[committed 6/6] amdgcn: vector testsuite tweaks

[Andrew Stubbs <ams@codesourcery.com>]

[-- Attachment #1: Type: text/plain, Size: 1656 bytes --]


The testsuite needs a few tweaks following my patches to add multiple vector
sizes for amdgcn.

gcc/testsuite/ChangeLog:

	* gcc.dg/pr104464.c: Xfail on amdgcn.
	* gcc.dg/signbit-2.c: Likewise.
	* gcc.dg/signbit-5.c: Likewise.
	* gcc.dg/vect/bb-slp-68.c: Likewise.
	* gcc.dg/vect/bb-slp-cond-1.c: Change expectations on amdgcn.
	* gcc.dg/vect/bb-slp-subgroups-3.c: Likewise.
	* gcc.dg/vect/no-vfa-vect-depend-2.c: Change expectations for multiple
	vector sizes.
	* gcc.dg/vect/pr33953.c: Likewise.
	* gcc.dg/vect/pr65947-12.c: Likewise.
	* gcc.dg/vect/pr65947-13.c: Likewise.
	* gcc.dg/vect/pr80631-2.c: Likewise.
	* gcc.dg/vect/slp-reduc-4.c: Likewise.
	* gcc.dg/vect/trapv-vect-reduc-4.c: Likewise.
	* lib/target-supports.exp (available_vector_sizes): Add more sizes
	for amdgcn.
---
 gcc/testsuite/gcc.dg/pr104464.c                  | 2 ++
 gcc/testsuite/gcc.dg/signbit-2.c                 | 5 +++--
 gcc/testsuite/gcc.dg/signbit-5.c                 | 1 +
 gcc/testsuite/gcc.dg/vect/bb-slp-68.c            | 5 +++--
 gcc/testsuite/gcc.dg/vect/bb-slp-cond-1.c        | 3 ++-
 gcc/testsuite/gcc.dg/vect/bb-slp-subgroups-3.c   | 5 ++++-
 gcc/testsuite/gcc.dg/vect/no-vfa-vect-depend-2.c | 3 ++-
 gcc/testsuite/gcc.dg/vect/pr33953.c              | 3 ++-
 gcc/testsuite/gcc.dg/vect/pr65947-12.c           | 3 ++-
 gcc/testsuite/gcc.dg/vect/pr65947-13.c           | 3 ++-
 gcc/testsuite/gcc.dg/vect/pr80631-2.c            | 3 ++-
 gcc/testsuite/gcc.dg/vect/slp-reduc-4.c          | 3 ++-
 gcc/testsuite/gcc.dg/vect/trapv-vect-reduc-4.c   | 3 ++-
 gcc/testsuite/lib/target-supports.exp            | 3 ++-
 14 files changed, 31 insertions(+), 14 deletions(-)


[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #2: 0006-amdgcn-vector-testsuite-tweaks.patch --]
[-- Type: text/x-patch; name="0006-amdgcn-vector-testsuite-tweaks.patch", Size: 11137 bytes --]

diff --git a/gcc/testsuite/gcc.dg/pr104464.c b/gcc/testsuite/gcc.dg/pr104464.c
index ed6a22c39d5..d36a28678cb 100644
--- a/gcc/testsuite/gcc.dg/pr104464.c
+++ b/gcc/testsuite/gcc.dg/pr104464.c
@@ -9,3 +9,5 @@ foo(void)
 {
   f += (F)(f != (F){}[0]);
 }
+
+/* { dg-xfail-if "-fnon-call-exceptions unsupported" { amdgcn-*-* } } */
diff --git a/gcc/testsuite/gcc.dg/signbit-2.c b/gcc/testsuite/gcc.dg/signbit-2.c
index 2f2dc448286..99a455bc7d7 100644
--- a/gcc/testsuite/gcc.dg/signbit-2.c
+++ b/gcc/testsuite/gcc.dg/signbit-2.c
@@ -20,6 +20,7 @@ void fun2(int32_t *x, int n)
       x[i] = (-x[i]) >> 30;
 }
 
