[6/6,ver,3] rs6000 Add vector blend, permute builtin support

Message ID 5f85bbec1e27339ce510f92ffccd6cdf0b79e068.camel@us.ibm.com
State Superseded
Headers show
Series
  • ] Permute Class Operations
Related show

Commit Message

Christophe Lyon via Gcc-patches June 18, 2020, 10:20 p.m.
v3 fixes:
   Replace spaces with tabs in ChangeLog description.
   Fix implementation comments for define_expand "xxpermx" in file
     gcc/config/rs6000/alitvec.md.
   Fix minor typos in the comments for the changes in gcc/config/rs6000/rs6000-call.c.

--------------------
v2 changes:

   Updated ChangeLog per comments.

   Updated implementation of the define_expand "xxpermx".

   Fixed the comments and check for 3-bit immediate field for the
	CODE_FOR_xxpermx check.

   gcc/doc/extend.texi:
	comment "Maybe it should say it is related to vsel/xxsel, but per
	bigger element?", added comment.  I took the description directly
	from spec.  Don't really don't want to mess with the approved
	description.

       fixed typo for Vector Permute Extendedextracth

----------

GCC maintainers:

The following patch adds support for the vec_blendv and vec_permx
builtins.

The patch has been compiled and tested on

  powerpc64le-unknown-linux-gnu (Power 9 LE)

with no regression errors.

The test cases were compiled on a Power 9 system and then tested on
Mambo.

                         Carl Love

---------------------------------------------------------------
rs6000 RFC2609 vector blend, permute instructions

gcc/ChangeLog

2020-06-18  Carl Love  <cel@us.ibm.com>

	* config/rs6000/altivec.h (vec_blendv, vec_permx): Add define.
	* config/rs6000/altivec.md (UNSPEC_XXBLEND, UNSPEC_XXPERMX.): New
	unspecs.
	(VM3): New define_mode.
	(VM3_char): New define_attr.
	(xxblend_<mode> mode VM3): New define_insn.
	(xxpermx): New define_expand.
	(xxpermx_inst): New define_insn.
	* config/rs6000/rs6000-builtin.def (VXXBLEND_V16QI, VXXBLEND_V8HI,
	VXXBLEND_V4SI, VXXBLEND_V2DI, VXXBLEND_V4SF, VXXBLEND_V2DF): New
	BU_FUTURE_V_3 definitions.
	(XXBLENDBU_FUTURE_OVERLOAD_3): New BU_FUTURE_OVERLOAD_3 definition.
	(XXPERMX): New BU_FUTURE_OVERLOAD_4 definition.
	* config/rs6000/rs6000-c.c (altivec_resolve_overloaded_builtin):
	(FUTURE_BUILTIN_VXXPERMX): Add if case support.
	* config/rs6000/rs6000-call.c (FUTURE_BUILTIN_VXXBLEND_V16QI,
	FUTURE_BUILTIN_VXXBLEND_V8HI, FUTURE_BUILTIN_VXXBLEND_V4SI,
	FUTURE_BUILTIN_VXXBLEND_V2DI, FUTURE_BUILTIN_VXXBLEND_V4SF,
	FUTURE_BUILTIN_VXXBLEND_V2DF, FUTURE_BUILTIN_VXXPERMX): Define
	overloaded arguments.
	(rs6000_expand_quaternop_builtin): Add if case for CODE_FOR_xxpermx.
	(builtin_quaternary_function_type): Add v16uqi_type and xxpermx_type
	variables, add case statement for FUTURE_BUILTIN_VXXPERMX.
	(builtin_function_type)[FUTURE_BUILTIN_VXXBLEND_V16QI,
	FUTURE_BUILTIN_VXXBLEND_V8HI, FUTURE_BUILTIN_VXXBLEND_V4SI,
	FUTURE_BUILTIN_VXXBLEND_V2DI]: Add case statements.
	* doc/extend.texi: Add documentation for vec_blendv and vec_permx.

gcc/testsuite/ChangeLog

2020-06-18  Carl Love  <cel@us.ibm.com>
	gcc.target/powerpc/vec-blend-runnable.c: New test.
	gcc.target/powerpc/vec-permute-ext-runnable.c: New test.
---
 gcc/config/rs6000/altivec.h                   |   2 +
 gcc/config/rs6000/altivec.md                  |  71 +++++
 gcc/config/rs6000/rs6000-builtin.def          |  13 +
 gcc/config/rs6000/rs6000-c.c                  |  28 +-
 gcc/config/rs6000/rs6000-call.c               |  94 ++++++
 gcc/doc/extend.texi                           |  63 ++++
 .../gcc.target/powerpc/vec-blend-runnable.c   | 276 ++++++++++++++++
 .../powerpc/vec-permute-ext-runnable.c        | 294 ++++++++++++++++++
 8 files changed, 834 insertions(+), 7 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/powerpc/vec-blend-runnable.c
 create mode 100644 gcc/testsuite/gcc.target/powerpc/vec-permute-ext-runnable.c

-- 
2.17.1

Patch

diff --git a/gcc/config/rs6000/altivec.h b/gcc/config/rs6000/altivec.h
index 9ed41b1cbf1..1b532effebe 100644
--- a/gcc/config/rs6000/altivec.h
+++ b/gcc/config/rs6000/altivec.h
@@ -708,6 +708,8 @@  __altivec_scalar_pred(vec_any_nle,
 #define vec_splati(a)  __builtin_vec_xxspltiw (a)
 #define vec_splatid(a) __builtin_vec_xxspltid (a)
 #define vec_splati_ins(a, b, c)        __builtin_vec_xxsplti32dx (a, b, c)
+#define vec_blendv(a, b, c)    __builtin_vec_xxblend (a, b, c)
+#define vec_permx(a, b, c, d)  __builtin_vec_xxpermx (a, b, c, d)
 
 #define vec_gnb(a, b)	__builtin_vec_gnb (a, b)
 #define vec_clrl(a, b)	__builtin_vec_clrl (a, b)
diff --git a/gcc/config/rs6000/altivec.md b/gcc/config/rs6000/altivec.md
index 25f6b9b2f07..6280586fb2c 100644
--- a/gcc/config/rs6000/altivec.md
+++ b/gcc/config/rs6000/altivec.md
@@ -176,6 +176,8 @@ 
    UNSPEC_XXSPLTIW
    UNSPEC_XXSPLTID
    UNSPEC_XXSPLTI32DX
+   UNSPEC_XXBLEND
+   UNSPEC_XXPERMX
 ])
 
 (define_c_enum "unspecv"
@@ -218,6 +220,21 @@ 
 			   (KF "FLOAT128_VECTOR_P (KFmode)")
 			   (TF "FLOAT128_VECTOR_P (TFmode)")])
 
+;; Like VM2, just do char, short, int, long, float and double
+(define_mode_iterator VM3 [V4SI
+			   V8HI
+			   V16QI
+			   V4SF
+			   V2DF
+			   V2DI])
+
+(define_mode_attr VM3_char [(V2DI "d")
+			   (V4SI "w")
+			   (V8HI "h")
+			   (V16QI "b")
+			   (V2DF  "d")
+			   (V4SF  "w")])
+
 ;; Map the Vector convert single precision to double precision for integer
 ;; versus floating point
 (define_mode_attr VS_sxwsp [(V4SI "sxw") (V4SF "sp")])
@@ -908,6 +925,60 @@ 
   "xxsplti32dx %x0,%1,%2"
    [(set_attr "type" "vecsimple")])
 
