Hello,
This patch supports the following MVE ACLE load intrinsics with zero(_z)
suffix.
* ``_z`` (zero) which indicates false-predicated lanes are filled with zeroes,
these are only used for load instructions.
vldrbq_gather_offset_z_s16, vldrbq_gather_offset_z_u8,
vldrbq_gather_offset_z_s32,
vldrbq_gather_offset_z_u16, vldrbq_gather_offset_z_u32,
vldrbq_gather_offset_z_s8,
vldrbq_z_s16, vldrbq_z_u8, vldrbq_z_s8, vldrbq_z_s32, vldrbq_z_u16,
vldrbq_z_u32,
vldrwq_gather_base_z_u32, vldrwq_gather_base_z_s32.
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 <[email protected]>
Mihail Ionescu <[email protected]>
Srinath Parvathaneni <[email protected]>
* config/arm/arm-builtins.c (LDRGBS_Z_QUALIFIERS): Define builtin
qualifier.
(LDRGBU_Z_QUALIFIERS): Likewise.
(LDRGS_Z_QUALIFIERS): Likewise.
(LDRGU_Z_QUALIFIERS): Likewise.
(LDRS_Z_QUALIFIERS): Likewise.
(LDRU_Z_QUALIFIERS): Likewise.
* config/arm/arm_mve.h (vldrbq_gather_offset_z_s16): Define macro.
(vldrbq_gather_offset_z_u8): Likewise.
(vldrbq_gather_offset_z_s32): Likewise.
(vldrbq_gather_offset_z_u16): Likewise.
(vldrbq_gather_offset_z_u32): Likewise.
(vldrbq_gather_offset_z_s8): Likewise.
(vldrbq_z_s16): Likewise.
(vldrbq_z_u8): Likewise.
(vldrbq_z_s8): Likewise.
(vldrbq_z_s32): Likewise.
(vldrbq_z_u16): Likewise.
(vldrbq_z_u32): Likewise.
(vldrwq_gather_base_z_u32): Likewise.
(vldrwq_gather_base_z_s32): Likewise.
(__arm_vldrbq_gather_offset_z_s8): Define intrinsic.
(__arm_vldrbq_gather_offset_z_s32): Likewise.
(__arm_vldrbq_gather_offset_z_s16): Likewise.
(__arm_vldrbq_gather_offset_z_u8): Likewise.
(__arm_vldrbq_gather_offset_z_u32): Likewise.
(__arm_vldrbq_gather_offset_z_u16): Likewise.
(__arm_vldrbq_z_s8): Likewise.
(__arm_vldrbq_z_s32): Likewise.
(__arm_vldrbq_z_s16): Likewise.
(__arm_vldrbq_z_u8): Likewise.
(__arm_vldrbq_z_u32): Likewise.
(__arm_vldrbq_z_u16): Likewise.
(__arm_vldrwq_gather_base_z_s32): Likewise.
(__arm_vldrwq_gather_base_z_u32): Likewise.
(vldrbq_gather_offset_z): Define polymorphic variant.
* config/arm/arm_mve_builtins.def (LDRGBS_Z_QUALIFIERS): Use builtin
qualifier.
(LDRGBU_Z_QUALIFIERS): Likewise.
(LDRGS_Z_QUALIFIERS): Likewise.
(LDRGU_Z_QUALIFIERS): Likewise.
(LDRS_Z_QUALIFIERS): Likewise.
(LDRU_Z_QUALIFIERS): Likewise.
* config/arm/mve.md (mve_vldrbq_gather_offset_z_<supf><mode>): Define
RTL pattern.
(mve_vldrbq_z_<supf><mode>): Likewise.
(mve_vldrwq_gather_base_z_<supf>v4si): Likewise.
gcc/testsuite/ChangeLog: Likewise.
2019-11-01 Andre Vieira <[email protected]>
Mihail Ionescu <[email protected]>
Srinath Parvathaneni <[email protected]>
* gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s16.c: New test.
* gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s8.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u8.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrbq_z_s16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrbq_z_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrbq_z_s8.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrbq_z_u16.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrbq_z_u32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrbq_z_u8.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrwq_gather_base_z_s32.c: Likewise.
