This patch supports the following MVE ACLE load intrinsics which load a byte, halfword,
or word from memory.
vld1q_s8, vld1q_s32, vld1q_s16, vld1q_u8, vld1q_u32, vld1q_u16, vldrhq_gather_offset_s32,
vldrhq_gather_offset_s16, vldrhq_gather_offset_u32, vldrhq_gather_offset_u16,
vldrhq_gather_offset_z_s32, vldrhq_gather_offset_z_s16, vldrhq_gather_offset_z_u32,
vldrhq_gather_offset_z_u16, vldrhq_gather_shifted_offset_s32,vldrwq_f32, vldrwq_z_f32,
vldrhq_gather_shifted_offset_s16, vldrhq_gather_shifted_offset_u32,
vldrhq_gather_shifted_offset_u16, vldrhq_gather_shifted_offset_z_s32,
vldrhq_gather_shifted_offset_z_s16, vldrhq_gather_shifted_offset_z_u32,
vldrhq_gather_shifted_offset_z_u16, vldrhq_s32, vldrhq_s16, vldrhq_u32, vldrhq_u16,
vldrhq_z_s32, vldrhq_z_s16, vldrhq_z_u32, vldrhq_z_u16, vldrwq_s32, vldrwq_u32,
vldrwq_z_s32, vldrwq_z_u32, vld1q_f32, vld1q_f16, vldrhq_f16, vldrhq_z_f16.
Please refer to M-profile Vector Extension (MVE) intrinsics [1] for more details.
[1] https://developer.arm.com/architectures/instruction-sets/simd-isas/helium/mve-intrinsics
2020-03-18 Andre Vieira <andre.simoesdiasvieira@arm.com>
Mihail Ionescu <mihail.ionescu@arm.com>
Srinath Parvathaneni <srinath.parvathaneni@arm.com>
* config/arm/arm_mve.h (vld1q_s8): Define macro.
(vld1q_s32): Likewise.
(vld1q_s16): Likewise.
(vld1q_u8): Likewise.
(vld1q_u32): Likewise.
(vld1q_u16): Likewise.
(vldrhq_gather_offset_s32): Likewise.
(vldrhq_gather_offset_s16): Likewise.
(vldrhq_gather_offset_u32): Likewise.
(vldrhq_gather_offset_u16): Likewise.
(vldrhq_gather_offset_z_s32): Likewise.
(vldrhq_gather_offset_z_s16): Likewise.
(vldrhq_gather_offset_z_u32): Likewise.
(vldrhq_gather_offset_z_u16): Likewise.
(vldrhq_gather_shifted_offset_s32): Likewise.
(vldrhq_gather_shifted_offset_s16): Likewise.
(vldrhq_gather_shifted_offset_u32): Likewise.
(vldrhq_gather_shifted_offset_u16): Likewise.
(vldrhq_gather_shifted_offset_z_s32): Likewise.
(vldrhq_gather_shifted_offset_z_s16): Likewise.
(vldrhq_gather_shifted_offset_z_u32): Likewise.
(vldrhq_gather_shifted_offset_z_u16): Likewise.
(vldrhq_s32): Likewise.
(vldrhq_s16): Likewise.
(vldrhq_u32): Likewise.
(vldrhq_u16): Likewise.
(vldrhq_z_s32): Likewise.
(vldrhq_z_s16): Likewise.
(vldrhq_z_u32): Likewise.
(vldrhq_z_u16): Likewise.
(vldrwq_s32): Likewise.
(vldrwq_u32): Likewise.
(vldrwq_z_s32): Likewise.
(vldrwq_z_u32): Likewise.
(vld1q_f32): Likewise.
(vld1q_f16): Likewise.
(vldrhq_f16): Likewise.
(vldrhq_z_f16): Likewise.
(vldrwq_f32): Likewise.
(vldrwq_z_f32): Likewise.
(__arm_vld1q_s8): Define intrinsic.
(__arm_vld1q_s32): Likewise.
(__arm_vld1q_s16): Likewise.
(__arm_vld1q_u8): Likewise.
(__arm_vld1q_u32): Likewise.
(__arm_vld1q_u16): Likewise.
(__arm_vldrhq_gather_offset_s32): Likewise.
(__arm_vldrhq_gather_offset_s16): Likewise.
(__arm_vldrhq_gather_offset_u32): Likewise.
(__arm_vldrhq_gather_offset_u16): Likewise.
(__arm_vldrhq_gather_offset_z_s32): Likewise.
(__arm_vldrhq_gather_offset_z_s16): Likewise.
(__arm_vldrhq_gather_offset_z_u32): Likewise.
(__arm_vldrhq_gather_offset_z_u16): Likewise.
(__arm_vldrhq_gather_shifted_offset_s32): Likewise.
(__arm_vldrhq_gather_shifted_offset_s16): Likewise.
(__arm_vldrhq_gather_shifted_offset_u32): Likewise.
(__arm_vldrhq_gather_shifted_offset_u16): Likewise.
(__arm_vldrhq_gather_shifted_offset_z_s32): Likewise.
(__arm_vldrhq_gather_shifted_offset_z_s16): Likewise.
(__arm_vldrhq_gather_shifted_offset_z_u32): Likewise.
(__arm_vldrhq_gather_shifted_offset_z_u16): Likewise.
(__arm_vldrhq_s32): Likewise.
(__arm_vldrhq_s16): Likewise.
(__arm_vldrhq_u32): Likewise.
(__arm_vldrhq_u16): Likewise.
(__arm_vldrhq_z_s32): Likewise.
(__arm_vldrhq_z_s16): Likewise.
(__arm_vldrhq_z_u32): Likewise.
(__arm_vldrhq_z_u16): Likewise.
(__arm_vldrwq_s32): Likewise.
(__arm_vldrwq_u32): Likewise.
(__arm_vldrwq_z_s32): Likewise.
(__arm_vldrwq_z_u32): Likewise.
(__arm_vld1q_f32): Likewise.
(__arm_vld1q_f16): Likewise.
(__arm_vldrwq_f32): Likewise.
(__arm_vldrwq_z_f32): Likewise.
(__arm_vldrhq_z_f16): Likewise.
(__arm_vldrhq_f16): Likewise.
(vld1q): Define polymorphic variant.
(vldrhq_gather_offset): Likewise.
(vldrhq_gather_offset_z): Likewise.
(vldrhq_gather_shifted_offset): Likewise.
(vldrhq_gather_shifted_offset_z): Likewise.
* config/arm/arm_mve_builtins.def (LDRU): Use builtin qualifier.
(LDRS): Likewise.
(LDRU_Z): Likewise.
(LDRS_Z): Likewise.
(LDRGU_Z): Likewise.
(LDRGU): Likewise.
(LDRGS_Z): Likewise.
(LDRGS): Likewise.
* config/arm/mve.md (MVE_H_ELEM): Define mode iterator.
(V_sz_elem1): Likewise.
(VLD1Q): Define iterator.
(VLDRHGOQ): Likewise.
(VLDRHGSOQ): Likewise.
(VLDRHQ): Likewise.
(VLDRWQ): Likewise.
(mve_vldrhq_fv8hf): Define RTL pattern.
(mve_vldrhq_gather_offset_<supf><mode>): Likewise.
(mve_vldrhq_gather_offset_z_<supf><mode>): Likewise.
(mve_vldrhq_gather_shifted_offset_<supf><mode>): Likewise.
(mve_vldrhq_gather_shifted_offset_z_<supf><mode>): Likewise.
(mve_vldrhq_<supf><mode>): Likewise.
(mve_vldrhq_z_fv8hf): Likewise.
(mve_vldrhq_z_<supf><mode>): Likewise.
(mve_vldrwq_fv4sf): Likewise.
(mve_vldrwq_<supf>v4si): Likewise.
(mve_vldrwq_z_fv4sf): Likewise.
(mve_vldrwq_z_<supf>v4si): Likewise.
(mve_vld1q_f<mode>): Define RTL expand pattern.
(mve_vld1q_<supf><mode>): Likewise.
gcc/testsuite/ChangeLog:
2020-03-18 Andre Vieira <andre.simoesdiasvieira@arm.com>
Mihail Ionescu <mihail.ionescu@arm.com>
Srinath Parvathaneni <srinath.parvathaneni@arm.com>
* gcc.target/arm/mve/intrinsics/vld1q_f16.c: New test.
