aarch64: Add testcase for vld2 which was fixed by r16-1113 [PR89606]

This aarch64 specific vld2 intrinsics testcase was fixed by r16-1113-g069caa5cea91f
(simple copy propagation for aggregates). I didn't include it in the original
patch as I was testing on x86_64 but I got around to testing this
and now we don't have any more extra movs so let's add a testcase.

Tested for aarch64-linux-gnu.

	PR tree-optimization/89606

gcc/testsuite/ChangeLog:

	* gcc.target/aarch64/vld2-1.c: New test.

Signed-off-by: Andrew Pinski <quic_apinski@quicinc.com>

diff --git a/gcc/testsuite/gcc.target/aarch64/vld2-1.c b/gcc/testsuite/gcc.target/aarch64/vld2-1.c
new file mode 100644 (file)
index 0000000..8a26767
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/vld2-1.c
@@ -0,0 +1,45 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-forwprop1-details" } */
+/* { dg-final { check-function-bodies "**" "" "" } } */
+/* PR tree-optimization/89606 */
+
+#include <arm_neon.h>
+
+/*
+**func1:
+**     ld2     {v0.2d - v1.2d}, \[x0\]
+**     ld2     {v0.d - v1.d}\[1\], \[x1\]
+**     ret
+*/
+float64x2x2_t func1(const double *p1, const double *p2)
+{
+    float64x2x2_t v = vld2q_f64(p1);
+    return vld2q_lane_f64(p2, v, 1);
+}
+
+/*
+**func2:
+**     ld2     {v0.2s - v1.2s}, \[x0\]
+**     ld2     {v0.s - v1.s}\[1\], \[x1\]
+**     ret
+*/
+float32x2x2_t func2(const float *p1, const float *p2)
+{
+    float32x2x2_t v = vld2_f32(p1);
+    return vld2_lane_f32(p2, v, 1);
+}
+
+/*
+**func3:
+**     ld2     {v([0-9]+).2s - v([0-9]+).2s}, \[x1\]
+**     ld2     {v\1.s - v\2.s}\[1\], \[x2\]
+**     stp     d\1, d\2, \[x0\]
+**     ret
+*/
+void func3(float32x2x2_t *p, const float *p1, const float *p2)
+{
+    float32x2x2_t v = vld2_f32(p1);
+    *p = vld2_lane_f32(p2, v, 1);
+}
+
+/* { dg-final { scan-tree-dump-times "after previous" 3 "forwprop1" } } */