+
+  vector int dest;
+  baz2 (&dest, source);
+  if (dest[0] != 8 || dest[1] != 7)
+    abort ();
+
+  baz3 (&a_struct, source);
+  if (a_struct.a_vector[3] != 5 || a_struct.a_vector[0] != 8)
+    abort ();
+
+  return 0;
 }
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-36.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-36.c
index 52990a6c855..f825f8bcfec 100644
--- a/gcc/testsuite/gcc.target/powerpc/swaps-p8-36.c
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-36.c
@@ -2,27 +2,163 @@
 /* { dg-require-effective-target powerpc_p8vector_ok } */
 /* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power8" } } */
 /* { dg-options "-mcpu=power8 -O3 " } */
-/* { dg-final { scan-assembler-not "xxpermdi" } } */
-/* { dg-final { scan-assembler-not "xxswapd" } } */
+
+/* Previous versions of this test required that the assembler does not
+   contain xxpermdi or xxswapd.  However, with the more sophisticated
+   code generation used today, it is now possible that xxpermdi (aka
+   xxswapd) show up without being part of a lxvd2x or stxvd2x
+   sequence.  */
 
 #include <altivec.h>
 
 extern void abort (void);
 
+vector int x;
 const vector int y = { 0, 1, 2, 3 };
+vector int z;
 
 vector int
 foo (void)
 {
-  return y;
+  return y;			/* Remove 1 swap and use lvx.  */
+}
+
+vector int
+foo1 (void)
+{
+  x = y;			/* Remove 2 redundant swaps here.  */
+  return x;			/* Remove 1 swap and use lvx.  */
+}
+
+void __attribute__ ((noinline))
+fill_local (vector int *vp)
+{
+  *vp = x;			/* Remove 2 redundant swaps here.  */
+}
+
+/* Test aligned load from local.  */
+vector int
+foo2 (void)
+{
+  vector int v;
+
+  /* Need to be clever here because v will normally reside in a
+     register rather than memory.  */
+  fill_local (&v);
+  return v;			/* Remove 1 swap and use lvx.  */
+}
+
+
+/* Test aligned load from pointer.  */
+vector int
+foo3 (vector int *arg)
+{
+  return *arg;			/* Remove 1 swap and use lvx.  */
+}
+
+/* In this structure, the compiler should insert padding to assure
+   that a_vector is properly aligned.  */
+struct bar {
+  short a_field;
+  vector int a_vector;
+};
+
+vector int
+foo4 (struct bar *bp)
+{
+  return bp->a_vector;		/* Remove 1 swap and use lvx.  */
+}
+
+/* Test aligned store to global.  */
+void
+baz (vector int arg)
+{
+  x = arg;			/* Remove 1 swap and use stvx.  */
+}
+
+void __attribute__ ((noinline))
+copy_local (vector int *arg)
+{
+  x = *arg;			/* Remove 2 redundant swaps.  */
+}
+
+
+/* Test aligned store to local.  */
+void
+baz1 (vector int arg)
+{
+  vector int v;
+
+  /* Need cleverness, because v will normally reside in a register
+     rather than memory.  */
+  v = arg;			/* Aligned store to local: remove 1
+				   swap and use stvx.  */
+  copy_local (&v);
+}
+
+/* Test aligned store to pointer.  */
+void
+baz2 (vector int *arg1, vector int arg2)
+{
+  /* Assume arg2 resides in register.  */
+  *arg1 = arg2;			/* Remove 1 swap and use stvx.  */
+}
+
+void
+baz3 (struct bar *bp, vector int v)
+{
+  /* Assume v resides in register.  */
+  bp->a_vector = v;		/* Remove 1 swap and use stvx.  */
 }
 
 int
-main (int argc, char *argv[])
+main (int argc, int *argv[])
 {
   vector int fetched_value = foo ();
   if (fetched_value[0] != 0 || fetched_value[3] != 3)
     abort ();
-  else
-    return 0;
+
+  fetched_value = foo1 ();
+  if (fetched_value[1] != 1 || fetched_value[2] != 2)
+    abort ();
+
+  fetched_value = foo2 ();
+  if (fetched_value[2] != 2 || fetched_value[1] != 1)
+    abort ();
+
+  fetched_value = foo3 (&x);
+  if (fetched_value[3] != 3 || fetched_value[0] != 0)
+    abort ();
+
+  struct bar a_struct;
+  a_struct.a_vector = x;	/* Remove 2 redundant swaps.  */
+  fetched_value = foo4 (&a_struct);
+  if (fetched_value[2] != 2 || fetched_value[3] != 3)
+    abort ();
+
+  z[0] = 7;
+  z[1] = 6;
+  z[2] = 5;
+  z[3] = 4;
+
+  baz (z);
+  if (x[0] != 7 || x[3] != 4)
+    abort ();
+
+  vector int source = { 8, 7, 6, 5 };
+
+  baz1 (source);
+  if (x[3] != 6 || x[2] != 7)
+    abort ();
+
+  vector int dest;
+  baz2 (&dest, source);
+  if (dest[0] != 8 || dest[1] != 7)
+    abort ();
+
+  baz3 (&a_struct, source);
+  if (a_struct.a_vector[3] != 5 || a_struct.a_vector[0] != 8)
+    abort ();
+
+  return 0;
 }
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-37.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-37.c
index 4d8ae11bf97..775d37fe6f6 100644
--- a/gcc/testsuite/gcc.target/powerpc/swaps-p8-37.c
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-37.c
@@ -7,20 +7,152 @@
 
 extern void abort (void);
 
-vector float y = { 0.0f, 0.1f, 0.2f, 0.3f };
+vector float x;
+vector float y = { 0.0F, 0.1F, 0.2F, 0.3F };
+vector float z;
 
 vector float
 foo (void)
 {
-  return y;
+  return y;			/* Remove 1 swap and use lvx.  */
+}
+
+vector float
+foo1 (void)
+{
+  x = y;			/* Remove 2 redundant swaps here.  */
+  return x;			/* Remove 1 swap and use lvx.  */
+}
+
+void __attribute__ ((noinline))
+fill_local (vector float *vp)
+{
+  *vp = x;			/* Remove 2 redundant swaps here.  */
+}
+
+/* Test aligned load from local.  */
+vector float
+foo2 (void)
+{
+  vector float v;
+
+  /* Need to be clever here because v will normally reside in a
+     register rather than memory.  */
+  fill_local (&v);
+  return v;			/* Remove 1 swap and use lvx.  */
+}
+
+
+/* Test aligned load from pointer.  */
+vector float
+foo3 (vector float *arg)
+{
+  return *arg;			/* Remove 1 swap and use lvx.  */
+}
+
+/* In this structure, the compiler should insert padding to assure
+   that a_vector is properly aligned.  */
+struct bar {
+  short a_field;
+  vector float a_vector;
+};
+
+vector float
+foo4 (struct bar *bp)
+{
+  return bp->a_vector;		/* Remove 1 swap and use lvx.  */
+}
+
+/* Test aligned store to global.  */
+void
+baz (vector float arg)
+{
+  x = arg;			/* Remove 1 swap and use stvx.  */
+}
+
+void __attribute__ ((noinline))
+copy_local (vector float *arg)
+{
+  x = *arg;			/* Remove 2 redundant swaps.  */
+}
+
+
+/* Test aligned store to local.  */
+void
+baz1 (vector float arg)
+{
+  vector float v;
+
+  /* Need cleverness, because v will normally reside in a register
+     rather than memory.  */
+  v = arg;			/* Aligned store to local: remove 1
+				   swap and use stvx.  */
+  copy_local (&v);
+}
+
+/* Test aligned store to pointer.  */
+void
+baz2 (vector float *arg1, vector float arg2)
+{
+  /* Assume arg2 resides in register.  */
+  *arg1 = arg2;			/* Remove 1 swap and use stvx.  */
+}
+
+void
+baz3 (struct bar *bp, vector float v)
+{
+  /* Assume v resides in register.  */
+  bp->a_vector = v;		/* Remove 1 swap and use stvx.  */
 }
 
