This is part 2/2 for contributing PPC64LE support for X86 SSE3 instrisics.

This is part 2/2 for contributing PPC64LE support for X86 SSE3
instrisics. This patch includes testsuite/gcc.target tests for the
intrinsics defined in pmmintrin.h. 

Tested on POWER8 ppc64le and ppc64 (-m64 and -m32, the latter only reporting
10 new unsupported tests.)

[gcc/testsuite]

2018-10-09  Paul A. Clarke  <pc@us.ibm.com>

	* gcc.target/powerpc/sse3-check.h: New file.
	* gcc.target/powerpc/sse3-addsubps.c: New file.
	* gcc.target/powerpc/sse3-addsubpd.c: New file.
	* gcc.target/powerpc/sse3-haddps.c: New file.
	* gcc.target/powerpc/sse3-hsubps.c: New file.
	* gcc.target/powerpc/sse3-haddpd.c: New file.
	* gcc.target/powerpc/sse3-hsubpd.c: New file.
	* gcc.target/powerpc/sse3-lddqu.c: New file.
	* gcc.target/powerpc/sse3-movsldup.c: New file.
	* gcc.target/powerpc/sse3-movshdup.c: New file.
	* gcc.target/powerpc/sse3-movddup.c: New file.
	* gcc.target/powerpc/pr37191.c: New file.

From-SVN: r264992

gcc/testsuite/ChangeLog

+2018-10-09  Paul A. Clarke  <pc@us.ibm.com>
+
+	* gcc.target/powerpc/sse3-check.h: New file.
+	* gcc.target/powerpc/sse3-addsubps.c: New file.
+	* gcc.target/powerpc/sse3-addsubpd.c: New file.
+	* gcc.target/powerpc/sse3-haddps.c: New file.
+	* gcc.target/powerpc/sse3-hsubps.c: New file.
+	* gcc.target/powerpc/sse3-haddpd.c: New file.
+	* gcc.target/powerpc/sse3-hsubpd.c: New file.
+	* gcc.target/powerpc/sse3-lddqu.c: New file.
+	* gcc.target/powerpc/sse3-movsldup.c: New file.
+	* gcc.target/powerpc/sse3-movshdup.c: New file.
+	* gcc.target/powerpc/sse3-movddup.c: New file.
+	* gcc.target/powerpc/pr37191.c: New file.
+
 2018-10-09  Tobias Burnus <burnus@net-b.de>
 
 	PR fortran/83522

gcc/testsuite/gcc.target/powerpc/pr37191.c

+/* { dg-do compile } */
+/* { dg-skip-if "" { powerpc*-*-darwin* } { "*" } { "" } } */
+/* { dg-options "-O3 -mpower8-vector" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#define NO_WARN_X86_INTRINSICS 1
+
+#include <mmintrin.h>
+#include <stddef.h>
+#include <stdint.h>
+
+#if 0
+extern const uint64_t ff_bone;
+#endif
+
+static inline void transpose4x4(uint8_t *dst, uint8_t *src, ptrdiff_t dst_stride, ptrdiff_t src_stride) {
+  __m64 row0 = _mm_cvtsi32_si64(*(unsigned*)(src + (0 * src_stride)));
+  __m64 row1 = _mm_cvtsi32_si64(*(unsigned*)(src + (1 * src_stride)));
+  __m64 row2 = _mm_cvtsi32_si64(*(unsigned*)(src + (2 * src_stride)));
+  __m64 row3 = _mm_cvtsi32_si64(*(unsigned*)(src + (3 * src_stride)));
+  __m64 tmp0 = _mm_unpacklo_pi8(row0, row1);
+  __m64 tmp1 = _mm_unpacklo_pi8(row2, row3);
+  __m64 row01 = _mm_unpacklo_pi16(tmp0, tmp1);
+  __m64 row23 = _mm_unpackhi_pi16(tmp0, tmp1);
+  *((unsigned*)(dst + (0 * dst_stride))) = _mm_cvtsi64_si32(row01);
+  *((unsigned*)(dst + (1 * dst_stride))) = _mm_cvtsi64_si32(_mm_unpackhi_pi32(row01, row01));
+  *((unsigned*)(dst + (2 * dst_stride))) = _mm_cvtsi64_si32(row23);
+  *((unsigned*)(dst + (3 * dst_stride))) = _mm_cvtsi64_si32(_mm_unpackhi_pi32(row23, row23));
+}
+
+#if 0
+static inline void h264_loop_filter_chroma_intra_mmx2(uint8_t *pix, int stride, int alpha1, int beta1)
+{
+    asm volatile(
+        ""
+        :: "r"(pix-2*stride), "r"(pix), "r"((long)stride),
+           "m"(alpha1), "m"(beta1), "m"(ff_bone)
+    );
+}
+#endif
+
+void h264_h_loop_filter_chroma_intra_mmx2(uint8_t *pix, int stride, int alpha, int beta)
+{
+  uint8_t trans[8*4] __attribute__ ((aligned (8)));
+  transpose4x4(trans, pix-2, 8, stride);
+  transpose4x4(trans+4, pix-2+4*stride, 8, stride);
+//    h264_loop_filter_chroma_intra_mmx2(trans+2*8, 8, alpha-1, beta-1);
+  transpose4x4(pix-2, trans, stride, 8);
+  transpose4x4(pix-2+4*stride, trans+4, stride, 8);
+}
+/* { dg-do compile } */
+/* { dg-skip-if "" { powerpc*-*-darwin* } { "*" } { "" } } */
+/* { dg-options "-O3 -mpower8-vector" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#define NO_WARN_X86_INTRINSICS 1
+
+#include <mmintrin.h>
+#include <stddef.h>
+#include <stdint.h>
+
+#if 0
+extern const uint64_t ff_bone;
+#endif
+
+static inline void transpose4x4(uint8_t *dst, uint8_t *src, ptrdiff_t dst_stride, ptrdiff_t src_stride) {
+  __m64 row0 = _mm_cvtsi32_si64(*(unsigned*)(src + (0 * src_stride)));
+  __m64 row1 = _mm_cvtsi32_si64(*(unsigned*)(src + (1 * src_stride)));
+  __m64 row2 = _mm_cvtsi32_si64(*(unsigned*)(src + (2 * src_stride)));
+  __m64 row3 = _mm_cvtsi32_si64(*(unsigned*)(src + (3 * src_stride)));
+  __m64 tmp0 = _mm_unpacklo_pi8(row0, row1);
+  __m64 tmp1 = _mm_unpacklo_pi8(row2, row3);
+  __m64 row01 = _mm_unpacklo_pi16(tmp0, tmp1);
+  __m64 row23 = _mm_unpackhi_pi16(tmp0, tmp1);
+  *((unsigned*)(dst + (0 * dst_stride))) = _mm_cvtsi64_si32(row01);
+  *((unsigned*)(dst + (1 * dst_stride))) = _mm_cvtsi64_si32(_mm_unpackhi_pi32(row01, row01));
+  *((unsigned*)(dst + (2 * dst_stride))) = _mm_cvtsi64_si32(row23);
+  *((unsigned*)(dst + (3 * dst_stride))) = _mm_cvtsi64_si32(_mm_unpackhi_pi32(row23, row23));
+}
+
+#if 0
+static inline void h264_loop_filter_chroma_intra_mmx2(uint8_t *pix, int stride, int alpha1, int beta1)
+{
+    asm volatile(
+        ""
+        :: "r"(pix-2*stride), "r"(pix), "r"((long)stride),
+           "m"(alpha1), "m"(beta1), "m"(ff_bone)
+    );
+}
+#endif
+
+void h264_h_loop_filter_chroma_intra_mmx2(uint8_t *pix, int stride, int alpha, int beta)
+{
+  uint8_t trans[8*4] __attribute__ ((aligned (8)));
+  transpose4x4(trans, pix-2, 8, stride);
+  transpose4x4(trans+4, pix-2+4*stride, 8, stride);
+//    h264_loop_filter_chroma_intra_mmx2(trans+2*8, 8, alpha-1, beta-1);
+  transpose4x4(pix-2, trans, stride, 8);
+  transpose4x4(pix-2+4*stride, trans+4, stride, 8);
+}

