[AArch64] Split gcc.target/aarch64/sve/reduc_strict_3.c

This patch splits gcc.target/aarch64/sve/reduc_strict_3.c into one
test per function, so that it's easier to see what each scan is
matching and also so that we no longer rely on the number of times
that each dump message is printed.

The patch also generalises the tests to work with scalable vectors.
I think the test probably predates support for variable-length
loop-aware SLP.

2019-10-31  Richard Sandiford  <richard.sandiford@arm.com>

gcc/testsuite/
	* gcc.target/aarch64/sve/reduc_strict_3.c: Split all but the
	first function out into...
	* gcc.target/aarch64/sve/reduc_strict_4.c,
	* gcc.target/aarch64/sve/reduc_strict_5.c,
	* gcc.target/aarch64/sve/reduc_strict_6.c,
	* gcc.target/aarch64/sve/reduc_strict_7.c,
	* gcc.target/aarch64/sve/reduc_strict_8.c,
	* gcc.target/aarch64/sve/reduc_strict_9.c: ...these new tests.
	Test for scalable vectors instead of 256-bit vectors.

From-SVN: r277681

gcc/testsuite/ChangeLog

+2019-10-31  Richard Sandiford  <richard.sandiford@arm.com>
+
+	* gcc.target/aarch64/sve/reduc_strict_3.c: Split all but the
+	first function out into...
+	* gcc.target/aarch64/sve/reduc_strict_4.c,
+	* gcc.target/aarch64/sve/reduc_strict_5.c,
+	* gcc.target/aarch64/sve/reduc_strict_6.c,
+	* gcc.target/aarch64/sve/reduc_strict_7.c,
+	* gcc.target/aarch64/sve/reduc_strict_8.c,
+	* gcc.target/aarch64/sve/reduc_strict_9.c: ...these new tests.
+	Test for scalable vectors instead of 256-bit vectors.
+
 2019-10-31  Jakub Jelinek  <jakub@redhat.com>
 
 	PR fortran/92284

gcc/testsuite/gcc.target/aarch64/sve/reduc_strict_3.c

 /* { dg-do compile } */
-/* { dg-options "-O2 -ftree-vectorize -fno-inline -msve-vector-bits=256 -fdump-tree-vect-details" } */
-/* Disabling epilogues until we find a better way to deal with scans.  */
-/* { dg-additional-options "--param vect-epilogues-nomask=0" } */
+/* { dg-options "-O2 -ftree-vectorize" } */
 
-double mat[100][4];
-double mat2[100][8];
-double mat3[100][12];
-double mat4[100][3];
+double mat[100][2];
 
 double
 slp_reduc_plus (int n)
@@ -16,116 +11,8 @@ slp_reduc_plus (int n)
     {
       tmp = tmp + mat[i][0];
       tmp = tmp + mat[i][1];
-      tmp = tmp + mat[i][2];
-      tmp = tmp + mat[i][3];
     }
   return tmp;
 }
 