+(define_insn "xxblend_<mode>"
+  [(set (match_operand:VM3 0 "register_operand" "=wa")
+	(unspec:VM3 [(match_operand:VM3 1 "register_operand" "wa")
+		     (match_operand:VM3 2 "register_operand" "wa")
+		     (match_operand:VM3 3 "register_operand" "wa")]
+		    UNSPEC_XXBLEND))]
+  "TARGET_FUTURE"
+  "xxblendv<VM3_char> %x0,%x1,%x2,%x3"
+  [(set_attr "type" "vecsimple")])
+
+(define_expand "xxpermx"
+  [(set (match_operand:V2DI 0 "register_operand" "+wa")
+	(unspec:V2DI [(match_operand:V2DI 1 "register_operand" "wa")
+		      (match_operand:V2DI 2 "register_operand" "wa")
+		      (match_operand:V16QI 3 "register_operand" "wa")
+		      (match_operand:QI 4 "u8bit_cint_operand" "n")]
+		     UNSPEC_XXPERMX))]
+  "TARGET_FUTURE"
+{
+  if (BYTES_BIG_ENDIAN)
+    emit_insn (gen_xxpermx_inst (operands[0], operands[1],
+				 operands[2], operands[3],
+				 operands[4]));
+  else
+    {
+      /* Reverse value of byte element indexes by XORing with 0xFF.
+	 Reverse the 32-byte section identifier match by subracting bits [0:2]
+	 of elemet from 7.  */
+      int value = INTVAL (operands[4]);
+      rtx vreg = gen_reg_rtx (V16QImode);
+
+      emit_insn (gen_xxspltib_v16qi (vreg, GEN_INT (-1)));
+      emit_insn (gen_xorv16qi3 (operands[3], operands[3], vreg));
+      value = 7 - value;
+      emit_insn (gen_xxpermx_inst (operands[0], operands[2],
+				   operands[1], operands[3],
+				   GEN_INT (value)));
+    }
+
+  DONE;
+}
+  [(set_attr "type" "vecsimple")])
+
+(define_insn "xxpermx_inst"
+  [(set (match_operand:V2DI 0 "register_operand" "+v")
+	(unspec:V2DI [(match_operand:V2DI 1 "register_operand" "v")
+		      (match_operand:V2DI 2 "register_operand" "v")
+		      (match_operand:V16QI 3 "register_operand" "v")
+		      (match_operand:QI 4 "u3bit_cint_operand" "n")]
+		     UNSPEC_XXPERMX))]
+  "TARGET_FUTURE"
+  "xxpermx %x0,%x1,%x2,%x3,%4"
+  [(set_attr "type" "vecsimple")])
+
 (define_expand "vstrir_<mode>"
   [(set (match_operand:VIshort 0 "altivec_register_operand")
 	(unspec:VIshort [(match_operand:VIshort 1 "altivec_register_operand")]
diff --git a/gcc/config/rs6000/rs6000-builtin.def b/gcc/config/rs6000/rs6000-builtin.def
index c85326de7f2..d1d04f013bb 100644
--- a/gcc/config/rs6000/rs6000-builtin.def
+++ b/gcc/config/rs6000/rs6000-builtin.def
@@ -2675,6 +2675,15 @@  BU_FUTURE_V_1 (VXXSPLTID, "vxxspltidp", CONST, xxspltidp_v2df)
 BU_FUTURE_V_3 (VXXSPLTI32DX_V4SI, "vxxsplti32dx_v4si", CONST, xxsplti32dx_v4si)
 BU_FUTURE_V_3 (VXXSPLTI32DX_V4SF, "vxxsplti32dx_v4sf", CONST, xxsplti32dx_v4sf)
 
+BU_FUTURE_V_3 (VXXBLEND_V16QI, "xxblend_v16qi", CONST, xxblend_v16qi)
+BU_FUTURE_V_3 (VXXBLEND_V8HI, "xxblend_v8hi", CONST, xxblend_v8hi)
+BU_FUTURE_V_3 (VXXBLEND_V4SI, "xxblend_v4si", CONST, xxblend_v4si)
+BU_FUTURE_V_3 (VXXBLEND_V2DI, "xxblend_v2di", CONST, xxblend_v2di)
+BU_FUTURE_V_3 (VXXBLEND_V4SF, "xxblend_v4sf", CONST, xxblend_v4sf)
+BU_FUTURE_V_3 (VXXBLEND_V2DF, "xxblend_v2df", CONST, xxblend_v2df)
+
+BU_FUTURE_V_4 (VXXPERMX, "xxpermx", CONST, xxpermx)
+
 BU_FUTURE_V_1 (VSTRIBR, "vstribr", CONST, vstrir_v16qi)
 BU_FUTURE_V_1 (VSTRIHR, "vstrihr", CONST, vstrir_v8hi)
 BU_FUTURE_V_1 (VSTRIBL, "vstribl", CONST, vstril_v16qi)
@@ -2710,6 +2719,10 @@  BU_FUTURE_OVERLOAD_1 (VSTRIL_P, "stril_p")
 BU_FUTURE_OVERLOAD_1 (XXSPLTIW, "xxspltiw")
 BU_FUTURE_OVERLOAD_1 (XXSPLTID, "xxspltid")
 BU_FUTURE_OVERLOAD_3 (XXSPLTI32DX, "xxsplti32dx")
+
+BU_FUTURE_OVERLOAD_3 (XXBLEND, "xxblend")
+BU_FUTURE_OVERLOAD_4 (XXPERMX, "xxpermx")
+
 
 /* 1 argument crypto functions.  */
 BU_CRYPTO_1 (VSBOX,		"vsbox",	  CONST, crypto_vsbox_v2di)
diff --git a/gcc/config/rs6000/rs6000-c.c b/gcc/config/rs6000/rs6000-c.c
index 07ca33a89b4..3acbb3ca8a4 100644
--- a/gcc/config/rs6000/rs6000-c.c
+++ b/gcc/config/rs6000/rs6000-c.c
@@ -1796,22 +1796,36 @@  altivec_resolve_overloaded_builtin (location_t loc, tree fndecl,
 	      unsupported_builtin = true;
 	  }
       }
-    else if (fcode == FUTURE_BUILTIN_VEC_XXEVAL)
+    else if ((fcode == FUTURE_BUILTIN_VEC_XXEVAL)
+	     || (fcode == FUTURE_BUILTIN_VXXPERMX))
       {
-	/* Need to special case __builtin_vec_xxeval because this takes
-	   4 arguments, and the existing infrastructure handles no
-	   more than three.  */
+	signed char op3_type;
+
+	/* Need to special case the builins_xxeval because it takes
+	   4 arguments, and the existing infrastructure handles three.  */
 	if (nargs != 4)
 	  {
-	    error ("builtin %qs requires 4 arguments",
-		   "__builtin_vec_xxeval");
+	    if (fcode == FUTURE_BUILTIN_VEC_XXEVAL)
+	      error ("builtin %qs requires 4 arguments",
+		     "__builtin_vec_xxeval");
+	    else
+	      error ("builtin %qs requires 4 arguments",
+		     "__builtin_vec_xxpermx");
+
 	    return error_mark_node;
 	  }
+
+	/* Set value for vec_xxpermx here as it is a constant.  */
+	op3_type = RS6000_BTI_V16QI;
+
 	for ( ; desc->code == fcode; desc++)
 	  {
+	    if (fcode == FUTURE_BUILTIN_VEC_XXEVAL)
+	      op3_type = desc->op3;
+
 	    if (rs6000_builtin_type_compatible (types[0], desc->op1)
 		&& rs6000_builtin_type_compatible (types[1], desc->op2)
-		&& rs6000_builtin_type_compatible (types[2], desc->op3)
+		&& rs6000_builtin_type_compatible (types[2], op3_type)
 		&& rs6000_builtin_type_compatible (types[3],
 						   RS6000_BTI_UINTSI))
 	      {
diff --git a/gcc/config/rs6000/rs6000-call.c b/gcc/config/rs6000/rs6000-call.c
index e36aafaf71c..6770a7f05a2 100644
--- a/gcc/config/rs6000/rs6000-call.c
+++ b/gcc/config/rs6000/rs6000-call.c
@@ -5554,6 +5554,39 @@  const struct altivec_builtin_types altivec_overloaded_builtins[] = {
     RS6000_BTI_unsigned_V1TI, RS6000_BTI_unsigned_V1TI,
     RS6000_BTI_unsigned_V1TI, RS6000_BTI_unsigned_V1TI },
 