* gcc.target/arm/mve/intrinsics/vldrwq_gather_base_z_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
b5639051bf07785d906ed596e08d670f4de1a67e..c3d12375d2fbc933ad33f7a15a3bbf53079d0639
100644
--- a/gcc/config/arm/arm-builtins.c
+++ b/gcc/config/arm/arm-builtins.c
@@ -653,6 +653,40 @@ arm_ldrgbu_qualifiers[SIMD_MAX_BUILTIN_ARGS]
= { qualifier_unsigned, qualifier_unsigned, qualifier_immediate};
#define LDRGBU_QUALIFIERS (arm_ldrgbu_qualifiers)
+static enum arm_type_qualifiers
+arm_ldrgbs_z_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_none, qualifier_unsigned, qualifier_immediate,
+ qualifier_unsigned};
+#define LDRGBS_Z_QUALIFIERS (arm_ldrgbs_z_qualifiers)
+
+static enum arm_type_qualifiers
+arm_ldrgbu_z_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_unsigned, qualifier_unsigned, qualifier_immediate,
+ qualifier_unsigned};
+#define LDRGBU_Z_QUALIFIERS (arm_ldrgbu_z_qualifiers)
+
+static enum arm_type_qualifiers
+arm_ldrgs_z_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_none, qualifier_pointer, qualifier_unsigned,
+ qualifier_unsigned};
+#define LDRGS_Z_QUALIFIERS (arm_ldrgs_z_qualifiers)
+
+static enum arm_type_qualifiers
+arm_ldrgu_z_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_unsigned, qualifier_pointer, qualifier_unsigned,
+ qualifier_unsigned};
+#define LDRGU_Z_QUALIFIERS (arm_ldrgu_z_qualifiers)
+
+static enum arm_type_qualifiers
+arm_ldrs_z_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_none, qualifier_pointer, qualifier_unsigned};
+#define LDRS_Z_QUALIFIERS (arm_ldrs_z_qualifiers)
+
+static enum arm_type_qualifiers
+arm_ldru_z_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_unsigned, qualifier_pointer, qualifier_unsigned};
+#define LDRU_Z_QUALIFIERS (arm_ldru_z_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
f852acb575b596c534c474d19faa73c03cf85c5e..b40a9c238b7f883a0e91dd6fcc5f41182ea6efe3
100644
--- a/gcc/config/arm/arm_mve.h
+++ b/gcc/config/arm/arm_mve.h
@@ -1744,6 +1744,20 @@ typedef struct { uint8x16_t val[4]; } uint8x16x4_t;
#define vstrbq_scatter_offset_p_u16( __base, __offset, __value, __p)
__arm_vstrbq_scatter_offset_p_u16( __base, __offset, __value, __p)
#define vstrwq_scatter_base_p_s32(__addr, __offset, __value, __p)
__arm_vstrwq_scatter_base_p_s32(__addr, __offset, __value, __p)
#define vstrwq_scatter_base_p_u32(__addr, __offset, __value, __p)
__arm_vstrwq_scatter_base_p_u32(__addr, __offset, __value, __p)
+#define vldrbq_gather_offset_z_s16(__base, __offset, __p)
__arm_vldrbq_gather_offset_z_s16(__base, __offset, __p)
+#define vldrbq_gather_offset_z_u8(__base, __offset, __p)
__arm_vldrbq_gather_offset_z_u8(__base, __offset, __p)
+#define vldrbq_gather_offset_z_s32(__base, __offset, __p)
__arm_vldrbq_gather_offset_z_s32(__base, __offset, __p)
+#define vldrbq_gather_offset_z_u16(__base, __offset, __p)
__arm_vldrbq_gather_offset_z_u16(__base, __offset, __p)
+#define vldrbq_gather_offset_z_u32(__base, __offset, __p)
__arm_vldrbq_gather_offset_z_u32(__base, __offset, __p)
+#define vldrbq_gather_offset_z_s8(__base, __offset, __p)
__arm_vldrbq_gather_offset_z_s8(__base, __offset, __p)
+#define vldrbq_z_s16(__base, __p) __arm_vldrbq_z_s16(__base, __p)
+#define vldrbq_z_u8(__base, __p) __arm_vldrbq_z_u8(__base, __p)
+#define vldrbq_z_s8(__base, __p) __arm_vldrbq_z_s8(__base, __p)
+#define vldrbq_z_s32(__base, __p) __arm_vldrbq_z_s32(__base, __p)
+#define vldrbq_z_u16(__base, __p) __arm_vldrbq_z_u16(__base, __p)
+#define vldrbq_z_u32(__base, __p) __arm_vldrbq_z_u32(__base, __p)
+#define vldrwq_gather_base_z_u32(__addr, __offset, __p)
__arm_vldrwq_gather_base_z_u32(__addr, __offset, __p)
+#define vldrwq_gather_base_z_s32(__addr, __offset, __p)
__arm_vldrwq_gather_base_z_s32(__addr, __offset, __p)
#endif
__extension__ extern __inline void
@@ -11330,6 +11344,105 @@ __arm_vstrwq_scatter_base_p_u32 (uint32x4_t __addr,
const int __offset, uint32x4
{
