Re: [PATCH 1/6] rs6000: Support SSE4.1 "round" intrinsics

[Bill Schmidt via Gcc-patches]

Hi, Paul!

On 8/9/21 3:23 PM, Paul A. Clarke via Gcc-patches wrote:
Suppress exceptions (when specified), by saving, manipulating, and
restoring the FPSCR.  Similarly, save, set, and restore the floating-point
rounding mode when required.
No attempt is made to optimize writing the FPSCR (by checking if the new
value would be the same), other than using lighter weight instructions
when possible.

The scalar versions naively use the parallel versions to compute the
single scalar result and then construct the remainder of the result.

Of minor note, the values of _MM_FROUND_TO_NEG_INF and _MM_FROUND_TO_ZERO
are swapped from the corresponding values on x86 so as to match the
corresponding rounding mode values in the Power ISA.

Move implementations of _mm_ceil* and _mm_floor* into _mm_round*, and
convert _mm_ceil* and _mm_floor* into macros. This matches the current
analogous implementations in config/i386/smmintrin.h.

Add tests for _mm_round_pd, _mm_round_ps, _mm_round_sd, _mm_round_ss,
modeled after the very similar "floor" and "ceil" tests.

Include basic tests, plus tests at the boundaries for floating-point
representation, positive and negative, test all of the parameterized
rounding modes as well as the C99 rounding modes and interactions
between the two.

Exceptions are not explicitly tested.


Reminder:  Please specify what testing you've done and on which 
platforms, and where you want to apply the patches (i.e., do you want 
backports?).


2021-08-09  Paul A. Clarke  <p...@us.ibm.com>

gcc
        * config/rs6000/smmintrin.h (_mm_round_pd, _mm_round_ps,
        _mm_round_sd, _mm_round_ss, _MM_FROUND_TO_NEAREST_INT


Missing comma

        _MM_FROUND_TO_ZERO, _MM_FROUND_TO_POS_INF, _MM_FROUND_TO_NEG_INF,
        _MM_FROUND_CUR_DIRECTION, _MM_FROUND_RAISE_EXC, _MM_FROUND_NO_EXC


Likewise

        _MM_FROUND_NINT, _MM_FROUND_FLOOR, _MM_FROUND_CEIL, _MM_FROUND_TRUNC,
        _MM_FROUND_RINT, _MM_FROUND_NEARBYINT): New.
        * config/rs6000/smmintrin.h (_mm_ceil_pd, _mm_ceil_ps, _mm_ceil_sd,
        _mm_ceil_ss, _mm_floor_pd, _mm_floor_ps, _mm_floor_sd, _mm_floor_ss):
        Convert from function to macro.

gcc/testsuite
        * gcc.target/powerpc/sse4_1-round3.h: New.
        * gcc.target/powerpc/sse4_1-roundpd.c: New.
        * gcc.target/powerpc/sse4_1-roundps.c: New.
        * gcc.target/powerpc/sse4_1-roundsd.c: New.
        * gcc.target/powerpc/sse4_1-roundss.c: New.
---
  gcc/config/rs6000/smmintrin.h                 | 246 ++++++++++++-----
  .../gcc.target/powerpc/sse4_1-round3.h        |  81 ++++++
  .../gcc.target/powerpc/sse4_1-roundpd.c       | 143 ++++++++++
  .../gcc.target/powerpc/sse4_1-roundps.c       |  98 +++++++
  .../gcc.target/powerpc/sse4_1-roundsd.c       | 256 ++++++++++++++++++
  .../gcc.target/powerpc/sse4_1-roundss.c       | 208 ++++++++++++++
  6 files changed, 968 insertions(+), 64 deletions(-)
  create mode 100644 gcc/testsuite/gcc.target/powerpc/sse4_1-round3.h
  create mode 100644 gcc/testsuite/gcc.target/powerpc/sse4_1-roundpd.c
  create mode 100644 gcc/testsuite/gcc.target/powerpc/sse4_1-roundps.c
  create mode 100644 gcc/testsuite/gcc.target/powerpc/sse4_1-roundsd.c
  create mode 100644 gcc/testsuite/gcc.target/powerpc/sse4_1-roundss.c

diff --git a/gcc/config/rs6000/smmintrin.h b/gcc/config/rs6000/smmintrin.h
index 3767a67eada7..862e78ac7d60 100644
--- a/gcc/config/rs6000/smmintrin.h
+++ b/gcc/config/rs6000/smmintrin.h
@@ -42,6 +42,188 @@
  #include <altivec.h>
  #include <tmmintrin.h>

+/* Rounding mode macros. */
+#define _MM_FROUND_TO_NEAREST_INT       0x00
+#define _MM_FROUND_TO_ZERO              0x01
+#define _MM_FROUND_TO_POS_INF           0x02
+#define _MM_FROUND_TO_NEG_INF           0x03
+#define _MM_FROUND_CUR_DIRECTION        0x04
+
+#define _MM_FROUND_NINT                \
+  (_MM_FROUND_TO_NEAREST_INT | _MM_FROUND_RAISE_EXC)
+#define _MM_FROUND_FLOOR       \
+  (_MM_FROUND_TO_NEG_INF | _MM_FROUND_RAISE_EXC)
+#define _MM_FROUND_CEIL                \
+  (_MM_FROUND_TO_POS_INF | _MM_FROUND_RAISE_EXC)
+#define _MM_FROUND_TRUNC       \
+  (_MM_FROUND_TO_ZERO | _MM_FROUND_RAISE_EXC)
+#define _MM_FROUND_RINT                \
+  (_MM_FROUND_CUR_DIRECTION | _MM_FROUND_RAISE_EXC)
+#define _MM_FROUND_NEARBYINT   \
+  (_MM_FROUND_CUR_DIRECTION | _MM_FROUND_NO_EXC)
+
+#define _MM_FROUND_RAISE_EXC            0x00
+#define _MM_FROUND_NO_EXC               0x08
+
+__inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_round_pd (__m128d __A, int __rounding)
+{
+  __v2df __r;
+  union {
+    double __fr;
+    long long __fpscr;
+  } __save, __tmp;
+
+  if (__rounding & _MM_FROUND_NO_EXC)
+  {
+    /* Save enabled exceptions, and disable all exceptions.
+       Pre-POWER9, mffsce decodes to mffs, requiring the additional
+       mtfsf, below, to disable exceptions.  */
+    __asm__ __volatile__ (
+      ".machine push; .machine \"power9\"; mffsce %0; .machine pop"


