ACLE intrinsics: BFloat16 load intrinsics for AArch32

2020-03-06  Delia Burduv  <delia.burduv@arm.com>

	* config/arm/arm_neon.h (vld2_bf16): New.
	(vld2q_bf16): New.
	(vld3_bf16): New.
	(vld3q_bf16): New.
	(vld4_bf16): New.
	(vld4q_bf16): New.
	(vld2_dup_bf16): New.
	(vld2q_dup_bf16): New.
	(vld3_dup_bf16): New.
	(vld3q_dup_bf16): New.
	(vld4_dup_bf16): New.
	(vld4q_dup_bf16): New.
	* config/arm/arm_neon_builtins.def
	(vld2): Changed to VAR13 and added v4bf, v8bf
	(vld2_dup): Changed to VAR8 and added v4bf, v8bf
	(vld3): Changed to VAR13 and added v4bf, v8bf
	(vld3_dup): Changed to VAR8 and added v4bf, v8bf
	(vld4): Changed to VAR13 and added v4bf, v8bf
	(vld4_dup): Changed to VAR8 and added v4bf, v8bf
	* config/arm/iterators.md (VDXBF2): New iterator.
	*config/arm/neon.md (neon_vld2): Use new iterators.
	(neon_vld2_dup<mode): Use new iterators.
	(neon_vld3<mode>): Likewise.
	(neon_vld3qa<mode>): Likewise.
	(neon_vld3qb<mode>): Likewise.
	(neon_vld3_dup<mode>): Likewise.
	(neon_vld4<mode>): Likewise.
	(neon_vld4qa<mode>): Likewise.
	(neon_vld4qb<mode>): Likewise.
	(neon_vld4_dup<mode>): Likewise.
	(neon_vld2_dupv8bf): New.
	(neon_vld3_dupv8bf): Likewise.
	(neon_vld4_dupv8bf): Likewise.

	* gcc.target/arm/simd/bf16_vldn_1.c: New test.

gcc/ChangeLog

 2020-03-06  Delia Burduv  <delia.burduv@arm.com>
 
+	* config/arm/arm_neon.h (vld2_bf16): New.
+	(vld2q_bf16): New.
+	(vld3_bf16): New.
+	(vld3q_bf16): New.
+	(vld4_bf16): New.
+	(vld4q_bf16): New.
+	(vld2_dup_bf16): New.
+	(vld2q_dup_bf16): New.
+	(vld3_dup_bf16): New.
+	(vld3q_dup_bf16): New.
+	(vld4_dup_bf16): New.
+	(vld4q_dup_bf16): New.
+	* config/arm/arm_neon_builtins.def
+	(vld2): Changed to VAR13 and added v4bf, v8bf
+	(vld2_dup): Changed to VAR8 and added v4bf, v8bf
+	(vld3): Changed to VAR13 and added v4bf, v8bf
+	(vld3_dup): Changed to VAR8 and added v4bf, v8bf
+	(vld4): Changed to VAR13 and added v4bf, v8bf
+	(vld4_dup): Changed to VAR8 and added v4bf, v8bf
+	* config/arm/iterators.md (VDXBF2): New iterator.
+	*config/arm/neon.md (neon_vld2): Use new iterators.
+	(neon_vld2_dup<mode): Use new iterators.
+	(neon_vld3<mode>): Likewise.
+	(neon_vld3qa<mode>): Likewise.
+	(neon_vld3qb<mode>): Likewise.
+	(neon_vld3_dup<mode>): Likewise.
+	(neon_vld4<mode>): Likewise.
+	(neon_vld4qa<mode>): Likewise.
+	(neon_vld4qb<mode>): Likewise.
+	(neon_vld4_dup<mode>): Likewise.
+	(neon_vld2_dupv8bf): New.
+	(neon_vld3_dupv8bf): Likewise.
+	(neon_vld4_dupv8bf): Likewise.
+
+2020-03-06  Delia Burduv  <delia.burduv@arm.com>
+
 	* config/arm/arm_neon.h (bfloat16x4x2_t): New typedef.
 	(bfloat16x8x2_t): New typedef.
 	(bfloat16x4x3_t): New typedef.

gcc/config/arm/arm_neon.h

@@ -19557,6 +19557,114 @@ vst4q_bf16 (bfloat16_t * __ptr, bfloat16x8x4_t __val)
   return __builtin_neon_vst4v8bf (__ptr, __bu.__o);
 }
 