__builtin_mve_vstrwq_scatter_base_p_uv4si (__addr, __offset, __value, __p);
}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset_z_s8 (int8_t const * __base, uint8x16_t __offset,
mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_gather_offset_z_sv16qi ((__builtin_neon_qi *)
__base, __offset, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset_z_s32 (int8_t const * __base, uint32x4_t __offset,
mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_gather_offset_z_sv4si ((__builtin_neon_qi *)
__base, __offset, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset_z_s16 (int8_t const * __base, uint16x8_t __offset,
mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_gather_offset_z_sv8hi ((__builtin_neon_qi *)
__base, __offset, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset_z_u8 (uint8_t const * __base, uint8x16_t __offset,
mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_gather_offset_z_uv16qi ((__builtin_neon_qi *)
__base, __offset, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset_z_u32 (uint8_t const * __base, uint32x4_t __offset,
mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_gather_offset_z_uv4si ((__builtin_neon_qi *)
__base, __offset, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset_z_u16 (uint8_t const * __base, uint16x8_t __offset,
mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_gather_offset_z_uv8hi ((__builtin_neon_qi *)
__base, __offset, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_z_s8 (int8_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_z_sv16qi ((__builtin_neon_qi *) __base, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_z_s32 (int8_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_z_sv4si ((__builtin_neon_qi *) __base, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_z_s16 (int8_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_z_sv8hi ((__builtin_neon_qi *) __base, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_z_u8 (uint8_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_z_uv16qi ((__builtin_neon_qi *) __base, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_z_u32 (uint8_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_z_uv4si ((__builtin_neon_qi *) __base, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_z_u16 (uint8_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_z_uv8hi ((__builtin_neon_qi *) __base, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_gather_base_z_s32 (uint32x4_t __addr, const int __offset,
mve_pred16_t __p)
+{
+ return __builtin_mve_vldrwq_gather_base_z_sv4si (__addr, __offset, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_gather_base_z_u32 (uint32x4_t __addr, const int __offset,
mve_pred16_t __p)
+{
+ return __builtin_mve_vldrwq_gather_base_z_uv4si (__addr, __offset, __p);
+}
+
#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */
__extension__ extern __inline void
@@ -13471,6 +13584,7 @@ __arm_vsubq_m_n_f16 (float16x8_t __inactive,
float16x8_t __a, float16_t __b, mve
{
return __builtin_mve_vsubq_m_n_fv8hf (__inactive, __a, __b, __p);
}
+
#endif
enum {
@@ -17946,6 +18060,17 @@ extern void *__ARM_undef;
int (*)[__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_base_p_s32 (p0, p1,
__ARM_mve_coerce(__p2, int32x4_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_base_p_u32 (p0, p1,
__ARM_mve_coerce(__p2, uint32x4_t), p3));})
+#define vldrbq_gather_offset_z(p0,p1,p2) __arm_vldrbq_gather_offset_z(p0,p1,p2)
+#define __arm_vldrbq_gather_offset_z(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+ int (*)[__ARM_mve_type_int8_t_const_ptr][__ARM_mve_type_uint8x16_t]:
__arm_vldrbq_gather_offset_z_s8 (__ARM_mve_coerce(__p0, int8_t const *),
__ARM_mve_coerce(__p1, uint8x16_t), p2), \
+ int (*)[__ARM_mve_type_int8_t_const_ptr][__ARM_mve_type_uint16x8_t]:
