aarch64: SVE: ICE in expand_direct_optab_fn [PR98177]

Problem comes from using the wrong interface to get the index type for a
COND_REDUCTION. For fixed-length SVE we get a V2SI (a 64-bit Advanced
SIMD vector) instead of a VNx2SI (an SVE vector that stores SI elements
in DI containers).

Credits to Richard Sandiford for pointing out the issue's root cause.

Original PR snippet proposed to reproduce issue was only causing ICE for C++
compiler (see pr98177-1 test cases). I've slightly modified original
snippet in order to reproduce issue on both C and C++ compilers. These
are pr98177-2 test cases.

gcc/ChangeLog:

	PR target/98177
	* tree-vect-loop.c (vect_create_epilog_for_reduction): Use
	get_same_sized_vectype to obtain index type.
	(vectorizable_reduction): Likewise.

gcc/testsuite/ChangeLog:

	PR target/98177
	* g++.target/aarch64/sve/pr98177-1.C: New test.
	* g++.target/aarch64/sve/pr98177-2.C: New test.
	* gcc.target/aarch64/sve/pr98177-1.c: New test.
	* gcc.target/aarch64/sve/pr98177-2.c: New test.

5 files changed, 44 insertions, 4 deletions

diff --git a/gcc/testsuite/g++.target/aarch64/sve/pr98177-1.C b/gcc/testsuite/g++.target/aarch64/sve/pr98177-1.C
new file mode 100644
index 0000000..9789193
--- /dev/null
+++ b/gcc/testsuite/g++.target/aarch64/sve/pr98177-1.C
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-options "-Ofast -msve-vector-bits=128" } */
+
+int a, b;
+short c;
+void d(long e) {
+  for (int f = 0; f < b; f += 1)
+    for (short g = 0; g < c; g += 5)
+      a = (short)e;
+}
diff --git a/gcc/testsuite/g++.target/aarch64/sve/pr98177-2.C b/gcc/testsuite/g++.target/aarch64/sve/pr98177-2.C
new file mode 100644
index 0000000..c7244ef
--- /dev/null
+++ b/gcc/testsuite/g++.target/aarch64/sve/pr98177-2.C
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-options "-Ofast -msve-vector-bits=128" } */
+
+int a, b, c;
+
+void foo(long e) {
+  for (int f = 0; f < b; f ++)
+    for (int g = 0; g < c; g ++)
+      a = (short)e;
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/pr98177-1.c b/gcc/testsuite/gcc.target/aarch64/sve/pr98177-1.c
new file mode 100644
index 0000000..9789193
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/pr98177-1.c
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-options "-Ofast -msve-vector-bits=128" } */
+
+int a, b;
+short c;
+void d(long e) {
+  for (int f = 0; f < b; f += 1)
+    for (short g = 0; g < c; g += 5)
+      a = (short)e;
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/pr98177-2.c b/gcc/testsuite/gcc.target/aarch64/sve/pr98177-2.c
new file mode 100644
index 0000000..c7244ef
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/pr98177-2.c
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-options "-Ofast -msve-vector-bits=128" } */
+
+int a, b, c;
+
+void foo(long e) {
+  for (int f = 0; f < b; f ++)
+    for (int g = 0; g < c; g ++)
+      a = (short)e;
+}
diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
index 688538a..d6f1ffc 100644
--- a/gcc/tree-vect-loop.c
+++ b/gcc/tree-vect-loop.c
@@ -5278,8 +5278,8 @@ vect_create_epilog_for_reduction (loop_vec_info loop_vinfo,
       int scalar_precision
 	= GET_MODE_PRECISION (SCALAR_TYPE_MODE (scalar_type));
       tree scalar_type_unsigned = make_unsigned_type (scalar_precision);
-      tree vectype_unsigned = build_vector_type
-	(scalar_type_unsigned, TYPE_VECTOR_SUBPARTS (vectype));
+      tree vectype_unsigned = get_same_sized_vectype (scalar_type_unsigned,
+						vectype);
 
       /* First we need to create a vector (ZERO_VEC) of zeros and another
 	 vector (MAX_INDEX_VEC) filled with the last matching index, which we
@@ -6942,8 +6942,8 @@ vectorizable_reduction (loop_vec_info loop_vinfo,
       int scalar_precision
 	= GET_MODE_PRECISION (SCALAR_TYPE_MODE (scalar_type));
       cr_index_scalar_type = make_unsigned_type (scalar_precision);
-      cr_index_vector_type = build_vector_type (cr_index_scalar_type,
-						nunits_out);
+      cr_index_vector_type = get_same_sized_vectype (cr_index_scalar_type,
+						vectype_out);
 
       if (direct_internal_fn_supported_p (IFN_REDUC_MAX, cr_index_vector_type,
 					  OPTIMIZE_FOR_SPEED))