[ARM] PR66791: Replace builtin in vld1_dup intrinsics

[Prathamesh Kulkarni via Gcc-patches]

Hi,
The attached patch replaces builtins in vld1_dup intrinsics with call
to corresponding vdup_n intrinsic and removes entry for vld1_dup from
arm_neon_builtins.def.
Bootstrapped+tested on arm-linux-gnueabihf.
OK to commit ?

Thanks,
Prathamesh

gcc/ChangeLog:

        PR target/66791
        * config/arm/arm_neon.h (vld1_dup_s8): Replace builtin with call to
        corresponding vdup_n intrinsic.
        (vld1_dup_s16): Likewise.
        (vld1_dup_s32): Likewise.
        (vld1_dup_f32): Likewise.
        (vld1_dup_u8): Likewise.
        (vld1_dup_u16): Likewise.
        (vld1_dup_u32): Likewise.
        (vld1_dup_p8): Likewise.
        (vld1_dup_p16): Likewise.
        (vld1_dup_p64): Likewise.
        (vld1_dup_s64): Likewise.
        (vld1_dup_u64): Likewise.
        (vld1q_dup_s8): Likewise.
        (vld1q_dup_s16): Likewise.
        (vld1q_dup_s32): Likewise.
        (vld1q_dup_f32): Likewise.
        (vld1q_dup_u8): Likewise.
        (vld1q_dup_u16): Likewise.
        (vld1q_dup_u32): Likewise.
        (vld1q_dup_p8): Likewise.
        (vld1q_dup_p16): Likewise.
        (vld1q_dup_p64): Likewise.
        (vld1q_dup_s64): Likewise.
        (vld1q_dup_u64): Likewise.
        * config/arm/arm_neon_builtins.def (vld1_dup): Remove entry.


diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h
index 41b596b5fc6..bc55dacffd3 100644
--- a/gcc/config/arm/arm_neon.h
+++ b/gcc/config/arm/arm_neon.h
@@ -10683,21 +10683,21 @@ __extension__ extern __inline int8x8_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1_dup_s8 (const int8_t * __a)
 {
-  return (int8x8_t)__builtin_neon_vld1_dupv8qi ((const __builtin_neon_qi *) 
__a);
+  return vdup_n_s8 (*__a);
 }
 
 __extension__ extern __inline int16x4_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1_dup_s16 (const int16_t * __a)
 {
-  return (int16x4_t)__builtin_neon_vld1_dupv4hi ((const __builtin_neon_hi *) 
__a);
+  return vdup_n_s16 (*__a);
 }
 
 __extension__ extern __inline int32x2_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1_dup_s32 (const int32_t * __a)
 {
-  return (int32x2_t)__builtin_neon_vld1_dupv2si ((const __builtin_neon_si *) 
__a);
+  return vdup_n_s32 (*__a);
 }
 
 #if defined (__ARM_FP16_FORMAT_IEEE) || defined (__ARM_FP16_FORMAT_ALTERNATIVE)
@@ -10714,42 +10714,42 @@ __extension__ extern __inline float32x2_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1_dup_f32 (const float32_t * __a)
 {
-  return (float32x2_t)__builtin_neon_vld1_dupv2sf ((const __builtin_neon_sf *) 
__a);
+  return vdup_n_f32 (*__a);
 }
 
 __extension__ extern __inline uint8x8_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1_dup_u8 (const uint8_t * __a)
 {
-  return (uint8x8_t)__builtin_neon_vld1_dupv8qi ((const __builtin_neon_qi *) 
__a);
+  return vdup_n_u8 (*__a);
 }
 
 __extension__ extern __inline uint16x4_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1_dup_u16 (const uint16_t * __a)
 {
-  return (uint16x4_t)__builtin_neon_vld1_dupv4hi ((const __builtin_neon_hi *) 
__a);
+  return vdup_n_u16 (*__a);
 }
 
 __extension__ extern __inline uint32x2_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1_dup_u32 (const uint32_t * __a)
 {
-  return (uint32x2_t)__builtin_neon_vld1_dupv2si ((const __builtin_neon_si *) 
__a);
+  return vdup_n_u32 (*__a);
 }
 
 __extension__ extern __inline poly8x8_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1_dup_p8 (const poly8_t * __a)
 {
-  return (poly8x8_t)__builtin_neon_vld1_dupv8qi ((const __builtin_neon_qi *) 
__a);
+  return vdup_n_p8 (*__a);
 }
 
 __extension__ extern __inline poly16x4_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1_dup_p16 (const poly16_t * __a)
 {
-  return (poly16x4_t)__builtin_neon_vld1_dupv4hi ((const __builtin_neon_hi *) 
__a);
+  return vdup_n_p16 (*__a);
 }
 
 #pragma GCC push_options
@@ -10758,7 +10758,7 @@ __extension__ extern __inline poly64x1_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1_dup_p64 (const poly64_t * __a)
 {
-  return (poly64x1_t)__builtin_neon_vld1_dupdi ((const __builtin_neon_di *) 
__a);
+  return vdup_n_p64 (*__a);
 }
 