* gcc.target/arm/mve/intrinsics/vld1q_f32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vld1q_s16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vld1q_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vld1q_s8.c: Likewise.
* gcc.target/arm/mve/intrinsics/vld1q_u16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vld1q_u32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vld1q_u8.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_f16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_gather_offset_s16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_gather_offset_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_gather_offset_u16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_gather_offset_u32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_gather_offset_z_s16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_gather_offset_z_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_gather_offset_z_u16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_gather_offset_z_u32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_gather_shifted_offset_s16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_gather_shifted_offset_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_gather_shifted_offset_u16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_gather_shifted_offset_u32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_gather_shifted_offset_z_s16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_gather_shifted_offset_z_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_gather_shifted_offset_z_u16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_gather_shifted_offset_z_u32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_s16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_u16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_u32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_z_f16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_z_s16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_z_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_z_u16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrhq_z_u32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrwq_f32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrwq_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrwq_u32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrwq_z_f32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrwq_z_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrwq_z_u32.c: Likewise.
+2020-03-18 Andre Vieira <andre.simoesdiasvieira@arm.com>
+ Mihail Ionescu <mihail.ionescu@arm.com>
+ Srinath Parvathaneni <srinath.parvathaneni@arm.com>
+
+ * config/arm/arm_mve.h (vld1q_s8): Define macro.
+ (vld1q_s32): Likewise.
+ (vld1q_s16): Likewise.
+ (vld1q_u8): Likewise.
+ (vld1q_u32): Likewise.
+ (vld1q_u16): Likewise.
+ (vldrhq_gather_offset_s32): Likewise.
+ (vldrhq_gather_offset_s16): Likewise.
+ (vldrhq_gather_offset_u32): Likewise.
+ (vldrhq_gather_offset_u16): Likewise.
+ (vldrhq_gather_offset_z_s32): Likewise.
+ (vldrhq_gather_offset_z_s16): Likewise.
+ (vldrhq_gather_offset_z_u32): Likewise.
+ (vldrhq_gather_offset_z_u16): Likewise.
+ (vldrhq_gather_shifted_offset_s32): Likewise.
+ (vldrhq_gather_shifted_offset_s16): Likewise.
+ (vldrhq_gather_shifted_offset_u32): Likewise.
+ (vldrhq_gather_shifted_offset_u16): Likewise.
+ (vldrhq_gather_shifted_offset_z_s32): Likewise.
+ (vldrhq_gather_shifted_offset_z_s16): Likewise.
+ (vldrhq_gather_shifted_offset_z_u32): Likewise.
+ (vldrhq_gather_shifted_offset_z_u16): Likewise.
+ (vldrhq_s32): Likewise.
+ (vldrhq_s16): Likewise.
+ (vldrhq_u32): Likewise.
+ (vldrhq_u16): Likewise.
+ (vldrhq_z_s32): Likewise.
+ (vldrhq_z_s16): Likewise.
+ (vldrhq_z_u32): Likewise.
+ (vldrhq_z_u16): Likewise.
+ (vldrwq_s32): Likewise.
+ (vldrwq_u32): Likewise.
+ (vldrwq_z_s32): Likewise.
+ (vldrwq_z_u32): Likewise.
+ (vld1q_f32): Likewise.
+ (vld1q_f16): Likewise.
+ (vldrhq_f16): Likewise.
+ (vldrhq_z_f16): Likewise.
+ (vldrwq_f32): Likewise.
+ (vldrwq_z_f32): Likewise.
+ (__arm_vld1q_s8): Define intrinsic.
+ (__arm_vld1q_s32): Likewise.
+ (__arm_vld1q_s16): Likewise.
+ (__arm_vld1q_u8): Likewise.
+ (__arm_vld1q_u32): Likewise.
+ (__arm_vld1q_u16): Likewise.
+ (__arm_vldrhq_gather_offset_s32): Likewise.
+ (__arm_vldrhq_gather_offset_s16): Likewise.
+ (__arm_vldrhq_gather_offset_u32): Likewise.
+ (__arm_vldrhq_gather_offset_u16): Likewise.
+ (__arm_vldrhq_gather_offset_z_s32): Likewise.
+ (__arm_vldrhq_gather_offset_z_s16): Likewise.
+ (__arm_vldrhq_gather_offset_z_u32): Likewise.
+ (__arm_vldrhq_gather_offset_z_u16): Likewise.
+ (__arm_vldrhq_gather_shifted_offset_s32): Likewise.
+ (__arm_vldrhq_gather_shifted_offset_s16): Likewise.
+ (__arm_vldrhq_gather_shifted_offset_u32): Likewise.
+ (__arm_vldrhq_gather_shifted_offset_u16): Likewise.
+ (__arm_vldrhq_gather_shifted_offset_z_s32): Likewise.
+ (__arm_vldrhq_gather_shifted_offset_z_s16): Likewise.
+ (__arm_vldrhq_gather_shifted_offset_z_u32): Likewise.
+ (__arm_vldrhq_gather_shifted_offset_z_u16): Likewise.
+ (__arm_vldrhq_s32): Likewise.
+ (__arm_vldrhq_s16): Likewise.
+ (__arm_vldrhq_u32): Likewise.
+ (__arm_vldrhq_u16): Likewise.
+ (__arm_vldrhq_z_s32): Likewise.
+ (__arm_vldrhq_z_s16): Likewise.
+ (__arm_vldrhq_z_u32): Likewise.
+ (__arm_vldrhq_z_u16): Likewise.
+ (__arm_vldrwq_s32): Likewise.
+ (__arm_vldrwq_u32): Likewise.
+ (__arm_vldrwq_z_s32): Likewise.
+ (__arm_vldrwq_z_u32): Likewise.
+ (__arm_vld1q_f32): Likewise.
+ (__arm_vld1q_f16): Likewise.
+ (__arm_vldrwq_f32): Likewise.
+ (__arm_vldrwq_z_f32): Likewise.
+ (__arm_vldrhq_z_f16): Likewise.
+ (__arm_vldrhq_f16): Likewise.
+ (vld1q): Define polymorphic variant.
+ (vldrhq_gather_offset): Likewise.
+ (vldrhq_gather_offset_z): Likewise.
+ (vldrhq_gather_shifted_offset): Likewise.
+ (vldrhq_gather_shifted_offset_z): Likewise.
+ * config/arm/arm_mve_builtins.def (LDRU): Use builtin qualifier.
+ (LDRS): Likewise.
+ (LDRU_Z): Likewise.
+ (LDRS_Z): Likewise.
+ (LDRGU_Z): Likewise.
+ (LDRGU): Likewise.
+ (LDRGS_Z): Likewise.
+ (LDRGS): Likewise.
+ * config/arm/mve.md (MVE_H_ELEM): Define mode iterator.
+ (V_sz_elem1): Likewise.
+ (VLD1Q): Define iterator.
+ (VLDRHGOQ): Likewise.
+ (VLDRHGSOQ): Likewise.
+ (VLDRHQ): Likewise.
+ (VLDRWQ): Likewise.
+ (mve_vldrhq_fv8hf): Define RTL pattern.
+ (mve_vldrhq_gather_offset_<supf><mode>): Likewise.
+ (mve_vldrhq_gather_offset_z_<supf><mode>): Likewise.
+ (mve_vldrhq_gather_shifted_offset_<supf><mode>): Likewise.
+ (mve_vldrhq_gather_shifted_offset_z_<supf><mode>): Likewise.
+ (mve_vldrhq_<supf><mode>): Likewise.
+ (mve_vldrhq_z_fv8hf): Likewise.
+ (mve_vldrhq_z_<supf><mode>): Likewise.
+ (mve_vldrwq_fv4sf): Likewise.
+ (mve_vldrwq_<supf>v4si): Likewise.
+ (mve_vldrwq_z_fv4sf): Likewise.
+ (mve_vldrwq_z_<supf>v4si): Likewise.
+ (mve_vld1q_f<mode>): Define RTL expand pattern.
+ (mve_vld1q_<supf><mode>): Likewise.
