Patchwork [AArch64] Remove arm_neon.h's dependency on stdint's macros.

login
register
mail settings
Submitter Tejas Belagod
Date Aug. 30, 2013, 2:03 p.m.
Message ID <5220A639.3060704@arm.com>
Download mbox | patch
Permalink /patch/271296/
State New
Headers show

Comments

Tejas Belagod - Aug. 30, 2013, 2:03 p.m.
Hi,

The attached patch removes dependency on stdint's macros used in arm_neon.h viz. 
UINT64_C() and INT64_C() making arm_neon.h more C++-friendly.

Tested on aarch64-none-elf.

OK for trunk?

Thanks,
Tejas Belagod.
ARM.

Changelog:

2013-08-30  Tejas Belagod  <tejas.belagod@arm.com>

gcc/
	* config/aarch64/arm_neon.h (__AARCH64_UINT64_C, __AARCH64_INT64_C): New
	arm_neon.h's internal macros to specify 64-bit constants. Avoid using
	stdint.h's macros.
Richard Earnshaw - Aug. 30, 2013, 2:41 p.m.
On 30/08/13 15:03, Tejas Belagod wrote:
> Hi,
> 
> The attached patch removes dependency on stdint's macros used in arm_neon.h viz. 
> UINT64_C() and INT64_C() making arm_neon.h more C++-friendly.
> 
> Tested on aarch64-none-elf.
> 
> OK for trunk?
> 
> Thanks,
> Tejas Belagod.
> ARM.
> 
> Changelog:
> 
> 2013-08-30  Tejas Belagod  <tejas.belagod@arm.com>
> 
> gcc/
> 	* config/aarch64/arm_neon.h (__AARCH64_UINT64_C, __AARCH64_INT64_C): New
> 	arm_neon.h's internal macros to specify 64-bit constants. Avoid using
> 	stdint.h's macros.
> 
> 

OK.

R.

Patch

diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 13ef11d..6e8d8cd 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -29,6 +29,9 @@ 
 