As we discussed, this cleverness causes trouble by introducing a 
dependency on a binutils that recognizes .machine "power9". Better to 
just #ifdef this and specify mffsce versus mffs.

+      : "=f" (__save.__fr));
+    __save.__fpscr &= 0xf8;
+    __tmp.__fpscr = __save.__fpscr;
+#ifndef _ARCH_PWR9
+    __tmp.__fpscr &= ~0xf8;


Just __tmp.fpscr = 0, please, given the preceding code.

+    __builtin_mtfsf (0x01, __tmp.__fr);
+#endif
+  }
+
+  switch (__rounding)
+  {
+    case _MM_FROUND_TO_NEAREST_INT:
+      __tmp.__fr = __builtin_mffsl ();


Another clever encoding trick, but dangerous.  __builtin_mffsl isn't 
guaranteed to be recognized on P8 or earlier, even if it happens to work 
today.  Just use mffs and mffsl under #ifdef control.

+      __attribute__((fallthrough));


Well done. :-)  A lot of people miss this.

+    case _MM_FROUND_TO_NEAREST_INT |_MM_FROUND_NO_EXC:
+      {
+       __builtin_set_fpscr_rn (0b00);
+       __r = vec_rint ((__v2df) __A);
+       __builtin_set_fpscr_rn (__tmp.__fpscr);
+      }
+      break;
+    case _MM_FROUND_TO_NEG_INF:
+    case _MM_FROUND_TO_NEG_INF |_MM_FROUND_NO_EXC:
+      __r = vec_floor ((__v2df) __A);
+      break;
+    case _MM_FROUND_TO_POS_INF:
+    case _MM_FROUND_TO_POS_INF |_MM_FROUND_NO_EXC:
+      __r = vec_ceil ((__v2df) __A);
+      break;
+    case _MM_FROUND_TO_ZERO:
+    case _MM_FROUND_TO_ZERO |_MM_FROUND_NO_EXC:
+      __r = vec_trunc ((__v2df) __A);
+      break;
+    case _MM_FROUND_CUR_DIRECTION:
+      __r = vec_rint ((__v2df) __A);
+      break;
+  }
+  if (__rounding & _MM_FROUND_NO_EXC)
+  {
+    /* Restore enabled exceptions.  */
+    __tmp.__fr = __builtin_mffsl ();


Same issue here.

+    __tmp.__fpscr |= __save.__fpscr & 0xf8;
+    __builtin_mtfsf (0x01, __tmp.__fr);
+  }
+  return (__m128d) __r;
+}
+
+__inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_round_sd (__m128d __A, __m128d __B, int __rounding)
+{
+  __B = _mm_round_pd (__B, __rounding);
+  __v2df __r = { ((__v2df)__B)[0], ((__v2df) __A)[1] };
+  return (__m128d) __r;
+}
+
+__inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_round_ps (__m128 __A, int __rounding)
+{
+  __v4sf __r;
+  union {
+    double __fr;
+    long long __fpscr;
+  } __save, __tmp;
+
+  if (__rounding & _MM_FROUND_NO_EXC)
+  {
+    /* Save enabled exceptions, and disable all exceptions.
+       Pre-POWER9, mffsce decodes to mffs, requiring the additional
+       mtfsf, below, to disable exceptions.  */
+    __asm__ __volatile__ (
+      ".machine push; .machine \"power9\"; mffsce %0; .machine pop"


Same issues in this function as above, I won't repeat them all.

