rs6000, Add vector splat builtin support

GCC maintainers:

The following patch adds support for the vec_splati, vec_splatid and
vec_splati_ins builtins.

This patch adds support for instructions that take a 32-bit immediate
value that represents a floating point value.  This support adds new
predicates and a support function to properly handle the immediate value.

The patch has been compiled and tested on

  powerpc64le-unknown-linux-gnu (Power 8 LE)
  powerpc64le-unknown-linux-gnu (Power 9 LE)

with no regression errors.

The test case was compiled on a Power 9 system and then tested on
Mambo.

Please let me know if this patch is acceptable for the mainline
branch.  Thanks.

                         Carl Love
--------------------------------------------------------
gcc/ChangeLog

	    2020-08-04  Carl Love  <cel@us.ibm.com>

	* config/rs6000/altivec.h (vec_splati, vec_splatid, vec_splati_ins):
	Add defines.
	* config/rs6000/altivec.md (UNSPEC_XXSPLTIW, UNSPEC_XXSPLTID,
	UNSPEC_XXSPLTI32DX): New.
	(vxxspltiw_v4si, vxxspltiw_v4sf_inst, vxxspltidp_v2df_inst,
	vxxsplti32dx_v4si_inst, vxxsplti32dx_v4sf_inst): New define_insn.
	(vxxspltiw_v4sf, vxxspltidp_v2df, vxxsplti32dx_v4si,
	vxxsplti32dx_v4sf.): New define_expands.
	* config/rs6000/predicates.md (u1bit_cint_operand,
	s32bit_cint_operand, c32bit_cint_operand): New predicates.
	* config/rs6000/rs6000-builtin.def (VXXSPLTIW_V4SI, VXXSPLTIW_V4SF,
	VXXSPLTID): New definitions.
	(VXXSPLTI32DX_V4SI, VXXSPLTI32DX_V4SF): New BU_P10V_3
	definitions.
	(XXSPLTIW, XXSPLTID): New definitions.
	(XXSPLTI32DX): Add definitions.
	* config/rs6000/rs6000-call.c (P10_BUILTIN_VEC_XXSPLTIW,
	P10_BUILTIN_VEC_XXSPLTID, P10_BUILTIN_VEC_XXSPLTI32DX):
	New definitions.
	* config/rs6000/rs6000-protos.h (rs6000_constF32toI32): New extern
	declaration.
	* config/rs6000/rs6000.c (rs6000_constF32toI32): New function.
	* doc/extend.texi: Add documentation for vec_splati,
	vec_splatid, and vec_splati_ins.

gcc/testsuite/ChangeLog

	    2020-08-04  Carl Love  <cel@us.ibm.com>

	* gcc.target/powerpc/vec-splati-runnable.c: New test.

9 files changed, 379 insertions, 0 deletions

diff --git a/gcc/config/rs6000/altivec.h b/gcc/config/rs6000/altivec.h
index 1a5c216..71249b5 100644
--- a/gcc/config/rs6000/altivec.h
+++ b/gcc/config/rs6000/altivec.h
@@ -709,6 +709,9 @@ __altivec_scalar_pred(vec_any_nle,
 #define vec_replace_unaligned(a, b, c) __builtin_vec_replace_un (a, b, c)
 #define vec_sldb(a, b, c)      __builtin_vec_sldb (a, b, c)
 #define vec_srdb(a, b, c)      __builtin_vec_srdb (a, b, c)
+#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_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 9d97341..2a5a254 100644
--- a/gcc/config/rs6000/altivec.md
+++ b/gcc/config/rs6000/altivec.md
@@ -175,6 +175,9 @@
    UNSPEC_VSTRIL
    UNSPEC_SLDB
    UNSPEC_SRDB
+   UNSPEC_XXSPLTIW
+   UNSPEC_XXSPLTID
+   UNSPEC_XXSPLTI32DX
 ])
 
 (define_c_enum "unspecv"
@@ -801,6 +804,109 @@
   "vs<SLDB_lr>dbi %0,%1,%2,%3"
   [(set_attr "type" "vecsimple")])
 
