Bug fix: cannot convert 'const short int*' to 'const __bf16*'

This patch fixes a bug introduced by my earlier patch (
https://gcc.gnu.org/pipermail/gcc-patches/2020-March/541680.html ).
It introduces a new scalar builtin type that was missing in the original
patch.

Bootstrapped cleanly on arm-none-linux-gnueabihf.
Tested for regression on arm-none-linux-gnueabihf. No regression from
before the original patch.
Tests that failed or became unsupported because of the original tests
now work as they did before it.

	* config/arm/arm-builtins.c
	(arm_init_simd_builtin_scalar_types): New.
	* config/arm/arm_neon.h (vld2_bf16): Used new builtin type.
	(vld2q_bf16): Used new builtin type.
	(vld3_bf16): Used new builtin type.
	(vld3q_bf16): Used new builtin type.
	(vld4_bf16): Used new builtin type.
	(vld4q_bf16): Used new builtin type.
	(vld2_dup_bf16): Used new builtin type.
	(vld2q_dup_bf16): Used new builtin type.
	(vld3_dup_bf16): Used new builtin type.
	(vld3q_dup_bf16): Used new builtin type.
	(vld4_dup_bf16): Used new builtin type.
	(vld4q_dup_bf16): Used new builtin type.

gcc/ChangeLog

+2020-03-11  Delia Burduv  <delia.burduv@arm.com>
+
+	* config/arm/arm-builtins.c
+	(arm_init_simd_builtin_scalar_types): New.
+	* config/arm/arm_neon.h (vld2_bf16): Used new builtin type.
+	(vld2q_bf16): Used new builtin type.
+	(vld3_bf16): Used new builtin type.
+	(vld3q_bf16): Used new builtin type.
+	(vld4_bf16): Used new builtin type.
+	(vld4q_bf16): Used new builtin type.
+	(vld2_dup_bf16): Used new builtin type.
+	(vld2q_dup_bf16): Used new builtin type.
+	(vld3_dup_bf16): Used new builtin type.
+	(vld3q_dup_bf16): Used new builtin type.
+	(vld4_dup_bf16): Used new builtin type.
+	(vld4q_dup_bf16): Used new builtin type.
+
 2020-03-11  Jakub Jelinek  <jakub@redhat.com>
 
 	PR target/94134

gcc/config/arm/arm-builtins.c

@@ -784,6 +784,7 @@ const char *arm_scalar_builtin_types[] = {
   "__builtin_neon_oi",
   "__builtin_neon_ci",
   "__builtin_neon_xi",
+  "__builtin_neon_bf",
   NULL
 };
 
@@ -1101,7 +1102,8 @@ arm_init_simd_builtin_scalar_types (void)
 					     "__builtin_neon_df");
   (*lang_hooks.types.register_builtin_type) (intTI_type_node,
 					     "__builtin_neon_ti");
-
+  (*lang_hooks.types.register_builtin_type) (arm_bf16_type_node,
+                                             "__builtin_neon_bf");
   /* Unsigned integer types for various mode sizes.  */
   (*lang_hooks.types.register_builtin_type) (unsigned_intQI_type_node,
 					     "__builtin_neon_uqi");

gcc/config/arm/arm_neon.h

@@ -19562,7 +19562,7 @@ __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);
+  __rv.__o = __builtin_neon_vld2v4bf ((const __builtin_neon_bf *) __ptr);
   return __rv.__i;
 }
 
@@ -19571,7 +19571,7 @@ __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);
+  __rv.__o = __builtin_neon_vld2v8bf ((const __builtin_neon_bf *) __ptr);
   return __rv.__i;
 }
 
@@ -19580,7 +19580,7 @@ __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);
+  __rv.__o = __builtin_neon_vld3v4bf ((const __builtin_neon_bf *) __ptr);
   return __rv.__i;
 }
 
@@ -19589,7 +19589,7 @@ __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);
+  __rv.__o = __builtin_neon_vld3v8bf ((const __builtin_neon_bf *) __ptr);
   return __rv.__i;
 }
 
@@ -19598,7 +19598,7 @@ __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);
+  __rv.__o = __builtin_neon_vld4v4bf ((const __builtin_neon_bf *) __ptr);
   return __rv.__i;
 }
 
@@ -19607,7 +19607,7 @@ __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);
+  __rv.__o = __builtin_neon_vld4v8bf ((const __builtin_neon_bf *) __ptr);
   return __rv.__i;
 }
 
@@ -19616,7 +19616,7 @@ __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);
+  __rv.__o = __builtin_neon_vld2_dupv4bf ((const __builtin_neon_bf *) __ptr);
   return __rv.__i;
 }
 
@@ -19625,7 +19625,7 @@ __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);
+  __rv.__o = __builtin_neon_vld2_dupv8bf ((const __builtin_neon_bf *) __ptr);
   return __rv.__i;
 }
 
@@ -19634,7 +19634,7 @@ __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);
+  __rv.__o = __builtin_neon_vld3_dupv4bf ((const __builtin_neon_bf *) __ptr);
   return __rv.__i;
 }
 
@@ -19643,7 +19643,7 @@ __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);
+  __rv.__o = __builtin_neon_vld3_dupv8bf ((const __builtin_neon_bf *) __ptr);
   return __rv.__i;
 }
 
@@ -19652,7 +19652,7 @@ __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);
+  __rv.__o = __builtin_neon_vld4_dupv4bf ((const __builtin_neon_bf *) __ptr);
   return __rv.__i;
 }
 
@@ -19661,7 +19661,7 @@ __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);
+  __rv.__o = __builtin_neon_vld4_dupv8bf ((const __builtin_neon_bf *) __ptr);
   return __rv.__i;
 }