-/* { dg-final { scan-tree-dump {\s+>\s+\{ 0(, 0)+ \}} optimized { target vect_int } } } */
+/* Xfail amdgcn where vector truth type is not integer type.  */
+/* { dg-final { scan-tree-dump {\s+>\s+\{ 0(, 0)+ \}} optimized { target vect_int xfail amdgcn-*-* } } } */
 /* { dg-final { scan-tree-dump {\s+>\s+0} optimized { target { ! vect_int } } } } */
-/* { dg-final { scan-tree-dump-not {\s+>>\s+31} optimized } } */
+/* { dg-final { scan-tree-dump-not {\s+>>\s+31} optimized { xfail amdgcn-*-* } } } */
diff --git a/gcc/testsuite/gcc.dg/signbit-5.c b/gcc/testsuite/gcc.dg/signbit-5.c
index 2b119cdfda7..0fad56c0ea8 100644
--- a/gcc/testsuite/gcc.dg/signbit-5.c
+++ b/gcc/testsuite/gcc.dg/signbit-5.c
@@ -4,6 +4,7 @@
 /* This test does not work when the truth type does not match vector type.  */
 /* { dg-additional-options "-mno-avx512f" { target { i?86-*-* x86_64-*-* } } } */
 /* { dg-additional-options "-march=armv8-a" { target aarch64_sve } } */
+/* { dg-xfail-run-if "truth type does not match vector type" { amdgcn-*-* } } */
 
 
 #include <stdint.h>
diff --git a/gcc/testsuite/gcc.dg/vect/bb-slp-68.c b/gcc/testsuite/gcc.dg/vect/bb-slp-68.c
index 8718031cc71..e7573a14933 100644
--- a/gcc/testsuite/gcc.dg/vect/bb-slp-68.c
+++ b/gcc/testsuite/gcc.dg/vect/bb-slp-68.c
@@ -18,5 +18,6 @@ void foo ()
   x[9] = z[3] + 1.;
 }
 
-/* We want to have the store group split into 4, 2, 4 when using 32byte vectors.  */
-/* { dg-final { scan-tree-dump-not "from scalars" "slp2" } } */
+/* We want to have the store group split into 4, 2, 4 when using 32byte vectors.
+   Unfortunately it does not work when 64-byte vectors are available.  */
+/* { dg-final { scan-tree-dump-not "from scalars" "slp2" { xfail amdgcn-*-* } } } */
diff --git a/gcc/testsuite/gcc.dg/vect/bb-slp-cond-1.c b/gcc/testsuite/gcc.dg/vect/bb-slp-cond-1.c
index 4bd286bf08c..1f5c621e5fd 100644
--- a/gcc/testsuite/gcc.dg/vect/bb-slp-cond-1.c
+++ b/gcc/testsuite/gcc.dg/vect/bb-slp-cond-1.c
@@ -46,5 +46,6 @@ int main ()
 }
 
 /* { dg-final { scan-tree-dump {(no need for alias check [^\n]* when VF is 1|no alias between [^\n]* when [^\n]* is outside \(-16, 16\))} "vect" { target vect_element_align } } } */
-/* { dg-final { scan-tree-dump-times "loop vectorized" 1 "vect" { target vect_element_align } } } */
+/* { dg-final { scan-tree-dump-times "loop vectorized" 1 "vect" { target { vect_element_align && !amdgcn-*-* } } } } */
+/* { dg-final { scan-tree-dump-times "loop vectorized" 2 "vect" { target amdgcn-*-* } } } */
 
diff --git a/gcc/testsuite/gcc.dg/vect/bb-slp-subgroups-3.c b/gcc/testsuite/gcc.dg/vect/bb-slp-subgroups-3.c
index 03c062ae6cf..fb719915db7 100644
--- a/gcc/testsuite/gcc.dg/vect/bb-slp-subgroups-3.c
+++ b/gcc/testsuite/gcc.dg/vect/bb-slp-subgroups-3.c
@@ -42,4 +42,7 @@ main (int argc, char **argv)
 /* Because we disable the cost model, targets with variable-length
    vectors can end up vectorizing the store to a[0..7] on its own.
    With the cost model we do something sensible.  */
-/* { dg-final { scan-tree-dump-times "optimized: basic block" 2 "slp2" { xfail vect_variable_length } } } */
+/* { dg-final { scan-tree-dump-times "optimized: basic block" 2 "slp2" { target { ! amdgcn-*-* } xfail vect_variable_length } } } */
+
+/* amdgcn can do this in one vector.  */
+/* { dg-final { scan-tree-dump-times "optimized: basic block" 1 "slp2" { target amdgcn-*-* } } } */
diff --git a/gcc/testsuite/gcc.dg/vect/no-vfa-vect-depend-2.c b/gcc/testsuite/gcc.dg/vect/no-vfa-vect-depend-2.c
index 1880d1edb32..89958378fca 100644
--- a/gcc/testsuite/gcc.dg/vect/no-vfa-vect-depend-2.c
+++ b/gcc/testsuite/gcc.dg/vect/no-vfa-vect-depend-2.c
@@ -51,4 +51,5 @@ int main (void)
 }
 
