Skip to content

R
riscv-gcc-1
Commit 8b2ea410 by James Greenhalgh Committed by James Greenhalgh
Options

[AARCH64] Make argument of ld1 intrinsics const. 

gcc/
	* config/aarch64/arm_neon.h (vld1_dup_*): Make argument const.
	(vld1q_dup_*): Likewise.
	(vld1_*): Likewise.
	(vld1q_*): Likewise.
	(vld1_lane_*): Likewise.
	(vld1q_lane_*): Likewise.

From-SVN: r194974
parent 9713d329
Showing with 81 additions and 72 deletions
gcc/ChangeLog
2013-01-07 James Greenhalgh <james.greenhalgh@arm.com>
* config/aarch64/arm_neon.h (vld1_dup_*): Make argument const.
(vld1q_dup_*): Likewise.
(vld1_*): Likewise.
(vld1q_*): Likewise.
(vld1_lane_*): Likewise.
(vld1q_lane_*): Likewise.
2013-01-07 Richard Biener <rguenther@suse.de> 2013-01-07 Richard Biener <rguenther@suse.de>
* lto-streamer.h (LTO_minor_version): Bump to 2. * lto-streamer.h (LTO_minor_version): Bump to 2.
......
gcc/config/aarch64/arm_neon.h
...@@ -8387,7 +8387,7 @@ vhsubq_u32 (uint32x4_t a, uint32x4_t b) ...@@ -8387,7 +8387,7 @@ vhsubq_u32 (uint32x4_t a, uint32x4_t b)
} }
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) __extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vld1_dup_f32 (float32_t * a) vld1_dup_f32 (const float32_t * a)
{ {
float32x2_t result; float32x2_t result;
__asm__ ("ld1r {%0.2s},[%1]" __asm__ ("ld1r {%0.2s},[%1]"
...@@ -8398,7 +8398,7 @@ vld1_dup_f32 (float32_t * a) ...@@ -8398,7 +8398,7 @@ vld1_dup_f32 (float32_t * a)
} }
__extension__ static __inline float64x1_t __attribute__ ((__always_inline__)) __extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vld1_dup_f64 (float64_t * a) vld1_dup_f64 (const float64_t * a)
{ {
float64x1_t result; float64x1_t result;
__asm__ ("ld1 {%0.1d},[%1]" __asm__ ("ld1 {%0.1d},[%1]"
...@@ -8409,7 +8409,7 @@ vld1_dup_f64 (float64_t * a) ...@@ -8409,7 +8409,7 @@ vld1_dup_f64 (float64_t * a)
} }
__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) __extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vld1_dup_p8 (poly8_t * a) vld1_dup_p8 (const poly8_t * a)
{ {
poly8x8_t result; poly8x8_t result;
__asm__ ("ld1r {%0.8b},[%1]" __asm__ ("ld1r {%0.8b},[%1]"
...@@ -8420,7 +8420,7 @@ vld1_dup_p8 (poly8_t * a) ...@@ -8420,7 +8420,7 @@ vld1_dup_p8 (poly8_t * a)
} }
__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) __extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vld1_dup_p16 (poly16_t * a) vld1_dup_p16 (const poly16_t * a)
{ {
poly16x4_t result; poly16x4_t result;
__asm__ ("ld1r {%0.4h},[%1]" __asm__ ("ld1r {%0.4h},[%1]"
...@@ -8431,7 +8431,7 @@ vld1_dup_p16 (poly16_t * a) ...@@ -8431,7 +8431,7 @@ vld1_dup_p16 (poly16_t * a)
} }
__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) __extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vld1_dup_s8 (int8_t * a) vld1_dup_s8 (const int8_t * a)
{ {
int8x8_t result; int8x8_t result;
__asm__ ("ld1r {%0.8b},[%1]" __asm__ ("ld1r {%0.8b},[%1]"
...@@ -8442,7 +8442,7 @@ vld1_dup_s8 (int8_t * a) ...@@ -8442,7 +8442,7 @@ vld1_dup_s8 (int8_t * a)
} }
__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) __extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vld1_dup_s16 (int16_t * a) vld1_dup_s16 (const int16_t * a)
{ {
int16x4_t result; int16x4_t result;
__asm__ ("ld1r {%0.4h},[%1]" __asm__ ("ld1r {%0.4h},[%1]"
...@@ -8453,7 +8453,7 @@ vld1_dup_s16 (int16_t * a) ...@@ -8453,7 +8453,7 @@ vld1_dup_s16 (int16_t * a)
} }
__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) __extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vld1_dup_s32 (int32_t * a) vld1_dup_s32 (const int32_t * a)
{ {
int32x2_t result; int32x2_t result;