+  /* The overloaded XXPERMX definitions are handled specially because the
+     fourth unsigned char operand is not encoded in this table.  */
+  {  FUTURE_BUILTIN_VEC_XXPERMX, FUTURE_BUILTIN_VXXPERMX,
+     RS6000_BTI_V16QI, RS6000_BTI_V16QI, RS6000_BTI_V16QI,
+     RS6000_BTI_unsigned_V16QI },
+  {  FUTURE_BUILTIN_VEC_XXPERMX, FUTURE_BUILTIN_VXXPERMX,
+     RS6000_BTI_unsigned_V16QI, RS6000_BTI_unsigned_V16QI,
+     RS6000_BTI_unsigned_V16QI, RS6000_BTI_unsigned_V16QI },
+  {  FUTURE_BUILTIN_VEC_XXPERMX, FUTURE_BUILTIN_VXXPERMX,
+     RS6000_BTI_V8HI, RS6000_BTI_V8HI, RS6000_BTI_V8HI,
+     RS6000_BTI_unsigned_V16QI },
+  {  FUTURE_BUILTIN_VEC_XXPERMX, FUTURE_BUILTIN_VXXPERMX,
+     RS6000_BTI_unsigned_V8HI, RS6000_BTI_unsigned_V8HI,
+     RS6000_BTI_unsigned_V8HI, RS6000_BTI_unsigned_V16QI },
+  {  FUTURE_BUILTIN_VEC_XXPERMX, FUTURE_BUILTIN_VXXPERMX,
+     RS6000_BTI_V4SI, RS6000_BTI_V4SI, RS6000_BTI_V4SI,
+     RS6000_BTI_unsigned_V16QI },
+  {  FUTURE_BUILTIN_VEC_XXPERMX, FUTURE_BUILTIN_VXXPERMX,
+     RS6000_BTI_unsigned_V4SI, RS6000_BTI_unsigned_V4SI,
+     RS6000_BTI_unsigned_V4SI, RS6000_BTI_unsigned_V16QI },
+  {  FUTURE_BUILTIN_VEC_XXPERMX, FUTURE_BUILTIN_VXXPERMX,
+     RS6000_BTI_V2DI, RS6000_BTI_V2DI, RS6000_BTI_V2DI,
+     RS6000_BTI_unsigned_V16QI },
+  {  FUTURE_BUILTIN_VEC_XXPERMX, FUTURE_BUILTIN_VXXPERMX,
+     RS6000_BTI_unsigned_V2DI, RS6000_BTI_unsigned_V2DI,
+     RS6000_BTI_unsigned_V2DI, RS6000_BTI_unsigned_V16QI },
+  {  FUTURE_BUILTIN_VEC_XXPERMX, FUTURE_BUILTIN_VXXPERMX,
+     RS6000_BTI_V4SF, RS6000_BTI_V4SF, RS6000_BTI_V4SF,
+     RS6000_BTI_unsigned_V16QI },
+  {  FUTURE_BUILTIN_VEC_XXPERMX, FUTURE_BUILTIN_VXXPERMX,
+     RS6000_BTI_V2DF, RS6000_BTI_V2DF, RS6000_BTI_V2DF,
+     RS6000_BTI_unsigned_V16QI },
+
   { FUTURE_BUILTIN_VEC_EXTRACTL, FUTURE_BUILTIN_VEXTRACTBL,
     RS6000_BTI_unsigned_V2DI, RS6000_BTI_unsigned_V16QI,
     RS6000_BTI_unsigned_V16QI, RS6000_BTI_UINTQI },
@@ -5695,6 +5728,37 @@  const struct altivec_builtin_types altivec_overloaded_builtins[] = {
   { FUTURE_BUILTIN_VEC_XXSPLTI32DX, FUTURE_BUILTIN_VXXSPLTI32DX_V4SF,
     RS6000_BTI_V4SF, RS6000_BTI_V4SF, RS6000_BTI_UINTQI, RS6000_BTI_float },
 
+  {  FUTURE_BUILTIN_VEC_XXBLEND, FUTURE_BUILTIN_VXXBLEND_V16QI,
+     RS6000_BTI_V16QI, RS6000_BTI_V16QI, RS6000_BTI_V16QI,
+     RS6000_BTI_unsigned_V16QI },
+  {  FUTURE_BUILTIN_VEC_XXBLEND, FUTURE_BUILTIN_VXXBLEND_V16QI,
+     RS6000_BTI_unsigned_V16QI, RS6000_BTI_unsigned_V16QI,
+     RS6000_BTI_unsigned_V16QI, RS6000_BTI_unsigned_V16QI },
+  {  FUTURE_BUILTIN_VEC_XXBLEND, FUTURE_BUILTIN_VXXBLEND_V8HI,
+     RS6000_BTI_V8HI, RS6000_BTI_V8HI, RS6000_BTI_V8HI,
+     RS6000_BTI_unsigned_V8HI },
+  {  FUTURE_BUILTIN_VEC_XXBLEND, FUTURE_BUILTIN_VXXBLEND_V8HI,
+     RS6000_BTI_unsigned_V8HI, RS6000_BTI_unsigned_V8HI,
+     RS6000_BTI_unsigned_V8HI, RS6000_BTI_unsigned_V8HI },
+  {  FUTURE_BUILTIN_VEC_XXBLEND, FUTURE_BUILTIN_VXXBLEND_V4SI,
+     RS6000_BTI_V4SI, RS6000_BTI_V4SI, RS6000_BTI_V4SI,
+     RS6000_BTI_unsigned_V4SI },
+  {  FUTURE_BUILTIN_VEC_XXBLEND, FUTURE_BUILTIN_VXXBLEND_V4SI,
+     RS6000_BTI_unsigned_V4SI, RS6000_BTI_unsigned_V4SI,
+     RS6000_BTI_unsigned_V4SI, RS6000_BTI_unsigned_V4SI },
+  {  FUTURE_BUILTIN_VEC_XXBLEND, FUTURE_BUILTIN_VXXBLEND_V2DI,
+     RS6000_BTI_V2DI, RS6000_BTI_V2DI, RS6000_BTI_V2DI,
+     RS6000_BTI_unsigned_V2DI },
+  {  FUTURE_BUILTIN_VEC_XXBLEND, FUTURE_BUILTIN_VXXBLEND_V2DI,
+     RS6000_BTI_unsigned_V2DI, RS6000_BTI_unsigned_V2DI,
+     RS6000_BTI_unsigned_V2DI, RS6000_BTI_unsigned_V2DI },
+  {  FUTURE_BUILTIN_VEC_XXBLEND, FUTURE_BUILTIN_VXXBLEND_V4SF,
+     RS6000_BTI_V4SF, RS6000_BTI_V4SF, RS6000_BTI_V4SF,
+     RS6000_BTI_unsigned_V4SI },
+  {  FUTURE_BUILTIN_VEC_XXBLEND, FUTURE_BUILTIN_VXXBLEND_V2DF,
+     RS6000_BTI_V2DF, RS6000_BTI_V2DF, RS6000_BTI_V2DF,
+     RS6000_BTI_unsigned_V2DI },
+
   { FUTURE_BUILTIN_VEC_SRDB, FUTURE_BUILTIN_VSRDB_V16QI,
     RS6000_BTI_V16QI, RS6000_BTI_V16QI,
     RS6000_BTI_V16QI, RS6000_BTI_UINTQI },
@@ -9911,6 +9975,18 @@  rs6000_expand_quaternop_builtin (enum insn_code icode, tree exp, rtx target)
 	}
     }
 