__arm_vldrbq_gather_offset_z_s16 (__ARM_mve_coerce(__p0, int8_t const *),
__ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_int8_t_const_ptr][__ARM_mve_type_uint32x4_t]:
__arm_vldrbq_gather_offset_z_s32 (__ARM_mve_coerce(__p0, int8_t const *),
__ARM_mve_coerce(__p1, uint32x4_t), p2), \
+ int (*)[__ARM_mve_type_uint8_t_const_ptr][__ARM_mve_type_uint8x16_t]:
__arm_vldrbq_gather_offset_z_u8 (__ARM_mve_coerce(__p0, uint8_t const *),
__ARM_mve_coerce(__p1, uint8x16_t), p2), \
+ int (*)[__ARM_mve_type_uint8_t_const_ptr][__ARM_mve_type_uint16x8_t]:
__arm_vldrbq_gather_offset_z_u16 (__ARM_mve_coerce(__p0, uint8_t const *),
__ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_uint8_t_const_ptr][__ARM_mve_type_uint32x4_t]:
__arm_vldrbq_gather_offset_z_u32 (__ARM_mve_coerce(__p0, uint8_t const *),
__ARM_mve_coerce(__p1, uint32x4_t), p2));})
+
#endif /* MVE Floating point. */
#ifdef __cplusplus
diff --git a/gcc/config/arm/arm_mve_builtins.def
b/gcc/config/arm/arm_mve_builtins.def
index
dc22c2f599702be5a4c4481033d3f413abf6d1c5..45b00e889cfe716a2c70fb86d72eb9a4c411b70d
100644
--- a/gcc/config/arm/arm_mve_builtins.def
+++ b/gcc/config/arm/arm_mve_builtins.def
@@ -703,3 +703,9 @@ VAR3 (STRSS_P, vstrbq_scatter_offset_p_s, v16qi, v8hi, v4si)
VAR3 (STRSU_P, vstrbq_scatter_offset_p_u, v16qi, v8hi, v4si)
VAR1 (STRSBS_P, vstrwq_scatter_base_p_s, v4si)
VAR1 (STRSBU_P, vstrwq_scatter_base_p_u, v4si)
+VAR1 (LDRGBS_Z, vldrwq_gather_base_z_s, v4si)
+VAR1 (LDRGBU_Z, vldrwq_gather_base_z_u, v4si)
+VAR3 (LDRGS_Z, vldrbq_gather_offset_z_s, v16qi, v8hi, v4si)
+VAR3 (LDRGU_Z, vldrbq_gather_offset_z_u, v16qi, v8hi, v4si)
+VAR3 (LDRS_Z, vldrbq_z_s, v16qi, v8hi, v4si)
+VAR3 (LDRU_Z, vldrbq_z_u, v16qi, v8hi, v4si)
diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md
index
266a7f830285521fd225c8b07bc15e412b7bab61..05b94e4ee283da427aee18c7223bf5ff4b0e1e4a
100644
--- a/gcc/config/arm/mve.md
+++ b/gcc/config/arm/mve.md
@@ -8135,3 +8135,69 @@
return "";
}
[(set_attr "length" "8")])
+
+;;
+;; [vldrbq_gather_offset_z_s vldrbq_gather_offset_z_u]
+;;
+(define_insn "mve_vldrbq_gather_offset_z_<supf><mode>"
+ [(set (match_operand:MVE_2 0 "s_register_operand" "=&w")
+ (unspec:MVE_2 [(match_operand:<MVE_B_ELEM> 1 "memory_operand" "Us")
+ (match_operand:MVE_2 2 "s_register_operand" "w")
+ (match_operand:HI 3 "vpr_register_operand" "Up")]
+ VLDRBGOQ))
+ ]
+ "TARGET_HAVE_MVE"
+{
+ rtx ops[4];
+ ops[0] = operands[0];
+ ops[1] = operands[1];
+ ops[2] = operands[2];
+ ops[3] = operands[3];
+ if (!strcmp ("<supf>","s") && <V_sz_elem> == 8)
+ output_asm_insn ("vpst\n\tvldrbt.u8\t%q0, [%m1, %q2]",ops);
+ else
+ output_asm_insn ("vpst\n\tvldrbt.<supf><V_sz_elem>\t%q0, [%m1, %q2]",ops);
+ return "";
+}
+ [(set_attr "length" "8")])
+
+;;
+;; [vldrbq_z_s vldrbq_z_u]
+;;
+(define_insn "mve_vldrbq_z_<supf><mode>"
+ [(set (match_operand:MVE_2 0 "s_register_operand" "=w")
+ (unspec:MVE_2 [(match_operand:<MVE_B_ELEM> 1 "memory_operand" "Us")
+ (match_operand:HI 2 "vpr_register_operand" "Up")]
+ VLDRBQ))
+ ]
+ "TARGET_HAVE_MVE"
+{
+ rtx ops[2];
+ int regno = REGNO (operands[0]);
+ ops[0] = gen_rtx_REG (TImode, regno);
+ ops[1] = operands[1];
+ output_asm_insn ("vpst\n\tvldrbt.<supf><V_sz_elem>\t%q0, %E1",ops);
+ return "";
+}
+ [(set_attr "length" "8")])
+
+;;
+;; [vldrwq_gather_base_z_s vldrwq_gather_base_z_u]
+;;
+(define_insn "mve_vldrwq_gather_base_z_<supf>v4si"
+ [(set (match_operand:V4SI 0 "s_register_operand" "=&w")
+ (unspec:V4SI [(match_operand:V4SI 1 "s_register_operand" "w")
+ (match_operand:SI 2 "immediate_operand" "i")
+ (match_operand:HI 3 "vpr_register_operand" "Up")]
+ VLDRWGBQ))
+ ]
+ "TARGET_HAVE_MVE"
+{
+ rtx ops[3];
+ ops[0] = operands[0];
+ ops[1] = operands[1];
+ ops[2] = operands[2];
+ output_asm_insn ("vpst\n\tvldrwt.u32\t%q0, [%q1, %2]",ops);
+ return "";
+}
+ [(set_attr "length" "8")])
diff --git
a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s16.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s16.c
new file mode 100644
