@@ -555,6 +555,39 @@ arm_quadop_unone_unone_unone_none_unone_qualifiers[SIMD_MAX_BUILTIN_ARGS]
#define QUADOP_UNONE_UNONE_UNONE_NONE_UNONE_QUALIFIERS \
(arm_quadop_unone_unone_unone_none_unone_qualifiers)
+static enum arm_type_qualifiers
+arm_strs_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_void, qualifier_pointer, qualifier_none };
+#define STRS_QUALIFIERS (arm_strs_qualifiers)
+
+static enum arm_type_qualifiers
+arm_stru_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_void, qualifier_pointer, qualifier_unsigned };
+#define STRU_QUALIFIERS (arm_stru_qualifiers)
+
+static enum arm_type_qualifiers
+arm_strss_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_void, qualifier_pointer, qualifier_unsigned,
+ qualifier_none};
+#define STRSS_QUALIFIERS (arm_strss_qualifiers)
+
+static enum arm_type_qualifiers
+arm_strsu_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_void, qualifier_pointer, qualifier_unsigned,
+ qualifier_unsigned};
+#define STRSU_QUALIFIERS (arm_strsu_qualifiers)
+
+static enum arm_type_qualifiers
+arm_strsbs_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_void, qualifier_unsigned, qualifier_immediate, qualifier_none};
+#define STRSBS_QUALIFIERS (arm_strsbs_qualifiers)
+
+static enum arm_type_qualifiers
+arm_strsbu_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_void, qualifier_unsigned, qualifier_immediate,
+ qualifier_unsigned};
+#define STRSBU_QUALIFIERS (arm_strsbu_qualifiers)
+
/* End of Qualifier for MVE builtins. */
/* void ([T element type] *, T, immediate). */
@@ -1702,6 +1702,20 @@ typedef struct { uint8x16_t val[4]; } uint8x16x4_t;
#define vsubq_m_f16(__inactive, __a, __b, __p) __arm_vsubq_m_f16(__inactive, __a, __b, __p)
#define vsubq_m_n_f32(__inactive, __a, __b, __p) __arm_vsubq_m_n_f32(__inactive, __a, __b, __p)
#define vsubq_m_n_f16(__inactive, __a, __b, __p) __arm_vsubq_m_n_f16(__inactive, __a, __b, __p)
+#define vstrbq_s8( __addr, __value) __arm_vstrbq_s8( __addr, __value)
+#define vstrbq_u8( __addr, __value) __arm_vstrbq_u8( __addr, __value)
+#define vstrbq_u16( __addr, __value) __arm_vstrbq_u16( __addr, __value)
+#define vstrbq_scatter_offset_s8( __base, __offset, __value) __arm_vstrbq_scatter_offset_s8( __base, __offset, __value)
+#define vstrbq_scatter_offset_u8( __base, __offset, __value) __arm_vstrbq_scatter_offset_u8( __base, __offset, __value)
+#define vstrbq_scatter_offset_u16( __base, __offset, __value) __arm_vstrbq_scatter_offset_u16( __base, __offset, __value)
+#define vstrbq_s16( __addr, __value) __arm_vstrbq_s16( __addr, __value)
+#define vstrbq_u32( __addr, __value) __arm_vstrbq_u32( __addr, __value)
+#define vstrbq_scatter_offset_s16( __base, __offset, __value) __arm_vstrbq_scatter_offset_s16( __base, __offset, __value)
+#define vstrbq_scatter_offset_u32( __base, __offset, __value) __arm_vstrbq_scatter_offset_u32( __base, __offset, __value)
+#define vstrbq_s32( __addr, __value) __arm_vstrbq_s32( __addr, __value)
+#define vstrbq_scatter_offset_s32( __base, __offset, __value) __arm_vstrbq_scatter_offset_s32( __base, __offset, __value)
+#define vstrwq_scatter_base_s32(__addr, __offset, __value) __arm_vstrwq_scatter_base_s32(__addr, __offset, __value)
+#define vstrwq_scatter_base_u32(__addr, __offset, __value) __arm_vstrwq_scatter_base_u32(__addr, __offset, __value)
#endif
__extension__ extern __inline void
@@ -10995,6 +11009,103 @@ __arm_vshrntq_m_n_u16 (uint8x16_t __a, uint16x8_t __b, const int __imm, mve_pred