 #include <stdint.h>
 
+#define __AARCH64_UINT64_C(__C) ((uint64_t) __C)
+#define __AARCH64_INT64_C(__C) ((int64_t) __C)
+
 typedef __builtin_aarch64_simd_qi int8x8_t
   __attribute__ ((__vector_size__ (8)));
 typedef __builtin_aarch64_simd_hi int16x4_t
@@ -9776,7 +9779,7 @@  vmovl_u32 (uint32x2_t a)
 __extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
 vmovn_high_s16 (int8x8_t a, int16x8_t b)
 {
-  int8x16_t result = vcombine_s8 (a, vcreate_s8 (UINT64_C (0x0)));
+  int8x16_t result = vcombine_s8 (a, vcreate_s8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("xtn2 %0.16b,%1.8h"
            : "+w"(result)
            : "w"(b)
@@ -9787,7 +9790,7 @@  vmovn_high_s16 (int8x8_t a, int16x8_t b)
 __extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
 vmovn_high_s32 (int16x4_t a, int32x4_t b)
 {
-  int16x8_t result = vcombine_s16 (a, vcreate_s16 (UINT64_C (0x0)));
+  int16x8_t result = vcombine_s16 (a, vcreate_s16 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("xtn2 %0.8h,%1.4s"
            : "+w"(result)
            : "w"(b)
@@ -9798,7 +9801,7 @@  vmovn_high_s32 (int16x4_t a, int32x4_t b)
 __extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
 vmovn_high_s64 (int32x2_t a, int64x2_t b)
 {
-  int32x4_t result = vcombine_s32 (a, vcreate_s32 (UINT64_C (0x0)));
+  int32x4_t result = vcombine_s32 (a, vcreate_s32 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("xtn2 %0.4s,%1.2d"
            : "+w"(result)
            : "w"(b)
@@ -9809,7 +9812,7 @@  vmovn_high_s64 (int32x2_t a, int64x2_t b)
 __extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
 vmovn_high_u16 (uint8x8_t a, uint16x8_t b)
 {
-  uint8x16_t result = vcombine_u8 (a, vcreate_u8 (UINT64_C (0x0)));
+  uint8x16_t result = vcombine_u8 (a, vcreate_u8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("xtn2 %0.16b,%1.8h"
            : "+w"(result)
            : "w"(b)
@@ -9820,7 +9823,7 @@  vmovn_high_u16 (uint8x8_t a, uint16x8_t b)
 __extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
 vmovn_high_u32 (uint16x4_t a, uint32x4_t b)
 {
-  uint16x8_t result = vcombine_u16 (a, vcreate_u16 (UINT64_C (0x0)));
+  uint16x8_t result = vcombine_u16 (a, vcreate_u16 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("xtn2 %0.8h,%1.4s"
            : "+w"(result)
            : "w"(b)
@@ -9831,7 +9834,7 @@  vmovn_high_u32 (uint16x4_t a, uint32x4_t b)
 __extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
 vmovn_high_u64 (uint32x2_t a, uint64x2_t b)
 {
-  uint32x4_t result = vcombine_u32 (a, vcreate_u32 (UINT64_C (0x0)));
+  uint32x4_t result = vcombine_u32 (a, vcreate_u32 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("xtn2 %0.4s,%1.2d"
            : "+w"(result)
            : "w"(b)
@@ -12250,7 +12253,7 @@  vqdmulhq_n_s32 (int32x4_t a, int32_t b)
 __extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
 vqmovn_high_s16 (int8x8_t a, int16x8_t b)
 {
-  int8x16_t result = vcombine_s8 (a, vcreate_s8 (UINT64_C (0x0)));
+  int8x16_t result = vcombine_s8 (a, vcreate_s8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("sqxtn2 %0.16b, %1.8h"
            : "+w"(result)
            : "w"(b)
@@ -12261,7 +12264,7 @@  vqmovn_high_s16 (int8x8_t a, int16x8_t b)
 __extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
 vqmovn_high_s32 (int16x4_t a, int32x4_t b)
 {
-  int16x8_t result = vcombine_s16 (a, vcreate_s16 (UINT64_C (0x0)));
+  int16x8_t result = vcombine_s16 (a, vcreate_s16 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("sqxtn2 %0.8h, %1.4s"
            : "+w"(result)
            : "w"(b)
@@ -12272,7 +12275,7 @@  vqmovn_high_s32 (int16x4_t a, int32x4_t b)
 __extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
 vqmovn_high_s64 (int32x2_t a, int64x2_t b)
 {
-  int32x4_t result = vcombine_s32 (a, vcreate_s32 (UINT64_C (0x0)));
+  int32x4_t result = vcombine_s32 (a, vcreate_s32 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("sqxtn2 %0.4s, %1.2d"
            : "+w"(result)
            : "w"(b)
@@ -12283,7 +12286,7 @@  vqmovn_high_s64 (int32x2_t a, int64x2_t b)
 __extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
 vqmovn_high_u16 (uint8x8_t a, uint16x8_t b)
 {
-  uint8x16_t result = vcombine_u8 (a, vcreate_u8 (UINT64_C (0x0)));
+  uint8x16_t result = vcombine_u8 (a, vcreate_u8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("uqxtn2 %0.16b, %1.8h"
            : "+w"(result)
            : "w"(b)
@@ -12294,7 +12297,7 @@  vqmovn_high_u16 (uint8x8_t a, uint16x8_t b)
 __extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
 vqmovn_high_u32 (uint16x4_t a, uint32x4_t b)
 {
-  uint16x8_t result = vcombine_u16 (a, vcreate_u16 (UINT64_C (0x0)));
+  uint16x8_t result = vcombine_u16 (a, vcreate_u16 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("uqxtn2 %0.8h, %1.4s"
            : "+w"(result)
            : "w"(b)
@@ -12305,7 +12308,7 @@  vqmovn_high_u32 (uint16x4_t a, uint32x4_t b)
 __extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
 vqmovn_high_u64 (uint32x2_t a, uint64x2_t b)
 {
-  uint32x4_t result = vcombine_u32 (a, vcreate_u32 (UINT64_C (0x0)));
+  uint32x4_t result = vcombine_u32 (a, vcreate_u32 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("uqxtn2 %0.4s, %1.2d"
            : "+w"(result)
            : "w"(b)
@@ -12316,7 +12319,7 @@  vqmovn_high_u64 (uint32x2_t a, uint64x2_t b)
 __extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
 vqmovun_high_s16 (uint8x8_t a, int16x8_t b)
 {
-  uint8x16_t result = vcombine_u8 (a, vcreate_u8 (UINT64_C (0x0)));
+  uint8x16_t result = vcombine_u8 (a, vcreate_u8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("sqxtun2 %0.16b, %1.8h"
            : "+w"(result)
            : "w"(b)
@@ -12327,7 +12330,7 @@  vqmovun_high_s16 (uint8x8_t a, int16x8_t b)
 __extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
 vqmovun_high_s32 (uint16x4_t a, int32x4_t b)
 {
-  uint16x8_t result = vcombine_u16 (a, vcreate_u16 (UINT64_C (0x0)));
+  uint16x8_t result = vcombine_u16 (a, vcreate_u16 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("sqxtun2 %0.8h, %1.4s"
            : "+w"(result)
            : "w"(b)
@@ -12338,7 +12341,7 @@  vqmovun_high_s32 (uint16x4_t a, int32x4_t b)
 __extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
 vqmovun_high_s64 (uint32x2_t a, int64x2_t b)
 {
-  uint32x4_t result = vcombine_u32 (a, vcreate_u32 (UINT64_C (0x0)));
+  uint32x4_t result = vcombine_u32 (a, vcreate_u32 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("sqxtun2 %0.4s, %1.2d"
            : "+w"(result)
            : "w"(b)
@@ -12396,7 +12399,8 @@  vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        int16x8_t b_ = (b);                                              \
        int8x8_t a_ = (a);                                               \
        int8x16_t result = vcombine_s8                                   \
-                            (a_, vcreate_s8 (UINT64_C (0x0)));          \
+                            (a_, vcreate_s8                             \
+                                   (__AARCH64_UINT64_C (0x0)));         \
        __asm__ ("sqrshrn2 %0.16b, %1.8h, #%2"                           \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -12410,7 +12414,8 @@  vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        int32x4_t b_ = (b);                                              \
        int16x4_t a_ = (a);                                              \
        int16x8_t result = vcombine_s16                                  \
-                            (a_, vcreate_s16 (UINT64_C (0x0)));         \
+                            (a_, vcreate_s16                            \
+                                   (__AARCH64_UINT64_C (0x0)));         \
        __asm__ ("sqrshrn2 %0.8h, %1.4s, #%2"                            \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -12424,7 +12429,8 @@  vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        int64x2_t b_ = (b);                                              \
        int32x2_t a_ = (a);                                              \
        int32x4_t result = vcombine_s32                                  \
-                            (a_, vcreate_s32 (UINT64_C (0x0)));         \
+                            (a_, vcreate_s32                            \
+                                   (__AARCH64_UINT64_C (0x0)));         \
        __asm__ ("sqrshrn2 %0.4s, %1.2d, #%2"                            \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -12438,7 +12444,8 @@  vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        uint16x8_t b_ = (b);                                             \
        uint8x8_t a_ = (a);                                              \
        uint8x16_t result = vcombine_u8                                  \
-                             (a_, vcreate_u8 (UINT64_C (0x0)));         \
+                             (a_, vcreate_u8                            \
+                                    (__AARCH64_UINT64_C (0x0)));        \
        __asm__ ("uqrshrn2 %0.16b, %1.8h, #%2"                           \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -12452,7 +12459,8 @@  vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        uint32x4_t b_ = (b);                                             \
        uint16x4_t a_ = (a);                                             \
        uint16x8_t result = vcombine_u16                                 \
-                             (a_, vcreate_u16 (UINT64_C (0x0)));        \
+                             (a_, vcreate_u16                           \
+                                    (__AARCH64_UINT64_C (0x0)));        \
        __asm__ ("uqrshrn2 %0.8h, %1.4s, #%2"                            \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -12466,7 +12474,8 @@  vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        uint64x2_t b_ = (b);                                             \
        uint32x2_t a_ = (a);                                             \
        uint32x4_t result = vcombine_u32                                 \
-                             (a_, vcreate_u32 (UINT64_C (0x0)));        \
+                             (a_, vcreate_u32                           \
+                                    (__AARCH64_UINT64_C (0x0)));        \
        __asm__ ("uqrshrn2 %0.4s, %1.2d, #%2"                            \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -12480,7 +12489,8 @@  vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        int16x8_t b_ = (b);                                              \
        uint8x8_t a_ = (a);                                              \
        uint8x16_t result = vcombine_u8                                  \
-                             (a_, vcreate_u8 (UINT64_C (0x0)));         \
+                             (a_, vcreate_u8                            \
+                                    (__AARCH64_UINT64_C (0x0)));        \
        __asm__ ("sqrshrun2 %0.16b, %1.8h, #%2"                          \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -12494,7 +12504,8 @@  vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        int32x4_t b_ = (b);                                              \
        uint16x4_t a_ = (a);                                             \
        uint16x8_t result = vcombine_u16                                 \
-                             (a_, vcreate_u16 (UINT64_C (0x0)));        \
+                             (a_, vcreate_u16                           \
+                                    (__AARCH64_UINT64_C (0x0)));        \
        __asm__ ("sqrshrun2 %0.8h, %1.4s, #%2"                           \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -12508,7 +12519,8 @@  vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        int64x2_t b_ = (b);                                              \
        uint32x2_t a_ = (a);                                             \
        uint32x4_t result = vcombine_u32                                 \
-                             (a_, vcreate_u32 (UINT64_C (0x0)));        \
+                             (a_, vcreate_u32                           \
+                                    (__AARCH64_UINT64_C (0x0)));        \
