[v2,ARM,1/5x] : MVE store intrinsics.

Message ID AM0PR08MB53800C78CE24E0F53B52E3799BF70@AM0PR08MB5380.eurprd08.prod.outlook.com
State New
Headers show
Series
  • [v2,ARM,1/5x] : MVE store intrinsics.
Related show

Commit Message

Srinath Parvathaneni March 18, 2020, 5:17 p.m.
Hello Kyrill,

Following patch is the rebased version of v1.
(version v1) https://gcc.gnu.org/pipermail/gcc-patches/2019-November/534334.html

####

Hello,

This patch supports the following MVE ACLE store intrinsics.

vstrbq_scatter_offset_s8, vstrbq_scatter_offset_s32, vstrbq_scatter_offset_s16,
vstrbq_scatter_offset_u8, vstrbq_scatter_offset_u32, vstrbq_scatter_offset_u16,
vstrbq_s8, vstrbq_s32, vstrbq_s16, vstrbq_u8, vstrbq_u32, vstrbq_u16,
vstrwq_scatter_base_s32, vstrwq_scatter_base_u32.

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

Regression tested on arm-none-eabi and found no regressions.

Ok for trunk?

Thanks,
Srinath.

gcc/ChangeLog:

2019-11-01  Andre Vieira  <andre.simoesdiasvieira@arm.com>
	    Mihail Ionescu  <mihail.ionescu@arm.com>
	    Srinath Parvathaneni  <srinath.parvathaneni@arm.com>

	* config/arm/arm-builtins.c (STRS_QUALIFIERS): Define builtin qualifier.
	(STRU_QUALIFIERS): Likewise.
	(STRSS_QUALIFIERS): Likewise.
	(STRSU_QUALIFIERS): Likewise.
	(STRSBS_QUALIFIERS): Likewise.
	(STRSBU_QUALIFIERS): Likewise.
	* config/arm/arm_mve.h (vstrbq_s8): Define macro.
	(vstrbq_u8): Likewise.
	(vstrbq_u16): Likewise.
	(vstrbq_scatter_offset_s8): Likewise.
	(vstrbq_scatter_offset_u8): Likewise.
	(vstrbq_scatter_offset_u16): Likewise.
	(vstrbq_s16): Likewise.
	(vstrbq_u32): Likewise.
	(vstrbq_scatter_offset_s16): Likewise.
	(vstrbq_scatter_offset_u32): Likewise.
	(vstrbq_s32): Likewise.
	(vstrbq_scatter_offset_s32): Likewise.
	(vstrwq_scatter_base_s32): Likewise.
	(vstrwq_scatter_base_u32): Likewise.
	(__arm_vstrbq_scatter_offset_s8): Define intrinsic.
	(__arm_vstrbq_scatter_offset_s32): Likewise.
	(__arm_vstrbq_scatter_offset_s16): Likewise.
	(__arm_vstrbq_scatter_offset_u8): Likewise.
	(__arm_vstrbq_scatter_offset_u32): Likewise.
	(__arm_vstrbq_scatter_offset_u16): Likewise.
	(__arm_vstrbq_s8): Likewise.
	(__arm_vstrbq_s32): Likewise.
	(__arm_vstrbq_s16): Likewise.
	(__arm_vstrbq_u8): Likewise.
	(__arm_vstrbq_u32): Likewise.
	(__arm_vstrbq_u16): Likewise.
	(__arm_vstrwq_scatter_base_s32): Likewise.
	(__arm_vstrwq_scatter_base_u32): Likewise.
	(vstrbq): Define polymorphic variant.
	(vstrbq_scatter_offset): Likewise.
	(vstrwq_scatter_base): Likewise.
	* config/arm/arm_mve_builtins.def (STRS_QUALIFIERS): Use builtin
	qualifier.
        (STRU_QUALIFIERS): Likewise.
        (STRSS_QUALIFIERS): Likewise.
        (STRSU_QUALIFIERS): Likewise.
        (STRSBS_QUALIFIERS): Likewise.
        (STRSBU_QUALIFIERS): Likewise.
	* config/arm/mve.md (MVE_B_ELEM): Define mode attribute iterator.
	(VSTRWSBQ): Define iterators.
	(VSTRBSOQ): Likewise. 
	(VSTRBQ): Likewise.
	(mve_vstrbq_<supf><mode>): Define RTL pattern.
	(mve_vstrbq_scatter_offset_<supf><mode>): Likewise.
	(mve_vstrwq_scatter_base_<supf>v4si): Likewise.

