>> Bootstrapped and regtested on x86, power10, and aarch64.
>> Regtested on riscv64.
>
> Given its a constant permute(?) you can just always use ssizetyoe here.
Ah, that's even simpler then, thanks. The attached v2 was bootstrapped and
regtested as before.
[PATCH v2] forwprop: Use ssizetype for mask [PR123414].
RVV's vectors can get very large with LMUL8. In the PR we have
256-element char vectors which get permuted. For permuting them
we use a mask vectype that is deduced from the element type
without checking if the permute indices fit this type.
That leads to an invalid permute mask which gets optimized away.
This patch uses ssizetype as masktype instead.
PR tree-optimization/123414
gcc/ChangeLog:
* tree-ssa-forwprop.cc (simplify_vector_constructor):
Use ssizetype as mask type.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/autovec/pr123414.c: New test.
---
.../gcc.target/riscv/rvv/autovec/pr123414.c | 29 +++++++++++++++++++
gcc/tree-ssa-forwprop.cc | 22 +++-----------
2 files changed, 33 insertions(+), 18 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/pr123414.c
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr123414.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr123414.c
new file mode 100644
index 00000000000..9a48085a562
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr123414.c
@@ -0,0 +1,29 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl256b -mrvv-max-lmul=m8 -O3 -fsigned-char
-fno-strict-aliasing -fwrapv -fdump-tree-optimized -std=gnu99" } */
+
+signed char a=2;
+long long b;
+long c = 93;
+int e[1][9];
+
+void
+g (long cc, int ee[][9])
+{
+ for (int i = 0; i < 4; i++)
+ for (int j = 0; j < 5; j++)
+ for (unsigned k = 0; k < 9; k++)
+ {
+ a *= cc;
+ for (int l = 0; l < 6; l += (ee[k] <= 0) + 2)
+ ;
+ }
+}
+
+int main() {
+ g( c, e);
+ b = (int)a;
+ if (b != 34)
+ __builtin_abort ();
+}
+
+/* { dg-final { scan-tree-dump-times
"\[a-zA-Z_\]\[a-zA-Z0-9_\]+.=.VEC_PERM_EXPR <_\[0-9\]+, \\\{ 1(?:, 1){255}
\\\}, \\\{ 0, 257, 258" 3 "optimized" } } */
diff --git a/gcc/tree-ssa-forwprop.cc b/gcc/tree-ssa-forwprop.cc
index c5bad3ddf38..b70fe8169ad 100644
--- a/gcc/tree-ssa-forwprop.cc
+++ b/gcc/tree-ssa-forwprop.cc
@@ -3829,8 +3829,8 @@ static bool
simplify_vector_constructor (gimple_stmt_iterator *gsi)
{
gimple *stmt = gsi_stmt (*gsi);
- tree op, orig[2], type, elem_type;
- unsigned elem_size, i;
+ tree op, orig[2], type;
+ unsigned i;
unsigned HOST_WIDE_INT nelts;
unsigned HOST_WIDE_INT refnelts;
enum tree_code conv_code;
@@ -3843,8 +3843,6 @@ simplify_vector_constructor (gimple_stmt_iterator *gsi)
if (!TYPE_VECTOR_SUBPARTS (type).is_constant (&nelts))
return false;
- elem_type = TREE_TYPE (type);
- elem_size = TREE_INT_CST_LOW (TYPE_SIZE (elem_type));
orig[0] = NULL;
orig[1] = NULL;
@@ -4177,13 +4175,7 @@ simplify_vector_constructor (gimple_stmt_iterator *gsi)
machine_mode vmode = TYPE_MODE (perm_type);
if (!can_vec_perm_const_p (vmode, vmode, indices))
return false;
- mask_type
- = build_vector_type (build_nonstandard_integer_type (elem_size, 1),
- refnelts);
- if (GET_MODE_CLASS (TYPE_MODE (mask_type)) != MODE_VECTOR_INT
- || maybe_ne (GET_MODE_SIZE (TYPE_MODE (mask_type)),
- GET_MODE_SIZE (TYPE_MODE (perm_type))))
- return false;
+ mask_type = build_vector_type (ssizetype, refnelts);
tree op2 = vec_perm_indices_to_tree (mask_type, indices);
bool converted_orig1 = false;
gimple_seq stmts = NULL;
@@ -4248,13 +4240,7 @@ simplify_vector_constructor (gimple_stmt_iterator *gsi)
machine_mode vmode = TYPE_MODE (type);
if (!can_vec_perm_const_p (vmode, vmode, indices))
return false;
- mask_type
- = build_vector_type (build_nonstandard_integer_type (elem_size, 1),
- nelts);
- if (GET_MODE_CLASS (TYPE_MODE (mask_type)) != MODE_VECTOR_INT
- || maybe_ne (GET_MODE_SIZE (TYPE_MODE (mask_type)),
- GET_MODE_SIZE (TYPE_MODE (type))))
- return false;
+ mask_type = build_vector_type (ssizetype, nelts);
blend_op2 = vec_perm_indices_to_tree (mask_type, indices);
}
--
2.52.0