__asm__ ("ld1r {%0.2s},[%1]" __asm__ ("ld1r {%0.2s},[%1]"
...@@ -8464,7 +8464,7 @@ vld1_dup_s32 (int32_t * a) ...@@ -8464,7 +8464,7 @@ vld1_dup_s32 (int32_t * a)
} }
__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) __extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vld1_dup_s64 (int64_t * a) vld1_dup_s64 (const int64_t * a)
{ {
int64x1_t result; int64x1_t result;
__asm__ ("ld1 {%0.1d},[%1]" __asm__ ("ld1 {%0.1d},[%1]"
...@@ -8475,7 +8475,7 @@ vld1_dup_s64 (int64_t * a) ...@@ -8475,7 +8475,7 @@ vld1_dup_s64 (int64_t * a)
} }
__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) __extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vld1_dup_u8 (uint8_t * a) vld1_dup_u8 (const uint8_t * a)
{ {
uint8x8_t result; uint8x8_t result;
__asm__ ("ld1r {%0.8b},[%1]" __asm__ ("ld1r {%0.8b},[%1]"
...@@ -8486,7 +8486,7 @@ vld1_dup_u8 (uint8_t * a) ...@@ -8486,7 +8486,7 @@ vld1_dup_u8 (uint8_t * a)
} }
__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) __extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vld1_dup_u16 (uint16_t * a) vld1_dup_u16 (const uint16_t * a)
{ {
uint16x4_t result; uint16x4_t result;
__asm__ ("ld1r {%0.4h},[%1]" __asm__ ("ld1r {%0.4h},[%1]"
...@@ -8497,7 +8497,7 @@ vld1_dup_u16 (uint16_t * a) ...@@ -8497,7 +8497,7 @@ vld1_dup_u16 (uint16_t * a)
} }
__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) __extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vld1_dup_u32 (uint32_t * a) vld1_dup_u32 (const uint32_t * a)
{ {
uint32x2_t result; uint32x2_t result;
__asm__ ("ld1r {%0.2s},[%1]" __asm__ ("ld1r {%0.2s},[%1]"
...@@ -8508,7 +8508,7 @@ vld1_dup_u32 (uint32_t * a) ...@@ -8508,7 +8508,7 @@ vld1_dup_u32 (uint32_t * a)
} }
__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) __extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vld1_dup_u64 (uint64_t * a) vld1_dup_u64 (const uint64_t * a)
{ {
uint64x1_t result; uint64x1_t result;
__asm__ ("ld1 {%0.1d},[%1]" __asm__ ("ld1 {%0.1d},[%1]"
...@@ -8519,7 +8519,7 @@ vld1_dup_u64 (uint64_t * a) ...@@ -8519,7 +8519,7 @@ vld1_dup_u64 (uint64_t * a)
} }
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__)) __extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vld1_f32 (float32_t * a) vld1_f32 (const float32_t * a)
{ {
float32x2_t result; float32x2_t result;
__asm__ ("ld1 {%0.2s},[%1]" __asm__ ("ld1 {%0.2s},[%1]"
...@@ -8530,7 +8530,7 @@ vld1_f32 (float32_t * a) ...@@ -8530,7 +8530,7 @@ vld1_f32 (float32_t * a)
} }
__extension__ static __inline float64x1_t __attribute__ ((__always_inline__)) __extension__ static __inline float64x1_t __attribute__ ((__always_inline__))
vld1_f64 (float64_t * a) vld1_f64 (const float64_t * a)
{ {
float64x1_t result; float64x1_t result;
__asm__ ("ld1 {%0.1d},[%1]" __asm__ ("ld1 {%0.1d},[%1]"
...@@ -8544,7 +8544,7 @@ vld1_f64 (float64_t * a) ...@@ -8544,7 +8544,7 @@ vld1_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
float32x2_t b_ = (b); \ float32x2_t b_ = (b); \
float32_t * a_ = (a); \ const float32_t * a_ = (a); \
float32x2_t result; \ float32x2_t result; \
__asm__ ("ld1 {%0.s}[%3],[%1]" \ __asm__ ("ld1 {%0.s}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -8557,7 +8557,7 @@ vld1_f64 (float64_t * a) ...@@ -8557,7 +8557,7 @@ vld1_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
float64x1_t b_ = (b); \ float64x1_t b_ = (b); \
float64_t * a_ = (a); \ const float64_t * a_ = (a); \
float64x1_t result; \ float64x1_t result; \
__asm__ ("ld1 {%0.d}[%3],[%1]" \ __asm__ ("ld1 {%0.d}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -8570,7 +8570,7 @@ vld1_f64 (float64_t * a) ...@@ -8570,7 +8570,7 @@ vld1_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
poly8x8_t b_ = (b); \ poly8x8_t b_ = (b); \
