avx512f-scatter-1.c: New.

gcc/testsuite/
	* gcc.target/i386/avx512f-scatter-1.c: New.
	* gcc.target/i386/avx512f-scatter-2.c: Ditto.
	* gcc.target/i386/avx512f-scatter-3.c: Ditto.

Co-Authored-By: Kirill Yukhin <kirill.yukhin@intel.com>
Co-Authored-By: Petr Murzin <petr.murzin@intel.com>

From-SVN: r227483

4 files changed, 479 insertions, 0 deletions

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index e2c55ba..8b444ab 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,11 @@
+2015-09-04  Andrey Turetskiy  <andrey.turetskiy@intel.com>
+	    Petr Murzin  <petr.murzin@intel.com>
+	    Kirill Yukhin <kirill.yukhin@intel.com>
+
+	* gcc.target/i386/avx512f-scatter-1.c: New.
+	* gcc.target/i386/avx512f-scatter-2.c: Ditto.
+	* gcc.target/i386/avx512f-scatter-3.c: Ditto.
+
 2015-09-04  Janne Blomqvist  <jb@gcc.gnu.org>
 
 	* gfortran.dg/read_dir.f90: Delete empty directory when closing
diff --git a/gcc/testsuite/gcc.target/i386/avx512f-scatter-1.c b/gcc/testsuite/gcc.target/i386/avx512f-scatter-1.c
new file mode 100644
index 0000000..575f3bf
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512f-scatter-1.c
@@ -0,0 +1,218 @@
+/* { dg-do run } */
+/* { dg-require-effective-target avx512f } */
+/* { dg-options "-O3 -mavx512f" } */
+
+#define AVX512F
+
+#include "avx512f-check.h"
+
+#define N 1024
+float vf1[N], vf2[2*N+16];
+double vd1[N], vd2[2*N+16];
+int vi1[N], vi2[2*N+16], k[N];
+long vl1[N], vl2[2*N+16], l[N];
+
+__attribute__((noinline, noclone)) void
+f1 (void)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vf2[k[i]] = vf1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f2 (void)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vi2[k[i]] = vi1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f3 (int x)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vf2[k[i] + x] = vf1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f4 (int x)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vi2[k[i] + x] = vi1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f5 (void)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vd2[k[i]] = vd1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f6 (void)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vl2[k[i]] = vl1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f7 (int x)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vd2[k[i] + x] = vd1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f8 (int x)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vl2[k[i] + x] = vl1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f9 (void)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vf2[l[i]] = vf1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f10 (void)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vi2[l[i]] = vi1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f11 (long x)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vf2[l[i] + x] = vf1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f12 (long x)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vi2[l[i] + x] = vi1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f13 (void)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vd2[l[i]] = vd1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f14 (void)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vl2[l[i]] = vl1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f15 (long x)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vd2[l[i] + x] = vd1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f16 (long x)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vl2[l[i] + x] = vl1[i];