        __asm__ ("sqrshrun2 %0.4s, %1.2d, #%2"                           \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -12522,7 +12534,8 @@  vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        int16x8_t b_ = (b);                                              \
        int8x8_t a_ = (a);                                               \
        int8x16_t result = vcombine_s8                                   \
-                            (a_, vcreate_s8 (UINT64_C (0x0)));          \
+                            (a_, vcreate_s8                             \
+                                   (__AARCH64_UINT64_C (0x0)));         \
        __asm__ ("sqshrn2 %0.16b, %1.8h, #%2"                            \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -12536,7 +12549,8 @@  vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        int32x4_t b_ = (b);                                              \
        int16x4_t a_ = (a);                                              \
        int16x8_t result = vcombine_s16                                  \
-                            (a_, vcreate_s16 (UINT64_C (0x0)));         \
+                            (a_, vcreate_s16                            \
+                                   (__AARCH64_UINT64_C (0x0)));         \
        __asm__ ("sqshrn2 %0.8h, %1.4s, #%2"                             \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -12550,7 +12564,8 @@  vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        int64x2_t b_ = (b);                                              \
        int32x2_t a_ = (a);                                              \
        int32x4_t result = vcombine_s32                                  \
-                            (a_, vcreate_s32 (UINT64_C (0x0)));         \
+                            (a_, vcreate_s32                            \
+                                   (__AARCH64_UINT64_C (0x0)));         \
        __asm__ ("sqshrn2 %0.4s, %1.2d, #%2"                             \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -12564,7 +12579,8 @@  vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        uint16x8_t b_ = (b);                                             \
        uint8x8_t a_ = (a);                                              \
        uint8x16_t result = vcombine_u8                                  \
-                             (a_, vcreate_u8 (UINT64_C (0x0)));         \
+                             (a_, vcreate_u8                            \
+                                    (__AARCH64_UINT64_C (0x0)));        \
        __asm__ ("uqshrn2 %0.16b, %1.8h, #%2"                            \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -12578,7 +12594,8 @@  vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        uint32x4_t b_ = (b);                                             \
        uint16x4_t a_ = (a);                                             \
        uint16x8_t result = vcombine_u16                                 \
-                             (a_, vcreate_u16 (UINT64_C (0x0)));        \
+                             (a_, vcreate_u16                           \
+                                    (__AARCH64_UINT64_C (0x0)));        \
        __asm__ ("uqshrn2 %0.8h, %1.4s, #%2"                             \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -12592,7 +12609,8 @@  vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        uint64x2_t b_ = (b);                                             \
        uint32x2_t a_ = (a);                                             \
        uint32x4_t result = vcombine_u32                                 \
-                             (a_, vcreate_u32 (UINT64_C (0x0)));        \
+                             (a_, vcreate_u32                           \
+                                    (__AARCH64_UINT64_C (0x0)));        \
        __asm__ ("uqshrn2 %0.4s, %1.2d, #%2"                             \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -12606,7 +12624,8 @@  vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        int16x8_t b_ = (b);                                              \
        uint8x8_t a_ = (a);                                              \
        uint8x16_t result = vcombine_u8                                  \
-                             (a_, vcreate_u8 (UINT64_C (0x0)));         \
+                             (a_, vcreate_u8                            \
+                                    (__AARCH64_UINT64_C (0x0)));        \
        __asm__ ("sqshrun2 %0.16b, %1.8h, #%2"                           \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -12620,7 +12639,8 @@  vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        int32x4_t b_ = (b);                                              \
        uint16x4_t a_ = (a);                                             \
        uint16x8_t result = vcombine_u16                                 \
-                             (a_, vcreate_u16 (UINT64_C (0x0)));        \
+                             (a_, vcreate_u16                           \
+                                    (__AARCH64_UINT64_C (0x0)));        \
        __asm__ ("sqshrun2 %0.8h, %1.4s, #%2"                            \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -12634,7 +12654,8 @@  vqrdmulhq_n_s32 (int32x4_t a, int32_t b)
        int64x2_t b_ = (b);                                              \
        uint32x2_t a_ = (a);                                             \
        uint32x4_t result = vcombine_u32                                 \
-                             (a_, vcreate_u32 (UINT64_C (0x0)));        \
+                             (a_, vcreate_u32                           \
+                                    (__AARCH64_UINT64_C (0x0)));        \
        __asm__ ("sqshrun2 %0.4s, %1.2d, #%2"                            \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -13110,7 +13131,8 @@  vrev64q_u32 (uint32x4_t a)
        int16x8_t b_ = (b);                                              \
        int8x8_t a_ = (a);                                               \
        int8x16_t result = vcombine_s8                                   \
-                            (a_, vcreate_s8 (UINT64_C (0x0)));          \
+                            (a_, vcreate_s8                             \
+                                   (__AARCH64_UINT64_C (0x0)));         \
        __asm__ ("rshrn2 %0.16b,%1.8h,#%2"                               \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -13124,7 +13146,8 @@  vrev64q_u32 (uint32x4_t a)
        int32x4_t b_ = (b);                                              \
        int16x4_t a_ = (a);                                              \
        int16x8_t result = vcombine_s16                                  \
-                            (a_, vcreate_s16 (UINT64_C (0x0)));         \
+                            (a_, vcreate_s16                            \
+                                   (__AARCH64_UINT64_C (0x0)));         \
        __asm__ ("rshrn2 %0.8h,%1.4s,#%2"                                \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -13138,7 +13161,8 @@  vrev64q_u32 (uint32x4_t a)
        int64x2_t b_ = (b);                                              \
        int32x2_t a_ = (a);                                              \
        int32x4_t result = vcombine_s32                                  \
-                            (a_, vcreate_s32 (UINT64_C (0x0)));         \
+                            (a_, vcreate_s32                            \
+                                   (__AARCH64_UINT64_C (0x0)));         \
        __asm__ ("rshrn2 %0.4s,%1.2d,#%2"                                \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -13152,7 +13176,8 @@  vrev64q_u32 (uint32x4_t a)
        uint16x8_t b_ = (b);                                             \
        uint8x8_t a_ = (a);                                              \
        uint8x16_t result = vcombine_u8                                  \
-                            (a_, vcreate_u8 (UINT64_C (0x0)));          \
+                            (a_, vcreate_u8                             \
+                                   (__AARCH64_UINT64_C (0x0)));         \
        __asm__ ("rshrn2 %0.16b,%1.8h,#%2"                               \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -13166,7 +13191,8 @@  vrev64q_u32 (uint32x4_t a)
        uint32x4_t b_ = (b);                                             \
        uint16x4_t a_ = (a);                                             \
        uint16x8_t result = vcombine_u16                                 \
-                            (a_, vcreate_u16 (UINT64_C (0x0)));         \
+                            (a_, vcreate_u16                            \
+                                   (__AARCH64_UINT64_C (0x0)));         \
        __asm__ ("rshrn2 %0.8h,%1.4s,#%2"                                \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -13180,7 +13206,8 @@  vrev64q_u32 (uint32x4_t a)
        uint64x2_t b_ = (b);                                             \
        uint32x2_t a_ = (a);                                             \
        uint32x4_t result = vcombine_u32                                 \
-                            (a_, vcreate_u32 (UINT64_C (0x0)));         \
+                            (a_, vcreate_u32                            \
+                                   (__AARCH64_UINT64_C (0x0)));         \
        __asm__ ("rshrn2 %0.4s,%1.2d,#%2"                                \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -13417,7 +13444,7 @@  vrsrtsq_f64 (float64x2_t a, float64x2_t b)
 __extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
 vrsubhn_high_s16 (int8x8_t a, int16x8_t b, int16x8_t c)
 {
-  int8x16_t result = vcombine_s8 (a, vcreate_s8 (UINT64_C (0x0)));
+  int8x16_t result = vcombine_s8 (a, vcreate_s8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("rsubhn2 %0.16b, %1.8h, %2.8h"
            : "+w"(result)
            : "w"(b), "w"(c)
@@ -13428,7 +13455,7 @@  vrsubhn_high_s16 (int8x8_t a, int16x8_t b, int16x8_t c)
 __extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
 vrsubhn_high_s32 (int16x4_t a, int32x4_t b, int32x4_t c)
 {
-  int16x8_t result = vcombine_s16 (a, vcreate_s16 (UINT64_C (0x0)));
+  int16x8_t result = vcombine_s16 (a, vcreate_s16 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("rsubhn2 %0.8h, %1.4s, %2.4s"
            : "+w"(result)
            : "w"(b), "w"(c)
@@ -13439,7 +13466,7 @@  vrsubhn_high_s32 (int16x4_t a, int32x4_t b, int32x4_t c)
 __extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
 vrsubhn_high_s64 (int32x2_t a, int64x2_t b, int64x2_t c)
 {
-  int32x4_t result = vcombine_s32 (a, vcreate_s32 (UINT64_C (0x0)));
+  int32x4_t result = vcombine_s32 (a, vcreate_s32 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("rsubhn2 %0.4s, %1.2d, %2.2d"
            : "+w"(result)
            : "w"(b), "w"(c)
@@ -13450,7 +13477,7 @@  vrsubhn_high_s64 (int32x2_t a, int64x2_t b, int64x2_t c)
 __extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
 vrsubhn_high_u16 (uint8x8_t a, uint16x8_t b, uint16x8_t c)
 {
-  uint8x16_t result = vcombine_u8 (a, vcreate_u8 (UINT64_C (0x0)));
+  uint8x16_t result = vcombine_u8 (a, vcreate_u8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("rsubhn2 %0.16b, %1.8h, %2.8h"
            : "+w"(result)
            : "w"(b), "w"(c)
@@ -13461,7 +13488,7 @@  vrsubhn_high_u16 (uint8x8_t a, uint16x8_t b, uint16x8_t c)
 __extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
 vrsubhn_high_u32 (uint16x4_t a, uint32x4_t b, uint32x4_t c)
 {
-  uint16x8_t result = vcombine_u16 (a, vcreate_u16 (UINT64_C (0x0)));
+  uint16x8_t result = vcombine_u16 (a, vcreate_u16 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("rsubhn2 %0.8h, %1.4s, %2.4s"
            : "+w"(result)
            : "w"(b), "w"(c)
@@ -13472,7 +13499,7 @@  vrsubhn_high_u32 (uint16x4_t a, uint32x4_t b, uint32x4_t c)
 __extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
 vrsubhn_high_u64 (uint32x2_t a, uint64x2_t b, uint64x2_t c)
 {
-  uint32x4_t result = vcombine_u32 (a, vcreate_u32 (UINT64_C (0x0)));
+  uint32x4_t result = vcombine_u32 (a, vcreate_u32 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("rsubhn2 %0.4s, %1.2d, %2.2d"