 int
-main (int argc, char *argv[])
+main (float argc, float *argv[])
 {
   vector float fetched_value = foo ();
-  if (fetched_value[0] != 0.0f || fetched_value[3] != 0.3f)
+  if (fetched_value[0] != 0.0F || fetched_value[3] != 0.3F)
+    abort ();
+
+  fetched_value = foo1 ();
+  if (fetched_value[1] != 0.1F || fetched_value[2] != 0.2F)
     abort ();
-  else
-    return 0;
+
+  fetched_value = foo2 ();
+  if (fetched_value[2] != 0.2F || fetched_value[1] != 0.1F)
+    abort ();
+
+  fetched_value = foo3 (&x);
+  if (fetched_value[3] != 0.3F || fetched_value[0] != 0.0F)
+    abort ();
+
+  struct bar a_struct;
+  a_struct.a_vector = x;	/* Remove 2 redundant swaps.  */
+  fetched_value = foo4 (&a_struct);
+  if (fetched_value[2] != 0.2F || fetched_value[3] != 0.3F)
+    abort ();
+
+  z[0] = 0.7F;
+  z[1] = 0.6F;
+  z[2] = 0.5F;
+  z[3] = 0.4F;
+
+  baz (z);
+  if (x[0] != 0.7F || x[3] != 0.4F)
+    abort ();
+
+  vector float source = { 0.8F, 0.7F, 0.6F, 0.5F };
+
+  baz1 (source);
+  if (x[2] != 0.6F || x[1] != 0.7F)
+    abort ();
+
+  vector float dest;
+  baz2 (&dest, source);
+  if (dest[0] != 0.8F || dest[1] != 0.7F)
+    abort ();
+
+  baz3 (&a_struct, source);
+  if (a_struct.a_vector[3] != 0.5F || a_struct.a_vector[0] != 0.8F)
+    abort ();
+
+  return 0;
 }
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-38.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-38.c
index bf08574bd74..8bd52dee391 100644
--- a/gcc/testsuite/gcc.target/powerpc/swaps-p8-38.c
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-38.c
@@ -7,20 +7,152 @@
 
 extern void abort (void);
 
-const vector float y = { 0.0f, 0.1f, 0.2f, 0.3f };
+vector float x;
+const vector float y = { 0.0F, 0.1F, 0.2F, 0.3F };
+vector float z;
 
 vector float
 foo (void)
 {
-  return y;
+  return y;			/* Remove 1 swap and use lvx.  */
+}
+
+vector float
+foo1 (void)
+{
+  x = y;			/* Remove 2 redundant swaps here.  */
+  return x;			/* Remove 1 swap and use lvx.  */
+}
+
+void __attribute__ ((noinline))
+fill_local (vector float *vp)
+{
+  *vp = x;			/* Remove 2 redundant swaps here.  */
+}
+
+/* Test aligned load from local.  */
+vector float
+foo2 (void)
+{
+  vector float v;
+
+  /* Need to be clever here because v will normally reside in a
+     register rather than memory.  */
+  fill_local (&v);
+  return v;			/* Remove 1 swap and use lvx.  */
+}
+
+
+/* Test aligned load from pointer.  */
+vector float
+foo3 (vector float *arg)
+{
+  return *arg;			/* Remove 1 swap and use lvx.  */
+}
+
+/* In this structure, the compiler should insert padding to assure
+   that a_vector is properly aligned.  */
+struct bar {
+  short a_field;
+  vector float a_vector;
+};
+
+vector float
+foo4 (struct bar *bp)
+{
+  return bp->a_vector;		/* Remove 1 swap and use lvx.  */
+}
+
+/* Test aligned store to global.  */
+void
+baz (vector float arg)
+{
+  x = arg;			/* Remove 1 swap and use stvx.  */
+}
+
+void __attribute__ ((noinline))
+copy_local (vector float *arg)
+{
+  x = *arg;			/* Remove 2 redundant swaps.  */
+}
+
+
+/* Test aligned store to local.  */
+void
+baz1 (vector float arg)
+{
+  vector float v;
+
+  /* Need cleverness, because v will normally reside in a register
+     rather than memory.  */
+  v = arg;			/* Aligned store to local: remove 1
+				   swap and use stvx.  */
+  copy_local (&v);
+}
+
+/* Test aligned store to pointer.  */
+void
+baz2 (vector float *arg1, vector float arg2)
+{
+  /* Assume arg2 resides in register.  */
+  *arg1 = arg2;			/* Remove 1 swap and use stvx.  */
+}
+
+void
+baz3 (struct bar *bp, vector float v)
+{
+  /* Assume v resides in register.  */
+  bp->a_vector = v;		/* Remove 1 swap and use stvx.  */
 }
 
 int
-main (int argc, char *argv[])
+main (float argc, float *argv[])
 {
   vector float fetched_value = foo ();
-  if (fetched_value[0] != 0.0f || fetched_value[3] != 0.3f)
+  if (fetched_value[0] != 0.0F || fetched_value[3] != 0.3F)
+    abort ();
+
+  fetched_value = foo1 ();
+  if (fetched_value[1] != 0.1F || fetched_value[2] != 0.2F)
     abort ();
-  else
-    return 0;
+
+  fetched_value = foo2 ();
+  if (fetched_value[2] != 0.2F || fetched_value[1] != 0.1F)
+    abort ();
+
+  fetched_value = foo3 (&x);
+  if (fetched_value[3] != 0.3F || fetched_value[0] != 0.0F)
+    abort ();
+
+  struct bar a_struct;
+  a_struct.a_vector = x;	/* Remove 2 redundant swaps.  */
+  fetched_value = foo4 (&a_struct);
+  if (fetched_value[2] != 0.2F || fetched_value[3] != 0.3F)
+    abort ();
+
+  z[0] = 0.7F;
+  z[1] = 0.6F;
+  z[2] = 0.5F;
+  z[3] = 0.4F;
+
+  baz (z);
+  if (x[0] != 0.7F || x[3] != 0.4F)
+    abort ();
+
+  vector float source = { 0.8F, 0.7F, 0.6F, 0.5F };
+
+  baz1 (source);
+  if (x[2] != 0.6F || x[1] != 0.7F)
+    abort ();
+
+  vector float dest;
+  baz2 (&dest, source);
+  if (dest[0] != 0.8F || dest[1] != 0.7F)
+    abort ();
+
+  baz3 (&a_struct, source);
+  if (a_struct.a_vector[3] != 0.5F || a_struct.a_vector[0] != 0.8F)
+    abort ();
+
+  return 0;
 }
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-39.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-39.c
index 8cd68ddcd72..94add40de7e 100644
--- a/gcc/testsuite/gcc.target/powerpc/swaps-p8-39.c
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-39.c
@@ -2,27 +2,163 @@
 /* { dg-require-effective-target powerpc_p8vector_ok } */
 /* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power8" } } */
 /* { dg-options "-mcpu=power8 -O3 " } */
-/* { dg-final { scan-assembler-not "xxpermdi" } } */
-/* { dg-final { scan-assembler-not "xxswapd" } } */
+
+/* Previous versions of this test required that the assembler does not
+   contain xxpermdi or xxswapd.  However, with the more sophisticated
+   code generation used today, it is now possible that xxpermdi (aka
+   xxswapd) show up without being part of a lxvd2x or stxvd2x
+   sequence.  */
 