gcc/testsuite/ChangeLog:

2019-11-01  Andre Vieira  <andre.simoesdiasvieira@arm.com>
	    Mihail Ionescu  <mihail.ionescu@arm.com>
	    Srinath Parvathaneni  <srinath.parvathaneni@arm.com>

	* gcc.target/arm/mve/intrinsics/vstrbq_s16.c: New test.
	* gcc.target/arm/mve/intrinsics/vstrbq_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vstrbq_s8.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s8.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u8.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vstrbq_u16.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vstrbq_u32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vstrbq_u8.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_s32.c: Likewise.
	* gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_u32.c: Likewise.


###############     Attachment also inlined for ease of reply    ###############
diff --git a/gcc/config/arm/arm-builtins.c b/gcc/config/arm/arm-builtins.c
index 26f0379f62b95886414d2eb4d7c6a6c4fc235e60..b285f074285116ce621e324b644d43efb6538b9d 100644
--- a/gcc/config/arm/arm-builtins.c
+++ b/gcc/config/arm/arm-builtins.c
@@ -579,6 +579,39 @@ 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).  */
diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h
index 4f8135d83f942e54b4db9dd43954af8bf027746e..019e907c6dc0b0572b7597f9e82b7ad8e6331bef 100644
--- a/gcc/config/arm/arm_mve.h
+++ b/gcc/config/arm/arm_mve.h
@@ -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
@@ -17630,6 +17741,35 @@ extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), 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 Integer.  */
 
 #define vqrdmlahq_m(p0,p1,p2,p3) __arm_vqrdmlahq_m(p0,p1,p2,p3)
diff --git a/gcc/config/arm/arm_mve_builtins.def b/gcc/config/arm/arm_mve_builtins.def
index b448889fc5f22e11975af97016d1908043254727..2c675240984ac3aa64faf6a9199441c29528c704 100644
--- a/gcc/config/arm/arm_mve_builtins.def
+++ b/gcc/config/arm/arm_mve_builtins.def
@@ -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)
diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md
index bf4eb5da11c27d8a10d7804ad28de9c40cb1878a..3d0a1725d416aa3e465de9409977394d06c19897 100644
--- a/gcc/config/arm/mve.md
+++ b/gcc/config/arm/mve.md
@@ -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 "nonimmediate_operand" "=w,w,r,w,w,r,w,Us")
@@ -7940,3 +7947,65 @@
   "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")])
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s16.c
new file mode 100644
index 0000000000000000000000000000000000000000..80fce9caebed26f782a10aa2b2aa2094e02f0af2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s16.c
@@ -0,0 +1,22 @@
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s32.c
new file mode 100644
index 0000000000000000000000000000000000000000..ae3c89e0d4becc810a08f52c6349582f70334649
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s32.c
@@ -0,0 +1,22 @@
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s8.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s8.c
new file mode 100644
index 0000000000000000000000000000000000000000..72a3673dd5f2707f2809ba2ae0eb55fbffecd69e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s8.c
@@ -0,0 +1,22 @@
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s16.c
new file mode 100644
index 0000000000000000000000000000000000000000..b4ad4f7e3a57473d9a99be66b3aaf803f76003e7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s16.c
@@ -0,0 +1,22 @@
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s32.c
new file mode 100644
index 0000000000000000000000000000000000000000..507eef819914bea10e6fd017d4cda902d568d767
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s32.c
@@ -0,0 +1,22 @@
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s8.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s8.c
new file mode 100644
index 0000000000000000000000000000000000000000..f5467c3bc3d086dc7c88bbe8073c65cdc3c718f9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s8.c
@@ -0,0 +1,22 @@
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u16.c
new file mode 100644
index 0000000000000000000000000000000000000000..cea669925436dc4a6867dafb47356642a7ee7238
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u16.c
@@ -0,0 +1,22 @@
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u32.c
new file mode 100644
index 0000000000000000000000000000000000000000..6ad7ec6f738e95056fd947fff979aafc2ecb7107
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u32.c
@@ -0,0 +1,22 @@
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u8.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u8.c
new file mode 100644
index 0000000000000000000000000000000000000000..4122622142d4d600b9fe992f4d0936f1ac0c2f42
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u8.c
@@ -0,0 +1,22 @@
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u16.c
new file mode 100644
index 0000000000000000000000000000000000000000..5871fbdbfa046e45cb47d3211afc5df7d9c1855d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u16.c
@@ -0,0 +1,22 @@
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u32.c
new file mode 100644
index 0000000000000000000000000000000000000000..31d6d86f9fd85854c4f2e333aef00a9d9d536d60
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u32.c
@@ -0,0 +1,22 @@
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u8.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u8.c
new file mode 100644
index 0000000000000000000000000000000000000000..7415b98e35e8c973b376598226417942812bfd28
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u8.c
@@ -0,0 +1,22 @@
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_s32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_s32.c
new file mode 100644
index 0000000000000000000000000000000000000000..0fb6af6b7c96b325e1d76699f42e86f7280884ee
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_s32.c
@@ -0,0 +1,22 @@
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_u32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_u32.c
new file mode 100644
index 0000000000000000000000000000000000000000..795c0b44e69ea9b969b1d4385b6f43de5d4923f2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_u32.c
@@ -0,0 +1,22 @@
+/* { 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"
+
+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"  }  } */