+(define_insn "xxspltiw_v4si"
+  [(set (match_operand:V4SI 0 "register_operand" "=wa")
+	(unspec:V4SI [(match_operand:SI 1 "s32bit_cint_operand" "n")]
+		     UNSPEC_XXSPLTIW))]
+ "TARGET_POWER10"
+ "xxspltiw %x0,%1"
+ [(set_attr "type" "vecsimple")])
+
+(define_expand "xxspltiw_v4sf"
+  [(set (match_operand:V4SF 0 "register_operand" "=wa")
+	(unspec:V4SF [(match_operand:SF 1 "const_double_operand" "n")]
+		     UNSPEC_XXSPLTIW))]
+ "TARGET_POWER10"
+{
+  long long value = rs6000_const_f32_to_i32 (operands[1]);
+  emit_insn (gen_xxspltiw_v4sf_inst (operands[0], GEN_INT (value)));
+  DONE;
+})
+
+(define_insn "xxspltiw_v4sf_inst"
+  [(set (match_operand:V4SF 0 "register_operand" "=wa")
+	(unspec:V4SF [(match_operand:SI 1 "c32bit_cint_operand" "n")]
+		     UNSPEC_XXSPLTIW))]
+ "TARGET_POWER10"
+ "xxspltiw %x0,%1"
+ [(set_attr "type" "vecsimple")])
+
+(define_expand "xxspltidp_v2df"
+  [(set (match_operand:V2DF 0 "register_operand" )
+	(unspec:V2DF [(match_operand:SF 1 "const_double_operand")]
+		     UNSPEC_XXSPLTID))]
+ "TARGET_POWER10"
+{
+  long value = rs6000_const_f32_to_i32 (operands[1]);
+  rs6000_emit_xxspltidp_v2df (operands[0], value);
+  DONE;
+})
+
+(define_insn "xxspltidp_v2df_inst"
+  [(set (match_operand:V2DF 0 "register_operand" "=wa")
+	(unspec:V2DF [(match_operand:SI 1 "c32bit_cint_operand" "n")]
+		     UNSPEC_XXSPLTID))]
+  "TARGET_POWER10"
+  "xxspltidp %x0,%1"
+  [(set_attr "type" "vecsimple")])
+
+(define_expand "xxsplti32dx_v4si"
+  [(set (match_operand:V4SI 0 "register_operand" "=wa")
+	(unspec:V4SI [(match_operand:V4SI 1 "register_operand" "0")
+		      (match_operand:QI 2 "u1bit_cint_operand" "n")
+		      (match_operand:SI 3 "s32bit_cint_operand" "n")]
+		     UNSPEC_XXSPLTI32DX))]
+ "TARGET_POWER10"
+{
+  int index = INTVAL (operands[2]);
+
+  if (!BYTES_BIG_ENDIAN)
+    index = 1 - index;
+
+   emit_insn (gen_xxsplti32dx_v4si_inst (operands[0], operands[1],
+					 GEN_INT (index), operands[3]));
+   DONE;
+}
+ [(set_attr "type" "vecsimple")])
+
+(define_insn "xxsplti32dx_v4si_inst"
+  [(set (match_operand:V4SI 0 "register_operand" "=wa")
+	(unspec:V4SI [(match_operand:V4SI 1 "register_operand" "0")
+		      (match_operand:QI 2 "u1bit_cint_operand" "n")
+		      (match_operand:SI 3 "s32bit_cint_operand" "n")]
+		     UNSPEC_XXSPLTI32DX))]
+  "TARGET_POWER10"
+  "xxsplti32dx %x0,%2,%3"
+  [(set_attr "type" "vecsimple")])
+
+(define_expand "xxsplti32dx_v4sf"
+  [(set (match_operand:V4SF 0 "register_operand" "=wa")
+	(unspec:V4SF [(match_operand:V4SF 1 "register_operand" "0")
+		      (match_operand:QI 2 "u1bit_cint_operand" "n")
+		      (match_operand:SF 3 "const_double_operand" "n")]
+		     UNSPEC_XXSPLTI32DX))]
+  "TARGET_POWER10"
+{
+  int index = INTVAL (operands[2]);
+  long value = rs6000_const_f32_to_i32 (operands[3]);
+  if (!BYTES_BIG_ENDIAN)
+    index = 1 - index;
+
+   emit_insn (gen_xxsplti32dx_v4sf_inst (operands[0], operands[1],
+					 GEN_INT (index), GEN_INT (value)));
+   DONE;
+})
+
+(define_insn "xxsplti32dx_v4sf_inst"
+  [(set (match_operand:V4SF 0 "register_operand" "=wa")
+	(unspec:V4SF [(match_operand:V4SF 1 "register_operand" "0")
+		      (match_operand:QI 2 "u1bit_cint_operand" "n")
+		      (match_operand:SI 3 "s32bit_cint_operand" "n")]
+		     UNSPEC_XXSPLTI32DX))]
+  "TARGET_POWER10"
+  "xxsplti32dx %x0,%2,%3"
+  [(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/predicates.md b/gcc/config/rs6000/predicates.md
index 9762855..afb7c02 100644
--- a/gcc/config/rs6000/predicates.md
+++ b/gcc/config/rs6000/predicates.md
@@ -214,6 +214,11 @@
   (and (match_code "const_int")
        (match_test "INTVAL (op) >= -16 && INTVAL (op) <= 15")))
 