 #include <altivec.h>
 
 extern void abort (void);
 
-const vector float y = { 0.0f, 0.1f, 0.2f, 0.3f };
+vector float x;
+const vector float y = { 0.0F, 0.1F, 0.2F, 0.3F };
+vector float z;
 
 vector float
 foo (void)
 {
-  return y;
+  return y;			/* Remove 1 swap and use lvx.  */
+}
+
+vector float
+foo1 (void)
+{
+  x = y;			/* Remove 2 redundant swaps here.  */
+  return x;			/* Remove 1 swap and use lvx.  */
+}
+
+void __attribute__ ((noinline))
+fill_local (vector float *vp)
+{
+  *vp = x;			/* Remove 2 redundant swaps here.  */
+}
+
+/* Test aligned load from local.  */
+vector float
+foo2 (void)
+{
+  vector float v;
+
+  /* Need to be clever here because v will normally reside in a
+     register rather than memory.  */
+  fill_local (&v);
+  return v;			/* Remove 1 swap and use lvx.  */
+}
+
+
+/* Test aligned load from pointer.  */
+vector float
+foo3 (vector float *arg)
+{
+  return *arg;			/* Remove 1 swap and use lvx.  */
+}
+
+/* In this structure, the compiler should insert padding to assure
+   that a_vector is properly aligned.  */
+struct bar {
+  short a_field;
+  vector float a_vector;
+};
+
+vector float
+foo4 (struct bar *bp)
+{
+  return bp->a_vector;		/* Remove 1 swap and use lvx.  */
+}
+
+/* Test aligned store to global.  */
+void
+baz (vector float arg)
+{
+  x = arg;			/* Remove 1 swap and use stvx.  */
+}
+
+void __attribute__ ((noinline))
+copy_local (vector float *arg)
+{
+  x = *arg;			/* Remove 2 redundant swaps.  */
+}
+
+
+/* Test aligned store to local.  */
+void
+baz1 (vector float arg)
+{
+  vector float v;
+
+  /* Need cleverness, because v will normally reside in a register
+     rather than memory.  */
+  v = arg;			/* Aligned store to local: remove 1
+				   swap and use stvx.  */
+  copy_local (&v);
+}
+
+/* Test aligned store to pointer.  */
+void
+baz2 (vector float *arg1, vector float arg2)
+{
+  /* Assume arg2 resides in register.  */
+  *arg1 = arg2;			/* Remove 1 swap and use stvx.  */
+}
+
+void
+baz3 (struct bar *bp, vector float v)
+{
+  /* Assume v resides in register.  */
+  bp->a_vector = v;		/* Remove 1 swap and use stvx.  */
 }
 
 int
-main (int argc, char *argv[])
+main (float argc, float *argv[])
 {
   vector float fetched_value = foo ();
-  if (fetched_value[0] != 0.0f || fetched_value[3] != 0.3)
+  if (fetched_value[0] != 0.0F || fetched_value[3] != 0.3F)
+    abort ();
+
+  fetched_value = foo1 ();
+  if (fetched_value[1] != 0.1F || fetched_value[2] != 0.2F)
     abort ();
-  else
-    return 0;
+
+  fetched_value = foo2 ();
+  if (fetched_value[2] != 0.2F || fetched_value[1] != 0.1F)
+    abort ();
+
+  fetched_value = foo3 (&x);
+  if (fetched_value[3] != 0.3F || fetched_value[0] != 0.0F)
+    abort ();
+
+  struct bar a_struct;
+  a_struct.a_vector = x;	/* Remove 2 redundant swaps.  */
+  fetched_value = foo4 (&a_struct);
+  if (fetched_value[2] != 0.2F || fetched_value[3] != 0.3F)
+    abort ();
+
+  z[0] = 0.7F;
+  z[1] = 0.6F;
+  z[2] = 0.5F;
+  z[3] = 0.4F;
+
+  baz (z);
+  if (x[0] != 0.7F || x[3] != 0.4F)
+    abort ();
+
+  vector float source = { 0.8F, 0.7F, 0.6F, 0.5F };
+
+  baz1 (source);
+  if (x[3] != 0.6F || x[2] != 0.7F)
+    abort ();
+
+  vector float dest;
+  baz2 (&dest, source);
+  if (dest[0] != 0.8F || dest[1] != 0.7F)
+    abort ();
+
+  baz3 (&a_struct, source);
+  if (a_struct.a_vector[3] != 0.5F || a_struct.a_vector[0] != 0.8F)
+    abort ();
+
+  return 0;
 }
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-40.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-40.c
index 3d1bd3f4b6f..50610d9ab81 100644
--- a/gcc/testsuite/gcc.target/powerpc/swaps-p8-40.c
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-40.c
@@ -7,20 +7,150 @@
 
 extern void abort (void);
 
-vector long long int y = { 0, 1 };
+vector long long x;
+vector long long y = { 1024, 2048 };
+vector long long z;
 
-vector long long int
+vector long long
 foo (void)
 {
-  return y;
+  return y;			/* Remove 1 swap and use lvx.  */
+}
+
+vector long long
+foo1 (void)
+{
+  x = y;			/* Remove 2 redundant swaps here.  */
+  return x;			/* Remove 1 swap and use lvx.  */
+}
+
+void __attribute__ ((noinline))
+fill_local (vector long long *vp)
+{
+  *vp = x;			/* Remove 2 redundant swaps here.  */
+}
+
+/* Test aligned load from local.  */
+vector long long
+foo2 (void)
+{
+  vector long long v;
+
+  /* Need to be clever here because v will normally reside in a
+     register rather than memory.  */
+  fill_local (&v);
+  return v;			/* Remove 1 swap and use lvx.  */
+}
+
+
+/* Test aligned load from pointer.  */
+vector long long
+foo3 (vector long long *arg)
+{
+  return *arg;			/* Remove 1 swap and use lvx.  */
+}
+
+/* In this structure, the compiler should insert padding to assure
+   that a_vector is properly aligned.  */
+struct bar {
+  short a_field;
+  vector long long a_vector;
+};
+
+vector long long
+foo4 (struct bar *bp)
+{
+  return bp->a_vector;		/* Remove 1 swap and use lvx.  */
+}
+
+/* Test aligned store to global.  */
+void
+baz (vector long long arg)
+{
+  x = arg;			/* Remove 1 swap and use stvx.  */
+}
+
+void __attribute__ ((noinline))
+copy_local (vector long long *arg)
+{
+  x = *arg;			/* Remove 2 redundant swaps.  */
+}
+
+
+/* Test aligned store to local.  */
+void
+baz1 (vector long long arg)
+{
+  vector long long v;
+
+  /* Need cleverness, because v will normally reside in a register
+     rather than memory.  */
+  v = arg;			/* Aligned store to local: remove 1
+				   swap and use stvx.  */
+  copy_local (&v);
+}
+
+/* Test aligned store to pointer.  */
+void
+baz2 (vector long long *arg1, vector long long arg2)
+{
+  /* Assume arg2 resides in register.  */
+  *arg1 = arg2;			/* Remove 1 swap and use stvx.  */
+}
+
+void
+baz3 (struct bar *bp, vector long long v)
+{
+  /* Assume v resides in register.  */
+  bp->a_vector = v;		/* Remove 1 swap and use stvx.  */
 }
 