Comments

Kyrylo Tkachov March 18, 2020, 5:56 p.m. | #1
Hi Srinath,

> -----Original Message-----

> From: Srinath Parvathaneni <Srinath.Parvathaneni@arm.com>

> Sent: 18 March 2020 17:18

> To: gcc-patches@gcc.gnu.org

> Cc: Kyrylo Tkachov <Kyrylo.Tkachov@arm.com>

> Subject: [PATCH v2][ARM][GCC][1/5x]: MVE store intrinsics.

> 

> Hello Kyrill,

> 

> Following patch is the rebased version of v1.

> (version v1) https://gcc.gnu.org/pipermail/gcc-patches/2019-

> November/534334.html

> 

> ####

> 

> Hello,

> 

> This patch supports the following MVE ACLE store intrinsics.

> 

> vstrbq_scatter_offset_s8, vstrbq_scatter_offset_s32,

> vstrbq_scatter_offset_s16, vstrbq_scatter_offset_u8,

> vstrbq_scatter_offset_u32, vstrbq_scatter_offset_u16, vstrbq_s8, vstrbq_s32,

> vstrbq_s16, vstrbq_u8, vstrbq_u32, vstrbq_u16, vstrwq_scatter_base_s32,

> vstrwq_scatter_base_u32.

> 

> 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

> 

> Regression tested on arm-none-eabi and found no regressions.

> 

> Ok for trunk?


Thanks, I've pushed this patch into master.
Kyrill

> 

> Thanks,

> Srinath.

> 

> gcc/ChangeLog:

> 

> 2019-11-01  Andre Vieira  <andre.simoesdiasvieira@arm.com>

> 	    Mihail Ionescu  <mihail.ionescu@arm.com>

> 	    Srinath Parvathaneni  <srinath.parvathaneni@arm.com>

> 

> 	* config/arm/arm-builtins.c (STRS_QUALIFIERS): Define builtin

> qualifier.

> 	(STRU_QUALIFIERS): Likewise.

> 	(STRSS_QUALIFIERS): Likewise.

> 	(STRSU_QUALIFIERS): Likewise.

> 	(STRSBS_QUALIFIERS): Likewise.

> 	(STRSBU_QUALIFIERS): Likewise.

> 	* config/arm/arm_mve.h (vstrbq_s8): Define macro.

> 	(vstrbq_u8): Likewise.

> 	(vstrbq_u16): Likewise.

> 	(vstrbq_scatter_offset_s8): Likewise.