poly8_t * a_ = (a); \ const poly8_t * a_ = (a); \
poly8x8_t result; \ poly8x8_t result; \
__asm__ ("ld1 {%0.b}[%3],[%1]" \ __asm__ ("ld1 {%0.b}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -8583,7 +8583,7 @@ vld1_f64 (float64_t * a) ...@@ -8583,7 +8583,7 @@ vld1_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
poly16x4_t b_ = (b); \ poly16x4_t b_ = (b); \
poly16_t * a_ = (a); \ const poly16_t * a_ = (a); \
poly16x4_t result; \ poly16x4_t result; \
__asm__ ("ld1 {%0.h}[%3],[%1]" \ __asm__ ("ld1 {%0.h}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -8596,7 +8596,7 @@ vld1_f64 (float64_t * a) ...@@ -8596,7 +8596,7 @@ vld1_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
int8x8_t b_ = (b); \ int8x8_t b_ = (b); \
int8_t * a_ = (a); \ const int8_t * a_ = (a); \
int8x8_t result; \ int8x8_t result; \
__asm__ ("ld1 {%0.b}[%3],[%1]" \ __asm__ ("ld1 {%0.b}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -8609,7 +8609,7 @@ vld1_f64 (float64_t * a) ...@@ -8609,7 +8609,7 @@ vld1_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
int16x4_t b_ = (b); \ int16x4_t b_ = (b); \
int16_t * a_ = (a); \ const int16_t * a_ = (a); \
int16x4_t result; \ int16x4_t result; \
__asm__ ("ld1 {%0.h}[%3],[%1]" \ __asm__ ("ld1 {%0.h}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -8622,7 +8622,7 @@ vld1_f64 (float64_t * a) ...@@ -8622,7 +8622,7 @@ vld1_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
int32x2_t b_ = (b); \ int32x2_t b_ = (b); \
int32_t * a_ = (a); \ const int32_t * a_ = (a); \
int32x2_t result; \ int32x2_t result; \
__asm__ ("ld1 {%0.s}[%3],[%1]" \ __asm__ ("ld1 {%0.s}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -8635,7 +8635,7 @@ vld1_f64 (float64_t * a) ...@@ -8635,7 +8635,7 @@ vld1_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
int64x1_t b_ = (b); \ int64x1_t b_ = (b); \
int64_t * a_ = (a); \ const int64_t * a_ = (a); \
int64x1_t result; \ int64x1_t result; \
__asm__ ("ld1 {%0.d}[%3],[%1]" \ __asm__ ("ld1 {%0.d}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -8648,7 +8648,7 @@ vld1_f64 (float64_t * a) ...@@ -8648,7 +8648,7 @@ vld1_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
uint8x8_t b_ = (b); \ uint8x8_t b_ = (b); \
uint8_t * a_ = (a); \ const uint8_t * a_ = (a); \
uint8x8_t result; \ uint8x8_t result; \
__asm__ ("ld1 {%0.b}[%3],[%1]" \ __asm__ ("ld1 {%0.b}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -8661,7 +8661,7 @@ vld1_f64 (float64_t * a) ...@@ -8661,7 +8661,7 @@ vld1_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
uint16x4_t b_ = (b); \ uint16x4_t b_ = (b); \
uint16_t * a_ = (a); \ const uint16_t * a_ = (a); \
uint16x4_t result; \ uint16x4_t result; \
__asm__ ("ld1 {%0.h}[%3],[%1]" \ __asm__ ("ld1 {%0.h}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -8674,7 +8674,7 @@ vld1_f64 (float64_t * a) ...@@ -8674,7 +8674,7 @@ vld1_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
uint32x2_t b_ = (b); \ uint32x2_t b_ = (b); \
uint32_t * a_ = (a); \ const uint32_t * a_ = (a); \
uint32x2_t result; \ uint32x2_t result; \
__asm__ ("ld1 {%0.s}[%3],[%1]" \ __asm__ ("ld1 {%0.s}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -8687,7 +8687,7 @@ vld1_f64 (float64_t * a) ...@@ -8687,7 +8687,7 @@ vld1_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
uint64x1_t b_ = (b); \ uint64x1_t b_ = (b); \
uint64_t * a_ = (a); \ const uint64_t * a_ = (a); \
uint64x1_t result; \ uint64x1_t result; \