index
0000000000000000000000000000000000000000..ce1b2b241989449e0bfee0f5a378eb9b5a3e250a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s16.c
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int16x8_t
+foo (int8_t const * base, uint16x8_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z_s16 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.s16" } } */
+
+int16x8_t
+foo1 (int8_t const * base, uint16x8_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.s16" } } */
diff --git
a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s32.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s32.c
new file mode 100644
index
0000000000000000000000000000000000000000..b79e1c8961cb52b4e16351064ee8f2e1be1baae5
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s32.c
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int32x4_t
+foo (int8_t const * base, uint32x4_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z_s32 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.s32" } } */
+
+int32x4_t
+foo1 (int8_t const * base, uint32x4_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.s32" } } */
diff --git
a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s8.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s8.c
new file mode 100644
index
0000000000000000000000000000000000000000..816634a7086ce290048a669144e715de03eed71c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s8.c
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int8x16_t
+foo (int8_t const * base, uint8x16_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z_s8 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u8" } } */
+
+int8x16_t
+foo1 (int8_t const * base, uint8x16_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u8" } } */
diff --git
a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u16.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u16.c
new file mode 100644
index
0000000000000000000000000000000000000000..67722400bb04be883b89d3a882023ef18b1e1c7d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u16.c
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint16x8_t
+foo (uint8_t const * base, uint16x8_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z_u16 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u16" } } */
+
+uint16x8_t
+foo1 (uint8_t const * base, uint16x8_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u16" } } */
diff --git
a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u32.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u32.c
new file mode 100644
index
0000000000000000000000000000000000000000..ed174404330e13e017edd07883dbdb261300f23b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u32.c
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint32x4_t
+foo (uint8_t const * base, uint32x4_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z_u32 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u32" } } */
+
+uint32x4_t
+foo1 (uint8_t const * base, uint32x4_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u32" } } */
diff --git
a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u8.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u8.c
new file mode 100644
index
0000000000000000000000000000000000000000..1ac9f4ee3669222020b6de6b8e89463128b61acd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u8.c
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint8x16_t
+foo (uint8_t const * base, uint8x16_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z_u8 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u8" } } */
+
+uint8x16_t
+foo1 (uint8_t const * base, uint8x16_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u8" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_s16.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_s16.c
new file mode 100644
index
