arm: Add vst1_lane_bf16 + vstq_lane_bf16 intrinsics

gcc/ChangeLog

2020-10-23  Andrea Corallo  <andrea.corallo@arm.com>

	* config/arm/arm_neon.h (vst1_lane_bf16, vst1q_lane_bf16): Add
	intrinsics.
	* config/arm/arm_neon_builtins.def (STORE1LANE): Add v4bf, v8bf.

gcc/testsuite/ChangeLog

2020-10-23  Andrea Corallo  <andrea.corallo@arm.com>

	* gcc.target/arm/simd/vst1_lane_bf16_1.c: New testcase.
	* gcc.target/arm/simd/vstq1_lane_bf16_indices_1.c: Likewise.
	* gcc.target/arm/simd/vst1_lane_bf16_indices_1.c: Likewise.

5 files changed, 67 insertions, 2 deletions

diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h
index fcd8020..432d77f 100644
--- a/gcc/config/arm/arm_neon.h
+++ b/gcc/config/arm/arm_neon.h
@@ -19679,6 +19679,20 @@ vld1q_lane_bf16 (const bfloat16_t * __a, bfloat16x8_t __b, const int __c)
   return __builtin_neon_vld1_lanev8bf (__a, __b, __c);
 }
 
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1_lane_bf16 (bfloat16_t * __a, bfloat16x4_t __b, const int __c)
+{
+  __builtin_neon_vst1_lanev4bf (__a, __b, __c);
+}
+
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_lane_bf16 (bfloat16_t * __a, bfloat16x8_t __b, const int __c)
+{
+  __builtin_neon_vst1_lanev8bf (__a, __b, __c);
+}
+
 #pragma GCC pop_options
 
 #ifdef __cplusplus
diff --git a/gcc/config/arm/arm_neon_builtins.def b/gcc/config/arm/arm_neon_builtins.def
index d0617a4..7a5dae0 100644
--- a/gcc/config/arm/arm_neon_builtins.def
+++ b/gcc/config/arm/arm_neon_builtins.def
@@ -318,8 +318,8 @@ 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)
-VAR12 (STORE1LANE, vst1_lane,
-	v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf, v2di)
+VAR14 (STORE1LANE, vst1_lane,
+       v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf, v2di, v4bf, v8bf)
 VAR13 (LOAD1, vld2,
 	v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf, v4bf, v8bf)
 VAR9 (LOAD1LANE, vld2_lane,
diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1_lane_bf16_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1_lane_bf16_1.c
new file mode 100644
index 0000000..e018ec6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/vst1_lane_bf16_1.c
@@ -0,0 +1,21 @@
+/* { dg-do assemble } */
+/* { dg-require-effective-target arm_v8_2a_bf16_neon_ok } */
+/* { dg-add-options arm_v8_2a_bf16_neon } */
+/* { dg-additional-options "-O3 --save-temps" } */
+
+#include "arm_neon.h"
+
+void
+test_vst1_lane_bf16 (bfloat16_t *a, bfloat16x4_t b)
+{
+  vst1_lane_bf16 (a, b, 1);
+}
+
+void
+test_vst1q_lane_bf16 (bfloat16_t *a, bfloat16x8_t b)
+{
+  vst1q_lane_bf16 (a, b, 2);
+}
+
+/* { dg-final { scan-assembler "vst1.16\t{d0\\\[1\\\]}, \\\[r0\\\]" } } */
+/* { dg-final { scan-assembler "vst1.16\t{d0\\\[2\\\]}, \\\[r0\\\]" } } */
diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1_lane_bf16_indices_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1_lane_bf16_indices_1.c
new file mode 100644
index 0000000..39870dc
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/vst1_lane_bf16_indices_1.c
@@ -0,0 +1,15 @@
+/* { dg-do assemble } */
+/* { dg-require-effective-target arm_v8_2a_bf16_neon_ok } */
+/* { dg-add-options arm_v8_2a_bf16_neon } */
+
+#include "arm_neon.h"
+
+void
+test_vst1_lane_bf16 (bfloat16_t *a, bfloat16x4_t b)
+{
+  vst1_lane_bf16 (a, b, -1);
+  vst1_lane_bf16 (a, b, 4);
+}
+
+/* { dg-error "lane -1 out of range 0 - 3" "" { target *-*-* } 0 } */
+/* { dg-error "lane 4 out of range 0 - 3" "" { target *-*-* } 0 } */
diff --git a/gcc/testsuite/gcc.target/arm/simd/vstq1_lane_bf16_indices_1.c b/gcc/testsuite/gcc.target/arm/simd/vstq1_lane_bf16_indices_1.c
new file mode 100644
index 0000000..f31bd12
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/vstq1_lane_bf16_indices_1.c
@@ -0,0 +1,15 @@
+/* { dg-do assemble } */
+/* { dg-require-effective-target arm_v8_2a_bf16_neon_ok } */
+/* { dg-add-options arm_v8_2a_bf16_neon } */
+
+#include "arm_neon.h"
+
+void
+test_vstq1_lane_bf16 (bfloat16_t *a, bfloat16x8_t b)
+{
+  vst1q_lane_bf16 (a, b, -1);
+  vst1q_lane_bf16 (a, b, 8);
+}
+
+/* { dg-error "lane -1 out of range 0 - 7" "" { target *-*-* } 0 } */
+/* { dg-error "lane 8 out of range 0 - 7" "" { target *-*-* } 0 } */