-double
-slp_reduc_plus2 (int n)
-{
-  double tmp = 0.0;
-  for (int i = 0; i < n; i++)
-    {
-      tmp = tmp + mat2[i][0];
-      tmp = tmp + mat2[i][1];
-      tmp = tmp + mat2[i][2];
-      tmp = tmp + mat2[i][3];
-      tmp = tmp + mat2[i][4];
-      tmp = tmp + mat2[i][5];
-      tmp = tmp + mat2[i][6];
-      tmp = tmp + mat2[i][7];
-    }
-  return tmp;
-}
-
-double
-slp_reduc_plus3 (int n)
-{
-  double tmp = 0.0;
-  for (int i = 0; i < n; i++)
-    {
-      tmp = tmp + mat3[i][0];
-      tmp = tmp + mat3[i][1];
-      tmp = tmp + mat3[i][2];
-      tmp = tmp + mat3[i][3];
-      tmp = tmp + mat3[i][4];
-      tmp = tmp + mat3[i][5];
-      tmp = tmp + mat3[i][6];
-      tmp = tmp + mat3[i][7];
-      tmp = tmp + mat3[i][8];
-      tmp = tmp + mat3[i][9];
-      tmp = tmp + mat3[i][10];
-      tmp = tmp + mat3[i][11];
-    }
-  return tmp;
-}
-
-void
-slp_non_chained_reduc (int n, double * restrict out)
-{
-  for (int i = 0; i < 3; i++)
-    out[i] = 0;
-
-  for (int i = 0; i < n; i++)
-    {
-      out[0] = out[0] + mat4[i][0];
-      out[1] = out[1] + mat4[i][1];
-      out[2] = out[2] + mat4[i][2];
-    }
-}
-
-/* Strict FP reductions shouldn't be used for the outer loops, only the
-   inner loops.  */
-
-float
-double_reduc1 (float (*restrict i)[16])
-{
-  float l = 0;
-
-#pragma GCC unroll 0
-  for (int a = 0; a < 8; a++)
-    for (int b = 0; b < 8; b++)
-      l += i[b][a];
-  return l;
-}
-
-float
-double_reduc2 (float *restrict i)
-{
-  float l = 0;
-
-  for (int a = 0; a < 8; a++)
-    for (int b = 0; b < 16; b++)
-      {
-        l += i[b * 4];
-        l += i[b * 4 + 1];
-        l += i[b * 4 + 2];
-        l += i[b * 4 + 3];
-      }
-  return l;
-}
-
-float
-double_reduc3 (float *restrict i, float *restrict j)
-{
-  float k = 0, l = 0;
-
-  for (int a = 0; a < 8; a++)
-    for (int b = 0; b < 8; b++)
-      {
-        k += i[b];
-        l += j[b];
-      }
-  return l * k;
-}
-
-/* { dg-final { scan-assembler-times {\tfadda\ts[0-9]+, p[0-7], s[0-9]+, z[0-9]+\.s} 4 } } */
-/* { dg-final { scan-assembler-times {\tfadda\td[0-9]+, p[0-7], d[0-9]+, z[0-9]+\.d} 9 } } */
-/* 1 reduction each for double_reduc{1,2} and 2 for double_reduc3.  Each one
-   is reported three times, once for SVE, once for 128-bit AdvSIMD and once
-   for 64-bit AdvSIMD.  */
-/* { dg-final { scan-tree-dump-times "Detected double reduction" 12 "vect" } } */
-/* double_reduc2 has 2 reductions and slp_non_chained_reduc has 3.  */
-/* { dg-final { scan-tree-dump-times "Detected reduction" 10 "vect" } } */
+/* { dg-final { scan-assembler-times {\tfadda\td[0-9]+, p[0-7], d[0-9]+, z[0-9]+\.d\n} 1 } } */

gcc/testsuite/gcc.target/aarch64/sve/reduc_strict_4.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize" } */
+
+double mat[100][8];
+
+double
+slp_reduc_plus (int n)
+{
+  double tmp = 0.0;
+  for (int i = 0; i < n; i++)
+    {
+      tmp = tmp + mat[i][0];
+      tmp = tmp + mat[i][1];
+      tmp = tmp + mat[i][2];
+      tmp = tmp + mat[i][3];
+      tmp = tmp + mat[i][4];
+      tmp = tmp + mat[i][5];
+      tmp = tmp + mat[i][6];
+      tmp = tmp + mat[i][7];
+    }
+  return tmp;
+}
+
+/* { dg-final { scan-assembler-times {\tfadda\td[0-9]+, p[0-7], d[0-9]+, z[0-9]+\.d} 4 } } */