0000000000000000000000000000000000000000..4fd604ed27da1d686f60b76c6a66a5377b32ed3c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_s16.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int16x8_t
+foo (int8_t const * base, mve_pred16_t p)
+{
+ return vldrbq_z_s16 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.s16" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_s32.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_s32.c
new file mode 100644
index
0000000000000000000000000000000000000000..faae9e17c15cc60d72a582e4f341dd2e132c4f7e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_s32.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int32x4_t
+foo (int8_t const * base, mve_pred16_t p)
+{
+ return vldrbq_z_s32 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.s32" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_s8.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_s8.c
new file mode 100644
index
0000000000000000000000000000000000000000..1bb0bed237f936739395d48be9509393a888ae3d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_s8.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int8x16_t
+foo (int8_t const * base, mve_pred16_t p)
+{
+ return vldrbq_z_s8 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.s8" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_u16.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_u16.c
new file mode 100644
index
0000000000000000000000000000000000000000..50e18a3cecc98fe83727b9256e14e8dd1088aa61
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_u16.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint16x8_t
+foo (uint8_t const * base, mve_pred16_t p)
+{
+ return vldrbq_z_u16 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u16" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_u32.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_u32.c
new file mode 100644
index
0000000000000000000000000000000000000000..78590dda496acb26d8eeff273932541f7f1a3869
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_u32.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint32x4_t
+foo (uint8_t const * base, mve_pred16_t p)
+{
+ return vldrbq_z_u32 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u32" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_u8.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_u8.c
new file mode 100644
index
0000000000000000000000000000000000000000..54192ae94af60bbb2525d0f3dc830d603de69fb6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_u8.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint8x16_t
+foo (uint8_t const * base, mve_pred16_t p)
+{
+ return vldrbq_z_u8 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u8" } } */
diff --git
a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_z_s32.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_z_s32.c
new file mode 100644
index
0000000000000000000000000000000000000000..3bb1ba826f309e53810aa675e5442d2aeb15f4b1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_z_s32.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int32x4_t
+foo (uint32x4_t addr, mve_pred16_t p)
+{
+ return vldrwq_gather_base_z_s32 (addr, 4, p);
+}
+
+/* { dg-final { scan-assembler "vldrwt.u32" } } */
diff --git
a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_z_u32.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_z_u32.c
new file mode 100644
index
0000000000000000000000000000000000000000..2a92e4d915fb77c42efd9be0ab04f43dc836a4d4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_z_u32.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint32x4_t
+foo (uint32x4_t addr, mve_pred16_t p)
+{
+ return vldrwq_gather_base_z_u32 (addr, 4, p);
+}
+
+/* { dg-final { scan-assembler "vldrwt.u32" } } */
diff --git a/gcc/config/arm/arm-builtins.c b/gcc/config/arm/arm-builtins.c
index
b5639051bf07785d906ed596e08d670f4de1a67e..c3d12375d2fbc933ad33f7a15a3bbf53079d0639
100644
--- a/gcc/config/arm/arm-builtins.c
+++ b/gcc/config/arm/arm-builtins.c