+  else if (icode == CODE_FOR_xxpermx)
+    {
+      /* Only allow 3-bit unsigned literals.  */
+      STRIP_NOPS (arg3);
+      if (TREE_CODE (arg3) != INTEGER_CST
+	  || TREE_INT_CST_LOW (arg3) & ~0x7)
+	{
+	  error ("argument 4 must be an 3-bit unsigned literal");
+	  return CONST0_RTX (tmode);
+	}
+    }
+
   if (target == 0
       || GET_MODE (target) != tmode
       || ! (*insn_data[icode].operand[0].predicate) (target, tmode))
@@ -13293,12 +13369,17 @@  builtin_quaternary_function_type (machine_mode mode_ret,
   tree function_type = NULL;
 
   static tree v2udi_type = builtin_mode_to_type[V2DImode][1];
+  static tree v16uqi_type = builtin_mode_to_type[V16QImode][1];
   static tree uchar_type = builtin_mode_to_type[QImode][1];
 
   static tree xxeval_type =
     build_function_type_list (v2udi_type, v2udi_type, v2udi_type,
 			      v2udi_type, uchar_type, NULL_TREE);
 
+  static tree xxpermx_type =
+    build_function_type_list (v2udi_type, v2udi_type, v2udi_type,
+			      v16uqi_type, uchar_type, NULL_TREE);
+
   switch (builtin) {
 
   case FUTURE_BUILTIN_XXEVAL:
@@ -13310,6 +13391,15 @@  builtin_quaternary_function_type (machine_mode mode_ret,
     function_type = xxeval_type;
     break;
 
+  case FUTURE_BUILTIN_VXXPERMX:
+    gcc_assert ((mode_ret == V2DImode)
+		&& (mode_arg0 == V2DImode)
+		&& (mode_arg1 == V2DImode)
+		&& (mode_arg2 == V16QImode)
+		&& (mode_arg3 == QImode));
+    function_type = xxpermx_type;
+    break;
+
   default:
     /* A case for each quaternary built-in must be provided above.  */
     gcc_unreachable ();
@@ -13489,6 +13579,10 @@  builtin_function_type (machine_mode mode_ret, machine_mode mode_arg0,
     case FUTURE_BUILTIN_VREPLACE_ELT_UV2DI:
     case FUTURE_BUILTIN_VREPLACE_UN_UV4SI:
     case FUTURE_BUILTIN_VREPLACE_UN_UV2DI:
+    case FUTURE_BUILTIN_VXXBLEND_V16QI:
+    case FUTURE_BUILTIN_VXXBLEND_V8HI:
+    case FUTURE_BUILTIN_VXXBLEND_V4SI:
+    case FUTURE_BUILTIN_VXXBLEND_V2DI:
       h.uns_p[0] = 1;
       h.uns_p[1] = 1;
       h.uns_p[2] = 1;
diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
index 37d11e1ef41..63d3a9babe8 100644
--- a/gcc/doc/extend.texi
+++ b/gcc/doc/extend.texi
@@ -21185,6 +21185,69 @@  result.  The other words of argument 1 are unchanged.
 