+      : "=f" (__save.__fr));
+    __save.__fpscr &= 0xf8;
+    __tmp.__fpscr = __save.__fpscr;
+#ifndef _ARCH_PWR9
+    __tmp.__fpscr &= ~0xf8;
+    __builtin_mtfsf (0x01, __tmp.__fr);
+#endif
+  }
+
+  switch (__rounding)
+  {
+    case _MM_FROUND_TO_NEAREST_INT:
+      __tmp.__fr = __builtin_mffsl ();
+      __attribute__((fallthrough));
+    case _MM_FROUND_TO_NEAREST_INT |_MM_FROUND_NO_EXC:
+      {
+       __builtin_set_fpscr_rn (0b00);
+       __r = vec_rint ((__v4sf) __A);
+       __builtin_set_fpscr_rn (__tmp.__fpscr);
+      }
+      break;
+    case _MM_FROUND_TO_NEG_INF:
+    case _MM_FROUND_TO_NEG_INF |_MM_FROUND_NO_EXC:
+      __r = vec_floor ((__v4sf) __A);
+      break;
+    case _MM_FROUND_TO_POS_INF:
+    case _MM_FROUND_TO_POS_INF |_MM_FROUND_NO_EXC:
+      __r = vec_ceil ((__v4sf) __A);
+      break;
+    case _MM_FROUND_TO_ZERO:
+    case _MM_FROUND_TO_ZERO |_MM_FROUND_NO_EXC:
+      __r = vec_trunc ((__v4sf) __A);
+      break;
+    case _MM_FROUND_CUR_DIRECTION:
+      __r = vec_rint ((__v4sf) __A);
+      break;
+  }
+  if (__rounding & _MM_FROUND_NO_EXC)
+  {
+    /* Restore enabled exceptions.  */
+    __tmp.__fr = __builtin_mffsl ();
+    __tmp.__fpscr |= __save.__fpscr & 0xf8;
+    __builtin_mtfsf (0x01, __tmp.__fr);
+  }
+  return (__m128) __r;
+}
+
+__inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_round_ss (__m128 __A, __m128 __B, int __rounding)
+{
+  __B = _mm_round_ps (__B, __rounding);
+  __v4sf __r = (__v4sf) __A;
+  __r[0] = ((__v4sf)__B)[0];
+  return (__m128) __r;
+}
+
+#define _mm_ceil_pd(V)    _mm_round_pd ((V), _MM_FROUND_CEIL)
+#define _mm_ceil_sd(D, V)  _mm_round_sd ((D), (V), _MM_FROUND_CEIL)
+
+#define _mm_floor_pd(V)           _mm_round_pd((V), _MM_FROUND_FLOOR)
+#define _mm_floor_sd(D, V) _mm_round_sd ((D), (V), _MM_FROUND_FLOOR)
+
+#define _mm_ceil_ps(V)    _mm_round_ps ((V), _MM_FROUND_CEIL)
+#define _mm_ceil_ss(D, V)  _mm_round_ss ((D), (V), _MM_FROUND_CEIL)
+
+#define _mm_floor_ps(V)           _mm_round_ps ((V), _MM_FROUND_FLOOR)
+#define _mm_floor_ss(D, V) _mm_round_ss ((D), (V), _MM_FROUND_FLOOR)
+
  extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, 
__artificial__))
  _mm_insert_epi8 (__m128i const __A, int const __D, int const __N)
  {
@@ -232,70 +414,6 @@ _mm_test_mix_ones_zeros (__m128i __A, __m128i __mask)
    return any_ones * any_zeros;
  }

-__inline __m128d
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_ceil_pd (__m128d __A)
-{
-  return (__m128d) vec_ceil ((__v2df) __A);
-}
-
-__inline __m128d
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_ceil_sd (__m128d __A, __m128d __B)
-{
-  __v2df __r = vec_ceil ((__v2df) __B);
-  __r[1] = ((__v2df) __A)[1];
-  return (__m128d) __r;
-}
-
-__inline __m128d
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_floor_pd (__m128d __A)
-{
-  return (__m128d) vec_floor ((__v2df) __A);
-}
-
-__inline __m128d
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_floor_sd (__m128d __A, __m128d __B)
-{
-  __v2df __r = vec_floor ((__v2df) __B);
-  __r[1] = ((__v2df) __A)[1];
-  return (__m128d) __r;
-}
-
-__inline __m128
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_ceil_ps (__m128 __A)
-{
-  return (__m128) vec_ceil ((__v4sf) __A);
-}
-
-__inline __m128
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_ceil_ss (__m128 __A, __m128 __B)
-{
-  __v4sf __r = (__v4sf) __A;
-  __r[0] = __builtin_ceil (((__v4sf) __B)[0]);
-  return __r;
-}
-
-__inline __m128
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_floor_ps (__m128 __A)