return __builtin_mve_vshrntq_m_n_uv8hi (__a, __b, __imm, __p);
}
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_scatter_offset_s8 (int8_t * __base, uint8x16_t __offset, int8x16_t __value)
+{
+ __builtin_mve_vstrbq_scatter_offset_sv16qi ((__builtin_neon_qi *) __base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_scatter_offset_s32 (int8_t * __base, uint32x4_t __offset, int32x4_t __value)
+{
+ __builtin_mve_vstrbq_scatter_offset_sv4si ((__builtin_neon_qi *) __base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_scatter_offset_s16 (int8_t * __base, uint16x8_t __offset, int16x8_t __value)
+{
+ __builtin_mve_vstrbq_scatter_offset_sv8hi ((__builtin_neon_qi *) __base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_scatter_offset_u8 (uint8_t * __base, uint8x16_t __offset, uint8x16_t __value)
+{
+ __builtin_mve_vstrbq_scatter_offset_uv16qi ((__builtin_neon_qi *) __base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_scatter_offset_u32 (uint8_t * __base, uint32x4_t __offset, uint32x4_t __value)
+{
+ __builtin_mve_vstrbq_scatter_offset_uv4si ((__builtin_neon_qi *) __base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_scatter_offset_u16 (uint8_t * __base, uint16x8_t __offset, uint16x8_t __value)
+{
+ __builtin_mve_vstrbq_scatter_offset_uv8hi ((__builtin_neon_qi *) __base, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_s8 (int8_t * __addr, int8x16_t __value)
+{
+ __builtin_mve_vstrbq_sv16qi ((__builtin_neon_qi *) __addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_s32 (int8_t * __addr, int32x4_t __value)
+{
+ __builtin_mve_vstrbq_sv4si ((__builtin_neon_qi *) __addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_s16 (int8_t * __addr, int16x8_t __value)
+{
+ __builtin_mve_vstrbq_sv8hi ((__builtin_neon_qi *) __addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_u8 (uint8_t * __addr, uint8x16_t __value)
+{
+ __builtin_mve_vstrbq_uv16qi ((__builtin_neon_qi *) __addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_u32 (uint8_t * __addr, uint32x4_t __value)
+{
+ __builtin_mve_vstrbq_uv4si ((__builtin_neon_qi *) __addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrbq_u16 (uint8_t * __addr, uint16x8_t __value)
+{
+ __builtin_mve_vstrbq_uv8hi ((__builtin_neon_qi *) __addr, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_base_s32 (uint32x4_t __addr, const int __offset, int32x4_t __value)
+{
+ __builtin_mve_vstrwq_scatter_base_sv4si (__addr, __offset, __value);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vstrwq_scatter_base_u32 (uint32x4_t __addr, const int __offset, uint32x4_t __value)
+{
+ __builtin_mve_vstrwq_scatter_base_uv4si (__addr, __offset, __value);
+}
#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */
__extension__ extern __inline void
@@ -17542,6 +17653,35 @@ extern void *__ARM_undef;
#define vrmlsldavhaxq_p(p0,p1,p2,p3) __arm_vrmlsldavhaxq_p(p0,p1,p2,p3)
#define __arm_vrmlsldavhaxq_p(p0,p1,p2,p3) __arm_vrmlsldavhaxq_p_s32(p0,p1,p2,p3)
+#define vstrbq(p0,p1) __arm_vstrbq(p0,p1)
+#define __arm_vstrbq(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_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vstrbq_s8 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t)), \
+ int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrbq_s16 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, int16x8_t)), \