            : "+w"(result)
            : "w"(b), "w"(c)
@@ -13864,7 +13891,8 @@  vrsubhn_u64 (uint64x2_t a, uint64x2_t b)
        int16x8_t b_ = (b);                                              \
        int8x8_t a_ = (a);                                               \
        int8x16_t result = vcombine_s8                                   \
-                            (a_, vcreate_s8 (UINT64_C (0x0)));          \
+                            (a_, vcreate_s8                             \
+                                   (__AARCH64_UINT64_C (0x0)));         \
        __asm__ ("shrn2 %0.16b,%1.8h,#%2"                                \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -13878,7 +13906,8 @@  vrsubhn_u64 (uint64x2_t a, uint64x2_t b)
        int32x4_t b_ = (b);                                              \
        int16x4_t a_ = (a);                                              \
        int16x8_t result = vcombine_s16                                  \
-                            (a_, vcreate_s16 (UINT64_C (0x0)));         \
+                            (a_, vcreate_s16                            \
+                                   (__AARCH64_UINT64_C (0x0)));         \
        __asm__ ("shrn2 %0.8h,%1.4s,#%2"                                 \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -13892,7 +13921,8 @@  vrsubhn_u64 (uint64x2_t a, uint64x2_t b)
        int64x2_t b_ = (b);                                              \
        int32x2_t a_ = (a);                                              \
        int32x4_t result = vcombine_s32                                  \
-                            (a_, vcreate_s32 (UINT64_C (0x0)));         \
+                            (a_, vcreate_s32                            \
+                                   (__AARCH64_UINT64_C (0x0)));         \
        __asm__ ("shrn2 %0.4s,%1.2d,#%2"                                 \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -13906,7 +13936,8 @@  vrsubhn_u64 (uint64x2_t a, uint64x2_t b)
        uint16x8_t b_ = (b);                                             \
        uint8x8_t a_ = (a);                                              \
        uint8x16_t result = vcombine_u8                                  \
-                            (a_, vcreate_u8 (UINT64_C (0x0)));          \
+                            (a_, vcreate_u8                             \
+                                   (__AARCH64_UINT64_C (0x0)));         \
        __asm__ ("shrn2 %0.16b,%1.8h,#%2"                                \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -13920,7 +13951,8 @@  vrsubhn_u64 (uint64x2_t a, uint64x2_t b)
        uint32x4_t b_ = (b);                                             \
        uint16x4_t a_ = (a);                                             \
        uint16x8_t result = vcombine_u16                                 \
-                            (a_, vcreate_u16 (UINT64_C (0x0)));         \
+                            (a_, vcreate_u16                            \
+                                   (__AARCH64_UINT64_C (0x0)));         \
        __asm__ ("shrn2 %0.8h,%1.4s,#%2"                                 \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -13934,7 +13966,8 @@  vrsubhn_u64 (uint64x2_t a, uint64x2_t b)
        uint64x2_t b_ = (b);                                             \
        uint32x2_t a_ = (a);                                             \
        uint32x4_t result = vcombine_u32                                 \
-                            (a_, vcreate_u32 (UINT64_C (0x0)));         \
+                            (a_, vcreate_u32                            \
+                                   (__AARCH64_UINT64_C (0x0)));         \
        __asm__ ("shrn2 %0.4s,%1.2d,#%2"                                 \
                 : "+w"(result)                                          \
                 : "w"(b_), "i"(c)                                       \
@@ -14386,7 +14419,7 @@  vrsubhn_u64 (uint64x2_t a, uint64x2_t b)
 __extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
 vsubhn_high_s16 (int8x8_t a, int16x8_t b, int16x8_t c)
 {
-  int8x16_t result = vcombine_s8 (a, vcreate_s8 (UINT64_C (0x0)));
+  int8x16_t result = vcombine_s8 (a, vcreate_s8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("subhn2 %0.16b, %1.8h, %2.8h"
            : "+w"(result)
            : "w"(b), "w"(c)
@@ -14397,7 +14430,7 @@  vsubhn_high_s16 (int8x8_t a, int16x8_t b, int16x8_t c)
 __extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
 vsubhn_high_s32 (int16x4_t a, int32x4_t b, int32x4_t c)
 {
-  int16x8_t result = vcombine_s16 (a, vcreate_s16 (UINT64_C (0x0)));
+  int16x8_t result = vcombine_s16 (a, vcreate_s16 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("subhn2 %0.8h, %1.4s, %2.4s"
            : "+w"(result)
            : "w"(b), "w"(c)
@@ -14408,7 +14441,7 @@  vsubhn_high_s32 (int16x4_t a, int32x4_t b, int32x4_t c)
 __extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
 vsubhn_high_s64 (int32x2_t a, int64x2_t b, int64x2_t c)
 {
-  int32x4_t result = vcombine_s32 (a, vcreate_s32 (UINT64_C (0x0)));
+  int32x4_t result = vcombine_s32 (a, vcreate_s32 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("subhn2 %0.4s, %1.2d, %2.2d"
            : "+w"(result)
            : "w"(b), "w"(c)
@@ -14419,7 +14452,7 @@  vsubhn_high_s64 (int32x2_t a, int64x2_t b, int64x2_t c)
 __extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
 vsubhn_high_u16 (uint8x8_t a, uint16x8_t b, uint16x8_t c)
 {
-  uint8x16_t result = vcombine_u8 (a, vcreate_u8 (UINT64_C (0x0)));
+  uint8x16_t result = vcombine_u8 (a, vcreate_u8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("subhn2 %0.16b, %1.8h, %2.8h"
            : "+w"(result)
            : "w"(b), "w"(c)
@@ -14430,7 +14463,7 @@  vsubhn_high_u16 (uint8x8_t a, uint16x8_t b, uint16x8_t c)
 __extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
 vsubhn_high_u32 (uint16x4_t a, uint32x4_t b, uint32x4_t c)
 {
-  uint16x8_t result = vcombine_u16 (a, vcreate_u16 (UINT64_C (0x0)));
+  uint16x8_t result = vcombine_u16 (a, vcreate_u16 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("subhn2 %0.8h, %1.4s, %2.4s"
            : "+w"(result)
            : "w"(b), "w"(c)
@@ -14441,7 +14474,7 @@  vsubhn_high_u32 (uint16x4_t a, uint32x4_t b, uint32x4_t c)
 __extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
 vsubhn_high_u64 (uint32x2_t a, uint64x2_t b, uint64x2_t c)
 {
-  uint32x4_t result = vcombine_u32 (a, vcreate_u32 (UINT64_C (0x0)));
+  uint32x4_t result = vcombine_u32 (a, vcreate_u32 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("subhn2 %0.4s, %1.2d, %2.2d"
            : "+w"(result)
            : "w"(b), "w"(c)
@@ -17039,7 +17072,7 @@  __extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
 vtbl1_s8 (int8x8_t tab, int8x8_t idx)
 {
   int8x8_t result;
-  int8x16_t temp = vcombine_s8 (tab, vcreate_s8 (UINT64_C (0x0)));
+  int8x16_t temp = vcombine_s8 (tab, vcreate_s8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("tbl %0.8b, {%1.16b}, %2.8b"
            : "=w"(result)
            : "w"(temp), "w"(idx)
@@ -17051,7 +17084,7 @@  __extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
 vtbl1_u8 (uint8x8_t tab, uint8x8_t idx)
 {
   uint8x8_t result;
-  uint8x16_t temp = vcombine_u8 (tab, vcreate_u8 (UINT64_C (0x0)));
+  uint8x16_t temp = vcombine_u8 (tab, vcreate_u8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("tbl %0.8b, {%1.16b}, %2.8b"
            : "=w"(result)
            : "w"(temp), "w"(idx)
@@ -17063,7 +17096,7 @@  __extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
 vtbl1_p8 (poly8x8_t tab, uint8x8_t idx)
 {
   poly8x8_t result;
-  poly8x16_t temp = vcombine_p8 (tab, vcreate_p8 (UINT64_C (0x0)));
+  poly8x16_t temp = vcombine_p8 (tab, vcreate_p8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("tbl %0.8b, {%1.16b}, %2.8b"
            : "=w"(result)
            : "w"(temp), "w"(idx)
@@ -17113,7 +17146,7 @@  vtbl3_s8 (int8x8x3_t tab, int8x8_t idx)
   int8x8_t result;
   int8x16x2_t temp;
   temp.val[0] = vcombine_s8 (tab.val[0], tab.val[1]);
-  temp.val[1] = vcombine_s8 (tab.val[2], vcreate_s8 (UINT64_C (0x0)));
+  temp.val[1] = vcombine_s8 (tab.val[2], vcreate_s8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("ld1 {v16.16b - v17.16b }, %1\n\t"
 	   "tbl %0.8b, {v16.16b - v17.16b}, %2.8b\n\t"
            : "=w"(result)
@@ -17128,7 +17161,7 @@  vtbl3_u8 (uint8x8x3_t tab, uint8x8_t idx)
   uint8x8_t result;
   uint8x16x2_t temp;
   temp.val[0] = vcombine_u8 (tab.val[0], tab.val[1]);
-  temp.val[1] = vcombine_u8 (tab.val[2], vcreate_u8 (UINT64_C (0x0)));
+  temp.val[1] = vcombine_u8 (tab.val[2], vcreate_u8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("ld1 {v16.16b - v17.16b }, %1\n\t"
 	   "tbl %0.8b, {v16.16b - v17.16b}, %2.8b\n\t"
            : "=w"(result)
@@ -17143,7 +17176,7 @@  vtbl3_p8 (poly8x8x3_t tab, uint8x8_t idx)
   poly8x8_t result;
   poly8x16x2_t temp;
   temp.val[0] = vcombine_p8 (tab.val[0], tab.val[1]);
-  temp.val[1] = vcombine_p8 (tab.val[2], vcreate_p8 (UINT64_C (0x0)));
+  temp.val[1] = vcombine_p8 (tab.val[2], vcreate_p8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("ld1 {v16.16b - v17.16b }, %1\n\t"
 	   "tbl %0.8b, {v16.16b - v17.16b}, %2.8b\n\t"
            : "=w"(result)
@@ -17202,7 +17235,7 @@  vtbx1_s8 (int8x8_t r, int8x8_t tab, int8x8_t idx)
 {
   int8x8_t result;
   int8x8_t tmp1;
-  int8x16_t temp = vcombine_s8 (tab, vcreate_s8 (UINT64_C (0x0)));
+  int8x16_t temp = vcombine_s8 (tab, vcreate_s8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("movi %0.8b, 8\n\t"
 	   "cmhs %0.8b, %3.8b, %0.8b\n\t"
 	   "tbl %1.8b, {%2.16b}, %3.8b\n\t"
@@ -17218,7 +17251,7 @@  vtbx1_u8 (uint8x8_t r, uint8x8_t tab, uint8x8_t idx)
 {
   uint8x8_t result;
   uint8x8_t tmp1;
-  uint8x16_t temp = vcombine_u8 (tab, vcreate_u8 (UINT64_C (0x0)));
+  uint8x16_t temp = vcombine_u8 (tab, vcreate_u8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("movi %0.8b, 8\n\t"
 	   "cmhs %0.8b, %3.8b, %0.8b\n\t"
 	   "tbl %1.8b, {%2.16b}, %3.8b\n\t"
@@ -17234,7 +17267,7 @@  vtbx1_p8 (poly8x8_t r, poly8x8_t tab, uint8x8_t idx)
 {
   poly8x8_t result;
   poly8x8_t tmp1;
-  poly8x16_t temp = vcombine_p8 (tab, vcreate_p8 (UINT64_C (0x0)));
+  poly8x16_t temp = vcombine_p8 (tab, vcreate_p8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("movi %0.8b, 8\n\t"
 	   "cmhs %0.8b, %3.8b, %0.8b\n\t"
 	   "tbl %1.8b, {%2.16b}, %3.8b\n\t"
@@ -17288,7 +17321,7 @@  vtbx3_s8 (int8x8_t r, int8x8x3_t tab, int8x8_t idx)
   int8x8_t tmp1;
   int8x16x2_t temp;
   temp.val[0] = vcombine_s8 (tab.val[0], tab.val[1]);
-  temp.val[1] = vcombine_s8 (tab.val[2], vcreate_s8 (UINT64_C (0x0)));
+  temp.val[1] = vcombine_s8 (tab.val[2], vcreate_s8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("ld1 {v16.16b - v17.16b}, %2\n\t"
 	   "movi %0.8b, 24\n\t"
 	   "cmhs %0.8b, %3.8b, %0.8b\n\t"
@@ -17307,7 +17340,7 @@  vtbx3_u8 (uint8x8_t r, uint8x8x3_t tab, uint8x8_t idx)
   uint8x8_t tmp1;
   uint8x16x2_t temp;
   temp.val[0] = vcombine_u8 (tab.val[0], tab.val[1]);
-  temp.val[1] = vcombine_u8 (tab.val[2], vcreate_u8 (UINT64_C (0x0)));
+  temp.val[1] = vcombine_u8 (tab.val[2], vcreate_u8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("ld1 {v16.16b - v17.16b}, %2\n\t"
 	   "movi %0.8b, 24\n\t"
 	   "cmhs %0.8b, %3.8b, %0.8b\n\t"
@@ -17326,7 +17359,7 @@  vtbx3_p8 (poly8x8_t r, poly8x8x3_t tab, uint8x8_t idx)
   poly8x8_t tmp1;
   poly8x16x2_t temp;
   temp.val[0] = vcombine_p8 (tab.val[0], tab.val[1]);
-  temp.val[1] = vcombine_p8 (tab.val[2], vcreate_p8 (UINT64_C (0x0)));
+  temp.val[1] = vcombine_p8 (tab.val[2], vcreate_p8 (__AARCH64_UINT64_C (0x0)));
   __asm__ ("ld1 {v16.16b - v17.16b}, %2\n\t"
 	   "movi %0.8b, 24\n\t"
 	   "cmhs %0.8b, %3.8b, %0.8b\n\t"
@@ -21448,7 +21481,7 @@  vqdmlal_high_n_s16 (int32x4_t __a, int16x8_t __b, int16_t __c)
 __extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
 vqdmlal_lane_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c, int const __d)
 {
-  int16x8_t __tmp = vcombine_s16 (__c, vcreate_s16 (INT64_C (0)));
+  int16x8_t __tmp = vcombine_s16 (__c, vcreate_s16 (__AARCH64_INT64_C (0)));
   return __builtin_aarch64_sqdmlal_lanev4hi (__a, __b, __tmp, __d);
 }
 