gcc/testsuite/gcc.target/powerpc/sse3-addsubpd.c

+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_addsubpd_1
+#endif
+
+#define NO_WARN_X86_INTRINSICS 1
+#include <pmmintrin.h>
+
+static void
+sse3_test_addsubpd (double *i1, double *i2, double *r)
+{
+  __m128d t1 = _mm_loadu_pd (i1);
+  __m128d t2 = _mm_loadu_pd (i2);
+
+  t1 = _mm_addsub_pd (t1, t2);
+
+  _mm_storeu_pd (r, t1);
+}
+
+static void
+sse3_test_addsubpd_subsume (double *i1, double *i2, double *r)
+{
+  __m128d t1 = _mm_load_pd (i1);
+  __m128d t2 = _mm_load_pd (i2);
+
+  t1 = _mm_addsub_pd (t1, t2);
+
+  _mm_storeu_pd (r, t1);
+}
+
+static int
+chk_pd (double *v1, double *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 2; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static double p1[2] __attribute__ ((aligned(16)));
+static double p2[2] __attribute__ ((aligned(16)));
+static double p3[2];
+static double ck[2];
+
+double vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+static
+void
+TEST (void)
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals[0]); i += 4)
+    {
+      p1[0] = vals[i+0];
+      p1[1] = vals[i+1];
+
+      p2[0] = vals[i+2];
+      p2[1] = vals[i+3];
+
+      ck[0] = p1[0] - p2[0];
+      ck[1] = p1[1] + p2[1];
+
+      sse3_test_addsubpd (p1, p2, p3);
+
+      fail += chk_pd (ck, p3);
+
+      sse3_test_addsubpd_subsume (p1, p2, p3);
+
+      fail += chk_pd (ck, p3);
+    }
+
+  if (fail != 0)
+    abort ();
+}
+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_addsubpd_1
+#endif
+
+#define NO_WARN_X86_INTRINSICS 1
+#include <pmmintrin.h>
+
+static void
+sse3_test_addsubpd (double *i1, double *i2, double *r)
+{
+  __m128d t1 = _mm_loadu_pd (i1);
+  __m128d t2 = _mm_loadu_pd (i2);
+
+  t1 = _mm_addsub_pd (t1, t2);
+
+  _mm_storeu_pd (r, t1);
+}
+
+static void
+sse3_test_addsubpd_subsume (double *i1, double *i2, double *r)
+{
+  __m128d t1 = _mm_load_pd (i1);
+  __m128d t2 = _mm_load_pd (i2);
+
+  t1 = _mm_addsub_pd (t1, t2);
+
+  _mm_storeu_pd (r, t1);
+}
+
+static int
+chk_pd (double *v1, double *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 2; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static double p1[2] __attribute__ ((aligned(16)));
+static double p2[2] __attribute__ ((aligned(16)));
+static double p3[2];
+static double ck[2];
+
+double vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+static void
+TEST (void)
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals[0]); i += 4)
+    {
+      p1[0] = vals[i+0];
+      p1[1] = vals[i+1];
+
+      p2[0] = vals[i+2];
+      p2[1] = vals[i+3];
+
+      ck[0] = p1[0] - p2[0];
+      ck[1] = p1[1] + p2[1];
+
+      sse3_test_addsubpd (p1, p2, p3);
+
+      fail += chk_pd (ck, p3);
+
+      sse3_test_addsubpd_subsume (p1, p2, p3);
+
+      fail += chk_pd (ck, p3);
+    }
+
+  if (fail != 0)
+    abort ();
+}