-{
-  return (__m128) vec_floor ((__v4sf) __A);
-}
-
-__inline __m128
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_floor_ss (__m128 __A, __m128 __B)
-{
-  __v4sf __r = (__v4sf) __A;
-  __r[0] = __builtin_floor (((__v4sf) __B)[0]);
-  return __r;
-}
-
  /* Return horizontal packed word minimum and its index in bits [15:0]
     and bits [18:16] respectively.  */
  __inline __m128i
diff --git a/gcc/testsuite/gcc.target/powerpc/sse4_1-round3.h 
b/gcc/testsuite/gcc.target/powerpc/sse4_1-round3.h
new file mode 100644
index 000000000000..de6cbf7be438
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/sse4_1-round3.h
@@ -0,0 +1,81 @@
+#include <smmintrin.h>
+#include <fenv.h>
+#include "sse4_1-check.h"
+
+#define DIM(a) (sizeof (a) / sizeof (a)[0])
+
+static int roundings[] =
+  {
+    _MM_FROUND_TO_NEAREST_INT,
+    _MM_FROUND_TO_NEG_INF,
+    _MM_FROUND_TO_POS_INF,
+    _MM_FROUND_TO_ZERO,
+    _MM_FROUND_CUR_DIRECTION
+  };
+
+static int modes[] =
+  {
+    FE_TONEAREST,
+    FE_UPWARD,
+    FE_DOWNWARD,
+    FE_TOWARDZERO
+  };
+
+static void
+TEST (void)
+{
+  int i, j, ri, mi, round_save;
+
+  round_save = fegetround ();
+  for (mi = 0; mi < DIM (modes); mi++) {
+    fesetround (modes[mi]);
+    for (i = 0; i < DIM (data); i++) {
+      for (ri = 0; ri < DIM (roundings); ri++) {
+       union value guess;
+       union value *current_answers = answers[ri];
+       switch ( roundings[ri] ) {
+         case _MM_FROUND_TO_NEAREST_INT:
+           guess.x = ROUND_INTRIN (data[i].value1.x, data[i].value2.x,
+                                   _MM_FROUND_TO_NEAREST_INT);
+           break;
+         case _MM_FROUND_TO_NEG_INF:
+           guess.x = ROUND_INTRIN (data[i].value1.x, data[i].value2.x,
+                                   _MM_FROUND_TO_NEG_INF);
+           break;
+         case _MM_FROUND_TO_POS_INF:
+           guess.x = ROUND_INTRIN (data[i].value1.x, data[i].value2.x,
+                                   _MM_FROUND_TO_POS_INF);
+           break;
+         case _MM_FROUND_TO_ZERO:
+           guess.x = ROUND_INTRIN (data[i].value1.x, data[i].value2.x,
+                                   _MM_FROUND_TO_ZERO);
+           break;
+         case _MM_FROUND_CUR_DIRECTION:
+           guess.x = ROUND_INTRIN (data[i].value1.x, data[i].value2.x,
+                                   _MM_FROUND_CUR_DIRECTION);
+           switch ( modes[mi] ) {
+             case FE_TONEAREST:
+               current_answers = answers_NEAREST_INT;
+               break;
+             case FE_UPWARD:
+               current_answers = answers_POS_INF;
+               break;
+             case FE_DOWNWARD:
+               current_answers = answers_NEG_INF;
+               break;
+             case FE_TOWARDZERO:
+               current_answers = answers_ZERO;
+               break;
+           }
+           break;
+         default:
+           abort ();
+       }
+       for (j = 0; j < DIM (guess.f); j++)
+         if (guess.f[j] != current_answers[i].f[j])
+           abort ();
+      }
+    }
+  }
+  fesetround (round_save);
+}
diff --git a/gcc/testsuite/gcc.target/powerpc/sse4_1-roundpd.c 
b/gcc/testsuite/gcc.target/powerpc/sse4_1-roundpd.c
new file mode 100644
index 000000000000..42fa453b9fd3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/sse4_1-roundpd.c
@@ -0,0 +1,143 @@
+/* { dg-do run } */
+/* { dg-require-effective-target powerpc_vsx_ok } */
+/* { dg-options "-O2 -mvsx -Wno-psabi" } */