 int
-main (int argc, int *argv[])
+main (long long argc, long long *argv[])
 {
-  vector long long int fetched_value = foo ();
-  if (fetched_value[0] != 0 || fetched_value[1] != 1)
+  vector long long fetched_value = foo ();
+  if (fetched_value[0] != 1024 || fetched_value[1] != 2048)
+    abort ();
+
+  fetched_value = foo1 ();
+  if (fetched_value[1] != 2048 || fetched_value[0] != 1024)
+    abort ();
+
+  fetched_value = foo2 ();
+  if (fetched_value[0] != 1024 || fetched_value[1] != 2048)
+    abort ();
+
+  fetched_value = foo3 (&x);
+  if (fetched_value[1] != 2048 || fetched_value[0] != 1024)
     abort ();
-  else
-    return 0;
+
+  struct bar a_struct;
+  a_struct.a_vector = x;	/* Remove 2 redundant swaps.  */
+  fetched_value = foo4 (&a_struct);
+  if (fetched_value[1] != 2048 || fetched_value[0] != 1024)
+    abort ();
+
+  z[0] = 7096;
+  z[1] = 6048;
+
+  baz (z);
+  if (x[0] != 7096 || x[1] != 6048)
+    abort ();
+
+  vector long long source = { 8192, 7096};
+
+  baz1 (source);
+  if (x[0] != 8192 || x[1] != 7096)
+    abort ();
+
+  vector long long dest;
+  baz2 (&dest, source);
+  if (dest[0] != 8192 || dest[1] != 7096)
+    abort ();
+
+  baz3 (&a_struct, source);
+  if (a_struct.a_vector[1] != 7096 || a_struct.a_vector[0] != 8192)
+    abort ();
+
+  return 0;
 }
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-41.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-41.c
index 3ac52fda59a..f8b1d03b908 100644
--- a/gcc/testsuite/gcc.target/powerpc/swaps-p8-41.c
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-41.c
@@ -7,20 +7,150 @@
 
 extern void abort (void);
 
-const vector long long int y = { 0, 1 };
+vector long long x;
+const vector long long y = { 1024, 2048 };
+vector long long z;
 
-vector long long int
+vector long long
 foo (void)
 {
-  return y;
+  return y;			/* Remove 1 swap and use lvx.  */
+}
+
+vector long long
+foo1 (void)
+{
+  x = y;			/* Remove 2 redundant swaps here.  */
+  return x;			/* Remove 1 swap and use lvx.  */
+}
+
+void __attribute__ ((noinline))
+fill_local (vector long long *vp)
+{
+  *vp = x;			/* Remove 2 redundant swaps here.  */
+}
+
+/* Test aligned load from local.  */
+vector long long
+foo2 (void)
+{
+  vector long long v;
+
+  /* Need to be clever here because v will normally reside in a
+     register rather than memory.  */
+  fill_local (&v);
+  return v;			/* Remove 1 swap and use lvx.  */
+}
+
+
+/* Test aligned load from pointer.  */
+vector long long
+foo3 (vector long long *arg)
+{
+  return *arg;			/* Remove 1 swap and use lvx.  */
+}
+
+/* In this structure, the compiler should insert padding to assure
+   that a_vector is properly aligned.  */
+struct bar {
+  short a_field;
+  vector long long a_vector;
+};
+
+vector long long
+foo4 (struct bar *bp)
+{
+  return bp->a_vector;		/* Remove 1 swap and use lvx.  */
+}
+
+/* Test aligned store to global.  */
+void
+baz (vector long long arg)
+{
+  x = arg;			/* Remove 1 swap and use stvx.  */
+}
+
+void __attribute__ ((noinline))
+copy_local (vector long long *arg)
+{
+  x = *arg;			/* Remove 2 redundant swaps.  */
+}
+
+
+/* Test aligned store to local.  */
+void
+baz1 (vector long long arg)
+{
+  vector long long v;
+
+  /* Need cleverness, because v will normally reside in a register
+     rather than memory.  */
+  v = arg;			/* Aligned store to local: remove 1
+				   swap and use stvx.  */
+  copy_local (&v);
+}
+
+/* Test aligned store to pointer.  */
+void
+baz2 (vector long long *arg1, vector long long arg2)
+{
+  /* Assume arg2 resides in register.  */
+  *arg1 = arg2;			/* Remove 1 swap and use stvx.  */
+}
+
+void
+baz3 (struct bar *bp, vector long long v)
+{
+  /* Assume v resides in register.  */
+  bp->a_vector = v;		/* Remove 1 swap and use stvx.  */
 }
 
 int
-main (int argc, char *argv[])
+main (long long argc, long long *argv[])
 {
-  vector long long int fetched_value = foo ();
-  if (fetched_value[0] != 0 || fetched_value[1] != 1)
+  vector long long fetched_value = foo ();
+  if (fetched_value[0] != 1024 || fetched_value[1] != 2048)
+    abort ();
+
+  fetched_value = foo1 ();
+  if (fetched_value[1] != 2048 || fetched_value[0] != 1024)
+    abort ();
+
+  fetched_value = foo2 ();
+  if (fetched_value[0] != 1024 || fetched_value[1] != 2048)
+    abort ();
+
+  fetched_value = foo3 (&x);
+  if (fetched_value[1] != 2048 || fetched_value[0] != 1024)
     abort ();
-  else
-    return 0;
+
+  struct bar a_struct;
+  a_struct.a_vector = x;	/* Remove 2 redundant swaps.  */
+  fetched_value = foo4 (&a_struct);
+  if (fetched_value[1] != 2048 || fetched_value[0] != 1024)
+    abort ();
+
+  z[0] = 7096;
+  z[1] = 6048;
+
+  baz (z);
+  if (x[0] != 7096 || x[1] != 6048)
+    abort ();
+
+  vector long long source = { 8192, 7096};
+
+  baz1 (source);
+  if (x[0] != 8192 || x[1] != 7096)
+    abort ();
+
+  vector long long dest;
+  baz2 (&dest, source);
+  if (dest[0] != 8192 || dest[1] != 7096)
+    abort ();
+
+  baz3 (&a_struct, source);
+  if (a_struct.a_vector[1] != 7096 || a_struct.a_vector[0] != 8192)
+    abort ();
+
+  return 0;
 }
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-42.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-42.c
index 1f2a73a07b0..a8efc304d51 100644
--- a/gcc/testsuite/gcc.target/powerpc/swaps-p8-42.c
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-42.c
@@ -2,27 +2,161 @@
 /* { dg-require-effective-target powerpc_p8vector_ok } */
 /* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power8" } } */
 /* { dg-options "-mcpu=power8 -O3 " } */
-/* { dg-final { scan-assembler-not "xxpermdi" } } */
-/* { dg-final { scan-assembler-not "xxswapd" } } */
+
+/* Previous versions of this test required that the assembler does not
+   contain xxpermdi or xxswapd.  However, with the more sophisticated
+   code generation used today, it is now possible that xxpermdi (aka
+   xxswapd) show up without being part of a lxvd2x or stxvd2x
+   sequence.  */
 