__asm__ ("ld1 {%0.d}[%3],[%1]" \ __asm__ ("ld1 {%0.d}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -8697,7 +8697,7 @@ vld1_f64 (float64_t * a) ...@@ -8697,7 +8697,7 @@ vld1_f64 (float64_t * a)
}) })
__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__)) __extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
vld1_p8 (poly8_t * a) vld1_p8 (const poly8_t * a)
{ {
poly8x8_t result; poly8x8_t result;
__asm__ ("ld1 {%0.8b}, [%1]" __asm__ ("ld1 {%0.8b}, [%1]"
...@@ -8708,7 +8708,7 @@ vld1_p8 (poly8_t * a) ...@@ -8708,7 +8708,7 @@ vld1_p8 (poly8_t * a)
} }
__extension__ static __inline poly16x4_t __attribute__ ((__always_inline__)) __extension__ static __inline poly16x4_t __attribute__ ((__always_inline__))
vld1_p16 (poly16_t * a) vld1_p16 (const poly16_t * a)
{ {
poly16x4_t result; poly16x4_t result;
__asm__ ("ld1 {%0.4h}, [%1]" __asm__ ("ld1 {%0.4h}, [%1]"
...@@ -8719,7 +8719,7 @@ vld1_p16 (poly16_t * a) ...@@ -8719,7 +8719,7 @@ vld1_p16 (poly16_t * a)
} }
__extension__ static __inline int8x8_t __attribute__ ((__always_inline__)) __extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
vld1_s8 (int8_t * a) vld1_s8 (const int8_t * a)
{ {
int8x8_t result; int8x8_t result;
__asm__ ("ld1 {%0.8b},[%1]" __asm__ ("ld1 {%0.8b},[%1]"
...@@ -8730,7 +8730,7 @@ vld1_s8 (int8_t * a) ...@@ -8730,7 +8730,7 @@ vld1_s8 (int8_t * a)
} }
__extension__ static __inline int16x4_t __attribute__ ((__always_inline__)) __extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
vld1_s16 (int16_t * a) vld1_s16 (const int16_t * a)
{ {
int16x4_t result; int16x4_t result;
__asm__ ("ld1 {%0.4h},[%1]" __asm__ ("ld1 {%0.4h},[%1]"
...@@ -8741,7 +8741,7 @@ vld1_s16 (int16_t * a) ...@@ -8741,7 +8741,7 @@ vld1_s16 (int16_t * a)
} }
__extension__ static __inline int32x2_t __attribute__ ((__always_inline__)) __extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
vld1_s32 (int32_t * a) vld1_s32 (const int32_t * a)
{ {
int32x2_t result; int32x2_t result;
__asm__ ("ld1 {%0.2s},[%1]" __asm__ ("ld1 {%0.2s},[%1]"
...@@ -8752,7 +8752,7 @@ vld1_s32 (int32_t * a) ...@@ -8752,7 +8752,7 @@ vld1_s32 (int32_t * a)
} }
__extension__ static __inline int64x1_t __attribute__ ((__always_inline__)) __extension__ static __inline int64x1_t __attribute__ ((__always_inline__))
vld1_s64 (int64_t * a) vld1_s64 (const int64_t * a)
{ {
int64x1_t result; int64x1_t result;
__asm__ ("ld1 {%0.1d},[%1]" __asm__ ("ld1 {%0.1d},[%1]"
...@@ -8763,7 +8763,7 @@ vld1_s64 (int64_t * a) ...@@ -8763,7 +8763,7 @@ vld1_s64 (int64_t * a)
} }
__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__)) __extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
vld1_u8 (uint8_t * a) vld1_u8 (const uint8_t * a)
{ {
uint8x8_t result; uint8x8_t result;
__asm__ ("ld1 {%0.8b},[%1]" __asm__ ("ld1 {%0.8b},[%1]"
...@@ -8774,7 +8774,7 @@ vld1_u8 (uint8_t * a) ...@@ -8774,7 +8774,7 @@ vld1_u8 (uint8_t * a)
} }
__extension__ static __inline uint16x4_t __attribute__ ((__always_inline__)) __extension__ static __inline uint16x4_t __attribute__ ((__always_inline__))
vld1_u16 (uint16_t * a) vld1_u16 (const uint16_t * a)
{ {
uint16x4_t result; uint16x4_t result;
__asm__ ("ld1 {%0.4h},[%1]" __asm__ ("ld1 {%0.4h},[%1]"
...@@ -8785,7 +8785,7 @@ vld1_u16 (uint16_t * a) ...@@ -8785,7 +8785,7 @@ vld1_u16 (uint16_t * a)
} }
__extension__ static __inline uint32x2_t __attribute__ ((__always_inline__)) __extension__ static __inline uint32x2_t __attribute__ ((__always_inline__))
vld1_u32 (uint32_t * a) vld1_u32 (const uint32_t * a)
{ {
uint32x2_t result; uint32x2_t result;
__asm__ ("ld1 {%0.2s},[%1]" __asm__ ("ld1 {%0.2s},[%1]"
...@@ -8796,7 +8796,7 @@ vld1_u32 (uint32_t * a) ...@@ -8796,7 +8796,7 @@ vld1_u32 (uint32_t * a)