Let's please be sure -Wno-psabi is needed.  If so, please document the 
warning you're avoiding.  Thanks!

I won't claim I went through all the tests in gory detail, but otherwise 
this patch LGTM with the indicated changes.

Thanks!
Bill

+
+#define NO_WARN_X86_INTRINSICS 1
+#include <smmintrin.h>
+
+#define VEC_T __m128d
+#define FP_T double
+
+#define ROUND_INTRIN(x, ignored, mode) _mm_round_pd (x, mode)
+
+#include "sse4_1-round-data.h"
+
+struct data2 data[] = {
+  { .value1 = { .f = {  0.00,  0.25 } } },
+  { .value1 = { .f = {  0.50,  0.75 } } },
+
+  { .value1 = { .f = {  0x1.ffffffffffffcp+50,  0x1.ffffffffffffdp+50 } } },
+  { .value1 = { .f = {  0x1.ffffffffffffep+50,  0x1.fffffffffffffp+50 } } },
+  { .value1 = { .f = {  0x1.0000000000000p+51,  0x1.0000000000001p+51 } } },
+  { .value1 = { .f = {  0x1.0000000000002p+51,  0x1.0000000000003p+51 } } },
+
+  { .value1 = { .f = {  0x1.ffffffffffffep+51,  0x1.fffffffffffffp+51 } } },
+  { .value1 = { .f = {  0x1.0000000000000p+52,  0x1.0000000000001p+52 } } },
+
+  { .value1 = { .f = { -0x1.0000000000001p+52, -0x1.0000000000000p+52 } } },
+  { .value1 = { .f = { -0x1.fffffffffffffp+51, -0x1.ffffffffffffep+51 } } },
+
+  { .value1 = { .f = { -0x1.0000000000004p+51, -0x1.0000000000002p+51 } } },
+  { .value1 = { .f = { -0x1.0000000000001p+51, -0x1.0000000000000p+51 } } },
+  { .value1 = { .f = { -0x1.ffffffffffffcp+50, -0x1.ffffffffffffep+50 } } },
+  { .value1 = { .f = { -0x1.ffffffffffffdp+50, -0x1.ffffffffffffcp+50 } } },
+
+  { .value1 = { .f = { -1.00, -0.75 } } },
+  { .value1 = { .f = { -0.50, -0.25 } } }
+};
+
+union value answers_NEAREST_INT[] = {
+  { .f = {  0.00,  0.00 } },
+  { .f = {  0.00,  1.00 } },
+
+  { .f = {  0x1.ffffffffffffcp+50,  0x1.ffffffffffffcp+50 } },
+  { .f = {  0x1.0000000000000p+51,  0x1.0000000000000p+51 } },
+  { .f = {  0x1.0000000000000p+51,  0x1.0000000000000p+51 } },
+  { .f = {  0x1.0000000000002p+51,  0x1.0000000000004p+51 } },
+
+  { .f = {  0x1.ffffffffffffep+51,  0x1.0000000000000p+52 } },
+  { .f = {  0x1.0000000000000p+52,  0x1.0000000000001p+52 } },
+
+  { .f = { -0x1.0000000000001p+52, -0x1.0000000000000p+52 } },
+  { .f = { -0x1.0000000000000p+52, -0x1.ffffffffffffep+51 } },
+
+  { .f = { -0x1.0000000000004p+51, -0x1.0000000000002p+51 } },
+  { .f = { -0x1.0000000000000p+51, -0x1.0000000000000p+51 } },
+  { .f = { -0x1.ffffffffffffcp+50, -0x1.0000000000000p+51 } },
+  { .f = { -0x1.ffffffffffffcp+50, -0x1.ffffffffffffcp+50 } },
+
+  { .f = { -1.00, -1.00 } },
+  { .f = {  0.00,  0.00 } }
+};
+
+union value answers_NEG_INF[] = {
+  { .f = {  0.00,  0.00 } },
+  { .f = {  0.00,  0.00 } },
+
+  { .f = {  0x1.ffffffffffffcp+50,  0x1.ffffffffffffcp+50 } },
+  { .f = {  0x1.ffffffffffffcp+50,  0x1.ffffffffffffcp+50 } },
+  { .f = {  0x1.0000000000000p+51,  0x1.0000000000000p+51 } },
+  { .f = {  0x1.0000000000002p+51,  0x1.0000000000002p+51 } },
+
+  { .f = {  0x1.ffffffffffffep+51,  0x1.ffffffffffffep+51 } },
+  { .f = {  0x1.0000000000000p+52,  0x1.0000000000001p+52 } },
+
+  { .f = { -0x1.0000000000001p+52, -0x1.0000000000000p+52 } },
+  { .f = { -0x1.0000000000000p+52, -0x1.ffffffffffffep+51 } },
+
+  { .f = { -0x1.0000000000004p+51, -0x1.0000000000002p+51 } },
+  { .f = { -0x1.0000000000002p+51, -0x1.0000000000000p+51 } },
+  { .f = { -0x1.ffffffffffffcp+50, -0x1.0000000000000p+51 } },
+  { .f = { -0x1.0000000000000p+51, -0x1.ffffffffffffcp+50 } },
+
+  { .f = { -1.00, -1.00 } },
+  { .f = { -1.00, -1.00 } }
+};
+
+union value answers_POS_INF[] = {
+  { .f = {  0.00,  1.00 } },
+  { .f = {  1.00,  1.00 } },
+
+  { .f = {  0x1.ffffffffffffcp+50,  0x1.0000000000000p+51 } },
+  { .f = {  0x1.0000000000000p+51,  0x1.0000000000000p+51 } },
+  { .f = {  0x1.0000000000000p+51,  0x1.0000000000002p+51 } },
+  { .f = {  0x1.0000000000002p+51,  0x1.0000000000004p+51 } },
+
+  { .f = {  0x1.ffffffffffffep+51,  0x1.0000000000000p+52 } },
+  { .f = {  0x1.0000000000000p+52,  0x1.0000000000001p+52 } },
+
+  { .f = { -0x1.0000000000001p+52, -0x1.0000000000000p+52 } },
+  { .f = { -0x1.ffffffffffffep+51, -0x1.ffffffffffffep+51 } },
+
+  { .f = { -0x1.0000000000004p+51, -0x1.0000000000002p+51 } },
+  { .f = { -0x1.0000000000000p+51, -0x1.0000000000000p+51 } },
+  { .f = { -0x1.ffffffffffffcp+50, -0x1.ffffffffffffcp+50 } },
+  { .f = { -0x1.ffffffffffffcp+50, -0x1.ffffffffffffcp+50 } },
+
+  { .f = { -1.00,  0.00 } },
+  { .f = {  0.00,  0.00 } }
+};
+
+union value answers_ZERO[] = {
+  { .f = {  0.00,  0.00 } },
+  { .f = {  0.00,  0.00 } },
+
+  { .f = {  0x1.ffffffffffffcp+50,  0x1.ffffffffffffcp+50 } },
+  { .f = {  0x1.ffffffffffffcp+50,  0x1.ffffffffffffcp+50 } },
+  { .f = {  0x1.0000000000000p+51,  0x1.0000000000000p+51 } },
+  { .f = {  0x1.0000000000002p+51,  0x1.0000000000002p+51 } },
+
+  { .f = {  0x1.ffffffffffffep+51,  0x1.ffffffffffffep+51 } },
+  { .f = {  0x1.0000000000000p+52,  0x1.0000000000001p+52 } },
+
+  { .f = { -0x1.0000000000001p+52, -0x1.0000000000000p+52 } },
+  { .f = { -0x1.ffffffffffffep+51, -0x1.ffffffffffffep+51 } },
+
+  { .f = { -0x1.0000000000004p+51, -0x1.0000000000002p+51 } },
+  { .f = { -0x1.0000000000000p+51, -0x1.0000000000000p+51 } },
+  { .f = { -0x1.ffffffffffffcp+50, -0x1.ffffffffffffcp+50 } },
+  { .f = { -0x1.ffffffffffffcp+50, -0x1.ffffffffffffcp+50 } },
+
+  { .f = { -1.00,  0.00 } },
+  { .f = {  0.00,  0.00 } }
+};
+
+union value *answers[] = {
+  answers_NEAREST_INT,
+  answers_NEG_INF,
+  answers_POS_INF,
+  answers_ZERO,
+  0 /* CUR_DIRECTION answers depend on current rounding mode.  */
+};
+
+#include "sse4_1-round3.h"
diff --git a/gcc/testsuite/gcc.target/powerpc/sse4_1-roundps.c 
b/gcc/testsuite/gcc.target/powerpc/sse4_1-roundps.c
new file mode 100644
index 000000000000..e36d325992db
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/sse4_1-roundps.c
@@ -0,0 +1,98 @@
+/* { dg-do run } */
+/* { dg-require-effective-target powerpc_vsx_ok } */
+/* { dg-options "-O2 -mvsx -Wno-psabi" } */
+
+#define NO_WARN_X86_INTRINSICS 1
+#include <smmintrin.h>
+
+#define VEC_T __m128
+#define FP_T float
+
+#define ROUND_INTRIN(x, ignored, mode) _mm_round_ps (x, mode)
+
+#include "sse4_1-round-data.h"
+
+struct data2 data[] = {
+  { .value1 = { .f = {  0.00,  0.25,  0.50,  0.75 } } },
+
+  { .value1 = { .f = {  0x1.fffff8p+21,  0x1.fffffap+21,
