Support for loop SLP splitting exposed that slp-11b.c has
folding that breaks SLP discovery which isn't what was intended
when the testcase was written. The following makes it SLP-able
and "only" run into the issue that a load permutation is required.
And tries to adjust the target selectors accordingly.
Pushed. (fingers crossing)
2021-01-18 Richard Biener <rguent...@suse.de>
PR testsuite/97494
* gcc.dg/vect/slp-11b.c: Adjust.
---
gcc/testsuite/gcc.dg/vect/slp-11b.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/gcc/testsuite/gcc.dg/vect/slp-11b.c
b/gcc/testsuite/gcc.dg/vect/slp-11b.c
index 0aece8092a8..c4d9ab0f36b 100644
--- a/gcc/testsuite/gcc.dg/vect/slp-11b.c
+++ b/gcc/testsuite/gcc.dg/vect/slp-11b.c
@@ -12,13 +12,13 @@ main1 ()
unsigned int out[N*8], a0, a1, a2, a3, a4, a5, a6, a7, b1, b0, b2, b3, b4,
b5, b6, b7;
unsigned int in[N*8] =
{0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63};
- /* Requires permutation - not SLPable. */
+ /* Requires permutation for SLP. */
for (i = 0; i < N*2; i++)
{
out[i*4] = (in[i*4] + 2) * 3;
out[i*4 + 1] = (in[i*4 + 2] + 2) * 7;
out[i*4 + 2] = (in[i*4 + 1] + 7) * 3;
- out[i*4 + 3] = (in[i*4 + 3] + 3) * 4;
+ out[i*4 + 3] = (in[i*4 + 3] + 3) * 7;
}
/* check results: */
@@ -27,7 +27,7 @@ main1 ()
if (out[i*4] != (in[i*4] + 2) * 3
|| out[i*4 + 1] != (in[i*4 + 2] + 2) * 7
|| out[i*4 + 2] != (in[i*4 + 1] + 7) * 3
- || out[i*4 + 3] != (in[i*4 + 3] + 3) * 4)
+ || out[i*4 + 3] != (in[i*4 + 3] + 3) * 7)
abort ();
}
@@ -43,7 +43,5 @@ int main (void)
return 0;
}
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target {
vect_strided4 && vect_int_mult } } } } */
-/* { dg-final { scan-tree-dump-times "vectorized 0 loops" 1 "vect" { target {
! { vect_strided4 && vect_int_mult } } } } } */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 0 "vect" {
target { ! vect_load_lanes } } } } */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" {
target { vect_load_lanes } } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target {
{ vect_strided4 || vect_perm } && vect_int_mult } } } } */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" {
target { vect_perm && vect_int_mult } } } } */
--
2.26.2