gcc/testsuite/gcc.target/powerpc/sse3-addsubps.c

+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#define NO_WARN_X86_INTRINSICS 1
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_addsubps_1
+#endif
+
+#include <pmmintrin.h>
+
+static void
+sse3_test_addsubps (float *i1, float *i2, float *r)
+{
+  __m128 t1 = _mm_loadu_ps (i1);
+  __m128 t2 = _mm_loadu_ps (i2);
+
+  t1 = _mm_addsub_ps (t1, t2);
+
+  _mm_storeu_ps (r, t1);
+}
+
+static void
+sse3_test_addsubps_subsume (float *i1, float *i2, float *r)
+{
+  __m128 t1 = _mm_load_ps (i1);
+  __m128 t2 = _mm_load_ps (i2);
+
+  t1 = _mm_addsub_ps (t1, t2);
+
+  _mm_storeu_ps (r, t1);
+}
+
+static int
+chk_ps (float *v1, float *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 4; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static float p1[4] __attribute__ ((aligned(16)));
+static float p2[4] __attribute__ ((aligned(16)));
+static float p3[4];
+static float ck[4];
+
+static float vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+//static
+void
+TEST (void)
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals); i += 8)
+    {
+      p1[0] = vals[i+0];
+      p1[1] = vals[i+1];
+      p1[2] = vals[i+2];
+      p1[3] = vals[i+3];
+
+      p2[0] = vals[i+4];
+      p2[1] = vals[i+5];
+      p2[2] = vals[i+6];
+      p2[3] = vals[i+7];
+
+      ck[0] = p1[0] - p2[0];
+      ck[1] = p1[1] + p2[1];
+      ck[2] = p1[2] - p2[2];
+      ck[3] = p1[3] + p2[3];
+
+      sse3_test_addsubps (p1, p2, p3);
+
+      fail += chk_ps (ck, p3);
+
+      sse3_test_addsubps_subsume (p1, p2, p3);
+
+      fail += chk_ps (ck, p3);
+    }
+
+  if (fail != 0)
+    abort ();
+}
+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#define NO_WARN_X86_INTRINSICS 1
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_addsubps_1
+#endif
+
+#include <pmmintrin.h>
+
+static void
+sse3_test_addsubps (float *i1, float *i2, float *r)
+{
+  __m128 t1 = _mm_loadu_ps (i1);
+  __m128 t2 = _mm_loadu_ps (i2);
+
+  t1 = _mm_addsub_ps (t1, t2);
+
+  _mm_storeu_ps (r, t1);
+}
+
+static void
+sse3_test_addsubps_subsume (float *i1, float *i2, float *r)
+{
+  __m128 t1 = _mm_load_ps (i1);
+  __m128 t2 = _mm_load_ps (i2);
+
+  t1 = _mm_addsub_ps (t1, t2);
+
+  _mm_storeu_ps (r, t1);
+}
+
+static int
+chk_ps (float *v1, float *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 4; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static float p1[4] __attribute__ ((aligned(16)));
+static float p2[4] __attribute__ ((aligned(16)));
+static float p3[4];
+static float ck[4];
+
+static float vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+static void
+TEST (void)
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals); i += 8)
+    {
+      p1[0] = vals[i+0];
+      p1[1] = vals[i+1];
+      p1[2] = vals[i+2];
+      p1[3] = vals[i+3];
+
+      p2[0] = vals[i+4];
+      p2[1] = vals[i+5];
+      p2[2] = vals[i+6];
+      p2[3] = vals[i+7];
+
+      ck[0] = p1[0] - p2[0];
+      ck[1] = p1[1] + p2[1];
+      ck[2] = p1[2] - p2[2];
+      ck[3] = p1[3] + p2[3];
+
+      sse3_test_addsubps (p1, p2, p3);
+
+      fail += chk_ps (ck, p3);
+
+      sse3_test_addsubps_subsume (p1, p2, p3);
+
+      fail += chk_ps (ck, p3);
+    }
+
+  if (fail != 0)
+    abort ();
+}

gcc/testsuite/gcc.target/powerpc/sse3-check.h

+#include <stdio.h>
+#include <stdlib.h>
+
+#include "m128-check.h"
+
+/* define DEBUG replace abort with printf on error.  */
+//#define DEBUG 1
+
+#define TEST sse3_test
+
+static void sse3_test (void);
+
+static void
+__attribute__ ((noinline))
+do_test (void)
+{
+  sse3_test ();
+}
+
+int
+main ()
+{
+#ifdef __BUILTIN_CPU_SUPPORTS__
+  /* Most SSE intrinsic operations can be implemented via VMX
+     instructions, but some operations may be faster / simpler
+     using the POWER8 VSX instructions.  This is especially true
+     when we are transferring / converting to / from __m64 types.
+     The direct register transfer instructions from POWER8 are
+     especially important.  So we test for arch_2_07.  */
+  if (__builtin_cpu_supports ("arch_2_07"))
+    {
+      do_test ();
+#ifdef DEBUG
+      printf ("PASSED\n");
+#endif
+    }
+#ifdef DEBUG
+  else
+    printf ("SKIPPED\n");
+#endif
+#endif /* __BUILTIN_CPU_SUPPORTS__ */
+  return 0;
+}
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "m128-check.h"
+
+/* define DEBUG replace abort with printf on error.  */
+//#define DEBUG 1
+
+#define TEST sse3_test
+
+static void sse3_test (void);
+
+static void
+__attribute__ ((noinline))
+do_test (void)
+{
+  sse3_test ();
+}
+
+int
+main ()
+{
+#ifdef __BUILTIN_CPU_SUPPORTS__
+  /* Most SSE intrinsic operations can be implemented via VMX
+     instructions, but some operations may be faster / simpler
+     using the POWER8 VSX instructions.  This is especially true
+     when we are transferring / converting to / from __m64 types.
+     The direct register transfer instructions from POWER8 are
+     especially important.  So we test for arch_2_07.  */
+  if (__builtin_cpu_supports ("arch_2_07"))
+    {
+      do_test ();
+#ifdef DEBUG
+      printf ("PASSED\n");
+#endif
+    }
+#ifdef DEBUG
+  else
+    printf ("SKIPPED\n");
+#endif
+#endif /* __BUILTIN_CPU_SUPPORTS__ */
+  return 0;
+}