+                       0x1.fffffcp+21,  0x1.fffffep+21 } } },
+  { .value1 = { .f = {  0x1.fffffap+22,  0x1.fffffcp+22,
+                       0x1.fffffep+22,  0x1.fffffep+23 } } },
+  { .value1 = { .f = { -0x1.fffffep+23, -0x1.fffffep+22,
+                      -0x1.fffffcp+22, -0x1.fffffap+22 } } },
+  { .value1 = { .f = { -0x1.fffffep+21, -0x1.fffffcp+21,
+                      -0x1.fffffap+21, -0x1.fffff8p+21 } } },
+
+  { .value1 = { .f = { -1.00, -0.75, -0.50, -0.25 } } }
+};
+
+union value answers_NEAREST_INT[] = {
+  { .f = {  0.00,  0.00,  0.00,  1.00 } },
+
+  { .f = {  0x1.fffff8p+21,  0x1.fffff8p+21,
+            0x1.000000p+22,  0x1.000000p+22 } },
+  { .f = {  0x1.fffff8p+22,  0x1.fffffcp+22,
+            0x1.000000p+23,  0x1.fffffep+23 } },
+  { .f = { -0x1.fffffep+23, -0x1.000000p+23,
+           -0x1.fffffcp+22, -0x1.fffff8p+22 } },
+  { .f = { -0x1.000000p+22, -0x1.000000p+22,
+           -0x1.fffff8p+21, -0x1.fffff8p+21 } },
+
+  { .f = { -1.00, -1.00,  0.00,  0.00 } }
+};
+
+union value answers_NEG_INF[] = {
+  { .f = {  0.00,  0.00,  0.00,  0.00 } },
+
+  { .f = {  0x1.fffff8p+21,  0x1.fffff8p+21,
+            0x1.fffff8p+21,  0x1.fffff8p+21 } },
+  { .f = {  0x1.fffff8p+22,  0x1.fffffcp+22,
+            0x1.fffffcp+22,  0x1.fffffep+23 } },
+  { .f = { -0x1.fffffep+23, -0x1.000000p+23,
+           -0x1.fffffcp+22, -0x1.fffffcp+22 } },
+  { .f = { -0x1.000000p+22, -0x1.000000p+22,
+           -0x1.000000p+22, -0x1.fffff8p+21 } },
+
+  { .f = { -1.00, -1.00, -1.00, -1.00 } }
+};
+
+union value answers_POS_INF[] = {
+  { .f = {  0.00,  1.00,  1.00,  1.00 } },
+
+  { .f = {  0x1.fffff8p+21,  0x1.000000p+22,
+            0x1.000000p+22,  0x1.000000p+22 } },
+  { .f = {  0x1.fffffcp+22,  0x1.fffffcp+22,
+            0x1.000000p+23,  0x1.fffffep+23 } },
+  { .f = { -0x1.fffffep+23, -0x1.fffffcp+22,
+           -0x1.fffffcp+22, -0x1.fffff8p+22 } },
+  { .f = { -0x1.fffff8p+21, -0x1.fffff8p+21,
+           -0x1.fffff8p+21, -0x1.fffff8p+21 } },
+
+  { .f = { -1.00,  0.00,  0.00,  0.00 } }
+};
+
+union value answers_ZERO[] = {
+  { .f = {  0.00,  0.00,  0.00,  0.00 } },
+
+  { .f = {  0x1.fffff8p+21,  0x1.fffff8p+21,
+            0x1.fffff8p+21,  0x1.fffff8p+21 } },
+  { .f = {  0x1.fffff8p+22,  0x1.fffffcp+22,
+            0x1.fffffcp+22,  0x1.fffffep+23 } },
+  { .f = { -0x1.fffffep+23, -0x1.fffffcp+22,
+           -0x1.fffffcp+22, -0x1.fffff8p+22 } },
+  { .f = { -0x1.fffff8p+21, -0x1.fffff8p+21,
+           -0x1.fffff8p+21, -0x1.fffff8p+21 } },
+
+  { .f = { -1.00,  0.00,  0.00,  0.00 } }
+};
+
+union value *answers[] = {
+  answers_NEAREST_INT,
+  answers_NEG_INF,
+  answers_POS_INF,
+  answers_ZERO,
+  0 /* CUR_DIRECTION answers depend on current rounding mode.  */
+};
+
+#include "sse4_1-round3.h"
diff --git a/gcc/testsuite/gcc.target/powerpc/sse4_1-roundsd.c 
b/gcc/testsuite/gcc.target/powerpc/sse4_1-roundsd.c
new file mode 100644
index 000000000000..00205dbd19bc
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/sse4_1-roundsd.c
@@ -0,0 +1,256 @@
+/* { dg-do run } */
+/* { dg-require-effective-target powerpc_vsx_ok } */
+/* { dg-options "-O2 -mvsx -Wno-psabi" } */
+
+#include <stdio.h>
+#define NO_WARN_X86_INTRINSICS 1
+#include <smmintrin.h>
+
+#define VEC_T __m128d
+#define FP_T double
+
+#define ROUND_INTRIN(x, y, mode) _mm_round_sd (x, y, mode)
+
+#include "sse4_1-round-data.h"
+
+static struct data2 data[] = {
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = {  0.00, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = {  0.25, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = {  0.50, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = {  0.75, IGNORED } } },
+
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.ffffffffffffcp+50, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.ffffffffffffdp+50, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.ffffffffffffep+50, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.fffffffffffffp+50, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.0000000000000p+51, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.0000000000001p+51, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.0000000000002p+51, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.0000000000003p+51, IGNORED } } },
+
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.ffffffffffffep+51, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.fffffffffffffp+51, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.0000000000000p+52, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.0000000000001p+52, IGNORED } } },
+
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.0000000000001p+52, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.0000000000000p+52, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.fffffffffffffp+51, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.ffffffffffffep+51, IGNORED } } },
+
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.0000000000004p+51, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.0000000000002p+51, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.0000000000001p+51, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.0000000000000p+51, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.ffffffffffffcp+50, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.ffffffffffffep+50, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.ffffffffffffdp+50, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.ffffffffffffcp+50, IGNORED } } },
+
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = { -1.00, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = { -0.75, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = { -0.50, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH } },
+    .value2 = { .f = { -0.25, IGNORED } } }
+};
+
+static union value answers_NEAREST_INT[] = {
+  { .f = {  0.00, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH } },
+  { .f = {  1.00, PASSTHROUGH } },
+
+  { .f = {  0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = {  0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = {  0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000002p+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000004p+51, PASSTHROUGH } },
+
+  { .f = {  0x1.ffffffffffffep+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000000p+52, PASSTHROUGH } },