} }
__extension__ static __inline uint64x1_t __attribute__ ((__always_inline__)) __extension__ static __inline uint64x1_t __attribute__ ((__always_inline__))
vld1_u64 (uint64_t * a) vld1_u64 (const uint64_t * a)
{ {
uint64x1_t result; uint64x1_t result;
__asm__ ("ld1 {%0.1d},[%1]" __asm__ ("ld1 {%0.1d},[%1]"
...@@ -8807,7 +8807,7 @@ vld1_u64 (uint64_t * a) ...@@ -8807,7 +8807,7 @@ vld1_u64 (uint64_t * a)
} }
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) __extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vld1q_dup_f32 (float32_t * a) vld1q_dup_f32 (const float32_t * a)
{ {
float32x4_t result; float32x4_t result;
__asm__ ("ld1r {%0.4s},[%1]" __asm__ ("ld1r {%0.4s},[%1]"
...@@ -8818,7 +8818,7 @@ vld1q_dup_f32 (float32_t * a) ...@@ -8818,7 +8818,7 @@ vld1q_dup_f32 (float32_t * a)
} }
__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) __extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vld1q_dup_f64 (float64_t * a) vld1q_dup_f64 (const float64_t * a)
{ {
float64x2_t result; float64x2_t result;
__asm__ ("ld1r {%0.2d},[%1]" __asm__ ("ld1r {%0.2d},[%1]"
...@@ -8829,7 +8829,7 @@ vld1q_dup_f64 (float64_t * a) ...@@ -8829,7 +8829,7 @@ vld1q_dup_f64 (float64_t * a)
} }
__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) __extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vld1q_dup_p8 (poly8_t * a) vld1q_dup_p8 (const poly8_t * a)
{ {
poly8x16_t result; poly8x16_t result;
__asm__ ("ld1r {%0.16b},[%1]" __asm__ ("ld1r {%0.16b},[%1]"
...@@ -8840,7 +8840,7 @@ vld1q_dup_p8 (poly8_t * a) ...@@ -8840,7 +8840,7 @@ vld1q_dup_p8 (poly8_t * a)
} }
__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) __extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vld1q_dup_p16 (poly16_t * a) vld1q_dup_p16 (const poly16_t * a)
{ {
poly16x8_t result; poly16x8_t result;
__asm__ ("ld1r {%0.8h},[%1]" __asm__ ("ld1r {%0.8h},[%1]"
...@@ -8851,7 +8851,7 @@ vld1q_dup_p16 (poly16_t * a) ...@@ -8851,7 +8851,7 @@ vld1q_dup_p16 (poly16_t * a)
} }
__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) __extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vld1q_dup_s8 (int8_t * a) vld1q_dup_s8 (const int8_t * a)
{ {
int8x16_t result; int8x16_t result;
__asm__ ("ld1r {%0.16b},[%1]" __asm__ ("ld1r {%0.16b},[%1]"
...@@ -8862,7 +8862,7 @@ vld1q_dup_s8 (int8_t * a) ...@@ -8862,7 +8862,7 @@ vld1q_dup_s8 (int8_t * a)
} }
__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) __extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vld1q_dup_s16 (int16_t * a) vld1q_dup_s16 (const int16_t * a)
{ {
int16x8_t result; int16x8_t result;
__asm__ ("ld1r {%0.8h},[%1]" __asm__ ("ld1r {%0.8h},[%1]"
...@@ -8873,7 +8873,7 @@ vld1q_dup_s16 (int16_t * a) ...@@ -8873,7 +8873,7 @@ vld1q_dup_s16 (int16_t * a)
} }
__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) __extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vld1q_dup_s32 (int32_t * a) vld1q_dup_s32 (const int32_t * a)
{ {
int32x4_t result; int32x4_t result;
__asm__ ("ld1r {%0.4s},[%1]" __asm__ ("ld1r {%0.4s},[%1]"
...@@ -8884,7 +8884,7 @@ vld1q_dup_s32 (int32_t * a) ...@@ -8884,7 +8884,7 @@ vld1q_dup_s32 (int32_t * a)
} }
__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) __extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vld1q_dup_s64 (int64_t * a) vld1q_dup_s64 (const int64_t * a)
{ {
int64x2_t result; int64x2_t result;
__asm__ ("ld1r {%0.2d},[%1]" __asm__ ("ld1r {%0.2d},[%1]"
...@@ -8895,7 +8895,7 @@ vld1q_dup_s64 (int64_t * a) ...@@ -8895,7 +8895,7 @@ vld1q_dup_s64 (int64_t * a)
} }