gcc/testsuite/gcc.target/powerpc/sse3-haddpd.c

+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#define NO_WARN_X86_INTRINSICS 1
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_haddpd_1
+#endif
+#include <pmmintrin.h>
+
+static void
+sse3_test_haddpd (double *i1, double *i2, double *r)
+{
+  __m128d t1 = _mm_loadu_pd (i1);
+  __m128d t2 = _mm_loadu_pd (i2);
+
+  t1 = _mm_hadd_pd (t1, t2);
+
+  _mm_storeu_pd (r, t1);
+}
+
+static void
+sse3_test_haddpd_subsume (double *i1, double *i2, double *r)
+{
+  __m128d t1 = _mm_load_pd (i1);
+  __m128d t2 = _mm_load_pd (i2);
+
+  t1 = _mm_hadd_pd (t1, t2);
+
+  _mm_storeu_pd (r, t1);
+}
+
+static int
+chk_pd (double *v1, double *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 2; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static double p1[2] __attribute__ ((aligned(16)));
+static double p2[2] __attribute__ ((aligned(16)));
+static double p3[2];
+static double ck[2];
+
+static double vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+//static
+void TEST (void)
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals[0]); i += 4)
+    {
+      p1[0] = vals[i + 0];
+      p1[1] = vals[i + 1];
+
+      p2[0] = vals[i + 2];
+      p2[1] = vals[i + 3];
+
+      ck[0] = p1[0] + p1[1];
+      ck[1] = p2[0] + p2[1];
+
+      sse3_test_haddpd (p1, p2, p3);
+
+      fail += chk_pd (ck, p3);
+
+      sse3_test_haddpd_subsume (p1, p2, p3);
+
+      fail += chk_pd (ck, p3);
+    }
+
+  if (fail != 0)
+    abort ();
+}
+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#define NO_WARN_X86_INTRINSICS 1
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_haddpd_1
+#endif
+#include <pmmintrin.h>
+
+static void
+sse3_test_haddpd (double *i1, double *i2, double *r)
+{
+  __m128d t1 = _mm_loadu_pd (i1);
+  __m128d t2 = _mm_loadu_pd (i2);
+
+  t1 = _mm_hadd_pd (t1, t2);
+
+  _mm_storeu_pd (r, t1);
+}
+
+static void
+sse3_test_haddpd_subsume (double *i1, double *i2, double *r)
+{
+  __m128d t1 = _mm_load_pd (i1);
+  __m128d t2 = _mm_load_pd (i2);
+
+  t1 = _mm_hadd_pd (t1, t2);
+
+  _mm_storeu_pd (r, t1);
+}
+
+static int
+chk_pd (double *v1, double *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 2; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static double p1[2] __attribute__ ((aligned(16)));
+static double p2[2] __attribute__ ((aligned(16)));
+static double p3[2];
+static double ck[2];
+
+static double vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+static void
+TEST (void)
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals[0]); i += 4)
+    {
+      p1[0] = vals[i + 0];
+      p1[1] = vals[i + 1];
+
+      p2[0] = vals[i + 2];
+      p2[1] = vals[i + 3];
+
+      ck[0] = p1[0] + p1[1];
+      ck[1] = p2[0] + p2[1];
+
+      sse3_test_haddpd (p1, p2, p3);
+
+      fail += chk_pd (ck, p3);
+
+      sse3_test_haddpd_subsume (p1, p2, p3);
+
+      fail += chk_pd (ck, p3);
+    }
+
+  if (fail != 0)
+    abort ();
+}

gcc/testsuite/gcc.target/powerpc/sse3-haddps.c

+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_haddps_1
+#endif
+
+#define NO_WARN_X86_INTRINSICS 1
+#include <pmmintrin.h>
+
+static void
+sse3_test_haddps (float *i1, float *i2, float *r)
+{
+  __m128 t1 = _mm_loadu_ps (i1);
+  __m128 t2 = _mm_loadu_ps (i2);
+
+  t1 = _mm_hadd_ps (t1, t2);
+
+  _mm_storeu_ps (r, t1);
+}
+
+static void
+sse3_test_haddps_subsume (float *i1, float *i2, float *r)
+{
+  __m128 t1 = _mm_load_ps (i1);
+  __m128 t2 = _mm_load_ps (i2);
+
+  t1 = _mm_hadd_ps (t1, t2);
+
+  _mm_storeu_ps (r, t1);
+}
+
+static int
+chk_ps(float *v1, float *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 4; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static float p1[4] __attribute__ ((aligned(16)));
+static float p2[4] __attribute__ ((aligned(16)));
+static float p3[4];
+static float ck[4];
+
+static float vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+//static
+void
+TEST ()
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals[0]); i += 8)
+    {
+      p1[0] = vals[i+0];
+      p1[1] = vals[i+1];
+      p1[2] = vals[i+2];
+      p1[3] = vals[i+3];
+
+      p2[0] = vals[i+4];
+      p2[1] = vals[i+5];
+      p2[2] = vals[i+6];
+      p2[3] = vals[i+7];
+
+      ck[0] = p1[0] + p1[1];
+      ck[1] = p1[2] + p1[3];
+      ck[2] = p2[0] + p2[1];
+      ck[3] = p2[2] + p2[3];
+
+      sse3_test_haddps (p1, p2, p3);
+
+      fail += chk_ps (ck, p3);
+
+      sse3_test_haddps_subsume (p1, p2, p3);
+
+      fail += chk_ps (ck, p3);
+    }
+
+  if (fail != 0)
+    abort ();
+}
+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_haddps_1
+#endif
+
+#define NO_WARN_X86_INTRINSICS 1
+#include <pmmintrin.h>
+
+static void
+sse3_test_haddps (float *i1, float *i2, float *r)
+{
+  __m128 t1 = _mm_loadu_ps (i1);
+  __m128 t2 = _mm_loadu_ps (i2);
+
+  t1 = _mm_hadd_ps (t1, t2);
+
+  _mm_storeu_ps (r, t1);
+}
+
+static void
+sse3_test_haddps_subsume (float *i1, float *i2, float *r)
+{
+  __m128 t1 = _mm_load_ps (i1);
+  __m128 t2 = _mm_load_ps (i2);
+
+  t1 = _mm_hadd_ps (t1, t2);
+
+  _mm_storeu_ps (r, t1);
+}
+
+static int
+chk_ps(float *v1, float *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 4; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static float p1[4] __attribute__ ((aligned(16)));
+static float p2[4] __attribute__ ((aligned(16)));
+static float p3[4];
+static float ck[4];
+
+static float vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+static void
+TEST ()
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals[0]); i += 8)
+    {
+      p1[0] = vals[i+0];
+      p1[1] = vals[i+1];
+      p1[2] = vals[i+2];
+      p1[3] = vals[i+3];
+
+      p2[0] = vals[i+4];
+      p2[1] = vals[i+5];
+      p2[2] = vals[i+6];
+      p2[3] = vals[i+7];
+
+      ck[0] = p1[0] + p1[1];
+      ck[1] = p1[2] + p1[3];
+      ck[2] = p2[0] + p2[1];
+      ck[3] = p2[2] + p2[3];
+
+      sse3_test_haddps (p1, p2, p3);
+
+      fail += chk_ps (ck, p3);
+
+      sse3_test_haddps_subsume (p1, p2, p3);
+
+      fail += chk_ps (ck, p3);
+    }
+
+  if (fail != 0)
+    abort ();
+}