+  { .f = {  0x1.0000000000000p+52, PASSTHROUGH } },
+  { .f = {  0x1.0000000000001p+52, PASSTHROUGH } },
+
+  { .f = { -0x1.0000000000001p+52, PASSTHROUGH } },
+  { .f = { -0x1.0000000000000p+52, PASSTHROUGH } },
+  { .f = { -0x1.0000000000000p+52, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffep+51, PASSTHROUGH } },
+
+  { .f = { -0x1.0000000000004p+51, PASSTHROUGH } },
+  { .f = { -0x1.0000000000002p+51, PASSTHROUGH } },
+  { .f = { -0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = { -0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = { -0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffcp+50, PASSTHROUGH } },
+
+  { .f = { -1.00, PASSTHROUGH } },
+  { .f = { -1.00, PASSTHROUGH } },
+  { .f = { -0.00, PASSTHROUGH } },
+  { .f = { -0.00, PASSTHROUGH } }
+};
+
+static union value answers_NEG_INF[] = {
+  { .f = {  0.00, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH } },
+
+  { .f = {  0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = {  0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = {  0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = {  0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = {  0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000002p+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000002p+51, PASSTHROUGH } },
+
+  { .f = {  0x1.ffffffffffffep+51, PASSTHROUGH } },
+  { .f = {  0x1.ffffffffffffep+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000000p+52, PASSTHROUGH } },
+  { .f = {  0x1.0000000000001p+52, PASSTHROUGH } },
+
+  { .f = { -0x1.0000000000001p+52, PASSTHROUGH } },
+  { .f = { -0x1.0000000000000p+52, PASSTHROUGH } },
+  { .f = { -0x1.0000000000000p+52, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffep+51, PASSTHROUGH } },
+
+  { .f = { -0x1.0000000000004p+51, PASSTHROUGH } },
+  { .f = { -0x1.0000000000002p+51, PASSTHROUGH } },
+  { .f = { -0x1.0000000000002p+51, PASSTHROUGH } },
+  { .f = { -0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = { -0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = { -0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffcp+50, PASSTHROUGH } },
+
+  { .f = { -1.00, PASSTHROUGH } },
+  { .f = { -1.00, PASSTHROUGH } },
+  { .f = { -1.00, PASSTHROUGH } },
+  { .f = { -1.00, PASSTHROUGH } }
+};
+
+static union value answers_POS_INF[] = {
+  { .f = {  0.00, PASSTHROUGH } },
+  { .f = {  1.00, PASSTHROUGH } },
+  { .f = {  1.00, PASSTHROUGH } },
+  { .f = {  1.00, PASSTHROUGH } },
+
+  { .f = {  0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = {  0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000002p+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000002p+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000004p+51, PASSTHROUGH } },
+
+  { .f = {  0x1.ffffffffffffep+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000000p+52, PASSTHROUGH } },
+  { .f = {  0x1.0000000000000p+52, PASSTHROUGH } },
+  { .f = {  0x1.0000000000001p+52, PASSTHROUGH } },
+
+  { .f = { -0x1.0000000000001p+52, PASSTHROUGH } },
+  { .f = { -0x1.0000000000000p+52, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffep+51, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffep+51, PASSTHROUGH } },
+
+  { .f = { -0x1.0000000000004p+51, PASSTHROUGH } },
+  { .f = { -0x1.0000000000002p+51, PASSTHROUGH } },
+  { .f = { -0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = { -0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffcp+50, PASSTHROUGH } },
+
+  { .f = { -1.00, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH } }
+};
+
+static union value answers_ZERO[] = {
+  { .f = {  0.00, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH } },
+
+  { .f = {  0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = {  0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = {  0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = {  0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = {  0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000002p+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000002p+51, PASSTHROUGH } },
+
+  { .f = {  0x1.ffffffffffffep+51, PASSTHROUGH } },
+  { .f = {  0x1.ffffffffffffep+51, PASSTHROUGH } },
+  { .f = {  0x1.0000000000000p+52, PASSTHROUGH } },
+  { .f = {  0x1.0000000000001p+52, PASSTHROUGH } },
+
+  { .f = { -0x1.0000000000001p+52, PASSTHROUGH } },
+  { .f = { -0x1.0000000000000p+52, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffep+51, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffep+51, PASSTHROUGH } },
+
+  { .f = { -0x1.0000000000004p+51, PASSTHROUGH } },
+  { .f = { -0x1.0000000000002p+51, PASSTHROUGH } },
+  { .f = { -0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = { -0x1.0000000000000p+51, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffcp+50, PASSTHROUGH } },
+  { .f = { -0x1.ffffffffffffcp+50, PASSTHROUGH } },
+
+  { .f = { -1.00, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH } }
+};
+
+union value *answers[] = {
+  answers_NEAREST_INT,
+  answers_NEG_INF,
+  answers_POS_INF,
+  answers_ZERO,
+  0 /* CUR_DIRECTION answers depend on current rounding mode.  */
+};
+
+#include "sse4_1-round3.h"
diff --git a/gcc/testsuite/gcc.target/powerpc/sse4_1-roundss.c 
b/gcc/testsuite/gcc.target/powerpc/sse4_1-roundss.c
new file mode 100644
index 000000000000..b9a8eae31f2d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/sse4_1-roundss.c
@@ -0,0 +1,208 @@
+/* { dg-do run } */
+/* { dg-require-effective-target powerpc_vsx_ok } */
+/* { dg-options "-O2 -mvsx -Wno-psabi" } */
+
+#include <stdio.h>
+#define NO_WARN_X86_INTRINSICS 1
+#include <smmintrin.h>
+
+#define VEC_T __m128
+#define FP_T float
+
+#define ROUND_INTRIN(x, y, mode) _mm_round_ss (x, y, mode)
+
+#include "sse4_1-round-data.h"
+
+static struct data2 data[] = {
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = {  0.00, IGNORED, IGNORED, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = {  0.25, IGNORED, IGNORED, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = {  0.50, IGNORED, IGNORED, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = {  0.75, IGNORED, IGNORED, IGNORED } } },
+