__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) __extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vld1q_dup_u8 (uint8_t * a) vld1q_dup_u8 (const uint8_t * a)
{ {
uint8x16_t result; uint8x16_t result;
__asm__ ("ld1r {%0.16b},[%1]" __asm__ ("ld1r {%0.16b},[%1]"
...@@ -8906,7 +8906,7 @@ vld1q_dup_u8 (uint8_t * a) ...@@ -8906,7 +8906,7 @@ vld1q_dup_u8 (uint8_t * a)
} }
__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) __extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vld1q_dup_u16 (uint16_t * a) vld1q_dup_u16 (const uint16_t * a)
{ {
uint16x8_t result; uint16x8_t result;
__asm__ ("ld1r {%0.8h},[%1]" __asm__ ("ld1r {%0.8h},[%1]"
...@@ -8917,7 +8917,7 @@ vld1q_dup_u16 (uint16_t * a) ...@@ -8917,7 +8917,7 @@ vld1q_dup_u16 (uint16_t * a)
} }
__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) __extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vld1q_dup_u32 (uint32_t * a) vld1q_dup_u32 (const uint32_t * a)
{ {
uint32x4_t result; uint32x4_t result;
__asm__ ("ld1r {%0.4s},[%1]" __asm__ ("ld1r {%0.4s},[%1]"
...@@ -8928,7 +8928,7 @@ vld1q_dup_u32 (uint32_t * a) ...@@ -8928,7 +8928,7 @@ vld1q_dup_u32 (uint32_t * a)
} }
__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) __extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vld1q_dup_u64 (uint64_t * a) vld1q_dup_u64 (const uint64_t * a)
{ {
uint64x2_t result; uint64x2_t result;
__asm__ ("ld1r {%0.2d},[%1]" __asm__ ("ld1r {%0.2d},[%1]"
...@@ -8939,7 +8939,7 @@ vld1q_dup_u64 (uint64_t * a) ...@@ -8939,7 +8939,7 @@ vld1q_dup_u64 (uint64_t * a)
} }
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__)) __extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vld1q_f32 (float32_t * a) vld1q_f32 (const float32_t * a)
{ {
float32x4_t result; float32x4_t result;
__asm__ ("ld1 {%0.4s},[%1]" __asm__ ("ld1 {%0.4s},[%1]"
...@@ -8950,7 +8950,7 @@ vld1q_f32 (float32_t * a) ...@@ -8950,7 +8950,7 @@ vld1q_f32 (float32_t * a)
} }
__extension__ static __inline float64x2_t __attribute__ ((__always_inline__)) __extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vld1q_f64 (float64_t * a) vld1q_f64 (const float64_t * a)
{ {
float64x2_t result; float64x2_t result;
__asm__ ("ld1 {%0.2d},[%1]" __asm__ ("ld1 {%0.2d},[%1]"
...@@ -8964,7 +8964,7 @@ vld1q_f64 (float64_t * a) ...@@ -8964,7 +8964,7 @@ vld1q_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
float32x4_t b_ = (b); \ float32x4_t b_ = (b); \
float32_t * a_ = (a); \ const float32_t * a_ = (a); \
float32x4_t result; \ float32x4_t result; \
__asm__ ("ld1 {%0.s}[%3],[%1]" \ __asm__ ("ld1 {%0.s}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -8977,7 +8977,7 @@ vld1q_f64 (float64_t * a) ...@@ -8977,7 +8977,7 @@ vld1q_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
float64x2_t b_ = (b); \ float64x2_t b_ = (b); \
float64_t * a_ = (a); \ const float64_t * a_ = (a); \
float64x2_t result; \ float64x2_t result; \
__asm__ ("ld1 {%0.d}[%3],[%1]" \ __asm__ ("ld1 {%0.d}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -8990,7 +8990,7 @@ vld1q_f64 (float64_t * a) ...@@ -8990,7 +8990,7 @@ vld1q_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
poly8x16_t b_ = (b); \ poly8x16_t b_ = (b); \
poly8_t * a_ = (a); \ const poly8_t * a_ = (a); \
poly8x16_t result; \ poly8x16_t result; \
__asm__ ("ld1 {%0.b}[%3],[%1]" \ __asm__ ("ld1 {%0.b}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -9003,7 +9003,7 @@ vld1q_f64 (float64_t * a) ...@@ -9003,7 +9003,7 @@ vld1q_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
poly16x8_t b_ = (b); \ poly16x8_t b_ = (b); \
poly16_t * a_ = (a); \ const poly16_t * a_ = (a); \