+
2020-03-18 Andre Vieira <andre.simoesdiasvieira@arm.com>
Mihail Ionescu <mihail.ionescu@arm.com>
Srinath Parvathaneni <srinath.parvathaneni@arm.com>
#define vldrbq_z_u32(__base, __p) __arm_vldrbq_z_u32(__base, __p)
#define vldrwq_gather_base_z_u32(__addr, __offset, __p) __arm_vldrwq_gather_base_z_u32(__addr, __offset, __p)
#define vldrwq_gather_base_z_s32(__addr, __offset, __p) __arm_vldrwq_gather_base_z_s32(__addr, __offset, __p)
+#define vld1q_s8(__base) __arm_vld1q_s8(__base)
+#define vld1q_s32(__base) __arm_vld1q_s32(__base)
+#define vld1q_s16(__base) __arm_vld1q_s16(__base)
+#define vld1q_u8(__base) __arm_vld1q_u8(__base)
+#define vld1q_u32(__base) __arm_vld1q_u32(__base)
+#define vld1q_u16(__base) __arm_vld1q_u16(__base)
+#define vldrhq_gather_offset_s32(__base, __offset) __arm_vldrhq_gather_offset_s32(__base, __offset)
+#define vldrhq_gather_offset_s16(__base, __offset) __arm_vldrhq_gather_offset_s16(__base, __offset)
+#define vldrhq_gather_offset_u32(__base, __offset) __arm_vldrhq_gather_offset_u32(__base, __offset)
+#define vldrhq_gather_offset_u16(__base, __offset) __arm_vldrhq_gather_offset_u16(__base, __offset)
+#define vldrhq_gather_offset_z_s32(__base, __offset, __p) __arm_vldrhq_gather_offset_z_s32(__base, __offset, __p)
+#define vldrhq_gather_offset_z_s16(__base, __offset, __p) __arm_vldrhq_gather_offset_z_s16(__base, __offset, __p)
+#define vldrhq_gather_offset_z_u32(__base, __offset, __p) __arm_vldrhq_gather_offset_z_u32(__base, __offset, __p)
+#define vldrhq_gather_offset_z_u16(__base, __offset, __p) __arm_vldrhq_gather_offset_z_u16(__base, __offset, __p)
+#define vldrhq_gather_shifted_offset_s32(__base, __offset) __arm_vldrhq_gather_shifted_offset_s32(__base, __offset)
+#define vldrhq_gather_shifted_offset_s16(__base, __offset) __arm_vldrhq_gather_shifted_offset_s16(__base, __offset)
+#define vldrhq_gather_shifted_offset_u32(__base, __offset) __arm_vldrhq_gather_shifted_offset_u32(__base, __offset)
+#define vldrhq_gather_shifted_offset_u16(__base, __offset) __arm_vldrhq_gather_shifted_offset_u16(__base, __offset)
+#define vldrhq_gather_shifted_offset_z_s32(__base, __offset, __p) __arm_vldrhq_gather_shifted_offset_z_s32(__base, __offset, __p)
+#define vldrhq_gather_shifted_offset_z_s16(__base, __offset, __p) __arm_vldrhq_gather_shifted_offset_z_s16(__base, __offset, __p)
+#define vldrhq_gather_shifted_offset_z_u32(__base, __offset, __p) __arm_vldrhq_gather_shifted_offset_z_u32(__base, __offset, __p)
+#define vldrhq_gather_shifted_offset_z_u16(__base, __offset, __p) __arm_vldrhq_gather_shifted_offset_z_u16(__base, __offset, __p)
+#define vldrhq_s32(__base) __arm_vldrhq_s32(__base)
+#define vldrhq_s16(__base) __arm_vldrhq_s16(__base)
+#define vldrhq_u32(__base) __arm_vldrhq_u32(__base)
+#define vldrhq_u16(__base) __arm_vldrhq_u16(__base)
+#define vldrhq_z_s32(__base, __p) __arm_vldrhq_z_s32(__base, __p)
+#define vldrhq_z_s16(__base, __p) __arm_vldrhq_z_s16(__base, __p)
+#define vldrhq_z_u32(__base, __p) __arm_vldrhq_z_u32(__base, __p)
+#define vldrhq_z_u16(__base, __p) __arm_vldrhq_z_u16(__base, __p)
+#define vldrwq_s32(__base) __arm_vldrwq_s32(__base)
+#define vldrwq_u32(__base) __arm_vldrwq_u32(__base)
+#define vldrwq_z_s32(__base, __p) __arm_vldrwq_z_s32(__base, __p)
+#define vldrwq_z_u32(__base, __p) __arm_vldrwq_z_u32(__base, __p)
+#define vld1q_f32(__base) __arm_vld1q_f32(__base)
+#define vld1q_f16(__base) __arm_vld1q_f16(__base)
+#define vldrhq_f16(__base) __arm_vldrhq_f16(__base)
+#define vldrhq_z_f16(__base, __p) __arm_vldrhq_z_f16(__base, __p)
+#define vldrwq_f32(__base) __arm_vldrwq_f32(__base)
+#define vldrwq_z_f32(__base, __p) __arm_vldrwq_z_f32(__base, __p)
#endif
__extension__ extern __inline void
return __builtin_mve_vldrwq_gather_base_z_uv4si (__addr, __offset, __p);
}
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q_s8 (int8_t const * __base)
+{
+ return __builtin_mve_vld1q_sv16qi ((__builtin_neon_qi *) __base);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q_s32 (int32_t const * __base)
+{
+ return __builtin_mve_vld1q_sv4si ((__builtin_neon_si *) __base);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q_s16 (int16_t const * __base)
+{
+ return __builtin_mve_vld1q_sv8hi ((__builtin_neon_hi *) __base);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q_u8 (uint8_t const * __base)
+{
+ return __builtin_mve_vld1q_uv16qi ((__builtin_neon_qi *) __base);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q_u32 (uint32_t const * __base)
+{
+ return __builtin_mve_vld1q_uv4si ((__builtin_neon_si *) __base);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q_u16 (uint16_t const * __base)
+{
+ return __builtin_mve_vld1q_uv8hi ((__builtin_neon_hi *) __base);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_offset_s32 (int16_t const * __base, uint32x4_t __offset)
+{
+ return __builtin_mve_vldrhq_gather_offset_sv4si ((__builtin_neon_hi *) __base, __offset);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_offset_s16 (int16_t const * __base, uint16x8_t __offset)
+{
+ return __builtin_mve_vldrhq_gather_offset_sv8hi ((__builtin_neon_hi *) __base, __offset);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_offset_u32 (uint16_t const * __base, uint32x4_t __offset)
+{
+ return __builtin_mve_vldrhq_gather_offset_uv4si ((__builtin_neon_hi *) __base, __offset);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_offset_u16 (uint16_t const * __base, uint16x8_t __offset)
+{
+ return __builtin_mve_vldrhq_gather_offset_uv8hi ((__builtin_neon_hi *) __base, __offset);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_offset_z_s32 (int16_t const * __base, uint32x4_t __offset, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrhq_gather_offset_z_sv4si ((__builtin_neon_hi *) __base, __offset, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_offset_z_s16 (int16_t const * __base, uint16x8_t __offset, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrhq_gather_offset_z_sv8hi ((__builtin_neon_hi *) __base, __offset, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_offset_z_u32 (uint16_t const * __base, uint32x4_t __offset, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrhq_gather_offset_z_uv4si ((__builtin_neon_hi *) __base, __offset, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_offset_z_u16 (uint16_t const * __base, uint16x8_t __offset, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrhq_gather_offset_z_uv8hi ((__builtin_neon_hi *) __base, __offset, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_shifted_offset_s32 (int16_t const * __base, uint32x4_t __offset)
+{
+ return __builtin_mve_vldrhq_gather_shifted_offset_sv4si ((__builtin_neon_hi *) __base, __offset);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_shifted_offset_s16 (int16_t const * __base, uint16x8_t __offset)
+{
+ return __builtin_mve_vldrhq_gather_shifted_offset_sv8hi ((__builtin_neon_hi *) __base, __offset);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_shifted_offset_u32 (uint16_t const * __base, uint32x4_t __offset)
+{
+ return __builtin_mve_vldrhq_gather_shifted_offset_uv4si ((__builtin_neon_hi *) __base, __offset);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_shifted_offset_u16 (uint16_t const * __base, uint16x8_t __offset)