gcc/testsuite/gcc.target/powerpc/sse3-hsubpd.c

+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_hsubpd_1
+#endif
+
+#define NO_WARN_X86_INTRINSICS 1
+#include <pmmintrin.h>
+
+static void
+sse3_test_hsubpd (double *i1, double *i2, double *r)
+{
+  __m128d t1 = _mm_loadu_pd (i1);
+  __m128d t2 = _mm_loadu_pd (i2);
+
+  t1 = _mm_hsub_pd (t1, t2);
+
+  _mm_storeu_pd (r, t1);
+}
+
+static void
+sse3_test_hsubpd_subsume (double *i1, double *i2, double *r)
+{
+  __m128d t1 = _mm_load_pd (i1);
+  __m128d t2 = _mm_load_pd (i2);
+
+  t1 = _mm_hsub_pd (t1, t2);
+
+  _mm_storeu_pd (r, t1);
+}
+
+static int
+chk_pd (double *v1, double *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 2; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static double p1[2] __attribute__ ((aligned(16)));
+static double p2[2] __attribute__ ((aligned(16)));
+static double p3[2];
+static double ck[2];
+
+static double vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+//static
+void TEST (void)
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals[0]); i += 4)
+    {
+      p1[0] = vals[i + 0];
+      p1[1] = vals[i + 1];
+
+      p2[0] = vals[i + 2];
+      p2[1] = vals[i + 3];
+
+      ck[0] = p1[0] - p1[1];
+      ck[1] = p2[0] - p2[1];
+
+      sse3_test_hsubpd (p1, p2, p3);
+
+      fail += chk_pd (ck, p3);
+
+      sse3_test_hsubpd_subsume (p1, p2, p3);
+
+      fail += chk_pd (ck, p3);
+    }
+
+  if (fail != 0)
+    abort ();
+}
+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_hsubpd_1
+#endif
+
+#define NO_WARN_X86_INTRINSICS 1
+#include <pmmintrin.h>
+
+static void
+sse3_test_hsubpd (double *i1, double *i2, double *r)
+{
+  __m128d t1 = _mm_loadu_pd (i1);
+  __m128d t2 = _mm_loadu_pd (i2);
+
+  t1 = _mm_hsub_pd (t1, t2);
+
+  _mm_storeu_pd (r, t1);
+}
+
+static void
+sse3_test_hsubpd_subsume (double *i1, double *i2, double *r)
+{
+  __m128d t1 = _mm_load_pd (i1);
+  __m128d t2 = _mm_load_pd (i2);
+
+  t1 = _mm_hsub_pd (t1, t2);
+
+  _mm_storeu_pd (r, t1);
+}
+
+static int
+chk_pd (double *v1, double *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 2; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static double p1[2] __attribute__ ((aligned(16)));
+static double p2[2] __attribute__ ((aligned(16)));
+static double p3[2];
+static double ck[2];
+
+static double vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+static void
+TEST (void)
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals[0]); i += 4)
+    {
+      p1[0] = vals[i + 0];
+      p1[1] = vals[i + 1];
+
+      p2[0] = vals[i + 2];
+      p2[1] = vals[i + 3];
+
+      ck[0] = p1[0] - p1[1];
+      ck[1] = p2[0] - p2[1];
+
+      sse3_test_hsubpd (p1, p2, p3);
+
+      fail += chk_pd (ck, p3);
+
+      sse3_test_hsubpd_subsume (p1, p2, p3);
+
+      fail += chk_pd (ck, p3);
+    }
+
+  if (fail != 0)
+    abort ();
+}