poly16x8_t result; \ poly16x8_t result; \
__asm__ ("ld1 {%0.h}[%3],[%1]" \ __asm__ ("ld1 {%0.h}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -9016,7 +9016,7 @@ vld1q_f64 (float64_t * a) ...@@ -9016,7 +9016,7 @@ vld1q_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
int8x16_t b_ = (b); \ int8x16_t b_ = (b); \
int8_t * a_ = (a); \ const int8_t * a_ = (a); \
int8x16_t result; \ int8x16_t result; \
__asm__ ("ld1 {%0.b}[%3],[%1]" \ __asm__ ("ld1 {%0.b}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -9029,7 +9029,7 @@ vld1q_f64 (float64_t * a) ...@@ -9029,7 +9029,7 @@ vld1q_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
int16x8_t b_ = (b); \ int16x8_t b_ = (b); \
int16_t * a_ = (a); \ const int16_t * a_ = (a); \
int16x8_t result; \ int16x8_t result; \
__asm__ ("ld1 {%0.h}[%3],[%1]" \ __asm__ ("ld1 {%0.h}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -9042,7 +9042,7 @@ vld1q_f64 (float64_t * a) ...@@ -9042,7 +9042,7 @@ vld1q_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
int32x4_t b_ = (b); \ int32x4_t b_ = (b); \
int32_t * a_ = (a); \ const int32_t * a_ = (a); \
int32x4_t result; \ int32x4_t result; \
__asm__ ("ld1 {%0.s}[%3],[%1]" \ __asm__ ("ld1 {%0.s}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -9055,7 +9055,7 @@ vld1q_f64 (float64_t * a) ...@@ -9055,7 +9055,7 @@ vld1q_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
int64x2_t b_ = (b); \ int64x2_t b_ = (b); \
int64_t * a_ = (a); \ const int64_t * a_ = (a); \
int64x2_t result; \ int64x2_t result; \
__asm__ ("ld1 {%0.d}[%3],[%1]" \ __asm__ ("ld1 {%0.d}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -9068,7 +9068,7 @@ vld1q_f64 (float64_t * a) ...@@ -9068,7 +9068,7 @@ vld1q_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
uint8x16_t b_ = (b); \ uint8x16_t b_ = (b); \
uint8_t * a_ = (a); \ const uint8_t * a_ = (a); \
uint8x16_t result; \ uint8x16_t result; \
__asm__ ("ld1 {%0.b}[%3],[%1]" \ __asm__ ("ld1 {%0.b}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -9081,7 +9081,7 @@ vld1q_f64 (float64_t * a) ...@@ -9081,7 +9081,7 @@ vld1q_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
uint16x8_t b_ = (b); \ uint16x8_t b_ = (b); \
uint16_t * a_ = (a); \ const uint16_t * a_ = (a); \
uint16x8_t result; \ uint16x8_t result; \
__asm__ ("ld1 {%0.h}[%3],[%1]" \ __asm__ ("ld1 {%0.h}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -9094,7 +9094,7 @@ vld1q_f64 (float64_t * a) ...@@ -9094,7 +9094,7 @@ vld1q_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
uint32x4_t b_ = (b); \ uint32x4_t b_ = (b); \
uint32_t * a_ = (a); \ const uint32_t * a_ = (a); \
uint32x4_t result; \ uint32x4_t result; \
__asm__ ("ld1 {%0.s}[%3],[%1]" \ __asm__ ("ld1 {%0.s}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -9107,7 +9107,7 @@ vld1q_f64 (float64_t * a) ...@@ -9107,7 +9107,7 @@ vld1q_f64 (float64_t * a)
__extension__ \ __extension__ \
({ \ ({ \
uint64x2_t b_ = (b); \ uint64x2_t b_ = (b); \
uint64_t * a_ = (a); \ const uint64_t * a_ = (a); \
uint64x2_t result; \ uint64x2_t result; \
__asm__ ("ld1 {%0.d}[%3],[%1]" \ __asm__ ("ld1 {%0.d}[%3],[%1]" \
: "=w"(result) \ : "=w"(result) \
...@@ -9117,7 +9117,7 @@ vld1q_f64 (float64_t * a) ...@@ -9117,7 +9117,7 @@ vld1q_f64 (float64_t * a)
}) })
__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__)) __extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
vld1q_p8 (poly8_t * a) vld1q_p8 (const poly8_t * a)
{ {
poly8x16_t result; poly8x16_t result;
__asm__ ("ld1 {%0.16b},[%1]" __asm__ ("ld1 {%0.16b},[%1]"
...@@ -9128,7 +9128,7 @@ vld1q_p8 (poly8_t * a) ...@@ -9128,7 +9128,7 @@ vld1q_p8 (poly8_t * a)