+__extension__ extern __inline bfloat16x4x2_t
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vld2_bf16 (bfloat16_t const * __ptr)
+{
+  union { bfloat16x4x2_t __i; __builtin_neon_ti __o; } __rv;
+  __rv.__o = __builtin_neon_vld2v4bf ((const __builtin_neon_hi *) __ptr);
+  return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x8x2_t
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vld2q_bf16 (const bfloat16_t * __ptr)
+{
+  union { bfloat16x8x2_t __i; __builtin_neon_oi __o; } __rv;
+  __rv.__o = __builtin_neon_vld2v8bf ((const __builtin_neon_hi *) __ptr);
+  return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x4x3_t
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vld3_bf16 (const bfloat16_t * __ptr)
+{
+  union { bfloat16x4x3_t __i; __builtin_neon_ei __o; } __rv;
+  __rv.__o = __builtin_neon_vld3v4bf ((const __builtin_neon_hi *) __ptr);
+  return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x8x3_t
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vld3q_bf16 (const bfloat16_t * __ptr)
+{
+  union { bfloat16x8x3_t __i; __builtin_neon_ci __o; } __rv;
+  __rv.__o = __builtin_neon_vld3v8bf ((const __builtin_neon_hi *) __ptr);
+  return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x4x4_t
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vld4_bf16 (const bfloat16_t * __ptr)
+{
+  union { bfloat16x4x4_t __i; __builtin_neon_oi __o; } __rv;
+  __rv.__o = __builtin_neon_vld4v4bf ((const __builtin_neon_hi *) __ptr);
+  return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x8x4_t
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vld4q_bf16 (const bfloat16_t * __ptr)
+{
+  union { bfloat16x8x4_t __i; __builtin_neon_xi __o; } __rv;
+  __rv.__o = __builtin_neon_vld4v8bf ((const __builtin_neon_hi *) __ptr);
+  return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x4x2_t
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vld2_dup_bf16 (const bfloat16_t * __ptr)
+{
+  union { bfloat16x4x2_t __i; __builtin_neon_ti __o; } __rv;
+  __rv.__o = __builtin_neon_vld2_dupv4bf ((const __builtin_neon_hi *) __ptr);
+  return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x8x2_t
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vld2q_dup_bf16 (const bfloat16_t * __ptr)
+{
+  union { bfloat16x8x2_t __i; __builtin_neon_oi __o; } __rv;
+  __rv.__o = __builtin_neon_vld2_dupv8bf ((const __builtin_neon_hi *) __ptr);
+  return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x4x3_t
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vld3_dup_bf16 (const bfloat16_t * __ptr)
+{
+  union { bfloat16x4x3_t __i; __builtin_neon_ei __o; } __rv;
+  __rv.__o = __builtin_neon_vld3_dupv4bf ((const __builtin_neon_hi *) __ptr);
+  return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x8x3_t
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vld3q_dup_bf16 (const bfloat16_t * __ptr)
+{
+  union { bfloat16x8x3_t __i; __builtin_neon_ci __o; } __rv;
+  __rv.__o = __builtin_neon_vld3_dupv8bf ((const __builtin_neon_hi *) __ptr);
+  return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x4x4_t
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vld4_dup_bf16 (const bfloat16_t * __ptr)
+{
+  union { bfloat16x4x4_t __i; __builtin_neon_oi __o; } __rv;
+  __rv.__o = __builtin_neon_vld4_dupv4bf ((const __builtin_neon_hi *) __ptr);
+  return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x8x4_t
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vld4q_dup_bf16 (const bfloat16_t * __ptr)
+{
+  union { bfloat16x8x4_t __i; __builtin_neon_xi __o; } __rv;
+  __rv.__o = __builtin_neon_vld4_dupv8bf ((const __builtin_neon_hi *) __ptr);
+  return __rv.__i;
+}
+
 #pragma GCC pop_options
 
