On Mon, Oct 31, 2011 at 03:23:32PM +0100, Jakub Jelinek wrote:
> Would be nice to cut down slightly this testcase into just one or two loops
> that are vectorized and turn it into a runtime testcase which verifies
> the vectorization was correct.
Here is one such testcase (though, in your case there are no loads
for the indexes, on the other side you have 3 of the IVs each multiplied
by some loop invariant and all added together. Though, on the other
side in your case there are far more expressions.
2011-10-31 Jakub Jelinek <ja...@redhat.com>
* gcc.target/i386/avx2-gather-4.c: New test.
--- gcc/testsuite/gcc.target/i386/avx2-gather-4.c.jj 2011-10-31
15:58:57.000000000 +0100
+++ gcc/testsuite/gcc.target/i386/avx2-gather-4.c 2011-10-31
15:59:44.000000000 +0100
@@ -0,0 +1,38 @@
+/* { dg-do run } */
+/* { dg-require-effective-target avx2 } */
+/* { dg-options "-O3 -mavx2" } */
+
+#include "avx2-check.h"
+
+#define N 1024
+int a[N], b[N], c[N], d[N];
+
+__attribute__((noinline, noclone)) void
+foo (float *__restrict p, float *__restrict q, float *__restrict r,
+ long s1, long s2, long s3)
+{
+ int i;
+ for (i = 0; i < N; i++)
+ p[i] = q[a[i] * s1 + b[i] * s2 + s3] * r[c[i] * s1 + d[i] * s2 + s3];
+}
+
+static void
+avx2_test (void)
+{
+ int i;
+ float e[N], f[N], g[N];
+ for (i = 0; i < N; i++)
+ {
+ a[i] = (i * 7) & (N / 8 - 1);
+ b[i] = (i * 13) & (N / 8 - 1);
+ c[i] = (i * 23) & (N / 8 - 1);
+ d[i] = (i * 5) & (N / 8 - 1);
+ e[i] = 16.5 + i;
+ f[i] = 127.5 - i;
+ }
+ foo (g, e, f, 3, 2, 4);
+ for (i = 0; i < N; i++)
+ if (g[i] != (float) ((20.5 + a[i] * 3 + b[i] * 2)
+ * (123.5 - c[i] * 3 - d[i] * 2)))
+ abort ();
+}
Jakub