 /* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" {xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
-/* { dg-final { scan-tree-dump-times "dependence distance negative" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "dependence distance negative" 1 "vect" { target { ! vect_multiple_sizes } } } } */
+/* { dg-final { scan-tree-dump "dependence distance negative" "vect" { target vect_multiple_sizes } } } */
diff --git a/gcc/testsuite/gcc.dg/vect/pr33953.c b/gcc/testsuite/gcc.dg/vect/pr33953.c
index 4dd54cd57f3..d376cf904b7 100644
--- a/gcc/testsuite/gcc.dg/vect/pr33953.c
+++ b/gcc/testsuite/gcc.dg/vect/pr33953.c
@@ -29,6 +29,7 @@ void blockmove_NtoN_blend_noremap32 (const UINT32 *srcdata, int srcwidth,
 }
 
 /* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { target { ! vect_multiple_sizes } xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
+/* { dg-final { scan-tree-dump "vectorizing stmts using SLP" "vect" { target vect_multiple_sizes xfail { vect_no_align && { ! vect_hw_misalign } } } } } */
 
 
diff --git a/gcc/testsuite/gcc.dg/vect/pr65947-12.c b/gcc/testsuite/gcc.dg/vect/pr65947-12.c
index a47f4146a29..9788eea0f54 100644
--- a/gcc/testsuite/gcc.dg/vect/pr65947-12.c
+++ b/gcc/testsuite/gcc.dg/vect/pr65947-12.c
@@ -42,5 +42,6 @@ main (void)
 }
 
 /* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 2 "vect" } } */
-/* { dg-final { scan-tree-dump-times "optimizing condition reduction with FOLD_EXTRACT_LAST" 2 "vect" { target vect_fold_extract_last } } } */
+/* { dg-final { scan-tree-dump-times "optimizing condition reduction with FOLD_EXTRACT_LAST" 2 "vect" { target { vect_fold_extract_last && { ! vect_multiple_sizes } } } } } */
+/* { dg-final { scan-tree-dump "optimizing condition reduction with FOLD_EXTRACT_LAST" "vect" { target { vect_fold_extract_last && vect_multiple_sizes } } } } */
 /* { dg-final { scan-tree-dump-not "condition expression based on integer induction." "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/pr65947-13.c b/gcc/testsuite/gcc.dg/vect/pr65947-13.c
index a703923151d..079b5f91ced 100644
--- a/gcc/testsuite/gcc.dg/vect/pr65947-13.c
+++ b/gcc/testsuite/gcc.dg/vect/pr65947-13.c
@@ -44,4 +44,5 @@ main (void)
 
 /* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 2 "vect" } } */
 /* { dg-final { scan-tree-dump-times "condition expression based on integer induction." 2 "vect" { xfail vect_fold_extract_last } } } */
-/* { dg-final { scan-tree-dump-times "optimizing condition reduction with FOLD_EXTRACT_LAST" 2 "vect" { target vect_fold_extract_last } } } */
+/* { dg-final { scan-tree-dump-times "optimizing condition reduction with FOLD_EXTRACT_LAST" 2 "vect" { target { vect_fold_extract_last && { ! vect_multiple_sizes } } } } } */
+/* { dg-final { scan-tree-dump "optimizing condition reduction with FOLD_EXTRACT_LAST" "vect" { target { vect_fold_extract_last && vect_multiple_sizes } } } } */
diff --git a/gcc/testsuite/gcc.dg/vect/pr80631-2.c b/gcc/testsuite/gcc.dg/vect/pr80631-2.c
index 61e11316af2..4e586275176 100644
--- a/gcc/testsuite/gcc.dg/vect/pr80631-2.c
+++ b/gcc/testsuite/gcc.dg/vect/pr80631-2.c
@@ -75,4 +75,5 @@ main ()
 