+{
+ return __builtin_mve_vldrhq_gather_shifted_offset_uv8hi ((__builtin_neon_hi *) __base, __offset);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_shifted_offset_z_s32 (int16_t const * __base, uint32x4_t __offset, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrhq_gather_shifted_offset_z_sv4si ((__builtin_neon_hi *) __base, __offset, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_shifted_offset_z_s16 (int16_t const * __base, uint16x8_t __offset, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrhq_gather_shifted_offset_z_sv8hi ((__builtin_neon_hi *) __base, __offset, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_shifted_offset_z_u32 (uint16_t const * __base, uint32x4_t __offset, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrhq_gather_shifted_offset_z_uv4si ((__builtin_neon_hi *) __base, __offset, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_gather_shifted_offset_z_u16 (uint16_t const * __base, uint16x8_t __offset, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrhq_gather_shifted_offset_z_uv8hi ((__builtin_neon_hi *) __base, __offset, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_s32 (int16_t const * __base)
+{
+ return __builtin_mve_vldrhq_sv4si ((__builtin_neon_hi *) __base);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_s16 (int16_t const * __base)
+{
+ return __builtin_mve_vldrhq_sv8hi ((__builtin_neon_hi *) __base);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_u32 (uint16_t const * __base)
+{
+ return __builtin_mve_vldrhq_uv4si ((__builtin_neon_hi *) __base);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_u16 (uint16_t const * __base)
+{
+ return __builtin_mve_vldrhq_uv8hi ((__builtin_neon_hi *) __base);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_z_s32 (int16_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrhq_z_sv4si ((__builtin_neon_hi *) __base, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_z_s16 (int16_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrhq_z_sv8hi ((__builtin_neon_hi *) __base, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_z_u32 (uint16_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrhq_z_uv4si ((__builtin_neon_hi *) __base, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_z_u16 (uint16_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrhq_z_uv8hi ((__builtin_neon_hi *) __base, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_s32 (int32_t const * __base)
+{
+ return __builtin_mve_vldrwq_sv4si ((__builtin_neon_si *) __base);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_u32 (uint32_t const * __base)
+{
+ return __builtin_mve_vldrwq_uv4si ((__builtin_neon_si *) __base);
+}
+
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_z_s32 (int32_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrwq_z_sv4si ((__builtin_neon_si *) __base, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_z_u32 (uint32_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrwq_z_uv4si ((__builtin_neon_si *) __base, __p);
+}
+
#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */
__extension__ extern __inline void
return __builtin_mve_vsubq_m_n_fv8hf (__inactive, __a, __b, __p);
}
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q_f32 (float32_t const * __base)
+{
+ return __builtin_mve_vld1q_fv4sf((__builtin_neon_si *) __base);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vld1q_f16 (float16_t const * __base)
+{
+ return __builtin_mve_vld1q_fv8hf((__builtin_neon_hi *) __base);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_f32 (float32_t const * __base)
+{
+ return __builtin_mve_vldrwq_fv4sf((__builtin_neon_si *) __base);
+}
+
+__extension__ extern __inline float32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_z_f32 (float32_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrwq_z_fv4sf((__builtin_neon_si *) __base, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_z_f16 (float16_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrhq_z_fv8hf((__builtin_neon_hi *) __base, __p);
+}
+
+__extension__ extern __inline float16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrhq_f16 (float16_t const * __base)
+{
+ return __builtin_mve_vldrhq_fv8hf((__builtin_neon_hi *) __base);
+}
#endif
enum {
int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t][__ARM_mve_type_float16x8_t]: __arm_vorrq_m_f16 (__ARM_mve_coerce(__p0, float16x8_t), __ARM_mve_coerce(__p1, float16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3), \
int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t][__ARM_mve_type_float32x4_t]: __arm_vorrq_m_f32 (__ARM_mve_coerce(__p0, float32x4_t), __ARM_mve_coerce(__p1, float32x4_t), __ARM_mve_coerce(__p2, float32x4_t), p3));})
+#define vld1q(p0) __arm_vld1q(p0)
+#define __arm_vld1q(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8_t_const_ptr]: __arm_vld1q_s8 (__ARM_mve_coerce(__p0, int8_t const *)), \
+ int (*)[__ARM_mve_type_int16_t_const_ptr]: __arm_vld1q_s16 (__ARM_mve_coerce(__p0, int16_t const *)), \
+ int (*)[__ARM_mve_type_int32_t_const_ptr]: __arm_vld1q_s32 (__ARM_mve_coerce(__p0, int32_t const *)), \
+ int (*)[__ARM_mve_type_uint8_t_const_ptr]: __arm_vld1q_u8 (__ARM_mve_coerce(__p0, uint8_t const *)), \
+ int (*)[__ARM_mve_type_uint16_t_const_ptr]: __arm_vld1q_u16 (__ARM_mve_coerce(__p0, uint16_t const *)), \
+ int (*)[__ARM_mve_type_uint32_t_const_ptr]: __arm_vld1q_u32 (__ARM_mve_coerce(__p0, uint32_t const *)), \
+ int (*)[__ARM_mve_type_float16_t_const_ptr]: __arm_vld1q_f16 (__ARM_mve_coerce(__p0, float16_t const *)), \
+ int (*)[__ARM_mve_type_float32_t_const_ptr]: __arm_vld1q_f32 (__ARM_mve_coerce(__p0, float32_t const *)));})
+
#else /* MVE Integer. */
#define vst4q(p0,p1) __arm_vst4q(p0,p1)
int (*)[__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_base_p_s32 (p0, p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_base_p_u32 (p0, p1, __ARM_mve_coerce(__p2, uint32x4_t), p3));})
+#define vld1q(p0) __arm_vld1q(p0)
+#define __arm_vld1q(p0) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8_t_const_ptr]: __arm_vld1q_s8 (__ARM_mve_coerce(__p0, int8_t const *)), \
+ int (*)[__ARM_mve_type_int16_t_const_ptr]: __arm_vld1q_s16 (__ARM_mve_coerce(__p0, int16_t const *)), \
+ int (*)[__ARM_mve_type_int32_t_const_ptr]: __arm_vld1q_s32 (__ARM_mve_coerce(__p0, int32_t const *)), \
+ int (*)[__ARM_mve_type_uint8_t_const_ptr]: __arm_vld1q_u8 (__ARM_mve_coerce(__p0, uint8_t const *)), \
+ int (*)[__ARM_mve_type_uint16_t_const_ptr]: __arm_vld1q_u16 (__ARM_mve_coerce(__p0, uint16_t const *)), \
+ int (*)[__ARM_mve_type_uint32_t_const_ptr]: __arm_vld1q_u32 (__ARM_mve_coerce(__p0, uint32_t const *)));})
+
+#define vldrhq_gather_offset(p0,p1) __arm_vldrhq_gather_offset(p0,p1)
+#define __arm_vldrhq_gather_offset(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+ int (*)[__ARM_mve_type_int16_t_const_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_s16 (__ARM_mve_coerce(__p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_int16_t_const_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_s32 (__ARM_mve_coerce(__p0, int16_t const *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_uint16_t_const_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_u16 (__ARM_mve_coerce(__p0, uint16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint16_t_const_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_u32 (__ARM_mve_coerce(__p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vldrhq_gather_offset_z(p0,p1,p2) __arm_vldrhq_gather_offset_z(p0,p1,p2)
