The following aligns ISEL VEC_COND_EXPR expansion using VCOND
with the optab query done by vector lowering. Instead of only
allowing the signed optab to provide EQ/NE compares we allow both
here though since there seems to be no documented canonicalization.
Bootstrap and regtest running on x86_64-unknown-linux-gnu,
I've cut&pasted neon boilerplate for the testcase but cannot
test it (a cc1 cross makes it UNSUPPORTED), if I don't hear
otherwise I'm going to push as-is after testing completed.
Thanks,
Richard.
2022-04-20 Richard Biener <rguent...@suse.de>
PR tree-optimization/105312
* gimple-isel.cc (gimple_expand_vec_cond_expr): Query both
VCOND and VCONDU for EQ and NE.
* gcc.target/arm/pr105312.c: New testcase.
---
gcc/gimple-isel.cc | 8 ++++++++
gcc/testsuite/gcc.target/arm/pr105312.c | 23 +++++++++++++++++++++++
2 files changed, 31 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/arm/pr105312.c
diff --git a/gcc/gimple-isel.cc b/gcc/gimple-isel.cc
index 3635585bf45..a8f7a0d25d0 100644
--- a/gcc/gimple-isel.cc
+++ b/gcc/gimple-isel.cc
@@ -245,6 +245,14 @@ gimple_expand_vec_cond_expr (struct function *fun,
gimple_stmt_iterator *gsi,
GET_MODE_NUNITS (cmp_op_mode)));
icode = get_vcond_icode (mode, cmp_op_mode, unsignedp);
+ /* Some targets do not have vcondeq and only vcond with NE/EQ
+ but not vcondu, so make sure to also try vcond here as
+ vcond_icode_p would canonicalize the optab query to. */
+ if (icode == CODE_FOR_nothing
+ && (tcode == NE_EXPR || tcode == EQ_EXPR)
+ && ((icode = get_vcond_icode (mode, cmp_op_mode, !unsignedp))
+ != CODE_FOR_nothing))
+ unsignedp = !unsignedp;
if (icode == CODE_FOR_nothing)
{
if (tcode == LT_EXPR
diff --git a/gcc/testsuite/gcc.target/arm/pr105312.c
b/gcc/testsuite/gcc.target/arm/pr105312.c
new file mode 100644
index 00000000000..a02831bcbcf
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/pr105312.c
@@ -0,0 +1,23 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_neon_ok } */
+/* { dg-options "-mcpu=cortex-a15" } */
+/* { dg-add-options arm_neon } */
+
+typedef float stress_matrix_type_t;
+typedef unsigned int size_t;
+static void __attribute__((optimize("-O3"))) stress_matrix_xy_identity(
+ const size_t n,
+ stress_matrix_type_t a[restrict n][n],
+ stress_matrix_type_t b[restrict n][n],
+ stress_matrix_type_t r[restrict n][n])
+{
+ register size_t i;
+ (void)a;
+ (void)b;
+ for (i = 0; i < n; i++) {
+ register size_t j;
+ for (j = 0; j < n; j++)
+ r[i][j] = (i == j) ? 1.0 : 0.0;
+ return;
+ }
+}
--
2.34.1