+}
+
+static void
+avx512f_test (void)
+{
+  int i;
+
+  for (i = 0; i < N; i++)
+    {
+      asm ("");
+      vf1[i] = 17.0f + i;
+      vd1[i] = 19.0 + i;
+      vi1[i] = 21 + i;
+      vl1[i] = 23L + i;
+    }
+  for (i = 0; i < N; i++)
+    {
+      asm ("");
+      k[i] = (i % 2) ? (N / 2 + i) : (N / 2 - i / 2);
+      l[i] = 2 * i + i % 2;
+    }
+
+  f1 ();
+  f2 ();
+  for (i = 0; i < N; i++)
+    if (vf2[(i % 2) ? (N / 2 + i) : (N / 2 - i / 2)] != i + 17
+	|| vi2[(i % 2) ? (N / 2 + i) : (N / 2 - i / 2)] != i + 21)
+      abort ();
+
+  f3 (12);
+  f4 (14);
+  for (i = 0; i < N; i++)
+    if (vf2[((i % 2) ? (N / 2 + i) : (N / 2 - i / 2)) + 12] != i + 17
+	|| vi2[((i % 2) ? (N / 2 + i) : (N / 2 - i / 2)) + 14] != i + 21)
+      abort ();
+
+  f5 ();
+  f6 ();
+  for (i = 0; i < N; i++)
+    if (vd2[(i % 2) ? (N / 2 + i) : (N / 2 - i / 2)] != i + 19
+	|| vl2[(i % 2) ? (N / 2 + i) : (N / 2 - i / 2)] != i + 23)
+      abort ();
+
+  f7 (7);
+  f8 (9);
+  for (i = 0; i < N; i++)
+    if (vd2[((i % 2) ? (N / 2 + i) : (N / 2 - i / 2)) + 7] != i + 19
+	|| vl2[((i % 2) ? (N / 2 + i) : (N / 2 - i / 2)) + 9] != i + 23)
+      abort ();
+
+  f9 ();
+  f10 ();
+  for (i = 0; i < N; i++)
+    if (vf2[2 * i + i % 2] != i + 17
+	|| vi2[2 * i + i % 2] != i + 21)
+      abort ();
+
+  f11 (2);
+  f12 (4);
+  for (i = 0; i < N; i++)
+    if (vf2[2 * i + i % 2 + 2] != i + 17
+	|| vi2[2 * i + i % 2 + 4] != i + 21)
+      abort ();
+
+  f13 ();
+  f14 ();
+  for (i = 0; i < N; i++)
+    if (vd2[2 * i + i % 2] != i + 19
+	|| vl2[2 * i + i % 2] != i + 23)
+      abort ();
+
+  f15 (13);
+  f16 (15);
+  for (i = 0; i < N; i++)
+    if (vd2[2 * i + i % 2 + 13] != i + 19
+	|| vl2[2 * i + i % 2 + 15] != i + 23)
+      abort ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512f-scatter-2.c b/gcc/testsuite/gcc.target/i386/avx512f-scatter-2.c
new file mode 100644
index 0000000..c59ce23
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512f-scatter-2.c
@@ -0,0 +1,217 @@
+/* { dg-do run } */
+/* { dg-require-effective-target avx512f } */
+/* { dg-options "-O3 -mavx512f" } */
+
+#define AVX512F
+
+#include "avx512f-check.h"
+
+#define N 1024
+float vf1[N], vf2[2*N+16];
+double vd1[N], vd2[2*N+16];
+int k[N];
+long l[N];
+short n[2*N+16];
+
+__attribute__((noinline, noclone)) void
+f1 (void)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vf2[k[i]] = vf1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f2 (void)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    n[k[i]] = (int) vf1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f3 (int x)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vf2[k[i] + x] = vf1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f4 (int x)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    n[k[i] + x] = (int) vf1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f5 (void)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vd2[k[i]] = vd1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f6 (void)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    n[k[i]] = (int) vd1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f7 (int x)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vd2[k[i] + x] = vd1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f8 (int x)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    n[k[i] + x] = vd1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f9 (void)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vf2[l[i]] = vf1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f10 (void)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    n[l[i]] = (int) vf1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f11 (long x)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vf2[l[i] + x] = vf1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f12 (long x)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    n[l[i] + x] = (int) vf1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f13 (void)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vd2[l[i]] = vd1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f14 (void)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    n[l[i]] = (int) vd1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f15 (long x)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    vd2[l[i] + x] = vd1[i];
+}
+
+__attribute__((noinline, noclone)) void
+f16 (long x)
+{
+  int i;
+  for (i = 0; i < N; i++)
+    n[l[i] + x] = (int) vd1[i];
+}
+
+static void
+avx512f_test (void)
+{
+  int i;
+
+  for (i = 0; i < N; i++)
+    {
+      asm ("");
+      vf1[i] = 17.0f + i;
+      vd1[i] = 19.0 + i;
+    }
+  for (i = 0; i < N; i++)
+    {
+      asm ("");
+      k[i] = (i % 2) ? (N / 2 + i) : (N / 2 - i / 2);
+      l[i] = 2 * i + i % 2;
+    }
+
+  f1 ();
+  f2 ();
+  for (i = 0; i < N; i++)
+    if (vf2[(i % 2) ? (N / 2 + i) : (N / 2 - i / 2)] != i + 17
+	|| n[(i % 2) ? (N / 2 + i) : (N / 2 - i / 2)] != i + 17)
+      abort ();
+
+  f3 (12);
+  f4 (14);
+  for (i = 0; i < N; i++)
+    if (vf2[((i % 2) ? (N / 2 + i) : (N / 2 - i / 2)) + 12] != i + 17
+	|| n[((i % 2) ? (N / 2 + i) : (N / 2 - i / 2)) + 14] != i + 17)
+      abort ();
+
+  f5 ();
+  f6 ();
+  for (i = 0; i < N; i++)
+    if (vd2[(i % 2) ? (N / 2 + i) : (N / 2 - i / 2)] != i + 19
+	|| n[(i % 2) ? (N / 2 + i) : (N / 2 - i / 2)] != i + 19)
+      abort ();
+
+  f7 (7);
+  f8 (9);
+  for (i = 0; i < N; i++)
+    if (vd2[((i % 2) ? (N / 2 + i) : (N / 2 - i / 2)) + 7] != i + 19
+	|| n[((i % 2) ? (N / 2 + i) : (N / 2 - i / 2)) + 9] != i + 19)
+      abort ();
+
+  f9 ();
+  f10 ();
+  for (i = 0; i < N; i++)
+    if (vf2[2 * i + i % 2] != i + 17
+	|| n[2 * i + i % 2] != i + 17)
+      abort ();
+
+  f11 (2);
+  f12 (4);
+  for (i = 0; i < N; i++)
+    if (vf2[2 * i + i % 2 + 2] != i + 17
+	|| n[2 * i + i % 2 + 4] != i + 17)
+      abort ();
+
+  f13 ();
+  f14 ();
+  for (i = 0; i < N; i++)
+    if (vd2[2 * i + i % 2] != i + 19
+	|| n[2 * i + i % 2] != i + 19)
+      abort ();
+
+  f15 (13);
+  f16 (15);
+  for (i = 0; i < N; i++)
+    if (vd2[2 * i + i % 2 + 13] != i + 19
+	|| n[2 * i + i % 2 + 15] != i + 19)
+      abort ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512f-scatter-3.c b/gcc/testsuite/gcc.target/i386/avx512f-scatter-3.c
new file mode 100644
index 0000000..37137fd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512f-scatter-3.c
@@ -0,0 +1,36 @@
+/* { dg-do run } */
+/* { dg-require-effective-target avx512f } */
+/* { dg-options "-O3 -mavx512f" } */
+
+#define AVX512F
+
+#include "avx512f-check.h"
+
+#define N 1024
+int a[N], b[N];
+
+__attribute__((noinline, noclone)) void
+foo (float *__restrict p, float *__restrict q,
+     int s1, int s2, int s3)
+{
+  int i;
+  for (i = 0; i < (N / 8); i++)
+    p[a[i] * s1 + b[i] * s2 + s3] = q[i];
+}
+
+static void
+avx512f_test (void)
+{
+  int i;
+  float c[N], d[N];
+  for (i = 0; i < N; i++)
+    {
+      a[i] = (i * 7) & (N / 8 - 1);
+      b[i] = (i * 13) & (N / 8 - 1);
+      c[i] = 179.13 + i;
+    }
+  foo (d, c, 3, 2, 4);
+  for (i = 0; i < (N / 8); i++)
+    if (d[a[i] * 3 + b[i] * 2 + 4] != (float) (179.13 + i))
+      abort ();
+}