 #ifdef __cplusplus

gcc/config/arm/arm_neon_builtins.def

@@ -320,29 +320,29 @@ 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)
-VAR11 (LOAD1, vld2,
-	v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf)
+VAR13 (LOAD1, vld2,
+	v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf, v4bf, v8bf)
 VAR9 (LOAD1LANE, vld2_lane,
 	v8qi, v4hi, v4hf, v2si, v2sf, v8hi, v8hf, v4si, v4sf)
-VAR6 (LOAD1, vld2_dup, v8qi, v4hi, v4hf, v2si, v2sf, di)
+VAR8 (LOAD1, vld2_dup, v8qi, v4hi, v4hf, v2si, v2sf, di, v4bf, v8bf)
 VAR13 (STORE1, vst2,
 	v8qi, v4hi, v4hf, v4bf, v2si, v2sf, di, v16qi, v8hi, v8hf, v8bf, v4si, v4sf)
 VAR9 (STORE1LANE, vst2_lane,
 	v8qi, v4hi, v4hf, v2si, v2sf, v8hi, v8hf, v4si, v4sf)
-VAR11 (LOAD1, vld3,
-	v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf)
+VAR13 (LOAD1, vld3,
+	v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf, v4bf, v8bf)
 VAR9 (LOAD1LANE, vld3_lane,
 	v8qi, v4hi, v4hf, v2si, v2sf, v8hi, v8hf, v4si, v4sf)
-VAR6 (LOAD1, vld3_dup, v8qi, v4hi, v4hf, v2si, v2sf, di)
+VAR8 (LOAD1, vld3_dup, v8qi, v4hi, v4hf, v2si, v2sf, di, v4bf, v8bf)
 VAR13 (STORE1, vst3,
 	v8qi, v4hi, v4hf, v4bf, v2si, v2sf, di, v16qi, v8hi, v8hf, v8bf, v4si, v4sf)
 VAR9 (STORE1LANE, vst3_lane,
 	v8qi, v4hi, v4hf, v2si, v2sf, v8hi, v8hf, v4si, v4sf)
-VAR11 (LOAD1, vld4,
-	v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf)
+VAR13 (LOAD1, vld4,
+	v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf, v4bf, v8bf)
 VAR9 (LOAD1LANE, vld4_lane,
 	v8qi, v4hi, v4hf, v2si, v2sf, v8hi, v8hf, v4si, v4sf)
-VAR6 (LOAD1, vld4_dup, v8qi, v4hi, v4hf, v2si, v2sf, di)
+VAR8 (LOAD1, vld4_dup, v8qi, v4hi, v4hf, v2si, v2sf, di, v4bf, v8bf)
 VAR13 (STORE1, vst4,
 	v8qi, v4hi, v4hf, v4bf, v2si, v2sf, di, v16qi, v8hi, v8hf, v8bf, v4si, v4sf)
 VAR9 (STORE1LANE, vst4_lane,

gcc/config/arm/iterators.md

@@ -87,6 +87,9 @@
 ;; Double-width vector modes plus 64-bit elements, including V4BF.
 (define_mode_iterator VDXBF [V8QI V4HI V4HF (V4BF "TARGET_BF16_SIMD") V2SI V2SF DI])
 
+;; Double-width vector modes plus 64-bit elements, V4BF and V8BF.
+(define_mode_iterator VDXBF2 [V8QI V4HI V4HF V2SI V2SF DI (V4BF "TARGET_BF16_SIMD") (V8BF ("TARGET_BF16_SIMD"))])
+
 ;; Double-width vector modes plus 64-bit elements,
 ;; with V4BFmode added, suitable for moves.
 (define_mode_iterator VDXMOV [V8QI V4HI V4HF V4BF V2SI V2SF DI])

gcc/config/arm/neon.md

@@ -5428,7 +5428,7 @@ if (BYTES_BIG_ENDIAN)
 (define_insn "neon_vld2<mode>"
   [(set (match_operand:TI 0 "s_register_operand" "=w")
         (unspec:TI [(match_operand:TI 1 "neon_struct_operand" "Um")
-                    (unspec:VDX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+                    (unspec:VDXBF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
                    UNSPEC_VLD2))]
   "TARGET_NEON"
 {
@@ -5453,7 +5453,7 @@ if (BYTES_BIG_ENDIAN)
 (define_insn "neon_vld2<mode>"
   [(set (match_operand:OI 0 "s_register_operand" "=w")
         (unspec:OI [(match_operand:OI 1 "neon_struct_operand" "Um")
-                    (unspec:VQ2 [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+                    (unspec:VQ2BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
                    UNSPEC_VLD2))]
   "TARGET_NEON"
   "vld2.<V_sz_elem>\t%h0, %A1"
@@ -5516,7 +5516,7 @@ if (BYTES_BIG_ENDIAN)
 (define_insn "neon_vld2_dup<mode>"
   [(set (match_operand:TI 0 "s_register_operand" "=w")
         (unspec:TI [(match_operand:<V_two_elem> 1 "neon_struct_operand" "Um")
-                    (unspec:VDX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+                    (unspec:VDXBF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
                    UNSPEC_VLD2_DUP))]
   "TARGET_NEON"
 {
@@ -5531,6 +5531,27 @@ if (BYTES_BIG_ENDIAN)
                     (const_string "neon_load1_1reg<q>")))]
 )
 