@@ -21499,7 +21532,7 @@  vqdmlal_high_n_s32 (int64x2_t __a, int32x4_t __b, int32_t __c)
 __extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
 vqdmlal_lane_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c, int const __d)
 {
-  int32x4_t __tmp = vcombine_s32 (__c, vcreate_s32 (INT64_C (0)));
+  int32x4_t __tmp = vcombine_s32 (__c, vcreate_s32 (__AARCH64_INT64_C (0)));
   return __builtin_aarch64_sqdmlal_lanev2si (__a, __b, __tmp, __d);
 }
 
@@ -21576,7 +21609,7 @@  vqdmlsl_high_n_s16 (int32x4_t __a, int16x8_t __b, int16_t __c)
 __extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
 vqdmlsl_lane_s16 (int32x4_t __a, int16x4_t __b, int16x4_t __c, int const __d)
 {
-  int16x8_t __tmp = vcombine_s16 (__c, vcreate_s16 (INT64_C (0)));
+  int16x8_t __tmp = vcombine_s16 (__c, vcreate_s16 (__AARCH64_INT64_C (0)));
   return __builtin_aarch64_sqdmlsl_lanev4hi (__a, __b, __tmp, __d);
 }
 
@@ -21627,7 +21660,7 @@  vqdmlsl_high_n_s32 (int64x2_t __a, int32x4_t __b, int32_t __c)
 __extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
 vqdmlsl_lane_s32 (int64x2_t __a, int32x2_t __b, int32x2_t __c, int const __d)
 {
-  int32x4_t __tmp = vcombine_s32 (__c, vcreate_s32 (INT64_C (0)));
+  int32x4_t __tmp = vcombine_s32 (__c, vcreate_s32 (__AARCH64_INT64_C (0)));
   return __builtin_aarch64_sqdmlsl_lanev2si (__a, __b, __tmp, __d);
 }
 
@@ -21752,7 +21785,7 @@  vqdmull_high_n_s16 (int16x8_t __a, int16_t __b)
 __extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
 vqdmull_lane_s16 (int16x4_t __a, int16x4_t __b, int const __c)
 {
-  int16x8_t __tmp = vcombine_s16 (__b, vcreate_s16 (INT64_C (0)));
+  int16x8_t __tmp = vcombine_s16 (__b, vcreate_s16 (__AARCH64_INT64_C (0)));
   return __builtin_aarch64_sqdmull_lanev4hi (__a, __tmp, __c);
 }
 
@@ -21801,7 +21834,7 @@  vqdmull_high_n_s32 (int32x4_t __a, int32_t __b)
 __extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
 vqdmull_lane_s32 (int32x2_t __a, int32x2_t __b, int const __c)
 {
-  int32x4_t __tmp = vcombine_s32 (__b, vcreate_s32 (INT64_C (0)));
+  int32x4_t __tmp = vcombine_s32 (__b, vcreate_s32 (__AARCH64_INT64_C (0)));
   return __builtin_aarch64_sqdmull_lanev2si (__a, __tmp, __c);
 }
 