 @findex vec_splati_ins
 
+Vector Blend Variable
+
+@smallexample
+@exdent vector signed char vec_blendv (vector signed char, vector signed char,
+vector unsigned char);
+@exdent vector unsigned char vec_blendv (vector unsigned char,
+vector unsigned char, vector unsigned char);
+@exdent vector signed short vec_blendv (vector signed short,
+vector signed short, vector unsigned short);
+@exdent vector unsigned short vec_blendv (vector unsigned short,
+vector unsigned short, vector unsigned short);
+@exdent vector signed int vec_blendv (vector signed int, vector signed int,
+vector unsigned int);
+@exdent vector unsigned int vec_blendv (vector unsigned int,
+vector unsigned int, vector unsigned int);
+@exdent vector signed long long vec_blendv (vector signed long long,
+vector signed long long, vector unsigned long long);
+@exdent vector unsigned long long vec_blendv (vector unsigned long long,
+vector unsigned long long, vector unsigned long long);
+@exdent vector float vec_blendv (vector float, vector float,
+vector unsigned int);
+@exdent vector double vec_blendv (vector double, vector double,
+vector unsigned long long);
+@end smallexample
+
+Blend the first and second argument vectors according to the sign bits of the
+corresponding elements of the third argument vector.  This is similar to the
+vsel and xxsel instructions but for bigger elements.
+
+@findex vec_blendv
+
+Vector Permute Extended
+
+@smallexample
+@exdent vector signed char vec_permx (vector signed char, vector signed char,
+vector unsigned char, const int);
+@exdent vector unsigned char vec_permx (vector unsigned char,
+vector unsigned char, vector unsigned char, const int);
+@exdent vector signed short vec_permx (vector signed short,
+vector signed short, vector unsigned char, const int);
+@exdent vector unsigned short vec_permx (vector unsigned short,
+vector unsigned short, vector unsigned char, const int);
+@exdent vector signed int vec_permx (vector signed int, vector signed int,
+vector unsigned char, const int);
+@exdent vector unsigned int vec_permx (vector unsigned int,
+vector unsigned int, vector unsigned char, const int);
+@exdent vector signed long long vec_permx (vector signed long long,
+vector signed long long, vector unsigned char, const int);
+@exdent vector unsigned long long vec_permx (vector unsigned long long,
+vector unsigned long long, vector unsigned char, const int);
+@exdent vector float (vector float, vector float, vector unsigned char,
+const int);
+@exdent vector double (vector double, vector double, vector unsigned char,
+const int);
+@end smallexample
+
+Perform a partial permute of the first two arguments, which form a 32-byte
+section of an emulated vector up to 256 bytes wide, using the partial permute
+control vector in the third argument.  The fourth argument (constrained to
+values of 0-7) identifies which 32-byte section of the emulated vector is
+contained in the first two arguments.
+@findex vec_permx
+
 @smallexample
 @exdent vector unsigned long long int
 @exdent vec_pdep (vector unsigned long long int, vector unsigned long long int)
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-blend-runnable.c b/gcc/testsuite/gcc.target/powerpc/vec-blend-runnable.c
new file mode 100644
index 00000000000..70b25be3bcb
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec-blend-runnable.c
@@ -0,0 +1,276 @@ 
+/* { dg-do run } */
+/* { dg-require-effective-target powerpc_future_hw } */
+/* { dg-options "-mdejagnu-cpu=future" } */
+#include <altivec.h>
+
+#define DEBUG 0
+
+#ifdef DEBUG
+#include <stdio.h>
+#endif
+
+extern void abort (void);
+
+int
+main (int argc, char *argv [])
+{
+  int i;
+  vector signed char vsrc_a_char, vsrc_b_char;
+  vector signed char vresult_char;
+  vector signed char expected_vresult_char;
+
+  vector unsigned char vsrc_a_uchar, vsrc_b_uchar, vsrc_c_uchar;
+  vector unsigned char vresult_uchar;
+  vector unsigned char expected_vresult_uchar;
+
+  vector signed short vsrc_a_short, vsrc_b_short, vsrc_c_short;
+  vector signed short vresult_short;
+  vector signed short expected_vresult_short;
+
+  vector unsigned short vsrc_a_ushort, vsrc_b_ushort, vsrc_c_ushort;
+  vector unsigned short vresult_ushort;
+  vector unsigned short expected_vresult_ushort;
+
+  vector int vsrc_a_int, vsrc_b_int, vsrc_c_int;
+  vector int vresult_int;
+  vector int expected_vresult_int;
+
+  vector unsigned int vsrc_a_uint, vsrc_b_uint, vsrc_c_uint;
+  vector unsigned int vresult_uint;
+  vector unsigned int expected_vresult_uint;
+
+  vector long long int vsrc_a_ll, vsrc_b_ll, vsrc_c_ll;
+  vector long long int vresult_ll;
+  vector long long int expected_vresult_ll;
+
+  vector unsigned long long int vsrc_a_ull,  vsrc_b_ull,  vsrc_c_ull;
+  vector unsigned long long int vresult_ull;
+  vector unsigned long long int expected_vresult_ull;
+
+  vector float vresult_f;
+  vector float expected_vresult_f;
+  vector float vsrc_a_f, vsrc_b_f;
+
+  vector double vsrc_a_d, vsrc_b_d;
+  vector double vresult_d;
+  vector double expected_vresult_d;
+ 
+  /* Vector blend */
+  vsrc_c_uchar = (vector unsigned char) { 0, 0x80, 0, 0x80, 0, 0x80, 0, 0x80,
+					  0, 0x80, 0, 0x80, 0, 0x80, 0, 0x80 };
+
+  vsrc_a_char = (vector signed char) { -1, 3, 5, 7, 9, 11, 13, 15,
+                                       17, 19, 21, 23, 25, 27, 29 };
+  vsrc_b_char = (vector signed char) { 2, -4, 6, 8, 10, 12, 14, 16,
+				       18, 20, 22, 24, 26, 28, 30, 32 };
+  vsrc_c_uchar = (vector unsigned char) { 0, 0x80, 0, 0x80, 0, 0x80, 0, 0x80,
+					  0, 0x80, 0, 0x80, 0, 0x80, 0, 0x80 };
+  vresult_char = (vector signed char) { 0, 0, 0, 0, 0, 0, 0, 0,
+					0, 0, 0, 0, 0, 0, 0, 0 };
+  expected_vresult_char = (vector signed char) { -1, -4, 5, 8,
+						 9, 12, 13, 16,
+						 17, 20, 21, 24,
+						 25, 28, 29, 32 };
+						 
+  vresult_char = vec_blendv (vsrc_a_char, vsrc_b_char, vsrc_c_uchar);
+
+  if (!vec_all_eq (vresult_char,  expected_vresult_char)) {
+#if DEBUG
+    printf("ERROR, vec_blendv (vsrc_a_char, vsrc_b_char, vsrc_c_uchar)\n");