+(define_insn "neon_vld2_dupv8bf"
+  [(set (match_operand:OI 0 "s_register_operand" "=w")
+        (unspec:OI [(match_operand:V2BF 1 "neon_struct_operand" "Um")
+                    (unspec:V8BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+                   UNSPEC_VLD2_DUP))]
+  "TARGET_BF16_SIMD"
+  {
+    rtx ops[5];
+    int tabbase = REGNO (operands[0]);
+
+    ops[4] = operands[1];
+    ops[0] = gen_rtx_REG (V4BFmode, tabbase);
+    ops[1] = gen_rtx_REG (V4BFmode, tabbase + 2);
+    ops[2] = gen_rtx_REG (V4BFmode, tabbase + 4);
+    ops[3] = gen_rtx_REG (V4BFmode, tabbase + 6);
+    output_asm_insn ("vld2.16\t{%P0, %P1, %P2, %P3}, %A4", ops);
+    return "";
+  }
+  [(set_attr "type" "neon_load2_all_lanes_q")]
+)
+
 (define_expand "vec_store_lanesti<mode>"
   [(set (match_operand:TI 0 "neon_struct_operand")
 	(unspec:TI [(match_operand:TI 1 "s_register_operand")
@@ -5637,7 +5658,7 @@ if (BYTES_BIG_ENDIAN)
 (define_insn "neon_vld3<mode>"
   [(set (match_operand:EI 0 "s_register_operand" "=w")
         (unspec:EI [(match_operand:EI 1 "neon_struct_operand" "Um")
-                    (unspec:VDX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+                    (unspec:VDXBF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
                    UNSPEC_VLD3))]
   "TARGET_NEON"
 {
@@ -5665,7 +5686,7 @@ if (BYTES_BIG_ENDIAN)
 (define_expand "neon_vld3<mode>"
   [(match_operand:CI 0 "s_register_operand")
    (match_operand:CI 1 "neon_struct_operand")
-   (unspec:VQ2 [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+   (unspec:VQ2BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
   "TARGET_NEON"
 {
   rtx mem;
@@ -5680,7 +5701,7 @@ if (BYTES_BIG_ENDIAN)
 (define_insn "neon_vld3qa<mode>"
   [(set (match_operand:CI 0 "s_register_operand" "=w")
         (unspec:CI [(match_operand:EI 1 "neon_struct_operand" "Um")
-                    (unspec:VQ2 [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+                    (unspec:VQ2BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
                    UNSPEC_VLD3A))]
   "TARGET_NEON"
 {
@@ -5700,7 +5721,7 @@ if (BYTES_BIG_ENDIAN)
   [(set (match_operand:CI 0 "s_register_operand" "=w")
         (unspec:CI [(match_operand:EI 1 "neon_struct_operand" "Um")
                     (match_operand:CI 2 "s_register_operand" "0")
-                    (unspec:VQ2 [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+                    (unspec:VQ2BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
                    UNSPEC_VLD3B))]
   "TARGET_NEON"
 {
@@ -5777,7 +5798,7 @@ if (BYTES_BIG_ENDIAN)
 (define_insn "neon_vld3_dup<mode>"
   [(set (match_operand:EI 0 "s_register_operand" "=w")
         (unspec:EI [(match_operand:<V_three_elem> 1 "neon_struct_operand" "Um")
-                    (unspec:VDX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+                    (unspec:VDXBF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
                    UNSPEC_VLD3_DUP))]
   "TARGET_NEON"
 {
@@ -5800,6 +5821,26 @@ if (BYTES_BIG_ENDIAN)
                     (const_string "neon_load3_all_lanes<q>")
                     (const_string "neon_load1_1reg<q>")))])
 