gcc/testsuite/gcc.target/aarch64/sve/reduc_strict_5.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize" } */
+
+double mat[100][12];
+
+double
+slp_reduc_plus (int n)
+{
+  double tmp = 0.0;
+  for (int i = 0; i < n; i++)
+    {
+      tmp = tmp + mat[i][0];
+      tmp = tmp + mat[i][1];
+      tmp = tmp + mat[i][2];
+      tmp = tmp + mat[i][3];
+      tmp = tmp + mat[i][4];
+      tmp = tmp + mat[i][5];
+      tmp = tmp + mat[i][6];
+      tmp = tmp + mat[i][7];
+      tmp = tmp + mat[i][8];
+      tmp = tmp + mat[i][9];
+      tmp = tmp + mat[i][10];
+      tmp = tmp + mat[i][11];
+    }
+  return tmp;
+}
+
+/* { dg-final { scan-assembler-times {\tfadda\td[0-9]+, p[0-7], d[0-9]+, z[0-9]+\.d} 6 } } */

gcc/testsuite/gcc.target/aarch64/sve/reduc_strict_6.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize" } */
+
+double mat[100][4];
+double mat2[100][8];
+double mat3[100][12];
+double mat4[100][3];
+
+void
+slp_non_chained_reduc (int n, double * restrict out)
+{
+  for (int i = 0; i < 3; i++)
+    out[i] = 0;
+
+  for (int i = 0; i < n; i++)
+    {
+      out[0] = out[0] + mat4[i][0];
+      out[1] = out[1] + mat4[i][1];
+      out[2] = out[2] + mat4[i][2];
+    }
+}
+
+/* { dg-final { scan-assembler-times {\tld3d\t} 1 } } */
+/* { dg-final { scan-assembler-times {\tfadda\td[0-9]+, p[0-7], d[0-9]+, z[0-9]+\.d} 3 } } */

gcc/testsuite/gcc.target/aarch64/sve/reduc_strict_7.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details" } */
+
+/* Strict FP reductions shouldn't be used for the outer loop, only the
+   inner loop.  */
+
+float
+double_reduc (float (*i)[16])
+{
+  float l = 0;
+
+#pragma GCC unroll 0
+  for (int a = 0; a < 8; a++)
+    for (int b = 0; b < 100; b++)
+      l += i[b][a];
+  return l;
+}
+
+/* { dg-final { scan-assembler-times {\tfadda\ts[0-9]+, p[0-7], s[0-9]+, z[0-9]+\.s\n} 1 } } */
+/* { dg-final { scan-tree-dump "Detected double reduction" "vect" } } */
+/* { dg-final { scan-tree-dump-not "OUTER LOOP VECTORIZED" "vect" } } */

gcc/testsuite/gcc.target/aarch64/sve/reduc_strict_8.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details" } */
+
+float
+double_reduc (float *i)
+{
+  float l = 0;
+
+  for (int a = 0; a < 8; a++)
+    for (int b = 0; b < 16; b++)
+      {
+        l += i[b * 4];
+        l += i[b * 4 + 1];
+        l += i[b * 4 + 2];
+        l += i[b * 4 + 3];
+      }
+  return l;
+}
+
+/* { dg-final { scan-assembler-times {\tfadda\ts[0-9]+, p[0-7], s[0-9]+, z[0-9]+\.s\n} 1 } } */
+/* { dg-final { scan-tree-dump "Detected double reduction" "vect" } } */
+/* { dg-final { scan-tree-dump-not "OUTER LOOP VECTORIZED" "vect" } } */

gcc/testsuite/gcc.target/aarch64/sve/reduc_strict_9.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details" } */
+
+float
+double_reduc (float *i, float *j)
+{
+  float k = 0, l = 0;
+
+  for (int a = 0; a < 8; a++)
+    for (int b = 0; b < 100; b++)
+      {
+        k += i[b];
+        l += j[b];
+      }
+  return l * k;
+}
+
+/* { dg-final { scan-assembler-times {\tld1w\t} 2 } } */
+/* { dg-final { scan-assembler-times {\tfadda\ts[0-9]+, p[0-7], s[0-9]+, z[0-9]+\.s\n} 2 } } */
+/* { dg-final { scan-tree-dump "Detected double reduction" "vect" } } */
+/* { dg-final { scan-tree-dump-not "OUTER LOOP VECTORIZED" "vect" } } */