@@ -24388,8 +24421,8 @@  vst2_s64 (int64_t * __a, int64x1x2_t val)
 {
   __builtin_aarch64_simd_oi __o;
   int64x2x2_t temp;
-  temp.val[0] = vcombine_s64 (val.val[0], vcreate_s64 (INT64_C (0)));
-  temp.val[1] = vcombine_s64 (val.val[1], vcreate_s64 (INT64_C (0)));
+  temp.val[0] = vcombine_s64 (val.val[0], vcreate_s64 (__AARCH64_INT64_C (0)));
+  temp.val[1] = vcombine_s64 (val.val[1], vcreate_s64 (__AARCH64_INT64_C (0)));
   __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) temp.val[1], 1);
   __builtin_aarch64_st2di ((__builtin_aarch64_simd_di *) __a, __o);
@@ -24400,8 +24433,8 @@  vst2_u64 (uint64_t * __a, uint64x1x2_t val)
 {
   __builtin_aarch64_simd_oi __o;
   uint64x2x2_t temp;
-  temp.val[0] = vcombine_u64 (val.val[0], vcreate_u64 (UINT64_C (0)));
-  temp.val[1] = vcombine_u64 (val.val[1], vcreate_u64 (UINT64_C (0)));
+  temp.val[0] = vcombine_u64 (val.val[0], vcreate_u64 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_u64 (val.val[1], vcreate_u64 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregoiv2di (__o, (int64x2_t) temp.val[1], 1);
   __builtin_aarch64_st2di ((__builtin_aarch64_simd_di *) __a, __o);
@@ -24412,8 +24445,8 @@  vst2_f64 (float64_t * __a, float64x1x2_t val)
 {
   __builtin_aarch64_simd_oi __o;
   float64x2x2_t temp;
-  temp.val[0] = vcombine_f64 (val.val[0], vcreate_f64 (UINT64_C (0)));
-  temp.val[1] = vcombine_f64 (val.val[1], vcreate_f64 (UINT64_C (0)));
+  temp.val[0] = vcombine_f64 (val.val[0], vcreate_f64 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_f64 (val.val[1], vcreate_f64 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregoiv2df (__o, (float64x2_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregoiv2df (__o, (float64x2_t) temp.val[1], 1);
   __builtin_aarch64_st2df ((__builtin_aarch64_simd_df *) __a, __o);
@@ -24424,8 +24457,8 @@  vst2_s8 (int8_t * __a, int8x8x2_t val)
 {
   __builtin_aarch64_simd_oi __o;
   int8x16x2_t temp;
-  temp.val[0] = vcombine_s8 (val.val[0], vcreate_s8 (INT64_C (0)));
-  temp.val[1] = vcombine_s8 (val.val[1], vcreate_s8 (INT64_C (0)));
+  temp.val[0] = vcombine_s8 (val.val[0], vcreate_s8 (__AARCH64_INT64_C (0)));
+  temp.val[1] = vcombine_s8 (val.val[1], vcreate_s8 (__AARCH64_INT64_C (0)));
   __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) temp.val[1], 1);
   __builtin_aarch64_st2v8qi ((__builtin_aarch64_simd_qi *) __a, __o);
@@ -24436,8 +24469,8 @@  vst2_p8 (poly8_t * __a, poly8x8x2_t val)
 {
   __builtin_aarch64_simd_oi __o;
   poly8x16x2_t temp;
-  temp.val[0] = vcombine_p8 (val.val[0], vcreate_p8 (UINT64_C (0)));
-  temp.val[1] = vcombine_p8 (val.val[1], vcreate_p8 (UINT64_C (0)));
+  temp.val[0] = vcombine_p8 (val.val[0], vcreate_p8 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_p8 (val.val[1], vcreate_p8 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) temp.val[1], 1);
   __builtin_aarch64_st2v8qi ((__builtin_aarch64_simd_qi *) __a, __o);
@@ -24448,8 +24481,8 @@  vst2_s16 (int16_t * __a, int16x4x2_t val)
 {
   __builtin_aarch64_simd_oi __o;
   int16x8x2_t temp;
-  temp.val[0] = vcombine_s16 (val.val[0], vcreate_s16 (INT64_C (0)));
-  temp.val[1] = vcombine_s16 (val.val[1], vcreate_s16 (INT64_C (0)));
+  temp.val[0] = vcombine_s16 (val.val[0], vcreate_s16 (__AARCH64_INT64_C (0)));
+  temp.val[1] = vcombine_s16 (val.val[1], vcreate_s16 (__AARCH64_INT64_C (0)));
   __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) temp.val[1], 1);
   __builtin_aarch64_st2v4hi ((__builtin_aarch64_simd_hi *) __a, __o);
@@ -24460,8 +24493,8 @@  vst2_p16 (poly16_t * __a, poly16x4x2_t val)
 {
   __builtin_aarch64_simd_oi __o;
   poly16x8x2_t temp;
-  temp.val[0] = vcombine_p16 (val.val[0], vcreate_p16 (UINT64_C (0)));
-  temp.val[1] = vcombine_p16 (val.val[1], vcreate_p16 (UINT64_C (0)));
+  temp.val[0] = vcombine_p16 (val.val[0], vcreate_p16 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_p16 (val.val[1], vcreate_p16 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) temp.val[1], 1);
   __builtin_aarch64_st2v4hi ((__builtin_aarch64_simd_hi *) __a, __o);
@@ -24472,8 +24505,8 @@  vst2_s32 (int32_t * __a, int32x2x2_t val)
 {
   __builtin_aarch64_simd_oi __o;
   int32x4x2_t temp;
-  temp.val[0] = vcombine_s32 (val.val[0], vcreate_s32 (INT64_C (0)));
-  temp.val[1] = vcombine_s32 (val.val[1], vcreate_s32 (INT64_C (0)));
+  temp.val[0] = vcombine_s32 (val.val[0], vcreate_s32 (__AARCH64_INT64_C (0)));
+  temp.val[1] = vcombine_s32 (val.val[1], vcreate_s32 (__AARCH64_INT64_C (0)));
   __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) temp.val[1], 1);
   __builtin_aarch64_st2v2si ((__builtin_aarch64_simd_si *) __a, __o);
@@ -24484,8 +24517,8 @@  vst2_u8 (uint8_t * __a, uint8x8x2_t val)
 {
   __builtin_aarch64_simd_oi __o;
   uint8x16x2_t temp;
-  temp.val[0] = vcombine_u8 (val.val[0], vcreate_u8 (UINT64_C (0)));
-  temp.val[1] = vcombine_u8 (val.val[1], vcreate_u8 (UINT64_C (0)));
+  temp.val[0] = vcombine_u8 (val.val[0], vcreate_u8 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_u8 (val.val[1], vcreate_u8 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregoiv16qi (__o, (int8x16_t) temp.val[1], 1);
   __builtin_aarch64_st2v8qi ((__builtin_aarch64_simd_qi *) __a, __o);
@@ -24496,8 +24529,8 @@  vst2_u16 (uint16_t * __a, uint16x4x2_t val)
 {
   __builtin_aarch64_simd_oi __o;
   uint16x8x2_t temp;
-  temp.val[0] = vcombine_u16 (val.val[0], vcreate_u16 (UINT64_C (0)));
-  temp.val[1] = vcombine_u16 (val.val[1], vcreate_u16 (UINT64_C (0)));
+  temp.val[0] = vcombine_u16 (val.val[0], vcreate_u16 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_u16 (val.val[1], vcreate_u16 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregoiv8hi (__o, (int16x8_t) temp.val[1], 1);
   __builtin_aarch64_st2v4hi ((__builtin_aarch64_simd_hi *) __a, __o);
@@ -24508,8 +24541,8 @@  vst2_u32 (uint32_t * __a, uint32x2x2_t val)
 {
   __builtin_aarch64_simd_oi __o;
   uint32x4x2_t temp;
-  temp.val[0] = vcombine_u32 (val.val[0], vcreate_u32 (UINT64_C (0)));
-  temp.val[1] = vcombine_u32 (val.val[1], vcreate_u32 (UINT64_C (0)));
+  temp.val[0] = vcombine_u32 (val.val[0], vcreate_u32 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_u32 (val.val[1], vcreate_u32 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregoiv4si (__o, (int32x4_t) temp.val[1], 1);
   __builtin_aarch64_st2v2si ((__builtin_aarch64_simd_si *) __a, __o);
@@ -24520,8 +24553,8 @@  vst2_f32 (float32_t * __a, float32x2x2_t val)
 {
   __builtin_aarch64_simd_oi __o;
   float32x4x2_t temp;
-  temp.val[0] = vcombine_f32 (val.val[0], vcreate_f32 (UINT64_C (0)));
-  temp.val[1] = vcombine_f32 (val.val[1], vcreate_f32 (UINT64_C (0)));
+  temp.val[0] = vcombine_f32 (val.val[0], vcreate_f32 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_f32 (val.val[1], vcreate_f32 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregoiv4sf (__o, (float32x4_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregoiv4sf (__o, (float32x4_t) temp.val[1], 1);
   __builtin_aarch64_st2v2sf ((__builtin_aarch64_simd_sf *) __a, __o);
@@ -24640,9 +24673,9 @@  vst3_s64 (int64_t * __a, int64x1x3_t val)
 {
   __builtin_aarch64_simd_ci __o;
   int64x2x3_t temp;
-  temp.val[0] = vcombine_s64 (val.val[0], vcreate_s64 (INT64_C (0)));
-  temp.val[1] = vcombine_s64 (val.val[1], vcreate_s64 (INT64_C (0)));
-  temp.val[2] = vcombine_s64 (val.val[2], vcreate_s64 (INT64_C (0)));
+  temp.val[0] = vcombine_s64 (val.val[0], vcreate_s64 (__AARCH64_INT64_C (0)));
+  temp.val[1] = vcombine_s64 (val.val[1], vcreate_s64 (__AARCH64_INT64_C (0)));
+  temp.val[2] = vcombine_s64 (val.val[2], vcreate_s64 (__AARCH64_INT64_C (0)));
   __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) temp.val[2], 2);
@@ -24654,9 +24687,9 @@  vst3_u64 (uint64_t * __a, uint64x1x3_t val)
 {
   __builtin_aarch64_simd_ci __o;
   uint64x2x3_t temp;
-  temp.val[0] = vcombine_u64 (val.val[0], vcreate_u64 (UINT64_C (0)));
-  temp.val[1] = vcombine_u64 (val.val[1], vcreate_u64 (UINT64_C (0)));
-  temp.val[2] = vcombine_u64 (val.val[2], vcreate_u64 (UINT64_C (0)));
+  temp.val[0] = vcombine_u64 (val.val[0], vcreate_u64 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_u64 (val.val[1], vcreate_u64 (__AARCH64_UINT64_C (0)));
+  temp.val[2] = vcombine_u64 (val.val[2], vcreate_u64 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregciv2di (__o, (int64x2_t) temp.val[2], 2);