+    for(i = 0; i < 16; i++)
+      printf(" vresult_char[%d] = %d, expected_vresult_char[%d] = %d\n",
+	     i, vresult_char[i], i, expected_vresult_char[i]);
+#else
+    abort();
+#endif
+  }
+
+  vsrc_a_uchar = (vector unsigned char) { 1, 3, 5, 7, 9, 11, 13, 15,
+					  17, 19, 21, 23, 25, 27, 29 };
+  vsrc_b_uchar = (vector unsigned char) { 2, 4, 6, 8, 10, 12, 14, 16,
+					  18, 20, 22, 24, 26, 28, 30, 32 };
+  vsrc_c_uchar = (vector unsigned char) { 0, 0x80, 0, 0x80, 0, 0x80, 0, 0x80,
+					  0, 0x80, 0, 0x80, 0, 0x80, 0, 0x80 };
+  vresult_uchar = (vector unsigned char) { 0, 0, 0, 0, 0, 0, 0, 0,
+					   0, 0, 0, 0, 0, 0, 0, 0 };
+  expected_vresult_uchar = (vector unsigned char) { 1, 4, 5, 8,
+						    9, 12, 13, 16,
+						    17, 20, 21, 24,
+						    25, 28, 29, 32 };
+						 
+  vresult_uchar = vec_blendv (vsrc_a_uchar, vsrc_b_uchar, vsrc_c_uchar);
+
+  if (!vec_all_eq (vresult_uchar,  expected_vresult_uchar)) {
+#if DEBUG
+    printf("ERROR, vec_blendv (vsrc_a_uchar, vsrc_b_uchar, vsrc_c_uchar)\n");
+    for(i = 0; i < 16; i++)
+      printf(" vresult_uchar[%d] = %d, expected_vresult_uchar[%d] = %d\n",
+	     i, vresult_uchar[i], i, expected_vresult_uchar[i]);
+#else
+    abort();
+#endif
+  }
+
+  vsrc_a_short = (vector signed short) { -1, 3, 5, 7, 9, 11, 13, 15 };
+  vsrc_b_short = (vector signed short) { 2, -4, 6, 8, 10, 12, 14, 16 };
+  vsrc_c_ushort = (vector unsigned short) { 0, 0x8000, 0, 0x8000,
+					    0, 0x8000, 0, 0x8000 };
+  vresult_short = (vector signed short) { 0, 0, 0, 0, 0, 0, 0, 0 };
+  expected_vresult_short = (vector signed short) { -1, -4, 5, 8,
+						   9, 12, 13, 16 };
+
+  vresult_short = vec_blendv (vsrc_a_short, vsrc_b_short, vsrc_c_ushort);
+
+  if (!vec_all_eq (vresult_short,  expected_vresult_short)) {
+#if DEBUG
+    printf("ERROR, vec_blendv (vsrc_a_short, vsrc_b_short, vsrc_c_ushort)\n");
+    for(i = 0; i < 8; i++)
+      printf(" vresult_short[%d] = %d, expected_vresult_short[%d] = %d\n",
+	     i, vresult_short[i], i, expected_vresult_short[i]);
+#else
+    abort();
+#endif
+  }
+
+  vsrc_a_ushort = (vector unsigned short) { 1, 3, 5, 7, 9, 11, 13, 15 };
+  vsrc_b_ushort = (vector unsigned short) { 2, 4, 6, 8, 10, 12, 14, 16 };
+  vsrc_c_ushort = (vector unsigned short) { 0, 0x8000, 0, 0x8000,
+					    0, 0x8000, 0, 0x8000 };
+  vresult_ushort = (vector unsigned short) { 0, 0, 0, 0, 0, 0, 0, 0 };
+  expected_vresult_ushort = (vector unsigned short) { 1, 4, 5, 8,
+						      9, 12, 13, 16 };
+						 
+  vresult_ushort = vec_blendv (vsrc_a_ushort, vsrc_b_ushort, vsrc_c_ushort);
+
+  if (!vec_all_eq (vresult_ushort,  expected_vresult_ushort)) {
+#if DEBUG
+    printf("ERROR, vec_blendv (vsrc_a_ushort, vsrc_b_ushort, vsrc_c_ushort)\n");
+    for(i = 0; i < 8; i++)
+      printf(" vresult_ushort[%d] = %d, expected_vresult_ushort[%d] = %d\n",
+	     i, vresult_ushort[i], i, expected_vresult_ushort[i]);
+#else
+    abort();
+#endif
+  }
+
+  vsrc_a_int = (vector signed int) { -1, -3, -5, -7 };
+  vsrc_b_int = (vector signed int) { 2, 4, 6, 8 };
+  vsrc_c_uint = (vector unsigned int) { 0, 0x80000000, 0, 0x80000000};
+  vresult_int = (vector signed int) { 0, 0, 0, 0 };
+  expected_vresult_int = (vector signed int) { -1, 4, -5, 8 };
+						 
+  vresult_int = vec_blendv (vsrc_a_int, vsrc_b_int, vsrc_c_uint);
+
+  if (!vec_all_eq (vresult_int,  expected_vresult_int)) {
+#if DEBUG
+    printf("ERROR, vec_blendv (vsrc_a_int, vsrc_b_int, vsrc_c_uint)\n");
+    for(i = 0; i < 4; i++)
+      printf(" vresult_int[%d] = %d, expected_vresult_int[%d] = %d\n",
+	     i, vresult_int[i], i, expected_vresult_int[i]);
+#else
+    abort();
+#endif
+  }
+
+  vsrc_a_uint = (vector unsigned int) { 1, 3, 5, 7 };
+  vsrc_b_uint = (vector unsigned int) { 2, 4, 6, 8 };
+  vsrc_c_uint = (vector unsigned int) { 0, 0x80000000, 0, 0x80000000 };
+  vresult_uint = (vector unsigned int) { 0, 0, 0, 0 };
+  expected_vresult_uint = (vector unsigned int) { 1, 4, 5, 8 };
+						 
+  vresult_uint = vec_blendv (vsrc_a_uint, vsrc_b_uint, vsrc_c_uint);
+
+  if (!vec_all_eq (vresult_uint,  expected_vresult_uint)) {
+#if DEBUG
+    printf("ERROR, vec_blendv (vsrc_a_uint, vsrc_b_uint, vsrc_c_uint)\n");
+    for(i = 0; i < 4; i++)
+      printf(" vresult_uint[%d] = %d, expected_vresult_uint[%d] = %d\n",
+	     i, vresult_uint[i], i, expected_vresult_uint[i]);
+#else
+    abort();
+#endif
+  }
+
+  vsrc_a_ll = (vector signed long long int) { -1, -3 };
+  vsrc_b_ll = (vector signed long long int) { 2, 4,  };
+  vsrc_c_ull = (vector unsigned long long int) { 0, 0x8000000000000000ULL };
+  vresult_ll = (vector signed long long int) { 0, 0 };
+  expected_vresult_ll = (vector signed long long int) { -1, 4 };
+						 
+  vresult_ll = vec_blendv (vsrc_a_ll, vsrc_b_ll, vsrc_c_ull);
+
+  if (!vec_all_eq (vresult_ll,  expected_vresult_ll)) {
+#if DEBUG
+    printf("ERROR, vec_blendv (vsrc_a_ll, vsrc_b_ll, vsrc_c_ull)\n");
+    for(i = 0; i < 2; i++)
+      printf(" vresult_ll[%d] = %d, expected_vresult_ll[%d] = %d\n",
+	     i, vresult_ll[i], i, expected_vresult_ll[i]);
+#else
+    abort();
+#endif
+  }
+
+  vsrc_a_ull = (vector unsigned long long) { 1, 3 };
+  vsrc_b_ull = (vector unsigned long long) { 2, 4 };
+  vsrc_c_ull = (vector unsigned long long int) { 0, 0x8000000000000000ULL };
+  vresult_ull = (vector unsigned long long) { 0, 0 };
+  expected_vresult_ull = (vector unsigned long long) { 1, 4 };
+						 
+  vresult_ull = vec_blendv (vsrc_a_ull, vsrc_b_ull, vsrc_c_ull);
+
+  if (!vec_all_eq (vresult_ull,  expected_vresult_ull)) {
+#if DEBUG
+    printf("ERROR, vec_blendv (vsrc_a_ull, vsrc_b_ull, vsrc_c_ull)\n");
+    for(i = 0; i < 2; i++)
+      printf(" vresult_ull[%d] = %d, expected_vresult_ull[%d] = %d\n",
+	     i, vresult_ull[i], i, expected_vresult_ull[i]);
+#else
+    abort();
+#endif
+  }
+
+  vsrc_a_f = (vector float) { -1.0, -3.0, -5.0, -7.0 };
+  vsrc_b_f = (vector float) { 2.0, 4.0, 6.0, 8.0 };
+  vsrc_c_uint = (vector unsigned int) { 0, 0x80000000, 0, 0x80000000};
