re PR tree-optimization/88464 (AVX-512 vectorization of masked scatter failing with "not suitable for scatter store")

PR tree-optimization/88464
	PR target/88498
	* tree-vect-stmts.c (vect_build_gather_load_calls): For NARROWING
	and mask with integral masktype, don't try to permute mask vectors,
	instead emit VEC_UNPACK_{LO,HI}_EXPR.  Fix up NOP_EXPR operand.
	(vectorizable_store): Handle masked scatters with decl and integral
	mask type.
	(permute_vec_elements): Allow scalar_dest to be NULL.
	* config/i386/i386.c (ix86_get_builtin)
	<case IX86_BUILTIN_GATHER3ALTDIV16SF>: Use lowpart_subreg for masks.
	<case IX86_BUILTIN_GATHER3ALTDIV8SF>: Don't assume mask and src have
	to be the same.

	* gcc.target/i386/avx512f-pr88462-1.c: Rename to ...
	* gcc.target/i386/avx512f-pr88464-1.c: ... this.  Fix up PR number.
	Expect 4 vectorized loops instead of 3.
	(f4): New function.
	* gcc.target/i386/avx512f-pr88462-2.c: Rename to ...
	* gcc.target/i386/avx512f-pr88464-2.c: ... this.  Fix up PR number
	and #include.
	(avx512f_test): Prepare arguments for f4 and check the results.
	* gcc.target/i386/avx512f-pr88464-3.c: New test.
	* gcc.target/i386/avx512f-pr88464-4.c: New test.

From-SVN: r267170

gcc/testsuite/gcc.target/i386/avx512f-pr88464-3.c

@@ -0,0 +1,45 @@
+/* PR tree-optimization/88464 */
+/* { dg-do compile } */
+/* { dg-options "-O3 -mavx512f -mprefer-vector-width=512 -mtune=skylake-avx512 -fdump-tree-vect-details" } */
+/* { dg-final { scan-tree-dump-times "loop vectorized using 64 byte vectors" 4 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 4 "vect" } } */
+
+__attribute__((noipa)) void
+f1 (double * __restrict__ a, const double * __restrict__ b, const int * __restrict__ c, int n)
+{
+  int i;
+#pragma GCC ivdep
+  for (i = 0; i < n; ++i)
+    if (b[i] > -2.0)
+      a[c[i]] = b[i];
+}
+
+__attribute__((noipa)) void
+f2 (double * __restrict__ a, const double * __restrict__ b, const long * __restrict__ c, int n)
+{
+  int i;
+#pragma GCC ivdep
+  for (i = 0; i < n; ++i)
+    if (b[i] > -2.0)
+      a[c[i]] = b[i];
+}
+
+__attribute__((noipa)) void
+f3 (float * __restrict__ a, const float * __restrict__ b, const int * __restrict__ c, int n)
+{
+  int i;
+#pragma GCC ivdep
+  for (i = 0; i < n; ++i)
+    if (b[i] > -2.0f)
+      a[c[i]] = b[i];
+}
+
+__attribute__((noipa)) void
+f4 (float * __restrict__ a, const float * __restrict__ b, const long * __restrict__ c, int n)
+{
+  int i;
+#pragma GCC ivdep
+  for (i = 0; i < n; ++i)
+    if (b[i] > -2.0f)
+      a[c[i]] = b[i];
+}

gcc/testsuite/gcc.target/i386/avx512f-pr88464-4.c

@@ -0,0 +1,61 @@
+/* PR tree-optimization/88464 */
+/* { dg-do run { target { avx512f } } } */
+/* { dg-options "-O3 -mavx512f -mprefer-vector-width=512 -mtune=skylake-avx512" } */
+
+#include "avx512f-check.h"
+
+#include "avx512f-pr88464-3.c"
+
+static void
+avx512f_test (void)
+{
+  double a[1024], b[1024];
+  float c[1024], f[1024];
+  int d[1024];
+  long e[1024];
+  int i;
+  for (i = 0; i < 1024; i++)
+    {
+      asm volatile ("" : "+g" (i));
+      a[i] = -5.0;
+      b[i] = (i % 3) != 0 ? 2.0 * i : -5.0;
+      d[i] = (i % 3) != 0 ? 1023 - i : __INT_MAX__;
+    }
+  f1 (a, b, d, 1024);
+  for (i = 0; i < 1024; i++)
+    {
+      asm volatile ("" : "+g" (i));
+      if (a[i] != ((i % 3) != 0 ? (1023 - i) * 2.0 : -5.0))
+	abort ();
+      a[i] = -5.0;
+      b[i] = (i % 3) != 1 ? 3.0 * i : -5.0;
+      e[i] = (i % 3) != 1 ? 1023 - i : __LONG_MAX__;
+    }
+  f2 (a, b, e, 1024);
+  for (i = 0; i < 1024; i++)
+    {
+      asm volatile ("" : "+g" (i));
+      if (a[i] != ((i % 3) != 2 ? (1023 - i) * 3.0 : -5.0))
+	abort ();
+      c[i] = -5.0f;
+      d[i] = (i % 3) != 2 ? 1023 - i : __INT_MAX__;
+      f[i] = (i % 3) != 2 ? 4.0f * i : -5.0f;
+    }
+  f3 (c, f, d, 1024);
+  for (i = 0; i < 1024; i++)
+    {
+      asm volatile ("" : "+g" (i));
+      if (c[i] != ((i % 3) != 1 ? (1023 - i) * 4.0f : -5.0f))
+	abort ();
+      c[i] = -5.0f;
+      e[i] = (i % 3) != 0 ? 1023 - i : __INT_MAX__;
+      f[i] = (i % 3) != 0 ? 5.0f * i : -5.0f;
+    }
+  f4 (c, f, e, 1024);
+  for (i = 0; i < 1024; i++)
+    {
+      asm volatile ("" : "+g" (i));
+      if (c[i] != ((i % 3) != 0 ? (1023 - i) * 5.0f : -5.0f))
+	abort ();
+    }
+}