} }
__extension__ static __inline poly16x8_t __attribute__ ((__always_inline__)) __extension__ static __inline poly16x8_t __attribute__ ((__always_inline__))
vld1q_p16 (poly16_t * a) vld1q_p16 (const poly16_t * a)
{ {
poly16x8_t result; poly16x8_t result;
__asm__ ("ld1 {%0.8h},[%1]" __asm__ ("ld1 {%0.8h},[%1]"
...@@ -9139,7 +9139,7 @@ vld1q_p16 (poly16_t * a) ...@@ -9139,7 +9139,7 @@ vld1q_p16 (poly16_t * a)
} }
__extension__ static __inline int8x16_t __attribute__ ((__always_inline__)) __extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
vld1q_s8 (int8_t * a) vld1q_s8 (const int8_t * a)
{ {
int8x16_t result; int8x16_t result;
__asm__ ("ld1 {%0.16b},[%1]" __asm__ ("ld1 {%0.16b},[%1]"
...@@ -9150,7 +9150,7 @@ vld1q_s8 (int8_t * a) ...@@ -9150,7 +9150,7 @@ vld1q_s8 (int8_t * a)
} }
__extension__ static __inline int16x8_t __attribute__ ((__always_inline__)) __extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
vld1q_s16 (int16_t * a) vld1q_s16 (const int16_t * a)
{ {
int16x8_t result; int16x8_t result;
__asm__ ("ld1 {%0.8h},[%1]" __asm__ ("ld1 {%0.8h},[%1]"
...@@ -9161,7 +9161,7 @@ vld1q_s16 (int16_t * a) ...@@ -9161,7 +9161,7 @@ vld1q_s16 (int16_t * a)
} }
__extension__ static __inline int32x4_t __attribute__ ((__always_inline__)) __extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
vld1q_s32 (int32_t * a) vld1q_s32 (const int32_t * a)
{ {
int32x4_t result; int32x4_t result;
__asm__ ("ld1 {%0.4s},[%1]" __asm__ ("ld1 {%0.4s},[%1]"
...@@ -9172,7 +9172,7 @@ vld1q_s32 (int32_t * a) ...@@ -9172,7 +9172,7 @@ vld1q_s32 (int32_t * a)
} }
__extension__ static __inline int64x2_t __attribute__ ((__always_inline__)) __extension__ static __inline int64x2_t __attribute__ ((__always_inline__))
vld1q_s64 (int64_t * a) vld1q_s64 (const int64_t * a)
{ {
int64x2_t result; int64x2_t result;
__asm__ ("ld1 {%0.2d},[%1]" __asm__ ("ld1 {%0.2d},[%1]"
...@@ -9183,7 +9183,7 @@ vld1q_s64 (int64_t * a) ...@@ -9183,7 +9183,7 @@ vld1q_s64 (int64_t * a)
} }
__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__)) __extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
vld1q_u8 (uint8_t * a) vld1q_u8 (const uint8_t * a)
{ {
uint8x16_t result; uint8x16_t result;
__asm__ ("ld1 {%0.16b},[%1]" __asm__ ("ld1 {%0.16b},[%1]"
...@@ -9194,7 +9194,7 @@ vld1q_u8 (uint8_t * a) ...@@ -9194,7 +9194,7 @@ vld1q_u8 (uint8_t * a)
} }
__extension__ static __inline uint16x8_t __attribute__ ((__always_inline__)) __extension__ static __inline uint16x8_t __attribute__ ((__always_inline__))
vld1q_u16 (uint16_t * a) vld1q_u16 (const uint16_t * a)
{ {
uint16x8_t result; uint16x8_t result;
__asm__ ("ld1 {%0.8h},[%1]" __asm__ ("ld1 {%0.8h},[%1]"
...@@ -9205,7 +9205,7 @@ vld1q_u16 (uint16_t * a) ...@@ -9205,7 +9205,7 @@ vld1q_u16 (uint16_t * a)
} }
__extension__ static __inline uint32x4_t __attribute__ ((__always_inline__)) __extension__ static __inline uint32x4_t __attribute__ ((__always_inline__))
vld1q_u32 (uint32_t * a) vld1q_u32 (const uint32_t * a)
{ {
uint32x4_t result; uint32x4_t result;
__asm__ ("ld1 {%0.4s},[%1]" __asm__ ("ld1 {%0.4s},[%1]"
...@@ -9216,7 +9216,7 @@ vld1q_u32 (uint32_t * a) ...@@ -9216,7 +9216,7 @@ vld1q_u32 (uint32_t * a)
} }
__extension__ static __inline uint64x2_t __attribute__ ((__always_inline__)) __extension__ static __inline uint64x2_t __attribute__ ((__always_inline__))
vld1q_u64 (uint64_t * a) vld1q_u64 (const uint64_t * a)
{ {
uint64x2_t result; uint64x2_t result;
__asm__ ("ld1 {%0.2d},[%1]" __asm__ ("ld1 {%0.2d},[%1]"
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment