return __builtin_neon_vfmat_laneqv8bf (__r, __a, __b, __index);
}
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vst1_bf16 (bfloat16_t * __a, bfloat16x4_t __b)
+{
+ __builtin_neon_vst1v4bf (__a, __b);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_bf16 (bfloat16_t * __a, bfloat16x8_t __b)
+{
+ __builtin_neon_vst1v8bf (__a, __b);
+}
+
__extension__ extern __inline void
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vst2_bf16 (bfloat16_t * __ptr, bfloat16x4x2_t __val)
v8qi, v4hi, v2si, v2sf, di, v16qi, v8hi, v4si, v4sf, v2di, v4bf, v8bf)
VAR10 (LOAD1, vld1_dup,
v8qi, v4hi, v2si, v2sf, di, v16qi, v8hi, v4si, v4sf, v2di)
-VAR12 (STORE1, vst1,
- v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf, v2di)
+VAR14 (STORE1, vst1,
+ v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf, v2di,
+ v4bf, v8bf)
VAR14 (STORE1LANE, vst1_lane,
v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf, v2di, v4bf, v8bf)
VAR13 (LOAD1, vld2,
--- /dev/null
+/* { dg-do assemble } */
+/* { dg-require-effective-target arm_v8_2a_bf16_neon_ok } */
+/* { dg-add-options arm_v8_2a_bf16_neon } */
+/* { dg-additional-options "-save-temps -O2 -mfloat-abi=hard" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#include "arm_neon.h"
+
+/*
+**test_vst1_bf16:
+** vst1.16 {d0}, \[r0\]
+** bx lr
+*/
+void
+test_vst1_bf16 (bfloat16_t *a, bfloat16x4_t b)
+{
+ vst1_bf16 (a, b);
+}
+
+/*
+**test_vst1q_bf16:
+** vst1.16 {d0-d1}, \[r0\]
+** bx lr
+*/
+void
+test_vst1q_bf16 (bfloat16_t *a, bfloat16x8_t b)
+{
+ vst1q_bf16 (a, b);
+}