> 	(vstrbq_scatter_offset_u8): Likewise.

> 	(vstrbq_scatter_offset_u16): Likewise.

> 	(vstrbq_s16): Likewise.

> 	(vstrbq_u32): Likewise.

> 	(vstrbq_scatter_offset_s16): Likewise.

> 	(vstrbq_scatter_offset_u32): Likewise.

> 	(vstrbq_s32): Likewise.

> 	(vstrbq_scatter_offset_s32): Likewise.

> 	(vstrwq_scatter_base_s32): Likewise.

> 	(vstrwq_scatter_base_u32): Likewise.

> 	(__arm_vstrbq_scatter_offset_s8): Define intrinsic.

> 	(__arm_vstrbq_scatter_offset_s32): Likewise.

> 	(__arm_vstrbq_scatter_offset_s16): Likewise.

> 	(__arm_vstrbq_scatter_offset_u8): Likewise.

> 	(__arm_vstrbq_scatter_offset_u32): Likewise.

> 	(__arm_vstrbq_scatter_offset_u16): Likewise.

> 	(__arm_vstrbq_s8): Likewise.

> 	(__arm_vstrbq_s32): Likewise.

> 	(__arm_vstrbq_s16): Likewise.

> 	(__arm_vstrbq_u8): Likewise.

> 	(__arm_vstrbq_u32): Likewise.

> 	(__arm_vstrbq_u16): Likewise.

> 	(__arm_vstrwq_scatter_base_s32): Likewise.

> 	(__arm_vstrwq_scatter_base_u32): Likewise.

> 	(vstrbq): Define polymorphic variant.

> 	(vstrbq_scatter_offset): Likewise.

> 	(vstrwq_scatter_base): Likewise.

> 	* config/arm/arm_mve_builtins.def (STRS_QUALIFIERS): Use builtin

> 	qualifier.

>         (STRU_QUALIFIERS): Likewise.

>         (STRSS_QUALIFIERS): Likewise.

>         (STRSU_QUALIFIERS): Likewise.

>         (STRSBS_QUALIFIERS): Likewise.

>         (STRSBU_QUALIFIERS): Likewise.

> 	* config/arm/mve.md (MVE_B_ELEM): Define mode attribute

> iterator.

> 	(VSTRWSBQ): Define iterators.

> 	(VSTRBSOQ): Likewise.

> 	(VSTRBQ): Likewise.

> 	(mve_vstrbq_<supf><mode>): Define RTL pattern.

> 	(mve_vstrbq_scatter_offset_<supf><mode>): Likewise.

> 	(mve_vstrwq_scatter_base_<supf>v4si): Likewise.

> 

> gcc/testsuite/ChangeLog:

> 

> 2019-11-01  Andre Vieira  <andre.simoesdiasvieira@arm.com>

> 	    Mihail Ionescu  <mihail.ionescu@arm.com>

> 	    Srinath Parvathaneni  <srinath.parvathaneni@arm.com>

> 

> 	* gcc.target/arm/mve/intrinsics/vstrbq_s16.c: New test.

> 	* gcc.target/arm/mve/intrinsics/vstrbq_s32.c: Likewise.

> 	* gcc.target/arm/mve/intrinsics/vstrbq_s8.c: Likewise.

> 	* gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s16.c:

> Likewise.

> 	* gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s32.c:

> Likewise.

> 	* gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s8.c: Likewise.

> 	* gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u16.c:

> Likewise.

> 	* gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u32.c:

> Likewise.

> 	* gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u8.c: Likewise.

> 	* gcc.target/arm/mve/intrinsics/vstrbq_u16.c: Likewise.

> 	* gcc.target/arm/mve/intrinsics/vstrbq_u32.c: Likewise.

> 	* gcc.target/arm/mve/intrinsics/vstrbq_u8.c: Likewise.

> 	* gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_s32.c: Likewise.

> 	* gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_u32.c: Likewise.