 #pragma GCC pop_options
@@ -10766,35 +10766,35 @@ __extension__ extern __inline int64x1_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1_dup_s64 (const int64_t * __a)
 {
-  return (int64x1_t)__builtin_neon_vld1_dupdi ((const __builtin_neon_di *) 
__a);
+  return vdup_n_s64 (*__a);
 }
 
 __extension__ extern __inline uint64x1_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1_dup_u64 (const uint64_t * __a)
 {
-  return (uint64x1_t)__builtin_neon_vld1_dupdi ((const __builtin_neon_di *) 
__a);
+  return vdup_n_u64 (*__a);
 }
 
 __extension__ extern __inline int8x16_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1q_dup_s8 (const int8_t * __a)
 {
-  return (int8x16_t)__builtin_neon_vld1_dupv16qi ((const __builtin_neon_qi *) 
__a);
+  return vdupq_n_s8 (*__a);
 }
 
 __extension__ extern __inline int16x8_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1q_dup_s16 (const int16_t * __a)
 {
-  return (int16x8_t)__builtin_neon_vld1_dupv8hi ((const __builtin_neon_hi *) 
__a);
+  return vdupq_n_s16 (*__a);
 }
 
 __extension__ extern __inline int32x4_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1q_dup_s32 (const int32_t * __a)
 {
-  return (int32x4_t)__builtin_neon_vld1_dupv4si ((const __builtin_neon_si *) 
__a);
+  return vdupq_n_s32 (*__a);
 }
 
 #if defined (__ARM_FP16_FORMAT_IEEE) || defined (__ARM_FP16_FORMAT_ALTERNATIVE)
@@ -10811,42 +10811,42 @@ __extension__ extern __inline float32x4_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1q_dup_f32 (const float32_t * __a)
 {
-  return (float32x4_t)__builtin_neon_vld1_dupv4sf ((const __builtin_neon_sf *) 
__a);
+  return vdupq_n_f32 (*__a);
 }
 
 __extension__ extern __inline uint8x16_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1q_dup_u8 (const uint8_t * __a)
 {
-  return (uint8x16_t)__builtin_neon_vld1_dupv16qi ((const __builtin_neon_qi *) 
__a);
+  return vdupq_n_u8 (*__a);
 }
 
 __extension__ extern __inline uint16x8_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1q_dup_u16 (const uint16_t * __a)
 {
-  return (uint16x8_t)__builtin_neon_vld1_dupv8hi ((const __builtin_neon_hi *) 
__a);
+  return vdupq_n_u16 (*__a);
 }
 
 __extension__ extern __inline uint32x4_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1q_dup_u32 (const uint32_t * __a)
 {
-  return (uint32x4_t)__builtin_neon_vld1_dupv4si ((const __builtin_neon_si *) 
__a);
+  return vdupq_n_u32 (*__a);
 }
 
 __extension__ extern __inline poly8x16_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1q_dup_p8 (const poly8_t * __a)
 {
-  return (poly8x16_t)__builtin_neon_vld1_dupv16qi ((const __builtin_neon_qi *) 
__a);
+  return vdupq_n_p8 (*__a);
 }
 
 __extension__ extern __inline poly16x8_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1q_dup_p16 (const poly16_t * __a)
 {
-  return (poly16x8_t)__builtin_neon_vld1_dupv8hi ((const __builtin_neon_hi *) 
__a);
+  return vdupq_n_p16 (*__a);
 }
 
 #pragma GCC push_options
@@ -10855,7 +10855,7 @@ __extension__ extern __inline poly64x2_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1q_dup_p64 (const poly64_t * __a)
 {
-  return (poly64x2_t)__builtin_neon_vld1_dupv2di ((const __builtin_neon_di *) 
__a);
+  return vdupq_n_p64 (*__a);
 }
 
 #pragma GCC pop_options
@@ -10863,14 +10863,14 @@ __extension__ extern __inline int64x2_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1q_dup_s64 (const int64_t * __a)
 {
-  return (int64x2_t)__builtin_neon_vld1_dupv2di ((const __builtin_neon_di *) 
__a);
+  return vdupq_n_s64 (*__a);
 }
 
 __extension__ extern __inline uint64x2_t
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vld1q_dup_u64 (const uint64_t * __a)
 {
-  return (uint64x2_t)__builtin_neon_vld1_dupv2di ((const __builtin_neon_di *) 
__a);
+  return vdupq_n_u64 (*__a);
 }
 
 #pragma GCC push_options
diff --git a/gcc/config/arm/arm_neon_builtins.def 
b/gcc/config/arm/arm_neon_builtins.def
index 70438ac1848..a2aeb21f350 100644
--- a/gcc/config/arm/arm_neon_builtins.def
+++ b/gcc/config/arm/arm_neon_builtins.def
@@ -307,8 +307,6 @@ VAR14 (LOAD1, vld1,
         v4bf, v8bf)
 VAR12 (LOAD1LANE, vld1_lane,
        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)
 VAR14 (STORE1, vst1,
         v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf, v2di,
         v4bf, v8bf)