+(define_insn "neon_vld3_dupv8bf"
+  [(set (match_operand:CI 0 "s_register_operand" "=w")
+        (unspec:CI [(match_operand:V2BF 1 "neon_struct_operand" "Um")
+                    (unspec:V8BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+                   UNSPEC_VLD2_DUP))]
+  "TARGET_BF16_SIMD"
+  {
+    rtx ops[4];
+    int tabbase = REGNO (operands[0]);
+
+    ops[3] = operands[1];
+    ops[0] = gen_rtx_REG (V4BFmode, tabbase);
+    ops[1] = gen_rtx_REG (V4BFmode, tabbase + 2);
+    ops[2] = gen_rtx_REG (V4BFmode, tabbase + 4);
+    output_asm_insn ("vld3.16\t{%P0[], %P1[], %P2[]}, %A3", ops);
+    return "";
+  }
+  [(set_attr "type" "neon_load3_all_lanes_q")]
+)
+
 (define_expand "vec_store_lanesei<mode>"
   [(set (match_operand:EI 0 "neon_struct_operand")
 	(unspec:EI [(match_operand:EI 1 "s_register_operand")
@@ -5955,7 +5996,7 @@ if (BYTES_BIG_ENDIAN)
 (define_insn "neon_vld4<mode>"
   [(set (match_operand:OI 0 "s_register_operand" "=w")
         (unspec:OI [(match_operand:OI 1 "neon_struct_operand" "Um")
-                    (unspec:VDX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+                    (unspec:VDXBF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
                    UNSPEC_VLD4))]
   "TARGET_NEON"
 {
@@ -5983,7 +6024,7 @@ if (BYTES_BIG_ENDIAN)
 (define_expand "neon_vld4<mode>"
   [(match_operand:XI 0 "s_register_operand")
    (match_operand:XI 1 "neon_struct_operand")
-   (unspec:VQ2 [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+   (unspec:VQ2BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
   "TARGET_NEON"
 {
   rtx mem;
@@ -5998,7 +6039,7 @@ if (BYTES_BIG_ENDIAN)
 (define_insn "neon_vld4qa<mode>"
   [(set (match_operand:XI 0 "s_register_operand" "=w")
         (unspec:XI [(match_operand:OI 1 "neon_struct_operand" "Um")
-                    (unspec:VQ2 [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+                    (unspec:VQ2BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
                    UNSPEC_VLD4A))]
   "TARGET_NEON"
 {
@@ -6019,7 +6060,7 @@ if (BYTES_BIG_ENDIAN)
   [(set (match_operand:XI 0 "s_register_operand" "=w")
         (unspec:XI [(match_operand:OI 1 "neon_struct_operand" "Um")
                     (match_operand:XI 2 "s_register_operand" "0")
-                    (unspec:VQ2 [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+                    (unspec:VQ2BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
                    UNSPEC_VLD4B))]
   "TARGET_NEON"
 {
@@ -6099,7 +6140,7 @@ if (BYTES_BIG_ENDIAN)
 (define_insn "neon_vld4_dup<mode>"
   [(set (match_operand:OI 0 "s_register_operand" "=w")
         (unspec:OI [(match_operand:<V_four_elem> 1 "neon_struct_operand" "Um")
-                    (unspec:VDX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+                    (unspec:VDXBF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
                    UNSPEC_VLD4_DUP))]
   "TARGET_NEON"
 {
@@ -6125,6 +6166,27 @@ if (BYTES_BIG_ENDIAN)
                     (const_string "neon_load1_1reg<q>")))]
 )
 
+(define_insn "neon_vld4_dupv8bf"
+  [(set (match_operand:XI 0 "s_register_operand" "=w")
+        (unspec:XI [(match_operand:V2BF 1 "neon_struct_operand" "Um")
+                    (unspec:V8BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+                   UNSPEC_VLD2_DUP))]
+  "TARGET_BF16_SIMD"
+  {
+    rtx ops[5];
+    int tabbase = REGNO (operands[0]);
+
+    ops[4] = operands[1];
+    ops[0] = gen_rtx_REG (V4BFmode, tabbase);
+    ops[1] = gen_rtx_REG (V4BFmode, tabbase + 2);
+    ops[2] = gen_rtx_REG (V4BFmode, tabbase + 4);
+    ops[3] = gen_rtx_REG (V4BFmode, tabbase + 6);
+    output_asm_insn ("vld4.16\t{%P0[], %P1[], %P2[], %P3[]}, %A4", ops);
+    return "";
+  }
+  [(set_attr "type" "neon_load4_all_lanes_q")]
+)
+
 (define_expand "vec_store_lanesoi<mode>"
   [(set (match_operand:OI 0 "neon_struct_operand")
 	(unspec:OI [(match_operand:OI 1 "s_register_operand")

gcc/testsuite/ChangeLog

 2020-03-06  Delia Burduv  <delia.burduv@arm.com>
 
+	* gcc.target/arm/simd/bf16_vldn_1.c: New test.
+
+2020-03-06  Delia Burduv  <delia.burduv@arm.com>
+
 	* gcc.target/arm/simd/bf16_vstn_1.c: New test.
 