+;; Return 1 if op is an unsigned 1-bit constant integer.
+(define_predicate "u1bit_cint_operand"
+  (and (match_code "const_int")
+       (match_test "INTVAL (op) >= 0 && INTVAL (op) <= 1")))
+
 ;; Return 1 if op is a unsigned 3-bit constant integer.
 (define_predicate "u3bit_cint_operand"
   (and (match_code "const_int")
@@ -272,6 +277,16 @@
        (match_test "(unsigned HOST_WIDE_INT)
 		    (INTVAL (op) + 0x8000) >= 0x10000")))
 
+;; Return 1 if op is a 32-bit constant signed integer
+(define_predicate "s32bit_cint_operand"
+  (and (match_code "const_int")
+       (match_test "(0x80000000 + UINTVAL (op)) >> 32 == 0")))
+
+;; Return 1 if op is a constant 32-bit unsigned
+(define_predicate "c32bit_cint_operand"
+  (and (match_code "const_int")
+       (match_test "((UINTVAL (op) >> 32) == 0)")))
+
 ;; Return 1 if op is a positive constant integer that is an exact power of 2.
 (define_predicate "exact_log2_cint_operand"
   (and (match_code "const_int")
diff --git a/gcc/config/rs6000/rs6000-builtin.def b/gcc/config/rs6000/rs6000-builtin.def
index bfb3376..c44587a 100644
--- a/gcc/config/rs6000/rs6000-builtin.def
+++ b/gcc/config/rs6000/rs6000-builtin.def
@@ -2774,6 +2774,14 @@ BU_P10V_3 (VSRDB_V8HI, "vsrdb_v8hi", CONST, vsrdb_v8hi)
 BU_P10V_3 (VSRDB_V4SI, "vsrdb_v4si", CONST, vsrdb_v4si)
 BU_P10V_3 (VSRDB_V2DI, "vsrdb_v2di", CONST, vsrdb_v2di)
 
+BU_P10V_1 (VXXSPLTIW_V4SI, "vxxspltiw_v4si", CONST, xxspltiw_v4si)
+BU_P10V_1 (VXXSPLTIW_V4SF, "vxxspltiw_v4sf", CONST, xxspltiw_v4sf)
+
+BU_P10V_1 (VXXSPLTID, "vxxspltidp", CONST, xxspltidp_v2df)
+
+BU_P10V_3 (VXXSPLTI32DX_V4SI, "vxxsplti32dx_v4si", CONST, xxsplti32dx_v4si)
+BU_P10V_3 (VXXSPLTI32DX_V4SF, "vxxsplti32dx_v4sf", CONST, xxsplti32dx_v4sf)
+
 BU_P10V_1 (VSTRIBR, "vstribr", CONST, vstrir_v16qi)
 BU_P10V_1 (VSTRIHR, "vstrihr", CONST, vstrir_v8hi)
 BU_P10V_1 (VSTRIBL, "vstribl", CONST, vstril_v16qi)
@@ -2841,6 +2849,9 @@ BU_P10_OVERLOAD_1 (MTVSRQM, "mtvsrqm")
 BU_P10_OVERLOAD_2 (VCNTM, "cntm")
 BU_P10_OVERLOAD_1 (VEXPANDM, "vexpandm")
 BU_P10_OVERLOAD_1 (VEXTRACTM, "vextractm")
+BU_P10_OVERLOAD_1 (XXSPLTIW, "xxspltiw")
+BU_P10_OVERLOAD_1 (XXSPLTID, "xxspltid")
+BU_P10_OVERLOAD_3 (XXSPLTI32DX, "xxsplti32dx")
 