+#define __arm_vldrhq_gather_offset_z(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+ int (*)[__ARM_mve_type_int16_t_const_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_s16 (__ARM_mve_coerce(__p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_int16_t_const_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_s32 (__ARM_mve_coerce(__p0, int16_t const *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+ int (*)[__ARM_mve_type_uint16_t_const_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_u16 (__ARM_mve_coerce(__p0, uint16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_uint16_t_const_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_u32 (__ARM_mve_coerce(__p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+
+#define vldrhq_gather_shifted_offset(p0,p1) __arm_vldrhq_gather_shifted_offset(p0,p1)
+#define __arm_vldrhq_gather_shifted_offset(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+ int (*)[__ARM_mve_type_int16_t_const_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_s16 (__ARM_mve_coerce(__p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_int16_t_const_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_s32 (__ARM_mve_coerce(__p0, int16_t const *), __ARM_mve_coerce(__p1, uint32x4_t)), \
+ int (*)[__ARM_mve_type_uint16_t_const_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_u16 (__ARM_mve_coerce(__p0, uint16_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint16_t_const_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_u32 (__ARM_mve_coerce(__p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vldrhq_gather_shifted_offset_z(p0,p1,p2) __arm_vldrhq_gather_shifted_offset_z(p0,p1,p2)
+#define __arm_vldrhq_gather_shifted_offset_z(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+ int (*)[__ARM_mve_type_int16_t_const_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_s16 (__ARM_mve_coerce(__p0, int16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_int16_t_const_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_s32 (__ARM_mve_coerce(__p0, int16_t const *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \
+ int (*)[__ARM_mve_type_uint16_t_const_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_u16 (__ARM_mve_coerce(__p0, uint16_t const *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_uint16_t_const_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_u32 (__ARM_mve_coerce(__p0, uint16_t const *), __ARM_mve_coerce(__p1, uint32x4_t), p2));})
+
#endif /* MVE Integer. */
#define vldrbq_gather_offset_z(p0,p1,p2) __arm_vldrbq_gather_offset_z(p0,p1,p2)
VAR3 (LDRGU_Z, vldrbq_gather_offset_z_u, v16qi, v8hi, v4si)
VAR3 (LDRS_Z, vldrbq_z_s, v16qi, v8hi, v4si)
VAR3 (LDRU_Z, vldrbq_z_u, v16qi, v8hi, v4si)
+VAR3 (LDRU, vld1q_u, v16qi, v8hi, v4si)
+VAR3 (LDRS, vld1q_s, v16qi, v8hi, v4si)
+VAR2 (LDRU_Z, vldrhq_z_u, v8hi, v4si)
+VAR2 (LDRU, vldrhq_u, v8hi, v4si)
+VAR2 (LDRS_Z, vldrhq_z_s, v8hi, v4si)
+VAR2 (LDRS, vldrhq_s, v8hi, v4si)
+VAR2 (LDRS, vld1q_f, v8hf, v4sf)
+VAR2 (LDRGU_Z, vldrhq_gather_shifted_offset_z_u, v8hi, v4si)
+VAR2 (LDRGU_Z, vldrhq_gather_offset_z_u, v8hi, v4si)
+VAR2 (LDRGU, vldrhq_gather_shifted_offset_u, v8hi, v4si)
+VAR2 (LDRGU, vldrhq_gather_offset_u, v8hi, v4si)
+VAR2 (LDRGS_Z, vldrhq_gather_shifted_offset_z_s, v8hi, v4si)
+VAR2 (LDRGS_Z, vldrhq_gather_offset_z_s, v8hi, v4si)
+VAR2 (LDRGS, vldrhq_gather_shifted_offset_s, v8hi, v4si)
+VAR2 (LDRGS, vldrhq_gather_offset_s, v8hi, v4si)
+VAR1 (LDRS, vldrhq_f, v8hf)
+VAR1 (LDRS_Z, vldrhq_z_f, v8hf)
+VAR1 (LDRS, vldrwq_f, v4sf)
+VAR1 (LDRS, vldrwq_s, v4si)
+VAR1 (LDRU, vldrwq_u, v4si)
+VAR1 (LDRS_Z, vldrwq_z_f, v4sf)
+VAR1 (LDRS_Z, vldrwq_z_s, v4si)
+VAR1 (LDRU_Z, vldrwq_z_u, v4si)
(define_mode_iterator MVE_3 [V16QI V8HI])
(define_mode_iterator MVE_2 [V16QI V8HI V4SI])
(define_mode_iterator MVE_5 [V8HI V4SI])
+(define_mode_iterator MVE_6 [V8HI V4SI])
(define_c_enum "unspec" [VST4Q VRNDXQ_F VRNDQ_F VRNDPQ_F VRNDNQ_F VRNDMQ_F
VRNDAQ_F VREV64Q_F VNEGQ_F VDUPQ_N_F VABSQ_F VREV32Q_F
VFMAQ_M_N_F VFMASQ_M_N_F VFMSQ_M_F VMAXNMQ_M_F
VMINNMQ_M_F VSUBQ_M_F VSTRWQSB_S VSTRWQSB_U
VSTRBQSO_S VSTRBQSO_U VSTRBQ_S VSTRBQ_U VLDRBQGO_S
- VLDRBQGO_U VLDRBQ_S VLDRBQ_U VLDRWQGB_S VLDRWQGB_U])
+ VLDRBQGO_U VLDRBQ_S VLDRBQ_U VLDRWQGB_S VLDRWQGB_U
+ VLD1Q_F VLD1Q_S VLD1Q_U VLDRHQ_F VLDRHQGO_S
+ VLDRHQGO_U VLDRHQGSO_S VLDRHQGSO_U VLDRHQ_S VLDRHQ_U
+ VLDRWQ_F VLDRWQ_S VLDRWQ_U])
-(define_mode_attr MVE_CNVT [(V8HI "V8HF") (V4SI "V4SF")
- (V8HF "V8HI") (V4SF "V4SI")])
+(define_mode_attr MVE_CNVT [(V8HI "V8HF") (V4SI "V4SF") (V8HF "V8HI")
+ (V4SF "V4SI")])
(define_int_attr supf [(VCVTQ_TO_F_S "s") (VCVTQ_TO_F_U "u") (VREV16Q_S "s")
(VREV16Q_U "u") (VMVNQ_N_S "s") (VMVNQ_N_U "u")
(VSTRWQSB_S "s") (VSTRWQSB_U "u") (VSTRBQSO_S "s")
(VSTRBQSO_U "u") (VSTRBQ_S "s") (VSTRBQ_U "u")
(VLDRBQGO_S "s") (VLDRBQGO_U "u") (VLDRBQ_S "s")
- (VLDRBQ_U "u") (VLDRWQGB_S "s") (VLDRWQGB_U "u")])
+ (VLDRBQ_U "u") (VLDRWQGB_S "s") (VLDRWQGB_U "u")
+ (VLD1Q_S "s") (VLD1Q_U "u") (VLDRHQGO_S "s")
+ (VLDRHQGO_U "u") (VLDRHQGSO_S "s") (VLDRHQGSO_U "u")
+ (VLDRHQ_S "s") (VLDRHQ_U "u") (VLDRWQ_S "s")
+ (VLDRWQ_U "u")])
(define_int_attr mode1 [(VCTP8Q "8") (VCTP16Q "16") (VCTP32Q "32")
(VCTP64Q "64") (VCTP8Q_M "8") (VCTP16Q_M "16")
(V4SI "mve_imm_31")])
(define_mode_attr MVE_constraint3 [ (V8HI "Rb") (V4SI "Rd")])
(define_mode_attr MVE_pred3 [ (V8HI "mve_imm_8") (V4SI "mve_imm_16")])
-
(define_mode_attr MVE_constraint1 [ (V8HI "Ra") (V4SI "Rc")])
(define_mode_attr MVE_pred1 [ (V8HI "mve_imm_7") (V4SI "mve_imm_15")])
(define_mode_attr MVE_B_ELEM [ (V16QI "V16QI") (V8HI "V8QI") (V4SI "V4QI")])
+(define_mode_attr MVE_H_ELEM [ (V8HI "V8HI") (V4SI "V4HI")])
+(define_mode_attr V_sz_elem1 [(V16QI "b") (V8HI "h") (V4SI "w") (V8HF "h")
+ (V4SF "w")])
(define_int_iterator VCVTQ_TO_F [VCVTQ_TO_F_S VCVTQ_TO_F_U])
(define_int_iterator VMVNQ_N [VMVNQ_N_U VMVNQ_N_S])
(define_int_iterator VLDRBGOQ [VLDRBQGO_S VLDRBQGO_U])
(define_int_iterator VLDRBQ [VLDRBQ_S VLDRBQ_U])
(define_int_iterator VLDRWGBQ [VLDRWQGB_S VLDRWQGB_U])
+(define_int_iterator VLD1Q [VLD1Q_S VLD1Q_U])
+(define_int_iterator VLDRHGOQ [VLDRHQGO_S VLDRHQGO_U])
+(define_int_iterator VLDRHGSOQ [VLDRHQGSO_S VLDRHQGSO_U])
+(define_int_iterator VLDRHQ [VLDRHQ_S VLDRHQ_U])
+(define_int_iterator VLDRWQ [VLDRWQ_S VLDRWQ_U])
(define_insn "*mve_mov<mode>"
[(set (match_operand:MVE_types 0 "nonimmediate_operand" "=w,w,r,w,w,r,w,Us")
return "";
}
[(set_attr "length" "8")])
+
+;;
+;; [vldrhq_f]
+;;
+(define_insn "mve_vldrhq_fv8hf"
+ [(set (match_operand:V8HF 0 "s_register_operand" "=w")
+ (unspec:V8HF [(match_operand:V8HI 1 "memory_operand" "Us")]
+ VLDRHQ_F))
+ ]
+ "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+{
+ rtx ops[2];
+ int regno = REGNO (operands[0]);
+ ops[0] = gen_rtx_REG (TImode, regno);
+ ops[1] = operands[1];
+ output_asm_insn ("vldrh.f16\t%q0, %E1",ops);
+ return "";
+}
+ [(set_attr "length" "4")])
+
+;;