gcc/testsuite/gcc.target/powerpc/sse3-hsubps.c

+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_hsubps_1
+#endif
+
+#define NO_WARN_X86_INTRINSICS 1
+#include <pmmintrin.h>
+
+static void
+sse3_test_hsubps (float *i1, float *i2, float *r)
+{
+  __m128 t1 = _mm_loadu_ps (i1);
+  __m128 t2 = _mm_loadu_ps (i2);
+
+  t1 = _mm_hsub_ps (t1, t2);
+
+  _mm_storeu_ps (r, t1);
+}
+
+static void
+sse3_test_hsubps_subsume (float *i1, float *i2, float *r)
+{
+  __m128 t1 = _mm_load_ps (i1);
+  __m128 t2 = _mm_load_ps (i2);
+
+  t1 = _mm_hsub_ps (t1, t2);
+
+  _mm_storeu_ps (r, t1);
+}
+
+static int
+chk_ps(float *v1, float *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 4; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static float p1[4] __attribute__ ((aligned(16)));
+static float p2[4] __attribute__ ((aligned(16)));
+static float p3[4];
+static float ck[4];
+
+static float vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+//static
+void
+TEST ()
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals[0]); i += 8)
+    {
+      p1[0] = vals[i+0];
+      p1[1] = vals[i+1];
+      p1[2] = vals[i+2];
+      p1[3] = vals[i+3];
+
+      p2[0] = vals[i+4];
+      p2[1] = vals[i+5];
+      p2[2] = vals[i+6];
+      p2[3] = vals[i+7];
+
+      ck[0] = p1[0] - p1[1];
+      ck[1] = p1[2] - p1[3];
+      ck[2] = p2[0] - p2[1];
+      ck[3] = p2[2] - p2[3];
+
+      sse3_test_hsubps (p1, p2, p3);
+
+      fail += chk_ps (ck, p3);
+
+      sse3_test_hsubps_subsume (p1, p2, p3);
+
+      fail += chk_ps (ck, p3);
+    }
+
+  if (fail != 0)
+    abort ();
+}
+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_hsubps_1
+#endif
+
+#define NO_WARN_X86_INTRINSICS 1
+#include <pmmintrin.h>
+
+static void
+sse3_test_hsubps (float *i1, float *i2, float *r)
+{
+  __m128 t1 = _mm_loadu_ps (i1);
+  __m128 t2 = _mm_loadu_ps (i2);
+
+  t1 = _mm_hsub_ps (t1, t2);
+
+  _mm_storeu_ps (r, t1);
+}
+
+static void
+sse3_test_hsubps_subsume (float *i1, float *i2, float *r)
+{
+  __m128 t1 = _mm_load_ps (i1);
+  __m128 t2 = _mm_load_ps (i2);
+
+  t1 = _mm_hsub_ps (t1, t2);
+
+  _mm_storeu_ps (r, t1);
+}
+
+static int
+chk_ps(float *v1, float *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 4; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static float p1[4] __attribute__ ((aligned(16)));
+static float p2[4] __attribute__ ((aligned(16)));
+static float p3[4];
+static float ck[4];
+
+static float vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+static void
+TEST ()
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals[0]); i += 8)
+    {
+      p1[0] = vals[i+0];
+      p1[1] = vals[i+1];
+      p1[2] = vals[i+2];
+      p1[3] = vals[i+3];
+
+      p2[0] = vals[i+4];
+      p2[1] = vals[i+5];
+      p2[2] = vals[i+6];
+      p2[3] = vals[i+7];
+
+      ck[0] = p1[0] - p1[1];
+      ck[1] = p1[2] - p1[3];
+      ck[2] = p2[0] - p2[1];
+      ck[3] = p2[2] - p2[3];
+
+      sse3_test_hsubps (p1, p2, p3);
+
+      fail += chk_ps (ck, p3);
+
+      sse3_test_hsubps_subsume (p1, p2, p3);
+
+      fail += chk_ps (ck, p3);
+    }
+
+  if (fail != 0)
+    abort ();
+}

gcc/testsuite/gcc.target/powerpc/sse3-lddqu.c

+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_lddqu_1
+#endif
+
+#define NO_WARN_X86_INTRINSICS 1
+#include <pmmintrin.h>
+
+static void
+sse3_test_lddqu (double *i1, double *r)
+{
+  __m128i t1 = _mm_lddqu_si128 ((__m128i *) i1);
+
+  _mm_storeu_si128 ((__m128i *) r, t1);
+}
+
+static int
+chk_pd (double *v1, double *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 2; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static double p1[2];
+static double p2[2];
+static double ck[2];
+
+static double vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+//static
+void
+TEST (void)
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals[0]); i += 2)
+    {
+      p1[0] = vals[i+0];
+      p1[1] = vals[i+1];
+
+      sse3_test_lddqu (p1, p2);
+
+      ck[0] = p1[0];
+      ck[1] = p1[1];
+
+      fail += chk_pd (ck, p2);
+    }
+
+  if (fail != 0)
+    abort ();
+}
+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_lddqu_1
+#endif
+
+#define NO_WARN_X86_INTRINSICS 1
+#include <pmmintrin.h>
+
+static void
+sse3_test_lddqu (double *i1, double *r)
+{
+  __m128i t1 = _mm_lddqu_si128 ((__m128i *) i1);
+
+  _mm_storeu_si128 ((__m128i *) r, t1);
+}
+
+static int
+chk_pd (double *v1, double *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 2; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static double p1[2];
+static double p2[2];
+static double ck[2];
+
+static double vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+static void
+TEST (void)
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals[0]); i += 2)
+    {
+      p1[0] = vals[i+0];
+      p1[1] = vals[i+1];
+
+      sse3_test_lddqu (p1, p2);
+
+      ck[0] = p1[0];
+      ck[1] = p1[1];
+
+      fail += chk_pd (ck, p2);
+    }
+
+  if (fail != 0)
+    abort ();
+}

gcc/testsuite/gcc.target/powerpc/sse3-movddup.c

+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_movddup_1
+#endif
+
+#define NO_WARN_X86_INTRINSICS 1
+#include <pmmintrin.h>
+
+static void
+sse3_test_movddup_mem (double *i1, double *r)
+{
+  __m128d t1 = _mm_loaddup_pd (i1);
+
+  _mm_storeu_pd (r, t1);
+}
+
+static double cnst1 [2] = {1.0, 1.0};
+
+static void
+sse3_test_movddup_reg (double *i1, double *r)
+{
+  __m128d t1 = _mm_loadu_pd (i1);
+  __m128d t2 = _mm_loadu_pd (&cnst1[0]);
+
+  t1  = _mm_mul_pd (t1, t2);
+  t2  = _mm_movedup_pd (t1);
+
+  _mm_storeu_pd (r, t2);
+}
+
+static void
+sse3_test_movddup_reg_subsume_unaligned (double *i1, double *r)
+{
+  __m128d t1 = _mm_loadu_pd (i1);
+  __m128d t2 = _mm_movedup_pd (t1);
+
+  _mm_storeu_pd (r, t2);
+}
+
+static void
+sse3_test_movddup_reg_subsume_ldsd (double *i1, double *r)
+{
+  __m128d t1 = _mm_load_sd (i1);
+  __m128d t2 = _mm_movedup_pd (t1);
+
+  _mm_storeu_pd (r, t2);
+}
+
+static void
+sse3_test_movddup_reg_subsume (double *i1, double *r)
+{
+  __m128d t1 = _mm_load_pd (i1);
+  __m128d t2 = _mm_movedup_pd (t1);
+
+  _mm_storeu_pd (r, t2);
+}
+
+static int
+chk_pd (double *v1, double *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 2; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static double p1[2] __attribute__ ((aligned(16)));
+static double p2[2];
+static double ck[2];
+
+static double vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+//static
+void
+TEST (void)
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals[0]); i += 1)
+    {
+      p1[0] = vals[i+0];
+
+      ck[0] = p1[0];
+      ck[1] = p1[0];
+
+      sse3_test_movddup_mem (p1, p2);
+
+      fail += chk_pd (ck, p2);
+
+      sse3_test_movddup_reg (p1, p2);
+
+      fail += chk_pd (ck, p2);
+
+      sse3_test_movddup_reg_subsume (p1, p2);
+
+      fail += chk_pd (ck, p2);
+
+      sse3_test_movddup_reg_subsume_unaligned (p1, p2);
+
+      fail += chk_pd (ck, p2);
+
+      sse3_test_movddup_reg_subsume_ldsd (p1, p2);
+
+      fail += chk_pd (ck, p2);
+    }
+
+  if (fail != 0)
+    abort ();
+}
+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_movddup_1
+#endif
+
+#define NO_WARN_X86_INTRINSICS 1
+#include <pmmintrin.h>
+
+static void
+sse3_test_movddup_mem (double *i1, double *r)
+{
+  __m128d t1 = _mm_loaddup_pd (i1);
+
+  _mm_storeu_pd (r, t1);
+}
+
+static double cnst1 [2] = {1.0, 1.0};
+
+static void
+sse3_test_movddup_reg (double *i1, double *r)
+{
+  __m128d t1 = _mm_loadu_pd (i1);
+  __m128d t2 = _mm_loadu_pd (&cnst1[0]);
+
+  t1  = _mm_mul_pd (t1, t2);
+  t2  = _mm_movedup_pd (t1);
+
+  _mm_storeu_pd (r, t2);
+}
+
+static void
+sse3_test_movddup_reg_subsume_unaligned (double *i1, double *r)
+{
+  __m128d t1 = _mm_loadu_pd (i1);
+  __m128d t2 = _mm_movedup_pd (t1);
+
+  _mm_storeu_pd (r, t2);
+}
+
+static void
+sse3_test_movddup_reg_subsume_ldsd (double *i1, double *r)
+{
+  __m128d t1 = _mm_load_sd (i1);
+  __m128d t2 = _mm_movedup_pd (t1);
+
+  _mm_storeu_pd (r, t2);
+}
+
+static void
+sse3_test_movddup_reg_subsume (double *i1, double *r)
+{
+  __m128d t1 = _mm_load_pd (i1);
+  __m128d t2 = _mm_movedup_pd (t1);
+
+  _mm_storeu_pd (r, t2);
+}
+
+static int
+chk_pd (double *v1, double *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 2; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static double p1[2] __attribute__ ((aligned(16)));
+static double p2[2];
+static double ck[2];
+
+static double vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+static void
+TEST (void)
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals[0]); i += 1)
+    {
+      p1[0] = vals[i+0];
+
+      ck[0] = p1[0];
+      ck[1] = p1[0];
+
+      sse3_test_movddup_mem (p1, p2);
+
+      fail += chk_pd (ck, p2);
+
+      sse3_test_movddup_reg (p1, p2);
+
+      fail += chk_pd (ck, p2);
+
+      sse3_test_movddup_reg_subsume (p1, p2);
+
+      fail += chk_pd (ck, p2);
+
+      sse3_test_movddup_reg_subsume_unaligned (p1, p2);
+
+      fail += chk_pd (ck, p2);
+
+      sse3_test_movddup_reg_subsume_ldsd (p1, p2);
+
+      fail += chk_pd (ck, p2);
+    }
+
+  if (fail != 0)
+    abort ();
+}

gcc/testsuite/gcc.target/powerpc/sse3-movshdup.c

+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_movshdup_1
+#endif
+
+#define NO_WARN_X86_INTRINSICS 1
+#include <pmmintrin.h>
+
+static void
+sse3_test_movshdup_reg (float *i1, float *r)
+{
+  __m128 t1 = _mm_loadu_ps (i1);
+  __m128 t2 = _mm_movehdup_ps (t1);
+
+  _mm_storeu_ps (r, t2);
+}
+
+static void
+sse3_test_movshdup_reg_subsume (float *i1, float *r)
+{
+  __m128 t1 = _mm_load_ps (i1);
+  __m128 t2 = _mm_movehdup_ps (t1);
+
+  _mm_storeu_ps (r, t2);
+}
+
+static int
+chk_ps (float *v1, float *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 4; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static float p1[4] __attribute__ ((aligned(16)));
+static float p2[4];
+static float ck[4];
+
+static float vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+//static
+void
+TEST (void)
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals[0]); i += 2)
+    {
+      p1[0] = 0.0;
+      p1[1] = vals[i+0];
+      p1[2] = 1.0;
+      p1[3] = vals[i+1];
+
+      ck[0] = p1[1];
+      ck[1] = p1[1];
+      ck[2] = p1[3];
+      ck[3] = p1[3];
+
+      sse3_test_movshdup_reg (p1, p2);
+
+      fail += chk_ps (ck, p2);
+
+      sse3_test_movshdup_reg_subsume (p1, p2);
+
+      fail += chk_ps (ck, p2);
+    }
+
+  if (fail != 0)
+    abort ();
+}
+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_movshdup_1
+#endif
+
+#define NO_WARN_X86_INTRINSICS 1
+#include <pmmintrin.h>
+
+static void
+sse3_test_movshdup_reg (float *i1, float *r)
+{
+  __m128 t1 = _mm_loadu_ps (i1);
+  __m128 t2 = _mm_movehdup_ps (t1);
+
+  _mm_storeu_ps (r, t2);
+}
+
+static void
+sse3_test_movshdup_reg_subsume (float *i1, float *r)
+{
+  __m128 t1 = _mm_load_ps (i1);
+  __m128 t2 = _mm_movehdup_ps (t1);
+
+  _mm_storeu_ps (r, t2);
+}
+
+static int
+chk_ps (float *v1, float *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 4; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static float p1[4] __attribute__ ((aligned(16)));
+static float p2[4];
+static float ck[4];
+
+static float vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+static void
+TEST (void)
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals[0]); i += 2)
+    {
+      p1[0] = 0.0;
+      p1[1] = vals[i+0];
+      p1[2] = 1.0;
+      p1[3] = vals[i+1];
+
+      ck[0] = p1[1];
+      ck[1] = p1[1];
+      ck[2] = p1[3];
+      ck[3] = p1[3];
+
+      sse3_test_movshdup_reg (p1, p2);
+
+      fail += chk_ps (ck, p2);
+
+      sse3_test_movshdup_reg_subsume (p1, p2);
+
+      fail += chk_ps (ck, p2);
+    }
+
+  if (fail != 0)
+    abort ();
+}