+ int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrbq_s32 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_u8 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_u16 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_u32 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t)));})
+
+#define vstrbq_scatter_offset(p0,p1,p2) __arm_vstrbq_scatter_offset(p0,p1,p2)
+#define __arm_vstrbq_scatter_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vstrbq_scatter_offset_s8 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, int8x16_t)), \
+ int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrbq_scatter_offset_s16 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
+ int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrbq_scatter_offset_s32 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_scatter_offset_u8 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t)), \
+ int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_scatter_offset_u16 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \
+ int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_scatter_offset_u32 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));})
+
+#define vstrwq_scatter_base(p0,p1,p2) __arm_vstrwq_scatter_base(p0,p1,p2)
+#define __arm_vstrwq_scatter_base(p0,p1,p2) ({ __typeof(p2) __p2 = (p2); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_base_s32(p0, p1, __ARM_mve_coerce(__p2, int32x4_t)), \
+ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_base_u32(p0, p1, __ARM_mve_coerce(__p2, uint32x4_t)));})
+
#endif /* MVE Floating point. */
#ifdef __cplusplus
@@ -685,3 +685,9 @@ VAR2 (QUADOP_NONE_NONE_NONE_NONE_UNONE, vandq_m_f, v8hf, v4sf)
VAR2 (QUADOP_NONE_NONE_NONE_NONE_UNONE, vaddq_m_n_f, v8hf, v4sf)
VAR2 (QUADOP_NONE_NONE_NONE_NONE_UNONE, vaddq_m_f, v8hf, v4sf)
VAR2 (QUADOP_NONE_NONE_NONE_NONE_UNONE, vabdq_m_f, v8hf, v4sf)
+VAR3 (STRS, vstrbq_s, v16qi, v8hi, v4si)
+VAR3 (STRU, vstrbq_u, v16qi, v8hi, v4si)
+VAR3 (STRSS, vstrbq_scatter_offset_s, v16qi, v8hi, v4si)
+VAR3 (STRSU, vstrbq_scatter_offset_u, v16qi, v8hi, v4si)
+VAR1 (STRSBS, vstrwq_scatter_base_s, v4si)
+VAR1 (STRSBU, vstrwq_scatter_base_u, v4si)
@@ -191,7 +191,8 @@
VCMLAQ_ROT90_M_F VCMULQ_M_F VCMULQ_ROT180_M_F
VCMULQ_ROT270_M_F VCMULQ_ROT90_M_F VFMAQ_M_F
VFMAQ_M_N_F VFMASQ_M_N_F VFMSQ_M_F VMAXNMQ_M_F
- VMINNMQ_M_F VSUBQ_M_F])
+ VMINNMQ_M_F VSUBQ_M_F VSTRWQSB_S VSTRWQSB_U
+ VSTRBQSO_S VSTRBQSO_U VSTRBQ_S VSTRBQ_U])
(define_mode_attr MVE_CNVT [(V8HI "V8HF") (V4SI "V4SF")
(V8HF "V8HI") (V4SF "V4SI")])
@@ -342,7 +343,9 @@
(VQRSHRNTQ_M_N_S "s") (VQRSHRNTQ_M_N_U "u")
(VQRSHRNBQ_M_N_S "s") (VQRSHRNBQ_M_N_U "u")
(VMLALDAVAXQ_P_S "s") (VMLALDAVAXQ_P_U "u")
- (VMLALDAVAQ_P_S "s") (VMLALDAVAQ_P_U "u")])
+ (VMLALDAVAQ_P_S "s") (VMLALDAVAQ_P_U "u")
+ (VSTRWQSB_S "s") (VSTRWQSB_U "u") (VSTRBQSO_S "s")
+ (VSTRBQSO_U "u") (VSTRBQ_S "s") (VSTRBQ_U "u")])
(define_int_attr mode1 [(VCTP8Q "8") (VCTP16Q "16") (VCTP32Q "32")
(VCTP64Q "64") (VCTP8Q_M "8") (VCTP16Q_M "16")
@@ -359,6 +362,7 @@
(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_int_iterator VCVTQ_TO_F [VCVTQ_TO_F_S VCVTQ_TO_F_U])
(define_int_iterator VMVNQ_N [VMVNQ_N_U VMVNQ_N_S])
@@ -562,6 +566,9 @@
(define_int_iterator VSHLLTQ_M_N [VSHLLTQ_M_N_U VSHLLTQ_M_N_S])
(define_int_iterator VSHRNBQ_M_N [VSHRNBQ_M_N_S VSHRNBQ_M_N_U])
(define_int_iterator VSHRNTQ_M_N [VSHRNTQ_M_N_S VSHRNTQ_M_N_U])