+;; [vldrhq_gather_offset_s vldrhq_gather_offset_u]
+;;
+(define_insn "mve_vldrhq_gather_offset_<supf><mode>"
+ [(set (match_operand:MVE_6 0 "s_register_operand" "=&w")
+ (unspec:MVE_6 [(match_operand:<MVE_H_ELEM> 1 "memory_operand" "Us")
+ (match_operand:MVE_6 2 "s_register_operand" "w")]
+ VLDRHGOQ))
+ ]
+ "TARGET_HAVE_MVE"
+{
+ rtx ops[3];
+ ops[0] = operands[0];
+ ops[1] = operands[1];
+ ops[2] = operands[2];
+ if (!strcmp ("<supf>","s") && <V_sz_elem> == 16)
+ output_asm_insn ("vldrh.u16\t%q0, [%m1, %q2]",ops);
+ else
+ output_asm_insn ("vldrh.<supf><V_sz_elem>\t%q0, [%m1, %q2]",ops);
+ return "";
+}
+ [(set_attr "length" "4")])
+
+;;
+;; [vldrhq_gather_offset_z_s vldrhq_gather_offset_z_u]
+;;
+(define_insn "mve_vldrhq_gather_offset_z_<supf><mode>"
+ [(set (match_operand:MVE_6 0 "s_register_operand" "=&w")
+ (unspec:MVE_6 [(match_operand:<MVE_H_ELEM> 1 "memory_operand" "Us")
+ (match_operand:MVE_6 2 "s_register_operand" "w")
+ (match_operand:HI 3 "vpr_register_operand" "Up")
+ ]VLDRHGOQ))
+ ]
+ "TARGET_HAVE_MVE"
+{
+ rtx ops[4];
+ ops[0] = operands[0];
+ ops[1] = operands[1];
+ ops[2] = operands[2];
+ ops[3] = operands[3];
+ if (!strcmp ("<supf>","s") && <V_sz_elem> == 16)
+ output_asm_insn ("vpst\n\tvldrht.u16\t%q0, [%m1, %q2]",ops);
+ else
+ output_asm_insn ("vpst\n\tvldrht.<supf><V_sz_elem>\t%q0, [%m1, %q2]",ops);
+ return "";
+}
+ [(set_attr "length" "8")])
+
+;;
+;; [vldrhq_gather_shifted_offset_s vldrhq_gather_shifted_offset_u]
+;;
+(define_insn "mve_vldrhq_gather_shifted_offset_<supf><mode>"
+ [(set (match_operand:MVE_6 0 "s_register_operand" "=&w")
+ (unspec:MVE_6 [(match_operand:<MVE_H_ELEM> 1 "memory_operand" "Us")
+ (match_operand:MVE_6 2 "s_register_operand" "w")]
+ VLDRHGSOQ))
+ ]
+ "TARGET_HAVE_MVE"
+{
+ rtx ops[3];
+ ops[0] = operands[0];
+ ops[1] = operands[1];
+ ops[2] = operands[2];
+ if (!strcmp ("<supf>","s") && <V_sz_elem> == 16)
+ output_asm_insn ("vldrh.u16\t%q0, [%m1, %q2, uxtw #1]",ops);
+ else
+ output_asm_insn ("vldrh.<supf><V_sz_elem>\t%q0, [%m1, %q2, uxtw #1]",ops);
+ return "";
+}
+ [(set_attr "length" "4")])
+
+;;
+;; [vldrhq_gather_shifted_offset_z_s vldrhq_gather_shited_offset_z_u]
+;;
+(define_insn "mve_vldrhq_gather_shifted_offset_z_<supf><mode>"
+ [(set (match_operand:MVE_6 0 "s_register_operand" "=&w")
+ (unspec:MVE_6 [(match_operand:<MVE_H_ELEM> 1 "memory_operand" "Us")
+ (match_operand:MVE_6 2 "s_register_operand" "w")
+ (match_operand:HI 3 "vpr_register_operand" "Up")
+ ]VLDRHGSOQ))
+ ]
+ "TARGET_HAVE_MVE"
+{
+ rtx ops[4];
+ ops[0] = operands[0];
+ ops[1] = operands[1];
+ ops[2] = operands[2];
+ ops[3] = operands[3];
+ if (!strcmp ("<supf>","s") && <V_sz_elem> == 16)
+ output_asm_insn ("vpst\n\tvldrht.u16\t%q0, [%m1, %q2, uxtw #1]",ops);
+ else
+ output_asm_insn ("vpst\n\tvldrht.<supf><V_sz_elem>\t%q0, [%m1, %q2, uxtw #1]",ops);
+ return "";
+}
+ [(set_attr "length" "8")])
+
+;;
+;;
+;; [vldrhq_s, vldrhq_u]
+;;
+(define_insn "mve_vldrhq_<supf><mode>"
+ [(set (match_operand:MVE_6 0 "s_register_operand" "=w")
+ (unspec:MVE_6 [(match_operand:<MVE_H_ELEM> 1 "memory_operand" "Us")]
+ VLDRHQ))
+ ]
+ "TARGET_HAVE_MVE"
+{
+ rtx ops[2];
+ int regno = REGNO (operands[0]);
+ ops[0] = gen_rtx_REG (TImode, regno);
+ ops[1] = operands[1];
+ output_asm_insn ("vldrh.<supf><V_sz_elem>\t%q0, %E1",ops);
+ return "";
+}
+ [(set_attr "length" "4")])
+
+;;
+;; [vldrhq_z_f]
+;;
+(define_insn "mve_vldrhq_z_fv8hf"
+ [(set (match_operand:V8HF 0 "s_register_operand" "=w")
+ (unspec:V8HF [(match_operand:V8HI 1 "memory_operand" "Us")
+ (match_operand:HI 2 "vpr_register_operand" "Up")]
+ VLDRHQ_F))
+ ]
+ "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+{
+ rtx ops[2];
+ int regno = REGNO (operands[0]);
+ ops[0] = gen_rtx_REG (TImode, regno);
+ ops[1] = operands[1];
+ output_asm_insn ("vpst\n\tvldrht.f16\t%q0, %E1",ops);
+ return "";
+}
+ [(set_attr "length" "8")])
+
+;;
+;; [vldrhq_z_s vldrhq_z_u]
+;;
+(define_insn "mve_vldrhq_z_<supf><mode>"
+ [(set (match_operand:MVE_6 0 "s_register_operand" "=w")
+ (unspec:MVE_6 [(match_operand:<MVE_H_ELEM> 1 "memory_operand" "Us")
+ (match_operand:HI 2 "vpr_register_operand" "Up")]
+ VLDRHQ))
+ ]
+ "TARGET_HAVE_MVE"
+{
+ rtx ops[2];
+ int regno = REGNO (operands[0]);
+ ops[0] = gen_rtx_REG (TImode, regno);
+ ops[1] = operands[1];
+ output_asm_insn ("vpst\n\tvldrht.<supf><V_sz_elem>\t%q0, %E1",ops);
+ return "";
+}
+ [(set_attr "length" "8")])
+
+;;
+;; [vldrwq_f]
+;;
+(define_insn "mve_vldrwq_fv4sf"
+ [(set (match_operand:V4SF 0 "s_register_operand" "=w")
+ (unspec:V4SF [(match_operand:V4SI 1 "memory_operand" "Us")]
+ VLDRWQ_F))
+ ]
+ "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+{
+ rtx ops[2];
+ int regno = REGNO (operands[0]);
+ ops[0] = gen_rtx_REG (TImode, regno);
+ ops[1] = operands[1];
+ output_asm_insn ("vldrw.f32\t%q0, %E1",ops);
+ return "";
+}
+ [(set_attr "length" "4")])
+
+;;
+;; [vldrwq_s vldrwq_u]
+;;
+(define_insn "mve_vldrwq_<supf>v4si"
+ [(set (match_operand:V4SI 0 "s_register_operand" "=w")
+ (unspec:V4SI [(match_operand:V4SI 1 "memory_operand" "Us")]
+ VLDRWQ))
+ ]
+ "TARGET_HAVE_MVE"
+{
+ rtx ops[2];
+ int regno = REGNO (operands[0]);
+ ops[0] = gen_rtx_REG (TImode, regno);
+ ops[1] = operands[1];
+ output_asm_insn ("vldrw.<supf>32\t%q0, %E1",ops);
+ return "";
+}
+ [(set_attr "length" "4")])
+
+;;
+;; [vldrwq_z_f]
+;;
+(define_insn "mve_vldrwq_z_fv4sf"
+ [(set (match_operand:V4SF 0 "s_register_operand" "=w")
+ (unspec:V4SF [(match_operand:V4SI 1 "memory_operand" "Us")
+ (match_operand:HI 2 "vpr_register_operand" "Up")]
+ VLDRWQ_F))
+ ]
+ "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+{
+ rtx ops[2];
+ int regno = REGNO (operands[0]);
+ ops[0] = gen_rtx_REG (TImode, regno);
+ ops[1] = operands[1];
+ output_asm_insn ("vpst\n\tvldrwt.f32\t%q0, %E1",ops);
+ return "";
+}
+ [(set_attr "length" "8")])
+
+;;
+;; [vldrwq_z_s vldrwq_z_u]
+;;
+(define_insn "mve_vldrwq_z_<supf>v4si"
+ [(set (match_operand:V4SI 0 "s_register_operand" "=w")
+ (unspec:V4SI [(match_operand:V4SI 1 "memory_operand" "Us")
+ (match_operand:HI 2 "vpr_register_operand" "Up")]
+ VLDRWQ))
+ ]
+ "TARGET_HAVE_MVE"
+{
+ rtx ops[2];
+ int regno = REGNO (operands[0]);
+ ops[0] = gen_rtx_REG (TImode, regno);
+ ops[1] = operands[1];
+ output_asm_insn ("vpst\n\tvldrwt.<supf>32\t%q0, %E1",ops);
+ return "";
+}
+ [(set_attr "length" "8")])
+
+(define_expand "mve_vld1q_f<mode>"
+ [(match_operand:MVE_0 0 "s_register_operand")
+ (unspec:MVE_0 [(match_operand:<MVE_CNVT> 1 "memory_operand")] VLD1Q_F)
+ ]
+ "TARGET_HAVE_MVE || TARGET_HAVE_MVE_FLOAT"
+{
+ emit_insn (gen_mve_vldr<V_sz_elem1>q_f<mode>(operands[0],operands[1]));
+ DONE;
+})
+
+(define_expand "mve_vld1q_<supf><mode>"
+ [(match_operand:MVE_2 0 "s_register_operand")
+ (unspec:MVE_2 [(match_operand:MVE_2 1 "memory_operand")] VLD1Q)
+ ]
+ "TARGET_HAVE_MVE"
+{
+ emit_insn (gen_mve_vldr<V_sz_elem1>q_<supf><mode>(operands[0],operands[1]));
+ DONE;
+})
+2020-03-18 Andre Vieira <andre.simoesdiasvieira@arm.com>
+ Mihail Ionescu <mihail.ionescu@arm.com>
+ Srinath Parvathaneni <srinath.parvathaneni@arm.com>
+
+ * gcc.target/arm/mve/intrinsics/vld1q_f16.c: New test.