 #include <altivec.h>
 
 extern void abort (void);
 
-const vector long long int y = { 0, 1 };
+vector long long x;
+const vector long long y = { 1024, 2048 };
+vector long long z;
 
-vector long long int
+vector long long
 foo (void)
 {
-  return y;
+  return y;			/* Remove 1 swap and use lvx.  */
+}
+
+vector long long
+foo1 (void)
+{
+  x = y;			/* Remove 2 redundant swaps here.  */
+  return x;			/* Remove 1 swap and use lvx.  */
+}
+
+void __attribute__ ((noinline))
+fill_local (vector long long *vp)
+{
+  *vp = x;			/* Remove 2 redundant swaps here.  */
+}
+
+/* Test aligned load from local.  */
+vector long long
+foo2 (void)
+{
+  vector long long v;
+
+  /* Need to be clever here because v will normally reside in a
+     register rather than memory.  */
+  fill_local (&v);
+  return v;			/* Remove 1 swap and use lvx.  */
+}
+
+
+/* Test aligned load from pointer.  */
+vector long long
+foo3 (vector long long *arg)
+{
+  return *arg;			/* Remove 1 swap and use lvx.  */
+}
+
+/* In this structure, the compiler should insert padding to assure
+   that a_vector is properly aligned.  */
+struct bar {
+  short a_field;
+  vector long long a_vector;
+};
+
+vector long long
+foo4 (struct bar *bp)
+{
+  return bp->a_vector;		/* Remove 1 swap and use lvx.  */
+}
+
+/* Test aligned store to global.  */
+void
+baz (vector long long arg)
+{
+  x = arg;			/* Remove 1 swap and use stvx.  */
+}
+
+void __attribute__ ((noinline))
+copy_local (vector long long *arg)
+{
+  x = *arg;			/* Remove 2 redundant swaps.  */
+}
+
+
+/* Test aligned store to local.  */
+void
+baz1 (vector long long arg)
+{
+  vector long long v;
+
+  /* Need cleverness, because v will normally reside in a register
+     rather than memory.  */
+  v = arg;			/* Aligned store to local: remove 1
+				   swap and use stvx.  */
+  copy_local (&v);
+}
+
+/* Test aligned store to pointer.  */
+void
+baz2 (vector long long *arg1, vector long long arg2)
+{
+  /* Assume arg2 resides in register.  */
+  *arg1 = arg2;			/* Remove 1 swap and use stvx.  */
+}
+
+void
+baz3 (struct bar *bp, vector long long v)
+{
+  /* Assume v resides in register.  */
+  bp->a_vector = v;		/* Remove 1 swap and use stvx.  */
 }
 
 int
-main (int argc, char *argv[])
+main (long long argc, long long *argv[])
 {
-  vector long long int fetched_value = foo ();
-  if (fetched_value[0] != 0 || fetched_value[1] != 1)
+  vector long long fetched_value = foo ();
+  if (fetched_value[0] != 1024 || fetched_value[1] != 2048)
+    abort ();
+
+  fetched_value = foo1 ();
+  if (fetched_value[1] != 2048 || fetched_value[0] != 1024)
+    abort ();
+
+  fetched_value = foo2 ();
+  if (fetched_value[0] != 1024 || fetched_value[1] != 2048)
+    abort ();
+
+  fetched_value = foo3 (&x);
+  if (fetched_value[1] != 2048 || fetched_value[0] != 1024)
     abort ();
-  else
-    return 0;
+
+  struct bar a_struct;
+  a_struct.a_vector = x;	/* Remove 2 redundant swaps.  */
+  fetched_value = foo4 (&a_struct);
+  if (fetched_value[1] != 2048 || fetched_value[0] != 1024)
+    abort ();
+
+  z[0] = 7096;
+  z[1] = 6048;
+
+  baz (z);
+  if (x[0] != 7096 || x[1] != 6048)
+    abort ();
+
+  vector long long source = { 8192, 7096};
+
+  baz1 (source);
+  if (x[0] != 8192 || x[1] != 7096)
+    abort ();
+
+  vector long long dest;
+  baz2 (&dest, source);
+  if (dest[0] != 8192 || dest[1] != 7096)
+    abort ();
+
+  baz3 (&a_struct, source);
+  if (a_struct.a_vector[1] != 7096 || a_struct.a_vector[0] != 8192)
+    abort ();
+
+  return 0;
 }
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-43.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-43.c
index c3caf8898e1..ca1dc97fabf 100644
--- a/gcc/testsuite/gcc.target/powerpc/swaps-p8-43.c
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-43.c
@@ -7,20 +7,150 @@
 
 extern void abort (void);
 
-vector double y = { 0.0, 0.1 };
+vector double x;
+vector double y = { 0.1, 0.2 };
+vector double z;
 
 vector double
 foo (void)
 {
-  return y;
+  return y;			/* Remove 1 swap and use lvx.  */
+}
+
+vector double
+foo1 (void)
+{
+  x = y;			/* Remove 2 redundant swaps here.  */
+  return x;			/* Remove 1 swap and use lvx.  */
+}
+
+void __attribute__ ((noinline))
+fill_local (vector double *vp)
+{
+  *vp = x;			/* Remove 2 redundant swaps here.  */
+}
+
+/* Test aligned load from local.  */
+vector double
+foo2 (void)
+{
+  vector double v;
+
+  /* Need to be clever here because v will normally reside in a
+     register rather than memory.  */
+  fill_local (&v);
+  return v;			/* Remove 1 swap and use lvx.  */
+}
+
+
+/* Test aligned load from pointer.  */
+vector double
+foo3 (vector double *arg)
+{
+  return *arg;			/* Remove 1 swap and use lvx.  */
+}
+
+/* In this structure, the compiler should insert padding to assure
+   that a_vector is properly aligned.  */
+struct bar {
+  short a_field;
+  vector double a_vector;
+};
+
+vector double
+foo4 (struct bar *bp)
+{
+  return bp->a_vector;		/* Remove 1 swap and use lvx.  */
+}
+
+/* Test aligned store to global.  */
+void
+baz (vector double arg)
+{
+  x = arg;			/* Remove 1 swap and use stvx.  */
+}
+
+void __attribute__ ((noinline))
+copy_local (vector double *arg)
+{
+  x = *arg;			/* Remove 2 redundant swaps.  */
+}
+
+
+/* Test aligned store to local.  */
+void
+baz1 (vector double arg)
+{
+  vector double v;
+
+  /* Need cleverness, because v will normally reside in a register
+     rather than memory.  */
+  v = arg;			/* Aligned store to local: remove 1
+				   swap and use stvx.  */
+  copy_local (&v);
+}
+
+/* Test aligned store to pointer.  */
+void
+baz2 (vector double *arg1, vector double arg2)
+{
+  /* Assume arg2 resides in register.  */
+  *arg1 = arg2;			/* Remove 1 swap and use stvx.  */
+}
+
+void
+baz3 (struct bar *bp, vector double v)
+{
+  /* Assume v resides in register.  */
+  bp->a_vector = v;		/* Remove 1 swap and use stvx.  */
 }
 