> 

> 

> ###############     Attachment also inlined for ease of reply

> ###############

> 

> 

> diff --git a/gcc/config/arm/arm-builtins.c b/gcc/config/arm/arm-builtins.c

> index

> 26f0379f62b95886414d2eb4d7c6a6c4fc235e60..b285f074285116ce621e324b

> 644d43efb6538b9d 100644

> --- a/gcc/config/arm/arm-builtins.c

> +++ b/gcc/config/arm/arm-builtins.c

> @@ -579,6 +579,39 @@

> arm_quadop_unone_unone_unone_none_unone_qualifiers[SIMD_MAX_BU

> ILTIN_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).  */ diff --git

> a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h index

> 4f8135d83f942e54b4db9dd43954af8bf027746e..019e907c6dc0b0572b7597f9

> e82b7ad8e6331bef 100644

> --- a/gcc/config/arm/arm_mve.h

> +++ b/gcc/config/arm/arm_mve.h

> @@ -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

> @@ -17630,6 +17741,35 @@ extern void *__ARM_undef;

>    int

> (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_m

> ve_type_uint16x8_t]: __arm_vmulq_m_u16 (__ARM_mve_coerce(__p0,

> uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t),

> __ARM_mve_coerce(__p2, uint16x8_t), p3), \

>    int

> (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_m

> ve_type_uint32x4_t]: __arm_vmulq_m_u32 (__ARM_mve_coerce(__p0,

> uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t),

> __ARM_mve_coerce(__p2, uint32x4_t), 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_ty

> peid(__

> +p2)])0, \

> +  int

> +(*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_

> mve_typ

> +e_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_typ

> +e_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_typ

> +e_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_ty

> +pe_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_ty

> +pe_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_ty

> +pe_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 Integer.  */

> 

>  #define vqrdmlahq_m(p0,p1,p2,p3) __arm_vqrdmlahq_m(p0,p1,p2,p3) diff

> --git a/gcc/config/arm/arm_mve_builtins.def

> b/gcc/config/arm/arm_mve_builtins.def

> index

> b448889fc5f22e11975af97016d1908043254727..2c675240984ac3aa64faf6a91

> 99441c29528c704 100644

> --- a/gcc/config/arm/arm_mve_builtins.def

> +++ b/gcc/config/arm/arm_mve_builtins.def

> @@ -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)

> diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md index

> bf4eb5da11c27d8a10d7804ad28de9c40cb1878a..3d0a1725d416aa3e465de9

> 409977394d06c19897 100644

> --- a/gcc/config/arm/mve.md

> +++ b/gcc/config/arm/mve.md

> @@ -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 "nonimmediate_operand"

> "=w,w,r,w,w,r,w,Us") @@ -7940,3 +7947,65 @@

>    "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")])

> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s16.c

> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s16.c

> new file mode 100644

> index

> 0000000000000000000000000000000000000000..80fce9caebed26f782a10aa

> 2b2aa2094e02f0af2

> --- /dev/null

> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s16.c

> @@ -0,0 +1,22 @@

> +/* { 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"

> +

> +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"  }  } */

> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s32.c

> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s32.c

> new file mode 100644

> index

> 0000000000000000000000000000000000000000..ae3c89e0d4becc810a08f52

> c6349582f70334649

> --- /dev/null

> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s32.c

> @@ -0,0 +1,22 @@

> +/* { 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"

> +

> +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"  }  } */

> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s8.c

> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s8.c

> new file mode 100644

> index

> 0000000000000000000000000000000000000000..72a3673dd5f2707f2809ba2

> ae0eb55fbffecd69e

> --- /dev/null

> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s8.c

> @@ -0,0 +1,22 @@

> +/* { 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"

> +

> +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"  }  } */

> diff --git

> a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s16.c

> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s16.c

> new file mode 100644

> index

> 0000000000000000000000000000000000000000..b4ad4f7e3a57473d9a99be6

> 6b3aaf803f76003e7

> --- /dev/null

> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_

> +++ s16.c

> @@ -0,0 +1,22 @@

> +/* { 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"

> +

> +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"  }  } */

> diff --git

> a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s32.c

> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s32.c

> new file mode 100644

> index

> 0000000000000000000000000000000000000000..507eef819914bea10e6fd01

> 7d4cda902d568d767

> --- /dev/null

> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_

> +++ s32.c

> @@ -0,0 +1,22 @@

> +/* { 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"