 /* 1 argument crypto functions.  */
 BU_CRYPTO_1 (VSBOX,		"vsbox",	  CONST, crypto_vsbox_v2di)
diff --git a/gcc/config/rs6000/rs6000-call.c b/gcc/config/rs6000/rs6000-call.c
index 2955399..838f518 100644
--- a/gcc/config/rs6000/rs6000-call.c
+++ b/gcc/config/rs6000/rs6000-call.c
@@ -5694,6 +5694,22 @@ const struct altivec_builtin_types altivec_overloaded_builtins[] = {
     RS6000_BTI_unsigned_V2DI, RS6000_BTI_unsigned_V2DI,
     RS6000_BTI_unsigned_V2DI, RS6000_BTI_UINTQI },
 
+  { P10_BUILTIN_VEC_XXSPLTIW, P10_BUILTIN_VXXSPLTIW_V4SI,
+    RS6000_BTI_V4SI, RS6000_BTI_INTSI, 0, 0 },
+  { P10_BUILTIN_VEC_XXSPLTIW, P10_BUILTIN_VXXSPLTIW_V4SF,
+    RS6000_BTI_V4SF, RS6000_BTI_float, 0, 0 },
+
+  { P10_BUILTIN_VEC_XXSPLTID, P10_BUILTIN_VXXSPLTID,
+    RS6000_BTI_V2DF, RS6000_BTI_float, 0, 0 },
+
+  { P10_BUILTIN_VEC_XXSPLTI32DX, P10_BUILTIN_VXXSPLTI32DX_V4SI,
+    RS6000_BTI_V4SI, RS6000_BTI_V4SI, RS6000_BTI_UINTQI, RS6000_BTI_INTSI },
+  { P10_BUILTIN_VEC_XXSPLTI32DX, P10_BUILTIN_VXXSPLTI32DX_V4SI,
+    RS6000_BTI_unsigned_V4SI, RS6000_BTI_unsigned_V4SI, RS6000_BTI_UINTQI,
+    RS6000_BTI_UINTSI },
+  { P10_BUILTIN_VEC_XXSPLTI32DX, P10_BUILTIN_VXXSPLTI32DX_V4SF,
+    RS6000_BTI_V4SF, RS6000_BTI_V4SF, RS6000_BTI_UINTQI, RS6000_BTI_float },
+
   { P10_BUILTIN_VEC_SRDB, P10_BUILTIN_VSRDB_V16QI,
     RS6000_BTI_V16QI, RS6000_BTI_V16QI,
     RS6000_BTI_V16QI, RS6000_BTI_UINTQI },
@@ -14109,6 +14125,9 @@ builtin_function_type (machine_mode mode_ret, machine_mode mode_arg0,
     case ALTIVEC_BUILTIN_VSRH:
     case ALTIVEC_BUILTIN_VSRW:
     case P8V_BUILTIN_VSRD:
+    /* Vector splat immediate insert */
+    case P10_BUILTIN_VXXSPLTI32DX_V4SI:
+    case P10_BUILTIN_VXXSPLTI32DX_V4SF:
       h.uns_p[2] = 1;
       break;
 
diff --git a/gcc/config/rs6000/rs6000-protos.h b/gcc/config/rs6000/rs6000-protos.h
index 5508484..28e859f 100644
--- a/gcc/config/rs6000/rs6000-protos.h
+++ b/gcc/config/rs6000/rs6000-protos.h
@@ -274,6 +274,7 @@ extern void rs6000_asm_output_dwarf_pcrel (FILE *file, int size,
 					   const char *label);
 extern void rs6000_asm_output_dwarf_datarel (FILE *file, int size,
 					     const char *label);
+extern long long rs6000_const_f32_to_i32 (rtx operand);
 
 /* Declare functions in rs6000-c.c */
 
@@ -309,4 +310,5 @@ 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);
 
+extern void rs6000_emit_xxspltidp_v2df (rtx, long value);
 #endif  /* rs6000-protos.h */
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 0c7506f..b48ec72 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -26806,6 +26806,28 @@ rs6000_invalid_conversion (const_tree fromtype, const_tree totype)
   return NULL;
 }
 