 int
-main (int argc, char *argv[])
+main (double argc, double *argv[])
 {
   vector double fetched_value = foo ();
-  if (fetched_value[0] != 0 || fetched_value[1] != 0.1)
+  if (fetched_value[0] != 0.1 || fetched_value[1] != 0.2)
+    abort ();
+
+  fetched_value = foo1 ();
+  if (fetched_value[1] != 0.2 || fetched_value[0] != 0.1)
     abort ();
-  else
-    return 0;
+
+  fetched_value = foo2 ();
+  if (fetched_value[0] != 0.1 || fetched_value[1] != 0.2)
+    abort ();
+
+  fetched_value = foo3 (&x);
+  if (fetched_value[1] != 0.2 || fetched_value[0] != 0.1)
+    abort ();
+
+  struct bar a_struct;
+  a_struct.a_vector = x;	/* Remove 2 redundant swaps.  */
+  fetched_value = foo4 (&a_struct);
+  if (fetched_value[1] != 0.2 || fetched_value[0] != 0.1)
+    abort ();
+
+  z[0] = 0.7;
+  z[1] = 0.6;
+
+  baz (z);
+  if (x[0] != 0.7 || x[1] != 0.6)
+    abort ();
+
+  vector double source = { 0.8, 0.7 };
+
+  baz1 (source);
+  if (x[0] != 0.8 || x[1] != 0.7)
+    abort ();
+
+  vector double dest;
+  baz2 (&dest, source);
+  if (dest[0] != 0.8 || dest[1] != 0.7)
+    abort ();
+
+  baz3 (&a_struct, source);
+  if (a_struct.a_vector[1] != 0.7 || a_struct.a_vector[0] != 0.8)
+    abort ();
+
+  return 0;
 }
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-44.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-44.c
index 8ab513c0440..648016988a9 100644
--- a/gcc/testsuite/gcc.target/powerpc/swaps-p8-44.c
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-44.c
@@ -7,20 +7,150 @@
 
 extern void abort (void);
 
-const vector double y = { 0.0, 0.1 };
+vector double x;
+const vector double y = { 0.1, 0.2 };
+vector double z;
 
 vector double
 foo (void)
 {
-  return y;
+  return y;			/* Remove 1 swap and use lvx.  */
+}
+
+vector double
+foo1 (void)
+{
+  x = y;			/* Remove 2 redundant swaps here.  */
+  return x;			/* Remove 1 swap and use lvx.  */
+}
+
+void __attribute__ ((noinline))
+fill_local (vector double *vp)
+{
+  *vp = x;			/* Remove 2 redundant swaps here.  */
+}
+
+/* Test aligned load from local.  */
+vector double
+foo2 (void)
+{
+  vector double v;
+
+  /* Need to be clever here because v will normally reside in a
+     register rather than memory.  */
+  fill_local (&v);
+  return v;			/* Remove 1 swap and use lvx.  */
+}
+
+
+/* Test aligned load from pointer.  */
+vector double
+foo3 (vector double *arg)
+{
+  return *arg;			/* Remove 1 swap and use lvx.  */
+}
+
+/* In this structure, the compiler should insert padding to assure
+   that a_vector is properly aligned.  */
+struct bar {
+  short a_field;
+  vector double a_vector;
+};
+
+vector double
+foo4 (struct bar *bp)
+{
+  return bp->a_vector;		/* Remove 1 swap and use lvx.  */
+}
+
+/* Test aligned store to global.  */
+void
+baz (vector double arg)
+{
+  x = arg;			/* Remove 1 swap and use stvx.  */
+}
+
+void __attribute__ ((noinline))
+copy_local (vector double *arg)
+{
+  x = *arg;			/* Remove 2 redundant swaps.  */
+}
+
+
+/* Test aligned store to local.  */
+void
+baz1 (vector double arg)
+{
+  vector double v;
+
+  /* Need cleverness, because v will normally reside in a register
+     rather than memory.  */
+  v = arg;			/* Aligned store to local: remove 1
+				   swap and use stvx.  */
+  copy_local (&v);
+}
+
+/* Test aligned store to pointer.  */
+void
+baz2 (vector double *arg1, vector double arg2)
+{
+  /* Assume arg2 resides in register.  */
+  *arg1 = arg2;			/* Remove 1 swap and use stvx.  */
+}
+
+void
+baz3 (struct bar *bp, vector double v)
+{
+  /* Assume v resides in register.  */
+  bp->a_vector = v;		/* Remove 1 swap and use stvx.  */
 }
 
 int
-main (int argc, char *argv[])
+main (double argc, double *argv[])
 {
   vector double fetched_value = foo ();
-  if (fetched_value[0] != 0.0 || fetched_value[1] != 0.1)
+  if (fetched_value[0] != 0.1 || fetched_value[1] != 0.2)
+    abort ();
+
+  fetched_value = foo1 ();
+  if (fetched_value[1] != 0.2 || fetched_value[0] != 0.1)
     abort ();
-  else
-    return 0;
+
+  fetched_value = foo2 ();
+  if (fetched_value[0] != 0.1 || fetched_value[1] != 0.2)
+    abort ();
+
+  fetched_value = foo3 (&x);
+  if (fetched_value[1] != 0.2 || fetched_value[0] != 0.1)
+    abort ();
+
+  struct bar a_struct;
+  a_struct.a_vector = x;	/* Remove 2 redundant swaps.  */
+  fetched_value = foo4 (&a_struct);
+  if (fetched_value[1] != 0.2 || fetched_value[0] != 0.1)
+    abort ();
+
+  z[0] = 0.7;
+  z[1] = 0.6;
+
+  baz (z);
+  if (x[0] != 0.7 || x[1] != 0.6)
+    abort ();
+
+  vector double source = { 0.8, 0.7 };
+
+  baz1 (source);
+  if (x[0] != 0.8 || x[1] != 0.7)
+    abort ();
+
+  vector double dest;
+  baz2 (&dest, source);
+  if (dest[0] != 0.8 || dest[1] != 0.7)
+    abort ();
+
+  baz3 (&a_struct, source);
+  if (a_struct.a_vector[1] != 0.7 || a_struct.a_vector[0] != 0.8)
+    abort ();
+
+  return 0;
 }
diff --git a/gcc/testsuite/gcc.target/powerpc/swaps-p8-45.c b/gcc/testsuite/gcc.target/powerpc/swaps-p8-45.c
index 69953589782..3e8c7e77567 100644
--- a/gcc/testsuite/gcc.target/powerpc/swaps-p8-45.c
+++ b/gcc/testsuite/gcc.target/powerpc/swaps-p8-45.c
@@ -2,27 +2,161 @@
 /* { dg-require-effective-target powerpc_p8vector_ok } */
 /* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power8" } } */
 /* { dg-options "-mcpu=power8 -O3 " } */
-/* { dg-final { scan-assembler-not "xxpermdi" } } */
-/* { dg-final { scan-assembler-not "xxswapd" } } */
+
+/* Previous versions of this test required that the assembler does not
+   contain xxpermdi or xxswapd.  However, with the more sophisticated
+   code generation used today, it is now possible that xxpermdi (aka
+   xxswapd) show up without being part of a lxvd2x or stxvd2x
+   sequence.  */
 