> +

> +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"  }  } */

> diff --git

> a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s8.c

> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s8.c

> new file mode 100644

> index

> 0000000000000000000000000000000000000000..f5467c3bc3d086dc7c88bbe

> 8073c65cdc3c718f9

> --- /dev/null

> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_

> +++ s8.c

> @@ -0,0 +1,22 @@

> +/* { 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"

> +

> +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"  }  } */

> diff --git

> a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u16.c

> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u16.c

> new file mode 100644

> index

> 0000000000000000000000000000000000000000..cea669925436dc4a6867daf

> b47356642a7ee7238

> --- /dev/null

> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_

> +++ u16.c

> @@ -0,0 +1,22 @@

> +/* { 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"

> +

> +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"  }  } */

> diff --git

> a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u32.c

> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u32.c

> new file mode 100644

> index

> 0000000000000000000000000000000000000000..6ad7ec6f738e95056fd947ff

> f979aafc2ecb7107

> --- /dev/null

> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_

> +++ u32.c

> @@ -0,0 +1,22 @@

> +/* { 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"

> +

> +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"  }  } */

> diff --git

> a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u8.c

> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u8.c

> new file mode 100644

> index

> 0000000000000000000000000000000000000000..4122622142d4d600b9fe992

> f4d0936f1ac0c2f42

> --- /dev/null

> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_

> +++ u8.c

> @@ -0,0 +1,22 @@

> +/* { 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"

> +

> +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"  }  } */

> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u16.c

> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u16.c

> new file mode 100644

> index

> 0000000000000000000000000000000000000000..5871fbdbfa046e45cb47d32

> 11afc5df7d9c1855d

> --- /dev/null

> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u16.c

> @@ -0,0 +1,22 @@

> +/* { 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"

> +

> +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"  }  } */

> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u32.c

> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u32.c

> new file mode 100644

> index

> 0000000000000000000000000000000000000000..31d6d86f9fd85854c4f2e333

> aef00a9d9d536d60

> --- /dev/null

> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u32.c

> @@ -0,0 +1,22 @@

> +/* { 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"

> +

> +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"  }  } */

> diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u8.c

> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u8.c

> new file mode 100644

> index

> 0000000000000000000000000000000000000000..7415b98e35e8c973b376598

> 226417942812bfd28

> --- /dev/null

> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u8.c

> @@ -0,0 +1,22 @@

> +/* { 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"

> +

> +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"  }  } */

> diff --git

> a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_s32.c

> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_s32.c

> new file mode 100644

> index

> 0000000000000000000000000000000000000000..0fb6af6b7c96b325e1d7669

> 9f42e86f7280884ee

> --- /dev/null

> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_s3

> +++ 2.c

> @@ -0,0 +1,22 @@

> +/* { 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"

> +

> +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"  }  } */

> diff --git

> a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_u32.c

> b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_u32.c

> new file mode 100644

> index

> 0000000000000000000000000000000000000000..795c0b44e69ea9b969b1d4

> 385b6f43de5d4923f2

> --- /dev/null

> +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_u3

> +++ 2.c

> @@ -0,0 +1,22 @@

> +/* { 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"

> +

> +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"  }  } */

Patch

diff --git a/gcc/config/arm/arm-builtins.c b/gcc/config/arm/arm-builtins.c
index 26f0379f62b95886414d2eb4d7c6a6c4fc235e60..b285f074285116ce621e324b644d43efb6538b9d 100644
--- a/gcc/config/arm/arm-builtins.c
+++ b/gcc/config/arm/arm-builtins.c
@@ -579,6 +579,39 @@  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).  */
diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h
index 4f8135d83f942e54b4db9dd43954af8bf027746e..019e907c6dc0b0572b7597f9e82b7ad8e6331bef 100644
--- a/gcc/config/arm/arm_mve.h
+++ b/gcc/config/arm/arm_mve.h
@@ -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
@@ -17630,6 +17741,35 @@  extern void *__ARM_undef;
   int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vmulq_m_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \
   int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vmulq_m_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), 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 Integer.  */
 