+long long
+rs6000_const_f32_to_i32 (rtx operand)
+{
+  long long value;
+  const struct real_value *rv = CONST_DOUBLE_REAL_VALUE (operand);
+
+  gcc_assert (GET_MODE (operand) == SFmode);
+  REAL_VALUE_TO_TARGET_SINGLE (*rv, value);
+  return value;
+}
+
+void
+rs6000_emit_xxspltidp_v2df (rtx dst, long value)
+{
+  printf("rs6000_emit_xxspltidp_v2df called %ld\n", value);
+  printf("rs6000_emit_xxspltidp_v2df called 0x%lx\n", value);
+  if (((value & 0x7F800000) == 0) && ((value & 0x7FFFFF) != 0))
+    inform (input_location,
+	    "the result for the xxspltidp instruction is undefined for subnormal input values.\n");
+  emit_insn( gen_xxspltidp_v2df_inst (dst, GEN_INT (value)));
+}
+
 struct gcc_target targetm = TARGET_INITIALIZER;
 
 #include "gt-rs6000.h"
diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
index d74f3a6..54a71c6 100644
--- a/gcc/doc/extend.texi
+++ b/gcc/doc/extend.texi
@@ -21193,6 +21193,41 @@ using this built-in must be endian-aware.
 
 @findex vec_srdb
 
+Vector Splat
+
+@smallexample
+@exdent vector signed int vec_splati (const signed int);
+@exdent vector float vec_splati (const float);
+@end smallexample
+
+Splat a 32-bit immediate into a vector of words.
+
+@findex vec_splati
+
+@smallexample
+@exdent vector double vec_splatid (const float);
+@end smallexample
+
+Convert a single precision floating-point value to double-precision and splat
+the result to a vector of double-precision floats.
+
+@findex vec_splatid
+
+@smallexample
+@exdent vector signed int vec_splati_ins (vector signed int,
+const unsigned int, const signed int);
+@exdent vector unsigned int vec_splati_ins (vector unsigned int,
+const unsigned int, const unsigned int);
+@exdent vector float vec_splati_ins (vector float, const unsigned int,
+const float);
+@end smallexample
+
+Argument 2 must be either 0 or 1.  Splat the value of argument 3 into the word
+identified by argument 2 of each doubleword of argument 1 and return the
+result.  The other words of argument 1 are unchanged.
+
+@findex vec_splati_ins
+
 @smallexample
 @exdent vector unsigned long long int
 @exdent vec_pext (vector unsigned long long int, vector unsigned long long int)
diff --git a/gcc/testsuite/gcc.target/powerpc/vec-splati-runnable.c b/gcc/testsuite/gcc.target/powerpc/vec-splati-runnable.c
new file mode 100644
index 0000000..afb0bfd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec-splati-runnable.c
@@ -0,0 +1,166 @@
+/* { dg-do run } */
+/* { dg-require-effective-target power10_hw } */
+/* { dg-options "-mdejagnu-cpu=power10" } */
+#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 int vsrc_a_int;
+  vector int vresult_int;
+  vector int expected_vresult_int;
+  int src_a_int = 13;
+
+  vector unsigned int vsrc_a_uint;
+  vector unsigned int vresult_uint;
+  vector unsigned int expected_vresult_uint;
+  unsigned int src_a_uint = 7;
+
+  vector float vresult_f;
+  vector float expected_vresult_f;
+  vector float vsrc_a_f;
+  float src_a_f = 23.0;
+
+  vector double vsrc_a_d;
+  vector double vresult_d;
+  vector double expected_vresult_d;
+ 
+  /* Vector splati word */
+  vresult_int = (vector signed int) { 1, 2, 3, 4 };
+  expected_vresult_int = (vector signed int) { -13, -13, -13, -13 }; 
+						 
+  vresult_int = vec_splati ( -13 );
+
+  if (!vec_all_eq (vresult_int,  expected_vresult_int)) {
+#if DEBUG
+    printf("ERROR, vec_splati (src_a_int)\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