 #include <altivec.h>
 
 extern void abort (void);
 
-const vector double y = { 0.0, 0.1 };
+vector double x;
+const vector double y = { 0.1, 0.2 };
+vector double z;
 
 vector double
 foo (void)
 {
-  return y;
+  return y;			/* Remove 1 swap and use lvx.  */
+}
+
+vector double
+foo1 (void)
+{
+  x = y;			/* Remove 2 redundant swaps here.  */
+  return x;			/* Remove 1 swap and use lvx.  */
+}
+
+void __attribute__ ((noinline))
+fill_local (vector double *vp)
+{
+  *vp = x;			/* Remove 2 redundant swaps here.  */
+}
+
+/* Test aligned load from local.  */
+vector double
+foo2 (void)
+{
+  vector double v;
+
+  /* Need to be clever here because v will normally reside in a
+     register rather than memory.  */
+  fill_local (&v);
+  return v;			/* Remove 1 swap and use lvx.  */
+}
+
+
+/* Test aligned load from pointer.  */
+vector double
+foo3 (vector double *arg)
+{
+  return *arg;			/* Remove 1 swap and use lvx.  */
+}
+
+/* In this structure, the compiler should insert padding to assure
+   that a_vector is properly aligned.  */
+struct bar {
+  short a_field;
+  vector double a_vector;
+};
+
+vector double
+foo4 (struct bar *bp)
+{
+  return bp->a_vector;		/* Remove 1 swap and use lvx.  */
+}
+
+/* Test aligned store to global.  */
+void
+baz (vector double arg)
+{
+  x = arg;			/* Remove 1 swap and use stvx.  */
+}
+
+void __attribute__ ((noinline))
+copy_local (vector double *arg)
+{
+  x = *arg;			/* Remove 2 redundant swaps.  */
+}
+
+
+/* Test aligned store to local.  */
+void
+baz1 (vector double arg)
+{
+  vector double v;
+
+  /* Need cleverness, because v will normally reside in a register
+     rather than memory.  */
+  v = arg;			/* Aligned store to local: remove 1
+				   swap and use stvx.  */
+  copy_local (&v);
+}
+
+/* Test aligned store to pointer.  */
+void
+baz2 (vector double *arg1, vector double arg2)
+{
+  /* Assume arg2 resides in register.  */
+  *arg1 = arg2;			/* Remove 1 swap and use stvx.  */
+}
+
+void
+baz3 (struct bar *bp, vector double v)
+{
+  /* Assume v resides in register.  */
+  bp->a_vector = v;		/* Remove 1 swap and use stvx.  */
 }
 