@@ -24668,9 +24701,9 @@  vst3_f64 (float64_t * __a, float64x1x3_t val)
 {
   __builtin_aarch64_simd_ci __o;
   float64x2x3_t temp;
-  temp.val[0] = vcombine_f64 (val.val[0], vcreate_f64 (UINT64_C (0)));
-  temp.val[1] = vcombine_f64 (val.val[1], vcreate_f64 (UINT64_C (0)));
-  temp.val[2] = vcombine_f64 (val.val[2], vcreate_f64 (UINT64_C (0)));
+  temp.val[0] = vcombine_f64 (val.val[0], vcreate_f64 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_f64 (val.val[1], vcreate_f64 (__AARCH64_UINT64_C (0)));
+  temp.val[2] = vcombine_f64 (val.val[2], vcreate_f64 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregciv2df (__o, (float64x2_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregciv2df (__o, (float64x2_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregciv2df (__o, (float64x2_t) temp.val[2], 2);
@@ -24682,9 +24715,9 @@  vst3_s8 (int8_t * __a, int8x8x3_t val)
 {
   __builtin_aarch64_simd_ci __o;
   int8x16x3_t temp;
-  temp.val[0] = vcombine_s8 (val.val[0], vcreate_s8 (INT64_C (0)));
-  temp.val[1] = vcombine_s8 (val.val[1], vcreate_s8 (INT64_C (0)));
-  temp.val[2] = vcombine_s8 (val.val[2], vcreate_s8 (INT64_C (0)));
+  temp.val[0] = vcombine_s8 (val.val[0], vcreate_s8 (__AARCH64_INT64_C (0)));
+  temp.val[1] = vcombine_s8 (val.val[1], vcreate_s8 (__AARCH64_INT64_C (0)));
+  temp.val[2] = vcombine_s8 (val.val[2], vcreate_s8 (__AARCH64_INT64_C (0)));
   __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[2], 2);
@@ -24696,9 +24729,9 @@  vst3_p8 (poly8_t * __a, poly8x8x3_t val)
 {
   __builtin_aarch64_simd_ci __o;
   poly8x16x3_t temp;
-  temp.val[0] = vcombine_p8 (val.val[0], vcreate_p8 (UINT64_C (0)));
-  temp.val[1] = vcombine_p8 (val.val[1], vcreate_p8 (UINT64_C (0)));
-  temp.val[2] = vcombine_p8 (val.val[2], vcreate_p8 (UINT64_C (0)));
+  temp.val[0] = vcombine_p8 (val.val[0], vcreate_p8 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_p8 (val.val[1], vcreate_p8 (__AARCH64_UINT64_C (0)));
+  temp.val[2] = vcombine_p8 (val.val[2], vcreate_p8 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[2], 2);
@@ -24710,9 +24743,9 @@  vst3_s16 (int16_t * __a, int16x4x3_t val)
 {
   __builtin_aarch64_simd_ci __o;
   int16x8x3_t temp;
-  temp.val[0] = vcombine_s16 (val.val[0], vcreate_s16 (INT64_C (0)));
-  temp.val[1] = vcombine_s16 (val.val[1], vcreate_s16 (INT64_C (0)));
-  temp.val[2] = vcombine_s16 (val.val[2], vcreate_s16 (INT64_C (0)));
+  temp.val[0] = vcombine_s16 (val.val[0], vcreate_s16 (__AARCH64_INT64_C (0)));
+  temp.val[1] = vcombine_s16 (val.val[1], vcreate_s16 (__AARCH64_INT64_C (0)));
+  temp.val[2] = vcombine_s16 (val.val[2], vcreate_s16 (__AARCH64_INT64_C (0)));
   __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[2], 2);
@@ -24724,9 +24757,9 @@  vst3_p16 (poly16_t * __a, poly16x4x3_t val)
 {
   __builtin_aarch64_simd_ci __o;
   poly16x8x3_t temp;
-  temp.val[0] = vcombine_p16 (val.val[0], vcreate_p16 (UINT64_C (0)));
-  temp.val[1] = vcombine_p16 (val.val[1], vcreate_p16 (UINT64_C (0)));
-  temp.val[2] = vcombine_p16 (val.val[2], vcreate_p16 (UINT64_C (0)));
+  temp.val[0] = vcombine_p16 (val.val[0], vcreate_p16 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_p16 (val.val[1], vcreate_p16 (__AARCH64_UINT64_C (0)));
+  temp.val[2] = vcombine_p16 (val.val[2], vcreate_p16 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[2], 2);
@@ -24738,9 +24771,9 @@  vst3_s32 (int32_t * __a, int32x2x3_t val)
 {
   __builtin_aarch64_simd_ci __o;
   int32x4x3_t temp;
-  temp.val[0] = vcombine_s32 (val.val[0], vcreate_s32 (INT64_C (0)));
-  temp.val[1] = vcombine_s32 (val.val[1], vcreate_s32 (INT64_C (0)));
-  temp.val[2] = vcombine_s32 (val.val[2], vcreate_s32 (INT64_C (0)));
+  temp.val[0] = vcombine_s32 (val.val[0], vcreate_s32 (__AARCH64_INT64_C (0)));
+  temp.val[1] = vcombine_s32 (val.val[1], vcreate_s32 (__AARCH64_INT64_C (0)));
+  temp.val[2] = vcombine_s32 (val.val[2], vcreate_s32 (__AARCH64_INT64_C (0)));
   __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) temp.val[2], 2);
@@ -24752,9 +24785,9 @@  vst3_u8 (uint8_t * __a, uint8x8x3_t val)
 {
   __builtin_aarch64_simd_ci __o;
   uint8x16x3_t temp;
-  temp.val[0] = vcombine_u8 (val.val[0], vcreate_u8 (UINT64_C (0)));
-  temp.val[1] = vcombine_u8 (val.val[1], vcreate_u8 (UINT64_C (0)));
-  temp.val[2] = vcombine_u8 (val.val[2], vcreate_u8 (UINT64_C (0)));
+  temp.val[0] = vcombine_u8 (val.val[0], vcreate_u8 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_u8 (val.val[1], vcreate_u8 (__AARCH64_UINT64_C (0)));
+  temp.val[2] = vcombine_u8 (val.val[2], vcreate_u8 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregciv16qi (__o, (int8x16_t) temp.val[2], 2);
@@ -24766,9 +24799,9 @@  vst3_u16 (uint16_t * __a, uint16x4x3_t val)
 {
   __builtin_aarch64_simd_ci __o;
   uint16x8x3_t temp;
-  temp.val[0] = vcombine_u16 (val.val[0], vcreate_u16 (UINT64_C (0)));
-  temp.val[1] = vcombine_u16 (val.val[1], vcreate_u16 (UINT64_C (0)));
-  temp.val[2] = vcombine_u16 (val.val[2], vcreate_u16 (UINT64_C (0)));
+  temp.val[0] = vcombine_u16 (val.val[0], vcreate_u16 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_u16 (val.val[1], vcreate_u16 (__AARCH64_UINT64_C (0)));
+  temp.val[2] = vcombine_u16 (val.val[2], vcreate_u16 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregciv8hi (__o, (int16x8_t) temp.val[2], 2);
@@ -24780,9 +24813,9 @@  vst3_u32 (uint32_t * __a, uint32x2x3_t val)
 {
   __builtin_aarch64_simd_ci __o;
   uint32x4x3_t temp;
-  temp.val[0] = vcombine_u32 (val.val[0], vcreate_u32 (UINT64_C (0)));
-  temp.val[1] = vcombine_u32 (val.val[1], vcreate_u32 (UINT64_C (0)));
-  temp.val[2] = vcombine_u32 (val.val[2], vcreate_u32 (UINT64_C (0)));
+  temp.val[0] = vcombine_u32 (val.val[0], vcreate_u32 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_u32 (val.val[1], vcreate_u32 (__AARCH64_UINT64_C (0)));
+  temp.val[2] = vcombine_u32 (val.val[2], vcreate_u32 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregciv4si (__o, (int32x4_t) temp.val[2], 2);
@@ -24794,9 +24827,9 @@  vst3_f32 (float32_t * __a, float32x2x3_t val)
 {
   __builtin_aarch64_simd_ci __o;
   float32x4x3_t temp;
-  temp.val[0] = vcombine_f32 (val.val[0], vcreate_f32 (UINT64_C (0)));
-  temp.val[1] = vcombine_f32 (val.val[1], vcreate_f32 (UINT64_C (0)));
-  temp.val[2] = vcombine_f32 (val.val[2], vcreate_f32 (UINT64_C (0)));
+  temp.val[0] = vcombine_f32 (val.val[0], vcreate_f32 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_f32 (val.val[1], vcreate_f32 (__AARCH64_UINT64_C (0)));
+  temp.val[2] = vcombine_f32 (val.val[2], vcreate_f32 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregciv4sf (__o, (float32x4_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregciv4sf (__o, (float32x4_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregciv4sf (__o, (float32x4_t) temp.val[2], 2);
@@ -24928,10 +24961,10 @@  vst4_s64 (int64_t * __a, int64x1x4_t val)
 {
   __builtin_aarch64_simd_xi __o;
   int64x2x4_t temp;
-  temp.val[0] = vcombine_s64 (val.val[0], vcreate_s64 (INT64_C (0)));
-  temp.val[1] = vcombine_s64 (val.val[1], vcreate_s64 (INT64_C (0)));
-  temp.val[2] = vcombine_s64 (val.val[2], vcreate_s64 (INT64_C (0)));
-  temp.val[3] = vcombine_s64 (val.val[3], vcreate_s64 (INT64_C (0)));
+  temp.val[0] = vcombine_s64 (val.val[0], vcreate_s64 (__AARCH64_INT64_C (0)));
+  temp.val[1] = vcombine_s64 (val.val[1], vcreate_s64 (__AARCH64_INT64_C (0)));
+  temp.val[2] = vcombine_s64 (val.val[2], vcreate_s64 (__AARCH64_INT64_C (0)));
+  temp.val[3] = vcombine_s64 (val.val[3], vcreate_s64 (__AARCH64_INT64_C (0)));
   __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[2], 2);
@@ -24944,10 +24977,10 @@  vst4_u64 (uint64_t * __a, uint64x1x4_t val)
 {
   __builtin_aarch64_simd_xi __o;
   uint64x2x4_t temp;
-  temp.val[0] = vcombine_u64 (val.val[0], vcreate_u64 (UINT64_C (0)));
-  temp.val[1] = vcombine_u64 (val.val[1], vcreate_u64 (UINT64_C (0)));
-  temp.val[2] = vcombine_u64 (val.val[2], vcreate_u64 (UINT64_C (0)));
-  temp.val[3] = vcombine_u64 (val.val[3], vcreate_u64 (UINT64_C (0)));
+  temp.val[0] = vcombine_u64 (val.val[0], vcreate_u64 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_u64 (val.val[1], vcreate_u64 (__AARCH64_UINT64_C (0)));