gcc/testsuite/gcc.target/powerpc/sse3-movsldup.c

+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_movsldup_1
+#endif
+
+#define NO_WARN_X86_INTRINSICS 1
+#include <pmmintrin.h>
+
+static void
+sse3_test_movsldup_reg (float *i1, float *r)
+{
+  __m128 t1 = _mm_loadu_ps (i1);
+  __m128 t2 = _mm_moveldup_ps (t1);
+
+  _mm_storeu_ps (r, t2);
+}
+
+static void
+sse3_test_movsldup_reg_subsume (float *i1, float *r)
+{
+  __m128 t1 = _mm_load_ps (i1);
+  __m128 t2 = _mm_moveldup_ps (t1);
+
+  _mm_storeu_ps (r, t2);
+}
+
+static int
+chk_ps (float *v1, float *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 4; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static float p1[4] __attribute__ ((aligned(16)));
+static float p2[4];
+static float ck[4];
+
+static float vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+//static
+void
+TEST (void)
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals[0]); i += 2)
+    {
+      p1[0] = vals[i+0];
+      p1[1] = 0.0;
+      p1[2] = vals[i+1];
+      p1[3] = 1.0;
+
+      ck[0] = p1[0];
+      ck[1] = p1[0];
+      ck[2] = p1[2];
+      ck[3] = p1[2];
+
+      sse3_test_movsldup_reg (p1, p2);
+
+      fail += chk_ps (ck, p2);
+
+      sse3_test_movsldup_reg_subsume (p1, p2);
+
+      fail += chk_ps (ck, p2);
+    }
+
+  if (fail != 0)
+    abort ();
+}
+/* { dg-do run } */
+/* { dg-options "-O3 -mpower8-vector -Wno-psabi" } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target p8vector_hw } */
+
+#ifndef CHECK_H
+#define CHECK_H "sse3-check.h"
+#endif
+
+#include CHECK_H
+
+#ifndef TEST
+#define TEST sse3_test_movsldup_1
+#endif
+
+#define NO_WARN_X86_INTRINSICS 1
+#include <pmmintrin.h>
+
+static void
+sse3_test_movsldup_reg (float *i1, float *r)
+{
+  __m128 t1 = _mm_loadu_ps (i1);
+  __m128 t2 = _mm_moveldup_ps (t1);
+
+  _mm_storeu_ps (r, t2);
+}
+
+static void
+sse3_test_movsldup_reg_subsume (float *i1, float *r)
+{
+  __m128 t1 = _mm_load_ps (i1);
+  __m128 t2 = _mm_moveldup_ps (t1);
+
+  _mm_storeu_ps (r, t2);
+}
+
+static int
+chk_ps (float *v1, float *v2)
+{
+  int i;
+  int n_fails = 0;
+
+  for (i = 0; i < 4; i++)
+    if (v1[i] != v2[i])
+      n_fails += 1;
+
+  return n_fails;
+}
+
+static float p1[4] __attribute__ ((aligned(16)));
+static float p2[4];
+static float ck[4];
+
+static float vals[] =
+  {
+    100.0,  200.0, 300.0, 400.0, 5.0, -1.0, .345, -21.5,
+    1100.0, 0.235, 321.3, 53.40, 0.3, 10.0, 42.0, 32.52,
+    32.6,   123.3, 1.234, 2.156, 0.1, 3.25, 4.75, 32.44,
+    12.16,  52.34, 64.12, 71.13, -.1, 2.30, 5.12, 3.785,
+    541.3,  321.4, 231.4, 531.4, 71., 321., 231., -531.,
+    23.45,  23.45, 23.45, 23.45, 23.45, 23.45, 23.45, 23.45,
+    23.45,  -1.43, -6.74, 6.345, -20.1, -20.1, -40.1, -40.1,
+    1.234,  2.345, 3.456, 4.567, 5.678, 6.789, 7.891, 8.912,
+    -9.32,  -8.41, -7.50, -6.59, -5.68, -4.77, -3.86, -2.95,
+    9.32,  8.41, 7.50, 6.59, -5.68, -4.77, -3.86, -2.95
+  };
+
+static void
+TEST (void)
+{
+  int i;
+  int fail = 0;
+
+  for (i = 0; i < sizeof (vals) / sizeof (vals[0]); i += 2)
+    {
+      p1[0] = vals[i+0];
+      p1[1] = 0.0;
+      p1[2] = vals[i+1];
+      p1[3] = 1.0;
+
+      ck[0] = p1[0];
+      ck[1] = p1[0];
+      ck[2] = p1[2];
+      ck[3] = p1[2];
+
+      sse3_test_movsldup_reg (p1, p2);
+
+      fail += chk_ps (ck, p2);
+
+      sse3_test_movsldup_reg_subsume (p1, p2);
+
+      fail += chk_ps (ck, p2);
+    }
+
+  if (fail != 0)
+    abort ();
+}