 2020-03-06  Kito Cheng  <kito.cheng@sifive.com>

gcc/testsuite/gcc.target/arm/simd/bf16_vldn_1.c

+/* { 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_vld2_bf16:
+**	...
+**	vld2.16	{d0-d1}, \[r0\]
+**	bx	lr
+*/
+bfloat16x4x2_t
+test_vld2_bf16 (bfloat16_t * ptr)
+{
+  return vld2_bf16 (ptr);
+}
+
+/*
+**test_vld2q_bf16:
+**	...
+**	vld2.16	{d0-d3}, \[r0\]
+**	bx	lr
+*/
+bfloat16x8x2_t
+test_vld2q_bf16 (bfloat16_t * ptr)
+{
+  return vld2q_bf16 (ptr);
+}
+
+/*
+**test_vld2_dup_bf16:
+**	...
+**	vld2.16	{d0\[\], d1\[\]}, \[r0\]
+**	bx	lr
+*/
+bfloat16x4x2_t
+test_vld2_dup_bf16 (bfloat16_t * ptr)
+{
+  return vld2_dup_bf16 (ptr);
+}
+
+/*
+**test_vld2q_dup_bf16:
+**	...
+**	vld2.16	{d0, d1, d2, d3}, \[r0\]
+**	bx	lr
+*/
+bfloat16x8x2_t
+test_vld2q_dup_bf16 (bfloat16_t * ptr)
+{
+  return vld2q_dup_bf16 (ptr);
+}
+
+/*
+**test_vld3_bf16:
+**	...
+**	vld3.16	{d0-d2}, \[r0\]
+**	bx	lr
+*/
+bfloat16x4x3_t
+test_vld3_bf16 (bfloat16_t * ptr)
+{
+  return vld3_bf16 (ptr);
+}
+
+/*
+**test_vld3q_bf16:
+**	...
+**	vld3.16	{d1, d3, d5}, \[r0\]
+**	bx	lr
+*/
+bfloat16x8x3_t
+test_vld3q_bf16 (bfloat16_t * ptr)
+{
+  return vld3q_bf16 (ptr);
+}
+
+/*
+**test_vld3_dup_bf16:
+**	...
+**	vld3.16	{d0\[\], d1\[\], d2\[\]}, \[r0\]
+**	bx	lr
+*/
+bfloat16x4x3_t
+test_vld3_dup_bf16 (bfloat16_t * ptr)
+{
+  return vld3_dup_bf16 (ptr);
+}
+
+/*
+**test_vld3q_dup_bf16:
+**	...
+**	vld3.16	{d0\[\], d1\[\], d2\[\]}, \[r0\]
+**	bx	lr
+*/
+bfloat16x8x3_t
+test_vld3q_dup_bf16 (bfloat16_t * ptr)
+{
+  return vld3q_dup_bf16 (ptr);
+}
+
+/*
+**test_vld4_bf16:
+**	...
+**	vld4.16	{d0-d3}, \[r0\]
+**	bx	lr
+*/
+bfloat16x4x4_t
+test_vld4_bf16 (bfloat16_t * ptr)
+{
+  return vld4_bf16 (ptr);
+}
+
+/*
+**test_vld4q_bf16:
+**	...
+**	vld4.16	{d1, d3, d5, d7}, \[r0\]
+**	bx	lr
+*/
+bfloat16x8x4_t
+test_vld4q_bf16 (bfloat16_t * ptr)
+{
+  return vld4q_bf16 (ptr);
+}
+
+/*
+**test_vld4_dup_bf16:
+**	...
+**	vld4.16	{d0\[\], d1\[\], d2\[\], d3\[\]}, \[r0\]
+**	bx	lr
+*/
+bfloat16x4x4_t
+test_vld4_dup_bf16 (bfloat16_t * ptr)
+{
+  return vld4_dup_bf16 (ptr);
+}
+
+/*
+**test_vld4q_dup_bf16:
+**	...
+**	vld4.16	{d0\[\], d1\[\], d2\[\], d3\[\]}, \[r0\]
+**	bx	lr
+*/
+bfloat16x8x4_t
+test_vld4q_dup_bf16 (bfloat16_t * ptr)
+{
+  return vld4q_dup_bf16 (ptr);
+}