 /* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 5 "vect" { target vect_condition } } } */
 /* { dg-final { scan-tree-dump-times "condition expression based on integer induction." 5 "vect" { target vect_condition xfail vect_fold_extract_last } } } */
-/* { dg-final { scan-tree-dump-times "optimizing condition reduction with FOLD_EXTRACT_LAST" 5 "vect" { target vect_fold_extract_last } } } */
+/* { dg-final { scan-tree-dump-times "optimizing condition reduction with FOLD_EXTRACT_LAST" 5 "vect" { target { { ! vect_multiple_sizes } && vect_fold_extract_last } } } } */
+/* { dg-final { scan-tree-dump "optimizing condition reduction with FOLD_EXTRACT_LAST" "vect" { target { vect_multiple_sizes && vect_fold_extract_last } } } } */
diff --git a/gcc/testsuite/gcc.dg/vect/slp-reduc-4.c b/gcc/testsuite/gcc.dg/vect/slp-reduc-4.c
index cffb0114bcb..15f5c259e98 100644
--- a/gcc/testsuite/gcc.dg/vect/slp-reduc-4.c
+++ b/gcc/testsuite/gcc.dg/vect/slp-reduc-4.c
@@ -59,6 +59,7 @@ int main (void)
 /* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail vect_no_int_min_max } } } */
 /* For variable-length SVE, the number of scalar statements in the
    reduction exceeds the number of elements in a 128-bit granule.  */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { xfail { vect_no_int_min_max || { aarch64_sve && vect_variable_length } } } } } */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { target { ! vect_multiple_sizes } xfail { vect_no_int_min_max || { aarch64_sve && vect_variable_length } } } } } */
+/* { dg-final { scan-tree-dump "vectorizing stmts using SLP" "vect" { target { vect_multiple_sizes } } } } */
 /* { dg-final { scan-tree-dump-times "VEC_PERM_EXPR" 0 "vect" { xfail { aarch64_sve && vect_variable_length } } } } */
 
diff --git a/gcc/testsuite/gcc.dg/vect/trapv-vect-reduc-4.c b/gcc/testsuite/gcc.dg/vect/trapv-vect-reduc-4.c
index f09c964fdc1..24cf1f793c7 100644
--- a/gcc/testsuite/gcc.dg/vect/trapv-vect-reduc-4.c
+++ b/gcc/testsuite/gcc.dg/vect/trapv-vect-reduc-4.c
@@ -50,6 +50,7 @@ int main (void)
 
 /* We can't handle the first loop with variable-length vectors and so
    fall back to the fixed-length mininum instead.  */
-/* { dg-final { scan-tree-dump-times "Detected reduction\\." 3 "vect" { xfail vect_variable_length } } } */
+/* { dg-final { scan-tree-dump-times "Detected reduction\\." 3 "vect" { target { ! vect_multiple_sizes } xfail vect_variable_length } } } */
+/* { dg-final { scan-tree-dump "Detected reduction\\." "vect" { target vect_multiple_sizes } } } */
 /* { dg-final { scan-tree-dump-times "vectorized 3 loops" 1 "vect" { target { ! vect_no_int_min_max } } } } */
 /* { dg-final { scan-tree-dump-times {using an in-order \(fold-left\) reduction} 1 "vect" } } */
diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp
index 7c9dd45f2a7..fdd88e6a516 100644
--- a/gcc/testsuite/lib/target-supports.exp
+++ b/gcc/testsuite/lib/target-supports.exp
@@ -8400,7 +8400,8 @@ proc available_vector_sizes { } {
     } elseif { [istarget sparc*-*-*] } {
 	lappend result 64
     } elseif { [istarget amdgcn*-*-*] } {
-	lappend result 4096
+        # 6 different lane counts, and 4 element sizes
+	lappend result 4096 2048 1024 512 256 128 64 32 16 8 4 2
     } else {
 	# The traditional default asumption.
 	lappend result 128