+  vresult_f = (vector float) { 0, 0, 0, 0 };
+  expected_vresult_f = (vector float) { -1, 4, -5, 8 };
+						 
+  vresult_f = vec_blendv (vsrc_a_f, vsrc_b_f, vsrc_c_uint);
+
+  if (!vec_all_eq (vresult_f,  expected_vresult_f)) {
+#if DEBUG
+    printf("ERROR, vec_blendv (vsrc_a_f, vsrc_b_f, vsrc_c_uint)\n");
+    for(i = 0; i < 4; i++)
+      printf(" vresult_f[%d] = %d, expected_vresult_f[%d] = %d\n",
+	     i, vresult_f[i], i, expected_vresult_f[i]);
+#else
+    abort();
+#endif
+  }
+
+  vsrc_a_d = (vector double) { -1.0, -3.0 };
+  vsrc_b_d = (vector double) { 2.0, 4.0 };
+  vsrc_c_ull = (vector unsigned long long int) { 0, 0x8000000000000000ULL };
+  vresult_d = (vector double) { 0, 0 };
+  expected_vresult_d = (vector double) { -1, 4 };
+						 
+  vresult_d = vec_blendv (vsrc_a_d, vsrc_b_d, vsrc_c_ull);
+
+  if (!vec_all_eq (vresult_d,  expected_vresult_d)) {
+#if DEBUG
+    printf("ERROR, vec_blendv (vsrc_a_d, vsrc_b_d, vsrc_c_ull)\n");
+    for(i = 0; i < 4; i++)
+      printf(" vresult_d[%d] = %d, expected_vresult_d[%d] = %d\n",
+	     i, vresult_d[i], i, expected_vresult_d[i]);
+#else
+    abort();
+#endif
+  }
+
+  return 0;
+}
+
+/* { dg-final { scan-assembler-times {\msplati\M} 6 } } */
+/* { dg-final { scan-assembler-times {\msrdbi\M} 6 } } */
+
+
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-permute-ext-runnable.c b/gcc/testsuite/gcc.target/powerpc/vec-permute-ext-runnable.c
new file mode 100644
index 00000000000..f5d223d0530
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec-permute-ext-runnable.c
@@ -0,0 +1,294 @@ 
+/* { dg-do run } */
+/* { dg-require-effective-target powerpc_future_hw } */
+/* { dg-options "-mdejagnu-cpu=future" } */
+#include <altivec.h>
+
+#define DEBUG 1
+
+#ifdef DEBUG
+#include <stdio.h>
+#endif
+
+extern void abort (void);
+
+int
+main (int argc, char *argv [])
+{
+  int i;
+  vector signed char vsrc_a_char, vsrc_b_char;
+  vector signed char vresult_char;
+  vector signed char expected_vresult_char;
+
+  vector unsigned char vsrc_a_uchar, vsrc_b_uchar, vsrc_c_uchar;
+  vector unsigned char vresult_uchar;
+  vector unsigned char expected_vresult_uchar;
+
+  vector signed short vsrc_a_short, vsrc_b_short, vsrc_c_short;
+  vector signed short vresult_short;
+  vector signed short expected_vresult_short;
+
+  vector unsigned short vsrc_a_ushort, vsrc_b_ushort, vsrc_c_ushort;
+  vector unsigned short vresult_ushort;
+  vector unsigned short expected_vresult_ushort;
+
+  vector int vsrc_a_int, vsrc_b_int, vsrc_c_int;
+  vector int vresult_int;
+  vector int expected_vresult_int;
+
+  vector unsigned int vsrc_a_uint, vsrc_b_uint, vsrc_c_uint;
+  vector unsigned int vresult_uint;
+  vector unsigned int expected_vresult_uint;
+
+  vector long long int vsrc_a_ll, vsrc_b_ll, vsrc_c_ll;
+  vector long long int vresult_ll;
+  vector long long int expected_vresult_ll;
+
+  vector unsigned long long int vsrc_a_ull,  vsrc_b_ull,  vsrc_c_ull;
+  vector unsigned long long int vresult_ull;
+  vector unsigned long long int expected_vresult_ull;
+
+  vector float vresult_f;
+  vector float expected_vresult_f;
+  vector float vsrc_a_f, vsrc_b_f;
+
+  vector double vsrc_a_d, vsrc_b_d;
+  vector double vresult_d;
+  vector double expected_vresult_d;
+ 
+  /* Vector permx */
+  vsrc_a_char = (vector signed char) { -1, 3, 5, 7, 9, 11, 13, 15,
+                                       17, 19, 21, 23, 25, 27, 29 };
+  vsrc_b_char = (vector signed char) { 2, -4, 6, 8, 10, 12, 14, 16,
+				       18, 20, 22, 24, 26, 28, 30, 32 };
+  vsrc_c_uchar = (vector unsigned char) { 0x0, 0x7, 0, 0x5, 0, 0x3, 0, 0x1,
+					  0, 0x2, 0, 0x4, 0, 0x6, 0, 0x0 };
+  vresult_char = (vector signed char) { 0, 0, 0, 0, 0, 0, 0, 0,
+					0, 0, 0, 0, 0, 0, 0, 0 };
+  expected_vresult_char = (vector signed char) { -1, 15, -1, 11,
+						 -1, 7, -1, 3,
+						 -1, 5, -1, 9,
+						 -1, 13, -1, -1 };
+						 
+  vresult_char = vec_permx (vsrc_a_char, vsrc_b_char, vsrc_c_uchar, 0);
+
+  if (!vec_all_eq (vresult_char,  expected_vresult_char)) {
+#if DEBUG
+    printf("ERROR, vec_permx (vsrc_a_char, vsrc_b_char, vsrc_c_uchar)\n");
+    for(i = 0; i < 16; i++)
+      printf(" vresult_char[%d] = %d, expected_vresult_char[%d] = %d\n",
+	     i, vresult_char[i], i, expected_vresult_char[i]);
+#else
+    abort();
+#endif
+  }
+
+  vsrc_a_uchar = (vector unsigned char) { 1, 3, 5, 7, 9, 11, 13, 15,
+					  17, 19, 21, 23, 25, 27, 29 };
+  vsrc_b_uchar = (vector unsigned char) { 2, 4, 6, 8, 10, 12, 14, 16,
+					  18, 20, 22, 24, 26, 28, 30, 32 };
+  vsrc_c_uchar = (vector unsigned char) { 0x0, 0x7, 0, 0x5, 0, 0x3, 0, 0x1,
+					  0, 0x2, 0, 0x4, 0, 0x6, 0, 0x0 };
+  vresult_uchar = (vector unsigned char) { 0, 0, 0, 0, 0, 0, 0, 0,
+					   0, 0, 0, 0, 0, 0, 0, 0 };
+  expected_vresult_uchar = (vector unsigned char) { 1, 15, 1, 11,
+						    1, 7, 1, 3,
+						    1, 5, 1, 9,
+						    1, 13, 1, 1 };
+						 
+  vresult_uchar = vec_permx (vsrc_a_uchar, vsrc_b_uchar, vsrc_c_uchar, 0);
+
+  if (!vec_all_eq (vresult_uchar,  expected_vresult_uchar)) {
+#if DEBUG
+    printf("ERROR, vec_permx (vsrc_a_uchar, vsrc_b_uchar, vsrc_c_uchar)\n");
+    for(i = 0; i < 16; i++)
+      printf(" vresult_uchar[%d] = %d, expected_vresult_uchar[%d] = %d\n",
+	     i, vresult_uchar[i], i, expected_vresult_uchar[i]);
+#else
+    abort();
+#endif
+  }
+
+  vsrc_a_short = (vector signed short int) { 1, -3, 5, 7, 9, 11, 13, 15 };
+  vsrc_b_short = (vector signed short int) { 2, 4, -6, 8, 10, 12, 14, 16 };
+  vsrc_c_uchar = (vector unsigned char) { 0x0, 0x1, 0x2, 0x3,
+					  0x4, 0x5, 0x2, 0x3,
+					  0x8, 0x9, 0x2, 0x3,
+					  0x1E, 0x1F, 0x2, 0x3 };
+  vresult_short = (vector signed short int) { 0, 0, 0, 0, 0, 0, 0, 0 };
+  expected_vresult_short = (vector signed short int) { 1, -3, 5, -3,
+						       9, -3, 16, -3 };
+						 
+  vresult_short = vec_permx (vsrc_a_short, vsrc_b_short, vsrc_c_uchar, 0);
+
+  if (!vec_all_eq (vresult_short,  expected_vresult_short)) {
+#if DEBUG