+  }
+
+  vresult_f = (vector float) { 1.0, 2.0, 3.0, 4.0 };
+  expected_vresult_f = (vector float) { 23.0, 23.0, 23.0, 23.0 };
+						 
+  vresult_f = vec_splati (23.0f);
+
+  if (!vec_all_eq (vresult_f,  expected_vresult_f)) {
+#if DEBUG
+    printf("ERROR, vec_splati (src_a_f)\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
+  }
+
+  /* Vector splati double */
+  vresult_d = (vector double) { 2.0, 3.0 };
+  expected_vresult_d = (vector double) { -31.0, -31.0 };
+						 
+  vresult_d = vec_splatid (-31.0f);
+
+  if (!vec_all_eq (vresult_d,  expected_vresult_d)) {
+#if DEBUG
+    printf("ERROR, vec_splati (-31.0f)\n");
+    for(i = 0; i < 2; i++)
+      printf(" vresult_d[%i] = %f, expected_vresult_d[%i] = %f\n",
+	     i, vresult_d[i], i, expected_vresult_d[i]);
+#else
+    abort();
+#endif
+  }
+
+  /* This test will generate a "note" to the user that the argument
+     is subnormal.  It is not an error, but results are not defined.  */
+  vresult_d = (vector double) { 2.0, 3.0 };
+  expected_vresult_d = (vector double) { 6.6E-42f, 6.6E-42f };
+
+  vresult_d = vec_splatid (6.6E-42f);
+
+  /* Although the instruction says the results are not defined, it does seem
+     to work, at least on Mambo.  But no guarentees!  */
+  if (!vec_all_eq (vresult_d,  expected_vresult_d)) {
+#if DEBUG
+    printf("ERROR, vec_splati (6.6E-42f)\n");
+    for(i = 0; i < 2; i++)
+      printf(" vresult_d[%i] = %e, expected_vresult_d[%i] = %e\n",
+	     i, vresult_d[i], i, expected_vresult_d[i]);
+#else
+    abort();
+#endif
+  }
+
+  /* Vector splat immediate */
+  vsrc_a_int = (vector int) { 2, 3, 4, 5 };
+  vresult_int = (vector int) { 1, 1, 1, 1 };
+  expected_vresult_int = (vector int) { 2, 20, 4, 20 };
+						 
+  vresult_int = vec_splati_ins (vsrc_a_int, 1, 20);
+
+  if (!vec_all_eq (vresult_int,  expected_vresult_int)) {
+#if DEBUG
+    printf("ERROR, vec_splati_ins (vsrc_a_int, 1, 20)\n");
+    for(i = 0; i < 4; i++)
+      printf(" vresult_int[%i] = %d, expected_vresult_int[%i] = %d\n",
+	     i, vresult_int[i], i, expected_vresult_int[i]);
+#else
+    abort();
+#endif
+  }
+  
+  vsrc_a_uint = (vector unsigned int) { 4, 5, 6, 7 };
+  vresult_uint = (vector unsigned int) { 1, 1, 1, 1 };
+  expected_vresult_uint = (vector unsigned int) { 4, 40, 6, 40 };
+						 
+  vresult_uint = vec_splati_ins (vsrc_a_uint, 1, 40);
+
+  if (!vec_all_eq (vresult_uint,  expected_vresult_uint)) {
+#if DEBUG
+    printf("ERROR, vec_splati_ins (vsrc_a_uint, 1, 40)\n");
+    for(i = 0; i < 4; i++)
+      printf(" vresult_uint[%i] = %d, expected_vresult_uint[%i] = %d\n",
+	     i, vresult_uint[i], i, expected_vresult_uint[i]);
+#else
+    abort();
+#endif
+  }
+  
+  vsrc_a_f = (vector float) { 2.0, 3.0, 4.0, 5.0 };
+  vresult_f = (vector float) { 1.0, 1.0, 1.0, 1.0 };
+  expected_vresult_f = (vector float) { 2.0, 20.1, 4.0, 20.1 };
+						 
+  vresult_f = vec_splati_ins (vsrc_a_f, 1, 20.1f);
+
+  if (!vec_all_eq (vresult_f,  expected_vresult_f)) {
+#if DEBUG
+    printf("ERROR, vec_splati_ins (vsrc_a_f, 1, 20.1)\n");
+    for(i = 0; i < 4; i++)
+      printf(" vresult_f[%i] = %f, expected_vresult_f[%i] = %f\n",
+	     i, vresult_f[i], i, expected_vresult_f[i]);
+#else
+    abort();
+#endif
+  }
+
+  return 0;
+}
+
+/* { dg-final { scan-assembler-times {\mxxspltiw\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mxxspltidp\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mxxsplti32dx\M} 3 } } */
+
+