+(define_int_iterator VSTRWSBQ [VSTRWQSB_S VSTRWQSB_U])
+(define_int_iterator VSTRBSOQ [VSTRBQSO_S VSTRBQSO_U])
+(define_int_iterator VSTRBQ [VSTRBQ_S VSTRBQ_U])
(define_insn "*mve_mov<mode>"
[(set (match_operand:MVE_types 0 "s_register_operand" "=w,w,r,w,w,r,w")
@@ -7933,3 +7940,65 @@
"vpst\;vsubt.f%#<V_sz_elem>\t%q0, %q2, %3"
[(set_attr "type" "mve_move")
(set_attr "length""8")])
+
+;;
+;; [vstrbq_s vstrbq_u]
+;;
+(define_insn "mve_vstrbq_<supf><mode>"
+ [(set (match_operand:<MVE_B_ELEM> 0 "memory_operand" "=Us")
+ (unspec:<MVE_B_ELEM> [(match_operand:MVE_2 1 "s_register_operand" "w")]
+ VSTRBQ))
+ ]
+ "TARGET_HAVE_MVE"
+{
+ rtx ops[2];
+ int regno = REGNO (operands[1]);
+ ops[1] = gen_rtx_REG (TImode, regno);
+ ops[0] = operands[0];
+ output_asm_insn("vstrb.<V_sz_elem>\t%q1, %E0",ops);
+ return "";
+}
+ [(set_attr "length" "4")])
+
+;;
+;; [vstrbq_scatter_offset_s vstrbq_scatter_offset_u]
+;;
+(define_insn "mve_vstrbq_scatter_offset_<supf><mode>"
+ [(set (match_operand:<MVE_B_ELEM> 0 "memory_operand" "=Us")
+ (unspec:<MVE_B_ELEM>
+ [(match_operand:MVE_2 1 "s_register_operand" "w")
+ (match_operand:MVE_2 2 "s_register_operand" "w")]
+ VSTRBSOQ))
+ ]
+ "TARGET_HAVE_MVE"
+{
+ rtx ops[3];
+ ops[0] = operands[0];
+ ops[1] = operands[1];
+ ops[2] = operands[2];
+ output_asm_insn("vstrb.<V_sz_elem>\t%q2, [%m0, %q1]",ops);
+ return "";
+}
+ [(set_attr "length" "4")])
+
+;;
+;; [vstrwq_scatter_base_s vstrwq_scatter_base_u]
+;;
+(define_insn "mve_vstrwq_scatter_base_<supf>v4si"
+ [(set (mem:BLK (scratch))
+ (unspec:BLK
+ [(match_operand:V4SI 0 "s_register_operand" "w")
+ (match_operand:SI 1 "immediate_operand" "i")
+ (match_operand:V4SI 2 "s_register_operand" "w")]
+ VSTRWSBQ))
+ ]
+ "TARGET_HAVE_MVE"
+{
+ rtx ops[3];
+ ops[0] = operands[0];
+ ops[1] = operands[1];
+ ops[2] = operands[2];
+ output_asm_insn("vstrw.u32\t%q2, [%q0, %1]",ops);
+ return "";
+}
+ [(set_attr "length" "4")])
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+void
+foo (int8_t * addr, int16x8_t value)
+{
+ vstrbq_s16 (addr, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.16" } } */
+
+void
+foo1 (int8_t * addr, int16x8_t value)
+{
+ vstrbq (addr, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.16" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+void
+foo (int8_t * addr, int32x4_t value)
+{
+ vstrbq_s32 (addr, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.32" } } */
+
+void
+foo1 (int8_t * addr, int32x4_t value)
+{
+ vstrbq (addr, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.32" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+void
+foo (int8_t * addr, int8x16_t value)
+{
+ vstrbq_s8 (addr, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.8" } } */
+
+void
+foo1 (int8_t * addr, int8x16_t value)
+{
+ vstrbq (addr, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.8" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+void
+foo (int8_t * base, uint16x8_t offset, int16x8_t value)
+{
+ vstrbq_scatter_offset_s16 (base, offset, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.16" } } */
+
+void
+foo1 (int8_t * base, uint16x8_t offset, int16x8_t value)
+{
+ vstrbq_scatter_offset (base, offset, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.16" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+void
+foo (int8_t * base, uint32x4_t offset, int32x4_t value)
+{
+ vstrbq_scatter_offset_s32 (base, offset, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.32" } } */