+    printf("ERROR, vec_permx (vsrc_a_short, vsrc_b_short, vsrc_c_uchar)\n");
+    for(i = 0; i < 8; i++)
+      printf(" vresult_short[%d] = %d, expected_vresult_short[%d] = %d\n",
+	     i, vresult_short[i], i, expected_vresult_short[i]);
+#else
+    abort();
+#endif
+  }
+
+  vsrc_a_ushort = (vector unsigned short int) { 1, 3, 5, 7, 9, 11, 13, 15 };
+  vsrc_b_ushort = (vector unsigned short int) { 2, 4, 6, 8, 10, 12, 14, 16 };
+  vsrc_c_uchar = (vector unsigned char) { 0x0, 0x1, 0x2, 0x3,
+					  0x4, 0x5, 0x2, 0x3,
+					  0x8, 0x9, 0x2, 0x3,
+					  0x1E, 0x1F, 0x2, 0x3 };
+  vresult_ushort = (vector unsigned short int) { 0, 0, 0, 0, 0, 0, 0, 0 };
+  expected_vresult_ushort = (vector unsigned short int) { 1, 3, 5, 3,
+							  9, 3, 16, 3 };
+						 
+  vresult_ushort = vec_permx (vsrc_a_ushort, vsrc_b_ushort, vsrc_c_uchar, 0);
+
+  if (!vec_all_eq (vresult_ushort,  expected_vresult_ushort)) {
+#if DEBUG
+    printf("ERROR, vec_permx (vsrc_a_ushort, vsrc_b_ushort, vsrc_c_uchar)\n");
+    for(i = 0; i < 8; i++)
+      printf(" vresult_ushort[%d] = %d, expected_vresult_ushort[%d] = %d\n",
+	     i, vresult_ushort[i], i, expected_vresult_ushort[i]);
+#else
+    abort();
+#endif
+  }
+
+  vsrc_a_int = (vector signed int) { 1, -3, 5, 7 };
+  vsrc_b_int = (vector signed int) { 2, 4, -6, 8 };
+  vsrc_c_uchar = (vector unsigned char) { 0x0, 0x1, 0x2, 0x3,
+					  0x4, 0x5, 0x6, 0x7,
+					  0x18, 0x19, 0x1A, 0x1B,
+					  0x1C, 0x1D, 0x1E, 0x1F };
+  vresult_int = (vector signed int) { 0, 0, 0, 0 };
+  expected_vresult_int = (vector signed int) { 1, -3, -6, 8 };
+						 
+  vresult_int = vec_permx (vsrc_a_int, vsrc_b_int, vsrc_c_uchar, 0);
+
+  if (!vec_all_eq (vresult_int,  expected_vresult_int)) {
+#if DEBUG
+    printf("ERROR, vec_permx (vsrc_a_int, vsrc_b_int, vsrc_c_uchar)\n");
+    for(i = 0; i < 4; i++)
+      printf(" vresult_int[%d] = %d, expected_vresult_int[%d] = %d\n",
+	     i, vresult_int[i], i, expected_vresult_int[i]);
+#else
+    abort();
+#endif
+  }
+
+  vsrc_a_uint = (vector unsigned int) { 1, 3, 5, 7 };
+  vsrc_b_uint = (vector unsigned int) { 10, 12, 14, 16 };
+  vsrc_c_uchar = (vector unsigned char) { 0x0, 0x1, 0x2, 0x3,
+					  0x4, 0x5, 0x6, 0x7,
+					  0x18, 0x19, 0x1A, 0x1B,
+					  0x1C, 0x1D, 0x1E, 0x1F };
+  vresult_uint = (vector unsigned int) { 0, 0, 0, 0 };
+  expected_vresult_uint = (vector unsigned int) { 1, 3, 14, 16 };
+						 
+  vresult_uint = vec_permx (vsrc_a_uint, vsrc_b_uint, vsrc_c_uchar, 0);
+
+  if (!vec_all_eq (vresult_uint,  expected_vresult_uint)) {
+#if DEBUG
+    printf("ERROR, vec_permx (vsrc_a_uint, vsrc_b_uint, vsrc_c_uchar)\n");
+    for(i = 0; i < 4; i++)
+      printf(" vresult_uint[%d] = %d, expected_vresult_uint[%d] = %d\n",
+	     i, vresult_uint[i], i, expected_vresult_uint[i]);
+#else
+    abort();
+#endif
+  }
+
+  vsrc_a_ll = (vector signed long long int) { 1, -3 };
+  vsrc_b_ll = (vector signed long long int) { 2, -4 };
+  vsrc_c_uchar = (vector unsigned char) { 0x0, 0x1, 0x2, 0x3,
+					  0x4, 0x5, 0x6, 0x7,
+					  0x18, 0x19, 0x1A, 0x1B,
+					  0x1C, 0x1D, 0x1E, 0x1F };
+  vresult_ll = (vector signed long long int) { 0, 0};
+  expected_vresult_ll = (vector signed long long int) { 1, -4 };
+						 
+  vresult_ll = vec_permx (vsrc_a_ll, vsrc_b_ll, vsrc_c_uchar, 0);
+
+  if (!vec_all_eq (vresult_ll,  expected_vresult_ll)) {
+#if DEBUG
+    printf("ERROR, vec_permx (vsrc_a_ll, vsrc_b_ll, vsrc_c_uchar)\n");
+    for(i = 0; i < 2; i++)
+      printf(" vresult_ll[%d] = %lld, expected_vresult_ll[%d] = %lld\n",
+	     i, vresult_ll[i], i, expected_vresult_ll[i]);
+#else
+    abort();
+#endif
+  }
+
+  vsrc_a_ull = (vector unsigned long long int) { 1, 3 };
+  vsrc_b_ull = (vector unsigned long long int) { 10, 12 };
+  vsrc_c_uchar = (vector unsigned char) { 0x0, 0x1, 0x2, 0x3,
+					  0x4, 0x5, 0x6, 0x7,
+					  0x18, 0x19, 0x1A, 0x1B,
+					  0x1C, 0x1D, 0x1E, 0x1F };
+  vresult_ull = (vector unsigned long long int) { 0, 0 };
+  expected_vresult_ull = (vector unsigned long long int) { 1, 12 };
+						 
+  vresult_ull = vec_permx (vsrc_a_ull, vsrc_b_ull, vsrc_c_uchar, 0);
+
+  if (!vec_all_eq (vresult_ull,  expected_vresult_ull)) {
+#if DEBUG
+    printf("ERROR, vec_permx (vsrc_a_ull, vsrc_b_ull, vsrc_c_uchar)\n");
+    for(i = 0; i < 2; i++)
+      printf(" vresult_ull[%d] = %d, expected_vresult_ull[%d] = %d\n",
+	     i, vresult_ull[i], i, expected_vresult_ull[i]);
+#else
+    abort();
+#endif
+  }
+
+  vsrc_a_f = (vector float) { -3.0, 5.0, 7.0, 9.0 };
+  vsrc_b_f = (vector float) { 2.0,  4.0, 6.0, 8.0  };
+  vsrc_c_uchar = (vector unsigned char) { 0x0, 0x1, 0x2, 0x3,
+					  0x4, 0x5, 0x6, 0x7,
+					  0x18, 0x19, 0x1A, 0x1B,
+					  0x1C, 0x1D, 0x1E, 0x1F };
+  vresult_f = (vector float) { 0.0, 0.0, 0.0, 0.0 };
+  expected_vresult_f = (vector float) { -3.0, 5.0, 6.0, 8.0 };
+						 
+  vresult_f = vec_permx (vsrc_a_f, vsrc_b_f, vsrc_c_uchar, 0);
+
+  if (!vec_all_eq (vresult_f,  expected_vresult_f)) {
+#if DEBUG
+    printf("ERROR, vec_permx (vsrc_a_f, vsrc_b_f, vsrc_c_uchar)\n");
+    for(i = 0; i < 4; i++)
+      printf(" vresult_f[%d] = %f, expected_vresult_f[%d] = %f\n",
+	     i, vresult_f[i], i, expected_vresult_f[i]);
+#else
+    abort();
+#endif
+  }
+
+  vsrc_a_d = (vector double) { 1.0, -3.0 };
+  vsrc_b_d = (vector double) { 2.0, -4.0 };
+  vsrc_c_uchar = (vector unsigned char) { 0x0, 0x1, 0x2, 0x3,
+					  0x4, 0x5, 0x6, 0x7,
+					  0x1A, 0x1B, 0x1C, 0x1B,
+					  0x1C, 0x1D, 0x1E, 0x1F };
+  vresult_d = (vector double) { 0.0, 0.0 };
+  expected_vresult_d = (vector double) { 1.0, -4.0 };
+						 
+  vresult_d = vec_permx (vsrc_a_d, vsrc_b_d, vsrc_c_uchar, 0);
+
+  if (!vec_all_eq (vresult_d,  expected_vresult_d)) {
+#if DEBUG
+    printf("ERROR, vec_permx (vsrc_a_d, vsrc_b_d, vsrc_c_uchar)\n");
+    for(i = 0; i < 2; i++)
+      printf(" vresult_d[%d] = %f, expected_vresult_d[%d] = %f\n",
+	     i, vresult_d[i], i, expected_vresult_d[i]);
+#else
+    abort();
+#endif
+  }
+
+  return 0;
+}
+
+/* { dg-final { scan-assembler-times {\mxxpermx\M} 6 } } */
+
+