 int
-main (int argc, char *argv[])
+main (double argc, double *argv[])
 {
   vector double fetched_value = foo ();
-  if (fetched_value[0] != 0.0 || fetched_value[15] != 0.1)
+  if (fetched_value[0] != 0.1 || fetched_value[1] != 0.2)
+    abort ();
+
+  fetched_value = foo1 ();
+  if (fetched_value[1] != 0.2 || fetched_value[0] != 0.1)
     abort ();
-  else
-    return 0;
+
+  fetched_value = foo2 ();
+  if (fetched_value[0] != 0.1 || fetched_value[1] != 0.2)
+    abort ();
+
+  fetched_value = foo3 (&x);
+  if (fetched_value[1] != 0.2 || fetched_value[0] != 0.1)
+    abort ();
+
+  struct bar a_struct;
+  a_struct.a_vector = x;	/* Remove 2 redundant swaps.  */
+  fetched_value = foo4 (&a_struct);
+  if (fetched_value[1] != 0.2 || fetched_value[0] != 0.1)
+    abort ();
+
+  z[0] = 0.7;
+  z[1] = 0.6;
+
+  baz (z);
+  if (x[0] != 0.7 || x[1] != 0.6)
+    abort ();
+
+  vector double source = { 0.8, 0.7 };
+
+  baz1 (source);
+  if (x[0] != 0.8 || x[1] != 0.7)
+    abort ();
+
+  vector double dest;
+  baz2 (&dest, source);
+  if (dest[0] != 0.8 || dest[1] != 0.7)
+    abort ();
+
+  baz3 (&a_struct, source);
+  if (a_struct.a_vector[1] != 0.7 || a_struct.a_vector[0] != 0.8)
+    abort ();
+
+  return 0;
 }
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-extract-2.c b/gcc/testsuite/gcc.target/powerpc/vec-extract-2.c
index 007aeaf2fa1..2aea0baeff4 100644
--- a/gcc/testsuite/gcc.target/powerpc/vec-extract-2.c
+++ b/gcc/testsuite/gcc.target/powerpc/vec-extract-2.c
@@ -33,5 +33,7 @@ add_long_1 (vector long *p, long x)
 /* { dg-final { scan-assembler-not "lxvw4x"   } } */
 /* { dg-final { scan-assembler-not "lxvx"     } } */
 /* { dg-final { scan-assembler-not "lxv"      } } */
-/* { dg-final { scan-assembler-not "lvx"      } } */
-/* { dg-final { scan-assembler-not "xxpermdi" } } */
+
+/* With recent enhancements to the code generator, it is considered
+ * legal to implement vec_extract with lvx and xxpermdi.  Previous
+ * versions of this test forbid both instructions.  */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-extract-3.c b/gcc/testsuite/gcc.target/powerpc/vec-extract-3.c
index 2df48489fc7..aeacbfb262b 100644
--- a/gcc/testsuite/gcc.target/powerpc/vec-extract-3.c
+++ b/gcc/testsuite/gcc.target/powerpc/vec-extract-3.c
@@ -22,5 +22,7 @@ add_long_n (vector long *p, long x, long n)
 /* { dg-final { scan-assembler-not "lxvw4x"   } } */
 /* { dg-final { scan-assembler-not "lxvx"     } } */
 /* { dg-final { scan-assembler-not "lxv"      } } */
-/* { dg-final { scan-assembler-not "lvx"      } } */
-/* { dg-final { scan-assembler-not "xxpermdi" } } */
+
+/* With recent enhancements to the code generator, it is considered
+ * legal to implement vec_extract with lvx and xxpermdi.  Previous
+ * versions of this test forbid both instructions.  */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-extract-5.c b/gcc/testsuite/gcc.target/powerpc/vec-extract-5.c
index d85dab96bb6..9ee7bf2aa6c 100644
--- a/gcc/testsuite/gcc.target/powerpc/vec-extract-5.c
+++ b/gcc/testsuite/gcc.target/powerpc/vec-extract-5.c
@@ -64,5 +64,7 @@ add_signed_char_n (vector signed char *p, int n)
 /* { dg-final { scan-assembler-not "lxvw4x"   } } */
 /* { dg-final { scan-assembler-not "lxvx"     } } */
 /* { dg-final { scan-assembler-not "lxv"      } } */
-/* { dg-final { scan-assembler-not "lvx"      } } */
-/* { dg-final { scan-assembler-not "xxpermdi" } } */
+
+/* With recent enhancements to the code generator, it is considered
+ * legal to implement vec_extract with lvx and xxpermdi.  Previous
+ * versions of this test forbid both instructions.  */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-extract-6.c b/gcc/testsuite/gcc.target/powerpc/vec-extract-6.c
index 667b34948ba..c18f439080d 100644
--- a/gcc/testsuite/gcc.target/powerpc/vec-extract-6.c
+++ b/gcc/testsuite/gcc.target/powerpc/vec-extract-6.c
@@ -64,5 +64,7 @@ add_unsigned_char_n (vector unsigned char *p, int n)
 /* { dg-final { scan-assembler-not "lxvw4x"   } } */
 /* { dg-final { scan-assembler-not "lxvx"     } } */
 /* { dg-final { scan-assembler-not "lxv"      } } */
-/* { dg-final { scan-assembler-not "lvx"      } } */
-/* { dg-final { scan-assembler-not "xxpermdi" } } */
+
+/* With recent enhancements to the code generator, it is considered
+ * legal to implement vec_extract with lvx and xxpermdi.  Previous
+ * versions of this test forbid both instructions.  */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-extract-7.c b/gcc/testsuite/gcc.target/powerpc/vec-extract-7.c
index 6ee7c66890e..c3bc1dec128 100644
--- a/gcc/testsuite/gcc.target/powerpc/vec-extract-7.c
+++ b/gcc/testsuite/gcc.target/powerpc/vec-extract-7.c
@@ -40,5 +40,7 @@ add_float_n (vector float *p, long n)
 /* { dg-final { scan-assembler-not "lxvw4x"   } } */
 /* { dg-final { scan-assembler-not "lxvx"     } } */
 /* { dg-final { scan-assembler-not "lxv"      } } */
-/* { dg-final { scan-assembler-not "lvx"      } } */
-/* { dg-final { scan-assembler-not "xxpermdi" } } */
+
+/* With recent enhancements to the code generator, it is considered
+ * legal to implement vec_extract with lvx and xxpermdi.  Previous
+ * versions of this test forbid both instructions.  */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-extract-8.c b/gcc/testsuite/gcc.target/powerpc/vec-extract-8.c
index 95430904639..12e7c8977fc 100644
--- a/gcc/testsuite/gcc.target/powerpc/vec-extract-8.c
+++ b/gcc/testsuite/gcc.target/powerpc/vec-extract-8.c
@@ -40,5 +40,7 @@ add_int_n (vector int *p, int n)
 /* { dg-final { scan-assembler-not "lxvw4x"   } } */
 /* { dg-final { scan-assembler-not "lxvx"     } } */
 /* { dg-final { scan-assembler-not "lxv"      } } */
-/* { dg-final { scan-assembler-not "lvx"      } } */
-/* { dg-final { scan-assembler-not "xxpermdi" } } */
+
+/* With recent enhancements to the code generator, it is considered
+ * legal to implement vec_extract with lvx and xxpermdi.  Previous
+ * versions of this test forbid both instructions.  */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-extract-9.c b/gcc/testsuite/gcc.target/powerpc/vec-extract-9.c
index 5932013696e..2adadf21951 100644
--- a/gcc/testsuite/gcc.target/powerpc/vec-extract-9.c
+++ b/gcc/testsuite/gcc.target/powerpc/vec-extract-9.c
@@ -64,5 +64,7 @@ add_short_n (vector short *p, int n)
 /* { dg-final { scan-assembler-not "lxvw4x"   } } */
 /* { dg-final { scan-assembler-not "lxvx"     } } */
 /* { dg-final { scan-assembler-not "lxv"      } } */
-/* { dg-final { scan-assembler-not "lvx"      } } */
-/* { dg-final { scan-assembler-not "xxpermdi" } } */
+
+/* With recent enhancements to the code generator, it is considered
+ * legal to implement vec_extract with lvx and xxpermdi.  Previous
+ * versions of this test forbid both instructions.  */
diff --git a/gcc/testsuite/gcc.target/powerpc/vsx-vector-6-le.c b/gcc/testsuite/gcc.target/powerpc/vsx-vector-6-le.c
index ad424b25572..ddb0089c396 100644
--- a/gcc/testsuite/gcc.target/powerpc/vsx-vector-6-le.c
+++ b/gcc/testsuite/gcc.target/powerpc/vsx-vector-6-le.c
@@ -7,10 +7,10 @@
 
 /* { dg-final { scan-assembler-times "xvabsdp" 1 } } */
 /* { dg-final { scan-assembler-times "xvadddp" 1 } } */
-/* { dg-final { scan-assembler-times "xxlnor" 6 } } */
-/* { dg-final { scan-assembler-times "xxlor" 16 } } */
+/* { dg-final { scan-assembler-times "xxlnor" 8 } } */
+/* { dg-final { scan-assembler-times "xxlor" 30 } } */
 /* { dg-final { scan-assembler-times "xvcmpeqdp" 5 } } */
-/* { dg-final { scan-assembler-times "xvcmpgtdp" 7 } } */
+/* { dg-final { scan-assembler-times "xvcmpgtdp" 8 } } */
 /* { dg-final { scan-assembler-times "xvcmpgedp" 6 } } */
 /* { dg-final { scan-assembler-times "xvrdpim" 1 } } */
 /* { dg-final { scan-assembler-times "xvmaddadp" 1 } } */
@@ -26,7 +26,7 @@
 /* { dg-final { scan-assembler-times "xvmsubasp" 1 } } */
 /* { dg-final { scan-assembler-times "xvnmaddasp" 1 } } */
 /* { dg-final { scan-assembler-times "vmsumshs" 1 } } */
-/* { dg-final { scan-assembler-times "xxland" 9 } } */
+/* { dg-final { scan-assembler-times "xxland" 13 } } */
 
 /* Source code for the test in vsx-vector-6.h */
 #include "vsx-vector-6.h"
diff --git a/libcpp/ChangeLog b/libcpp/ChangeLog
index 34b676db99e..b69e3645bad 100644
--- a/libcpp/ChangeLog
+++ b/libcpp/ChangeLog
@@ -1,3 +1,10 @@
+2018-01-10  Kelvin Nilsen  <kelvin@gcc.gnu.org>
+
+	* lex.c (search_line_fast): Remove illegal coercion of an
+	unaligned pointer value to vector pointer type and replace with
+	use of __builtin_vec_vsx_ld () built-in function, which operates
+	on unaligned pointer values.
+
 2018-01-03  Jakub Jelinek  <jakub@redhat.com>
 
 	Update copyright years.
diff --git a/libcpp/lex.c b/libcpp/lex.c
index 860b31ea6c3..92c62517a4d 100644
--- a/libcpp/lex.c
+++ b/libcpp/lex.c
@@ -568,7 +568,7 @@ search_line_fast (const uchar *s, const uchar *end ATTRIBUTE_UNUSED)
     {
       vc m_nl, m_cr, m_bs, m_qm;
 
-      data = *((const vc *)s);
+      data = __builtin_vec_vsx_ld (0, s);
       s += 16;
 
       m_nl = (vc) __builtin_vec_cmpeq(data, repl_nl);