+ * gcc.target/arm/mve/intrinsics/vld1q_f32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vld1q_s16.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vld1q_s32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vld1q_s8.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vld1q_u16.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vld1q_u32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vld1q_u8.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_f16.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_gather_offset_s16.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_gather_offset_s32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_gather_offset_u16.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_gather_offset_u32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_gather_offset_z_s16.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_gather_offset_z_s32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_gather_offset_z_u16.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_gather_offset_z_u32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_gather_shifted_offset_s16.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_gather_shifted_offset_s32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_gather_shifted_offset_u16.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_gather_shifted_offset_u32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_gather_shifted_offset_z_s16.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_gather_shifted_offset_z_s32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_gather_shifted_offset_z_u16.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_gather_shifted_offset_z_u32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_s16.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_s32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_u16.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_u32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_z_f16.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_z_s16.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_z_s32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_z_u16.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrhq_z_u32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrwq_f32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrwq_s32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrwq_u32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrwq_z_f32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrwq_z_s32.c: Likewise.
+ * gcc.target/arm/mve/intrinsics/vldrwq_z_u32.c: Likewise.
+
2020-03-18 Andre Vieira <andre.simoesdiasvieira@arm.com>
Mihail Ionescu <mihail.ionescu@arm.com>
Srinath Parvathaneni <srinath.parvathaneni@arm.com>
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+float16x8_t
+foo (float16_t const * base)
+{
+ return vld1q_f16 (base);
+}
+
+/* { dg-final { scan-assembler "vldrh.f16" } } */
+
+float16x8_t
+foo1 (float16_t const * base)
+{
+ return vld1q (base);
+}
+
+/* { dg-final { scan-assembler "vldrh.f16" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+float32x4_t
+foo (float32_t const * base)
+{
+ return vld1q_f32 (base);
+}
+
+/* { dg-final { scan-assembler "vldrw.f32" } } */
+
+float32x4_t
+foo1 (float32_t const * base)
+{
+ return vld1q (base);
+}
+
+/* { dg-final { scan-assembler "vldrw.f32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+int16x8_t
+foo (int16_t const * base)
+{
+ return vld1q_s16 (base);
+}
+
+/* { dg-final { scan-assembler "vldrh.s16" } } */
+
+int16x8_t
+foo1 (int16_t const * base)
+{
+ return vld1q (base);
+}
+
+/* { dg-final { scan-assembler "vldrh.s16" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+int32x4_t
+foo (int32_t const * base)
+{
+ return vld1q_s32 (base);
+}
+
+/* { dg-final { scan-assembler "vldrw.s32" } } */
+
+int32x4_t
+foo1 (int32_t const * base)
+{
+ return vld1q (base);
+}
+
+/* { dg-final { scan-assembler "vldrw.s32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+int8x16_t
+foo (int8_t const * base)
+{
+ return vld1q_s8 (base);
+}
+
+/* { dg-final { scan-assembler "vldrb.s8" } } */
+
+int8x16_t
+foo1 (int8_t const * base)
+{
+ return vld1q (base);
+}
+
+/* { dg-final { scan-assembler "vldrb.s8" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+uint16x8_t
+foo (uint16_t const * base)
+{
+ return vld1q_u16 (base);
+}
+
+/* { dg-final { scan-assembler "vldrh.u16" } } */
+
+uint16x8_t
+foo1 (uint16_t const * base)
+{
+ return vld1q (base);
+}
+
+/* { dg-final { scan-assembler "vldrh.u16" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+uint32x4_t
+foo (uint32_t const * base)
+{
+ return vld1q_u32 (base);
+}
+
+/* { dg-final { scan-assembler "vldrw.u32" } } */
+
+uint32x4_t
+foo1 (uint32_t const * base)
+{
+ return vld1q (base);
+}
+
+/* { dg-final { scan-assembler "vldrw.u32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+uint8x16_t
+foo (uint8_t const * base)
+{
+ return vld1q_u8 (base);
+}
+
+/* { dg-final { scan-assembler "vldrb.u8" } } */
+
+uint8x16_t
+foo1 (uint8_t const * base)
+{
+ return vld1q (base);
+}
+
+/* { dg-final { scan-assembler "vldrb.u8" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+float16x8_t
+foo (float16_t const * base)
+{
+ return vldrhq_f16 (base);
+}
+
+/* { dg-final { scan-assembler "vldrh.f16" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+int16x8_t
+foo (int16_t const * base, uint16x8_t offset)
+{
+ return vldrhq_gather_offset_s16 (base, offset);
+}
+
+/* { dg-final { scan-assembler "vldrh.u16" } } */
+
+int16x8_t
+foo1 (int16_t const * base, uint16x8_t offset)
+{
+ return vldrhq_gather_offset (base, offset);
+}
+
+/* { dg-final { scan-assembler "vldrh.u16" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+int32x4_t
+foo (int16_t const * base, uint32x4_t offset)
+{
+ return vldrhq_gather_offset_s32 (base, offset);
+}
+
+/* { dg-final { scan-assembler "vldrh.s32" } } */
+
+int32x4_t
+foo1 (int16_t const * base, uint32x4_t offset)
+{
+ return vldrhq_gather_offset (base, offset);
+}
+
+/* { dg-final { scan-assembler "vldrh.s32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+uint16x8_t
+foo (uint16_t const * base, uint16x8_t offset)
+{
+ return vldrhq_gather_offset_u16 (base, offset);
+}
+
+/* { dg-final { scan-assembler "vldrh.u16" } } */
+
+uint16x8_t
+foo1 (uint16_t const * base, uint16x8_t offset)
+{
+ return vldrhq_gather_offset (base, offset);
+}
+
+/* { dg-final { scan-assembler "vldrh.u16" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+uint32x4_t
+foo (uint16_t const * base, uint32x4_t offset)
+{
+ return vldrhq_gather_offset_u32 (base, offset);
+}
+
+/* { dg-final { scan-assembler "vldrh.u32" } } */
+
+uint32x4_t
+foo1 (uint16_t const * base, uint32x4_t offset)
+{
+ return vldrhq_gather_offset (base, offset);
+}
+
+/* { dg-final { scan-assembler "vldrh.u32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+int16x8_t
+foo (int16_t const * base, uint16x8_t offset, mve_pred16_t p)
+{
+ return vldrhq_gather_offset_z_s16 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.u16" } } */
+
+int16x8_t
+foo1 (int16_t const * base, uint16x8_t offset, mve_pred16_t p)
+{
+ return vldrhq_gather_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.u16" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+int32x4_t
+foo (int16_t const * base, uint32x4_t offset, mve_pred16_t p)