+
+void
+foo1 (int8_t * base, uint32x4_t offset, int32x4_t value)
+{
+ vstrbq_scatter_offset (base, offset, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.32" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+void
+foo (int8_t * base, uint8x16_t offset, int8x16_t value)
+{
+ vstrbq_scatter_offset_s8 (base, offset, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.8" } } */
+
+void
+foo1 (int8_t * base, uint8x16_t offset, int8x16_t value)
+{
+ vstrbq_scatter_offset (base, offset, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.8" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+void
+foo (uint8_t * base, uint16x8_t offset, uint16x8_t value)
+{
+ vstrbq_scatter_offset_u16 (base, offset, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.16" } } */
+
+void
+foo1 (uint8_t * base, uint16x8_t offset, uint16x8_t value)
+{
+ vstrbq_scatter_offset (base, offset, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.16" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+void
+foo (uint8_t * base, uint32x4_t offset, uint32x4_t value)
+{
+ vstrbq_scatter_offset_u32 (base, offset, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.32" } } */
+
+void
+foo1 (uint8_t * base, uint32x4_t offset, uint32x4_t value)
+{
+ vstrbq_scatter_offset (base, offset, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.32" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+void
+foo (uint8_t * base, uint8x16_t offset, uint8x16_t value)
+{
+ vstrbq_scatter_offset_u8 (base, offset, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.8" } } */
+
+void
+foo1 (uint8_t * base, uint8x16_t offset, uint8x16_t value)
+{
+ vstrbq_scatter_offset (base, offset, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.8" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+void
+foo (uint8_t * addr, uint16x8_t value)
+{
+ vstrbq_u16 (addr, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.16" } } */
+
+void
+foo1 (uint8_t * addr, uint16x8_t value)
+{
+ vstrbq (addr, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.16" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+void
+foo (uint8_t * addr, uint32x4_t value)
+{
+ vstrbq_u32 (addr, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.32" } } */
+
+void
+foo1 (uint8_t * addr, uint32x4_t value)
+{
+ vstrbq (addr, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.32" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+void
+foo (uint8_t * addr, uint8x16_t value)
+{
+ vstrbq_u8 (addr, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.8" } } */
+
+void
+foo1 (uint8_t * addr, uint8x16_t value)
+{
+ vstrbq (addr, value);
+}
+
+/* { dg-final { scan-assembler "vstrb.8" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+void
+foo (uint32x4_t addr, int32x4_t value)
+{
+ vstrwq_scatter_base_s32 (addr, 8, value);
+}
+
+/* { dg-final { scan-assembler "vstrw.u32" } } */
+
+void
+foo1 (uint32x4_t addr, int32x4_t value)
+{
+ vstrwq_scatter_base (addr, 8, value);
+}
+
+/* { dg-final { scan-assembler "vstrw.u32" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+void
+foo (uint32x4_t addr, uint32x4_t value)
+{
+ vstrwq_scatter_base_u32 (addr, 8, value);
+}
+
+/* { dg-final { scan-assembler "vstrw.u32" } } */
+
+void
+foo1 (uint32x4_t addr, uint32x4_t value)
+{
+ vstrwq_scatter_base (addr, 8, value);
+}
+
+/* { dg-final { scan-assembler "vstrw.u32" } } */