+  temp.val[2] = vcombine_u64 (val.val[2], vcreate_u64 (__AARCH64_UINT64_C (0)));
+  temp.val[3] = vcombine_u64 (val.val[3], vcreate_u64 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) temp.val[2], 2);
@@ -24960,10 +24993,10 @@  vst4_f64 (float64_t * __a, float64x1x4_t val)
 {
   __builtin_aarch64_simd_xi __o;
   float64x2x4_t temp;
-  temp.val[0] = vcombine_f64 (val.val[0], vcreate_f64 (UINT64_C (0)));
-  temp.val[1] = vcombine_f64 (val.val[1], vcreate_f64 (UINT64_C (0)));
-  temp.val[2] = vcombine_f64 (val.val[2], vcreate_f64 (UINT64_C (0)));
-  temp.val[3] = vcombine_f64 (val.val[3], vcreate_f64 (UINT64_C (0)));
+  temp.val[0] = vcombine_f64 (val.val[0], vcreate_f64 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_f64 (val.val[1], vcreate_f64 (__AARCH64_UINT64_C (0)));
+  temp.val[2] = vcombine_f64 (val.val[2], vcreate_f64 (__AARCH64_UINT64_C (0)));
+  temp.val[3] = vcombine_f64 (val.val[3], vcreate_f64 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) temp.val[2], 2);
@@ -24976,10 +25009,10 @@  vst4_s8 (int8_t * __a, int8x8x4_t val)
 {
   __builtin_aarch64_simd_xi __o;
   int8x16x4_t temp;
-  temp.val[0] = vcombine_s8 (val.val[0], vcreate_s8 (INT64_C (0)));
-  temp.val[1] = vcombine_s8 (val.val[1], vcreate_s8 (INT64_C (0)));
-  temp.val[2] = vcombine_s8 (val.val[2], vcreate_s8 (INT64_C (0)));
-  temp.val[3] = vcombine_s8 (val.val[3], vcreate_s8 (INT64_C (0)));
+  temp.val[0] = vcombine_s8 (val.val[0], vcreate_s8 (__AARCH64_INT64_C (0)));
+  temp.val[1] = vcombine_s8 (val.val[1], vcreate_s8 (__AARCH64_INT64_C (0)));
+  temp.val[2] = vcombine_s8 (val.val[2], vcreate_s8 (__AARCH64_INT64_C (0)));
+  temp.val[3] = vcombine_s8 (val.val[3], vcreate_s8 (__AARCH64_INT64_C (0)));
   __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[2], 2);
@@ -24992,10 +25025,10 @@  vst4_p8 (poly8_t * __a, poly8x8x4_t val)
 {
   __builtin_aarch64_simd_xi __o;
   poly8x16x4_t temp;
-  temp.val[0] = vcombine_p8 (val.val[0], vcreate_p8 (UINT64_C (0)));
-  temp.val[1] = vcombine_p8 (val.val[1], vcreate_p8 (UINT64_C (0)));
-  temp.val[2] = vcombine_p8 (val.val[2], vcreate_p8 (UINT64_C (0)));
-  temp.val[3] = vcombine_p8 (val.val[3], vcreate_p8 (UINT64_C (0)));
+  temp.val[0] = vcombine_p8 (val.val[0], vcreate_p8 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_p8 (val.val[1], vcreate_p8 (__AARCH64_UINT64_C (0)));
+  temp.val[2] = vcombine_p8 (val.val[2], vcreate_p8 (__AARCH64_UINT64_C (0)));
+  temp.val[3] = vcombine_p8 (val.val[3], vcreate_p8 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[2], 2);
@@ -25008,10 +25041,10 @@  vst4_s16 (int16_t * __a, int16x4x4_t val)
 {
   __builtin_aarch64_simd_xi __o;
   int16x8x4_t temp;
-  temp.val[0] = vcombine_s16 (val.val[0], vcreate_s16 (INT64_C (0)));
-  temp.val[1] = vcombine_s16 (val.val[1], vcreate_s16 (INT64_C (0)));
-  temp.val[2] = vcombine_s16 (val.val[2], vcreate_s16 (INT64_C (0)));
-  temp.val[3] = vcombine_s16 (val.val[3], vcreate_s16 (INT64_C (0)));
+  temp.val[0] = vcombine_s16 (val.val[0], vcreate_s16 (__AARCH64_INT64_C (0)));
+  temp.val[1] = vcombine_s16 (val.val[1], vcreate_s16 (__AARCH64_INT64_C (0)));
+  temp.val[2] = vcombine_s16 (val.val[2], vcreate_s16 (__AARCH64_INT64_C (0)));
+  temp.val[3] = vcombine_s16 (val.val[3], vcreate_s16 (__AARCH64_INT64_C (0)));
   __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[2], 2);
@@ -25024,10 +25057,10 @@  vst4_p16 (poly16_t * __a, poly16x4x4_t val)
 {
   __builtin_aarch64_simd_xi __o;
   poly16x8x4_t temp;
-  temp.val[0] = vcombine_p16 (val.val[0], vcreate_p16 (UINT64_C (0)));
-  temp.val[1] = vcombine_p16 (val.val[1], vcreate_p16 (UINT64_C (0)));
-  temp.val[2] = vcombine_p16 (val.val[2], vcreate_p16 (UINT64_C (0)));
-  temp.val[3] = vcombine_p16 (val.val[3], vcreate_p16 (UINT64_C (0)));
+  temp.val[0] = vcombine_p16 (val.val[0], vcreate_p16 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_p16 (val.val[1], vcreate_p16 (__AARCH64_UINT64_C (0)));
+  temp.val[2] = vcombine_p16 (val.val[2], vcreate_p16 (__AARCH64_UINT64_C (0)));
+  temp.val[3] = vcombine_p16 (val.val[3], vcreate_p16 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[2], 2);
@@ -25040,10 +25073,10 @@  vst4_s32 (int32_t * __a, int32x2x4_t val)
 {
   __builtin_aarch64_simd_xi __o;
   int32x4x4_t temp;
-  temp.val[0] = vcombine_s32 (val.val[0], vcreate_s32 (INT64_C (0)));
-  temp.val[1] = vcombine_s32 (val.val[1], vcreate_s32 (INT64_C (0)));
-  temp.val[2] = vcombine_s32 (val.val[2], vcreate_s32 (INT64_C (0)));
-  temp.val[3] = vcombine_s32 (val.val[3], vcreate_s32 (INT64_C (0)));
+  temp.val[0] = vcombine_s32 (val.val[0], vcreate_s32 (__AARCH64_INT64_C (0)));
+  temp.val[1] = vcombine_s32 (val.val[1], vcreate_s32 (__AARCH64_INT64_C (0)));
+  temp.val[2] = vcombine_s32 (val.val[2], vcreate_s32 (__AARCH64_INT64_C (0)));
+  temp.val[3] = vcombine_s32 (val.val[3], vcreate_s32 (__AARCH64_INT64_C (0)));
   __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[2], 2);
@@ -25056,10 +25089,10 @@  vst4_u8 (uint8_t * __a, uint8x8x4_t val)
 {
   __builtin_aarch64_simd_xi __o;
   uint8x16x4_t temp;
-  temp.val[0] = vcombine_u8 (val.val[0], vcreate_u8 (UINT64_C (0)));
-  temp.val[1] = vcombine_u8 (val.val[1], vcreate_u8 (UINT64_C (0)));
-  temp.val[2] = vcombine_u8 (val.val[2], vcreate_u8 (UINT64_C (0)));
-  temp.val[3] = vcombine_u8 (val.val[3], vcreate_u8 (UINT64_C (0)));
+  temp.val[0] = vcombine_u8 (val.val[0], vcreate_u8 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_u8 (val.val[1], vcreate_u8 (__AARCH64_UINT64_C (0)));
+  temp.val[2] = vcombine_u8 (val.val[2], vcreate_u8 (__AARCH64_UINT64_C (0)));
+  temp.val[3] = vcombine_u8 (val.val[3], vcreate_u8 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) temp.val[2], 2);
@@ -25072,10 +25105,10 @@  vst4_u16 (uint16_t * __a, uint16x4x4_t val)
 {
   __builtin_aarch64_simd_xi __o;
   uint16x8x4_t temp;
-  temp.val[0] = vcombine_u16 (val.val[0], vcreate_u16 (UINT64_C (0)));
-  temp.val[1] = vcombine_u16 (val.val[1], vcreate_u16 (UINT64_C (0)));
-  temp.val[2] = vcombine_u16 (val.val[2], vcreate_u16 (UINT64_C (0)));
-  temp.val[3] = vcombine_u16 (val.val[3], vcreate_u16 (UINT64_C (0)));
+  temp.val[0] = vcombine_u16 (val.val[0], vcreate_u16 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_u16 (val.val[1], vcreate_u16 (__AARCH64_UINT64_C (0)));
+  temp.val[2] = vcombine_u16 (val.val[2], vcreate_u16 (__AARCH64_UINT64_C (0)));
+  temp.val[3] = vcombine_u16 (val.val[3], vcreate_u16 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) temp.val[2], 2);
@@ -25088,10 +25121,10 @@  vst4_u32 (uint32_t * __a, uint32x2x4_t val)
 {
   __builtin_aarch64_simd_xi __o;
   uint32x4x4_t temp;
-  temp.val[0] = vcombine_u32 (val.val[0], vcreate_u32 (UINT64_C (0)));
-  temp.val[1] = vcombine_u32 (val.val[1], vcreate_u32 (UINT64_C (0)));
-  temp.val[2] = vcombine_u32 (val.val[2], vcreate_u32 (UINT64_C (0)));
-  temp.val[3] = vcombine_u32 (val.val[3], vcreate_u32 (UINT64_C (0)));
+  temp.val[0] = vcombine_u32 (val.val[0], vcreate_u32 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_u32 (val.val[1], vcreate_u32 (__AARCH64_UINT64_C (0)));
+  temp.val[2] = vcombine_u32 (val.val[2], vcreate_u32 (__AARCH64_UINT64_C (0)));
+  temp.val[3] = vcombine_u32 (val.val[3], vcreate_u32 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) temp.val[2], 2);
@@ -25104,10 +25137,10 @@  vst4_f32 (float32_t * __a, float32x2x4_t val)
 {
   __builtin_aarch64_simd_xi __o;
   float32x4x4_t temp;
-  temp.val[0] = vcombine_f32 (val.val[0], vcreate_f32 (UINT64_C (0)));
-  temp.val[1] = vcombine_f32 (val.val[1], vcreate_f32 (UINT64_C (0)));
-  temp.val[2] = vcombine_f32 (val.val[2], vcreate_f32 (UINT64_C (0)));
-  temp.val[3] = vcombine_f32 (val.val[3], vcreate_f32 (UINT64_C (0)));
+  temp.val[0] = vcombine_f32 (val.val[0], vcreate_f32 (__AARCH64_UINT64_C (0)));
+  temp.val[1] = vcombine_f32 (val.val[1], vcreate_f32 (__AARCH64_UINT64_C (0)));
+  temp.val[2] = vcombine_f32 (val.val[2], vcreate_f32 (__AARCH64_UINT64_C (0)));
+  temp.val[3] = vcombine_f32 (val.val[3], vcreate_f32 (__AARCH64_UINT64_C (0)));
   __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) temp.val[0], 0);
   __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) temp.val[1], 1);
   __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) temp.val[2], 2);