+{
+ return vldrhq_gather_offset_z_s32 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.s32" } } */
+
+int32x4_t
+foo1 (int16_t const * base, uint32x4_t offset, mve_pred16_t p)
+{
+ return vldrhq_gather_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.s32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+uint16x8_t
+foo (uint16_t const * base, uint16x8_t offset, mve_pred16_t p)
+{
+ return vldrhq_gather_offset_z_u16 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.u16" } } */
+
+uint16x8_t
+foo1 (uint16_t const * base, uint16x8_t offset, mve_pred16_t p)
+{
+ return vldrhq_gather_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.u16" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+uint32x4_t
+foo (uint16_t const * base, uint32x4_t offset, mve_pred16_t p)
+{
+ return vldrhq_gather_offset_z_u32 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.u32" } } */
+
+uint32x4_t
+foo1 (uint16_t const * base, uint32x4_t offset, mve_pred16_t p)
+{
+ return vldrhq_gather_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.u32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+int16x8_t
+foo (int16_t const * base, uint16x8_t offset)
+{
+ return vldrhq_gather_shifted_offset_s16 (base, offset);
+}
+
+/* { dg-final { scan-assembler "vldrh.u16" } } */
+
+int16x8_t
+foo1 (int16_t const * base, uint16x8_t offset)
+{
+ return vldrhq_gather_shifted_offset (base, offset);
+}
+
+/* { dg-final { scan-assembler "vldrh.u16" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+int32x4_t
+foo (int16_t const * base, uint32x4_t offset)
+{
+ return vldrhq_gather_shifted_offset_s32 (base, offset);
+}
+
+/* { dg-final { scan-assembler "vldrh.s32" } } */
+
+int32x4_t
+foo1 (int16_t const * base, uint32x4_t offset)
+{
+ return vldrhq_gather_shifted_offset (base, offset);
+}
+
+/* { dg-final { scan-assembler "vldrh.s32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+uint16x8_t
+foo (uint16_t const * base, uint16x8_t offset)
+{
+ return vldrhq_gather_shifted_offset_u16 (base, offset);
+}
+
+/* { dg-final { scan-assembler "vldrh.u16" } } */
+
+uint16x8_t
+foo1 (uint16_t const * base, uint16x8_t offset)
+{
+ return vldrhq_gather_shifted_offset (base, offset);
+}
+
+/* { dg-final { scan-assembler "vldrh.u16" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+uint32x4_t
+foo (uint16_t const * base, uint32x4_t offset)
+{
+ return vldrhq_gather_shifted_offset_u32 (base, offset);
+}
+
+/* { dg-final { scan-assembler "vldrh.u32" } } */
+
+uint32x4_t
+foo1 (uint16_t const * base, uint32x4_t offset)
+{
+ return vldrhq_gather_shifted_offset (base, offset);
+}
+
+/* { dg-final { scan-assembler "vldrh.u32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+int16x8_t
+foo (int16_t const * base, uint16x8_t offset, mve_pred16_t p)
+{
+ return vldrhq_gather_shifted_offset_z_s16 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.u16" } } */
+
+int16x8_t
+foo1 (int16_t const * base, uint16x8_t offset, mve_pred16_t p)
+{
+ return vldrhq_gather_shifted_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.u16" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+int32x4_t
+foo (int16_t const * base, uint32x4_t offset, mve_pred16_t p)
+{
+ return vldrhq_gather_shifted_offset_z_s32 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.s32" } } */
+
+int32x4_t
+foo1 (int16_t const * base, uint32x4_t offset, mve_pred16_t p)
+{
+ return vldrhq_gather_shifted_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.s32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+uint16x8_t
+foo (uint16_t const * base, uint16x8_t offset, mve_pred16_t p)
+{
+ return vldrhq_gather_shifted_offset_z_u16 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.u16" } } */
+
+uint16x8_t
+foo1 (uint16_t const * base, uint16x8_t offset, mve_pred16_t p)
+{
+ return vldrhq_gather_shifted_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.u16" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+uint32x4_t
+foo (uint16_t const * base, uint32x4_t offset, mve_pred16_t p)
+{
+ return vldrhq_gather_shifted_offset_z_u32 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.u32" } } */
+
+uint32x4_t
+foo1 (uint16_t const * base, uint32x4_t offset, mve_pred16_t p)
+{
+ return vldrhq_gather_shifted_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.u32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+int16x8_t
+foo (int16_t const * base)
+{
+ return vldrhq_s16 (base);
+}
+
+/* { dg-final { scan-assembler "vldrh.s16" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+int32x4_t
+foo (int16_t const * base)
+{
+ return vldrhq_s32 (base);
+}
+
+/* { dg-final { scan-assembler "vldrh.s32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+uint16x8_t
+foo (uint16_t const * base)
+{
+ return vldrhq_u16 (base);
+}
+
+/* { dg-final { scan-assembler "vldrh.u16" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+uint32x4_t
+foo (uint16_t const * base)
+{
+ return vldrhq_u32 (base);
+}
+
+/* { dg-final { scan-assembler "vldrh.u32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+float16x8_t
+foo (float16_t const * base, mve_pred16_t p)
+{
+ return vldrhq_z_f16 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.f16" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+int16x8_t
+foo (int16_t const * base, mve_pred16_t p)
+{
+ return vldrhq_z_s16 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.s16" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+int32x4_t
+foo (int16_t const * base, mve_pred16_t p)
+{
+ return vldrhq_z_s32 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.s32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+uint16x8_t
+foo (uint16_t const * base, mve_pred16_t p)
+{
+ return vldrhq_z_u16 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.u16" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+uint32x4_t
+foo (uint16_t const * base, mve_pred16_t p)
+{
+ return vldrhq_z_u32 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrht.u32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+float32x4_t
+foo (float32_t const * base)
+{
+ return vldrwq_f32 (base);
+}
+
+/* { dg-final { scan-assembler "vldrw.f32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+int32x4_t
+foo (int32_t const * base)
+{
+ return vldrwq_s32 (base);
+}
+
+/* { dg-final { scan-assembler "vldrw.s32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+uint32x4_t
+foo (uint32_t const * base)
+{
+ return vldrwq_u32 (base);
+}
+
+/* { dg-final { scan-assembler "vldrw.u32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */
+/* { dg-add-options arm_v8_1m_mve_fp } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+float32x4_t
+foo (float32_t const * base, mve_pred16_t p)
+{
+ return vldrwq_z_f32 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrwt.f32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+int32x4_t
+foo (int32_t const * base, mve_pred16_t p)
+{
+ return vldrwq_z_s32 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrwt.s32" } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O2" } */
+
+#include "arm_mve.h"
+
+uint32x4_t
+foo (uint32_t const * base, mve_pred16_t p)
+{
+ return vldrwq_z_u32 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrwt.u32" } } */