 #define vqrdmlahq_m(p0,p1,p2,p3) __arm_vqrdmlahq_m(p0,p1,p2,p3)
diff --git a/gcc/config/arm/arm_mve_builtins.def b/gcc/config/arm/arm_mve_builtins.def
index b448889fc5f22e11975af97016d1908043254727..2c675240984ac3aa64faf6a9199441c29528c704 100644
--- a/gcc/config/arm/arm_mve_builtins.def
+++ b/gcc/config/arm/arm_mve_builtins.def
@@ -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)
diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md
index bf4eb5da11c27d8a10d7804ad28de9c40cb1878a..3d0a1725d416aa3e465de9409977394d06c19897 100644
--- a/gcc/config/arm/mve.md
+++ b/gcc/config/arm/mve.md
@@ -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 "nonimmediate_operand" "=w,w,r,w,w,r,w,Us")
@@ -7940,3 +7947,65 @@ 
   "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")])
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s16.c
new file mode 100644
index 0000000000000000000000000000000000000000..80fce9caebed26f782a10aa2b2aa2094e02f0af2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s16.c
@@ -0,0 +1,22 @@ 
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s32.c
new file mode 100644
index 0000000000000000000000000000000000000000..ae3c89e0d4becc810a08f52c6349582f70334649
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s32.c
@@ -0,0 +1,22 @@ 
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s8.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s8.c
new file mode 100644
index 0000000000000000000000000000000000000000..72a3673dd5f2707f2809ba2ae0eb55fbffecd69e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_s8.c
@@ -0,0 +1,22 @@ 
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s16.c
new file mode 100644
index 0000000000000000000000000000000000000000..b4ad4f7e3a57473d9a99be66b3aaf803f76003e7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s16.c
@@ -0,0 +1,22 @@ 
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s32.c
new file mode 100644
index 0000000000000000000000000000000000000000..507eef819914bea10e6fd017d4cda902d568d767
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s32.c
@@ -0,0 +1,22 @@ 
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s8.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s8.c
new file mode 100644
index 0000000000000000000000000000000000000000..f5467c3bc3d086dc7c88bbe8073c65cdc3c718f9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_s8.c
@@ -0,0 +1,22 @@ 
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u16.c
new file mode 100644
index 0000000000000000000000000000000000000000..cea669925436dc4a6867dafb47356642a7ee7238
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u16.c
@@ -0,0 +1,22 @@ 
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u32.c
new file mode 100644
index 0000000000000000000000000000000000000000..6ad7ec6f738e95056fd947fff979aafc2ecb7107
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u32.c
@@ -0,0 +1,22 @@ 
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u8.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u8.c
new file mode 100644
index 0000000000000000000000000000000000000000..4122622142d4d600b9fe992f4d0936f1ac0c2f42
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_scatter_offset_u8.c
@@ -0,0 +1,22 @@ 
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u16.c
new file mode 100644
index 0000000000000000000000000000000000000000..5871fbdbfa046e45cb47d3211afc5df7d9c1855d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u16.c
@@ -0,0 +1,22 @@ 
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u32.c
new file mode 100644
index 0000000000000000000000000000000000000000..31d6d86f9fd85854c4f2e333aef00a9d9d536d60
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u32.c
@@ -0,0 +1,22 @@ 
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u8.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u8.c
new file mode 100644
index 0000000000000000000000000000000000000000..7415b98e35e8c973b376598226417942812bfd28
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrbq_u8.c
@@ -0,0 +1,22 @@ 
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_s32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_s32.c
new file mode 100644
index 0000000000000000000000000000000000000000..0fb6af6b7c96b325e1d76699f42e86f7280884ee
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_s32.c
@@ -0,0 +1,22 @@ 
+/* { 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"
+
+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"  }  } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_u32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_u32.c
new file mode 100644
index 0000000000000000000000000000000000000000..795c0b44e69ea9b969b1d4385b6f43de5d4923f2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vstrwq_scatter_base_u32.c
@@ -0,0 +1,22 @@ 
+/* { 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"
+
+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"  }  } */