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.fffff8p+21, IGNORED, IGNORED, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.fffffap+21, IGNORED, IGNORED, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.fffffcp+21, IGNORED, IGNORED, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.fffffep+21, IGNORED, IGNORED, IGNORED } } },
+
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.fffffap+22, IGNORED, IGNORED, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.fffffcp+22, IGNORED, IGNORED, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.fffffep+22, IGNORED, IGNORED, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = {  0x1.fffffep+23, IGNORED, IGNORED, IGNORED } } },
+
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.fffffep+23, IGNORED, IGNORED, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.fffffep+22, IGNORED, IGNORED, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.fffffcp+22, IGNORED, IGNORED, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.fffffap+22, IGNORED, IGNORED, IGNORED } } },
+
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.fffffep+21, IGNORED, IGNORED, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.fffffcp+21, IGNORED, IGNORED, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.fffffap+21, IGNORED, IGNORED, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = { -0x1.fffff8p+21, IGNORED, IGNORED, IGNORED } } },
+
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = { -1.00, IGNORED, IGNORED, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = { -0.75, IGNORED, IGNORED, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = { -0.50, IGNORED, IGNORED, IGNORED } } },
+  { .value1 = { .f = { IGNORED, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+    .value2 = { .f = { -0.25, IGNORED, IGNORED, IGNORED } } }
+};
+
+static union value answers_NEAREST_INT[] = {
+  { .f = {  0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  1.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = {  0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.000000p+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.000000p+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = {  0x1.fffff8p+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.fffffcp+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.000000p+23, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.fffffep+23, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = { -0x1.fffffep+23, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.000000p+23, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffffcp+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffff8p+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = { -0x1.000000p+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.000000p+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = { -1.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -1.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } }
+};
+
+static union value answers_NEG_INF[] = {
+  { .f = {  0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = {  0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = {  0x1.fffff8p+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.fffffcp+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.fffffcp+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.fffffep+23, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = { -0x1.fffffep+23, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.000000p+23, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffffcp+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffffcp+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = { -0x1.000000p+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.000000p+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.000000p+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = { -1.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -1.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -1.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -1.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } }
+};
+
+static union value answers_POS_INF[] = {
+  { .f = {  0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  1.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  1.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  1.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = {  0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.000000p+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.000000p+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.000000p+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = {  0x1.fffffcp+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.fffffcp+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.000000p+23, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.fffffep+23, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = { -0x1.fffffep+23, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffffcp+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffffcp+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffff8p+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = { -0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = { -1.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } }
+};
+
+static union value answers_ZERO[] = {
+  { .f = {  0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = {  0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = {  0x1.fffff8p+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.fffffcp+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.fffffcp+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0x1.fffffep+23, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = { -0x1.fffffep+23, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffffcp+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffffcp+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffff8p+22, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = { -0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = { -0x1.fffff8p+21, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+
+  { .f = { -1.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } },
+  { .f = {  0.00, PASSTHROUGH, PASSTHROUGH, PASSTHROUGH } }
+};
+
+union value *answers[] = {
+  answers_NEAREST_INT,
+  answers_NEG_INF,
+  answers_POS_INF,
+  answers_ZERO,
+  0 /* CUR_DIRECTION answers depend on current rounding mode.  */
+};
+
+#include "sse4_1-round3.h"