@@ -653,6 +653,40 @@ arm_ldrgbu_qualifiers[SIMD_MAX_BUILTIN_ARGS]
= { qualifier_unsigned, qualifier_unsigned, qualifier_immediate};
#define LDRGBU_QUALIFIERS (arm_ldrgbu_qualifiers)
+static enum arm_type_qualifiers
+arm_ldrgbs_z_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_none, qualifier_unsigned, qualifier_immediate,
+ qualifier_unsigned};
+#define LDRGBS_Z_QUALIFIERS (arm_ldrgbs_z_qualifiers)
+
+static enum arm_type_qualifiers
+arm_ldrgbu_z_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_unsigned, qualifier_unsigned, qualifier_immediate,
+ qualifier_unsigned};
+#define LDRGBU_Z_QUALIFIERS (arm_ldrgbu_z_qualifiers)
+
+static enum arm_type_qualifiers
+arm_ldrgs_z_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_none, qualifier_pointer, qualifier_unsigned,
+ qualifier_unsigned};
+#define LDRGS_Z_QUALIFIERS (arm_ldrgs_z_qualifiers)
+
+static enum arm_type_qualifiers
+arm_ldrgu_z_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_unsigned, qualifier_pointer, qualifier_unsigned,
+ qualifier_unsigned};
+#define LDRGU_Z_QUALIFIERS (arm_ldrgu_z_qualifiers)
+
+static enum arm_type_qualifiers
+arm_ldrs_z_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_none, qualifier_pointer, qualifier_unsigned};
+#define LDRS_Z_QUALIFIERS (arm_ldrs_z_qualifiers)
+
+static enum arm_type_qualifiers
+arm_ldru_z_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_unsigned, qualifier_pointer, qualifier_unsigned};
+#define LDRU_Z_QUALIFIERS (arm_ldru_z_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
f852acb575b596c534c474d19faa73c03cf85c5e..b40a9c238b7f883a0e91dd6fcc5f41182ea6efe3
100644
--- a/gcc/config/arm/arm_mve.h
+++ b/gcc/config/arm/arm_mve.h
@@ -1744,6 +1744,20 @@ typedef struct { uint8x16_t val[4]; } uint8x16x4_t;
#define vstrbq_scatter_offset_p_u16( __base, __offset, __value, __p)
__arm_vstrbq_scatter_offset_p_u16( __base, __offset, __value, __p)
#define vstrwq_scatter_base_p_s32(__addr, __offset, __value, __p)
__arm_vstrwq_scatter_base_p_s32(__addr, __offset, __value, __p)
#define vstrwq_scatter_base_p_u32(__addr, __offset, __value, __p)
__arm_vstrwq_scatter_base_p_u32(__addr, __offset, __value, __p)
+#define vldrbq_gather_offset_z_s16(__base, __offset, __p)
__arm_vldrbq_gather_offset_z_s16(__base, __offset, __p)
+#define vldrbq_gather_offset_z_u8(__base, __offset, __p)
__arm_vldrbq_gather_offset_z_u8(__base, __offset, __p)
+#define vldrbq_gather_offset_z_s32(__base, __offset, __p)
__arm_vldrbq_gather_offset_z_s32(__base, __offset, __p)
+#define vldrbq_gather_offset_z_u16(__base, __offset, __p)
__arm_vldrbq_gather_offset_z_u16(__base, __offset, __p)
+#define vldrbq_gather_offset_z_u32(__base, __offset, __p)
__arm_vldrbq_gather_offset_z_u32(__base, __offset, __p)
+#define vldrbq_gather_offset_z_s8(__base, __offset, __p)
__arm_vldrbq_gather_offset_z_s8(__base, __offset, __p)
+#define vldrbq_z_s16(__base, __p) __arm_vldrbq_z_s16(__base, __p)
+#define vldrbq_z_u8(__base, __p) __arm_vldrbq_z_u8(__base, __p)
+#define vldrbq_z_s8(__base, __p) __arm_vldrbq_z_s8(__base, __p)
+#define vldrbq_z_s32(__base, __p) __arm_vldrbq_z_s32(__base, __p)
+#define vldrbq_z_u16(__base, __p) __arm_vldrbq_z_u16(__base, __p)
+#define vldrbq_z_u32(__base, __p) __arm_vldrbq_z_u32(__base, __p)
+#define vldrwq_gather_base_z_u32(__addr, __offset, __p)
__arm_vldrwq_gather_base_z_u32(__addr, __offset, __p)
+#define vldrwq_gather_base_z_s32(__addr, __offset, __p)
__arm_vldrwq_gather_base_z_s32(__addr, __offset, __p)
#endif
__extension__ extern __inline void
@@ -11330,6 +11344,105 @@ __arm_vstrwq_scatter_base_p_u32 (uint32x4_t __addr,
const int __offset, uint32x4
{
__builtin_mve_vstrwq_scatter_base_p_uv4si (__addr, __offset, __value, __p);
}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset_z_s8 (int8_t const * __base, uint8x16_t __offset,
mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_gather_offset_z_sv16qi ((__builtin_neon_qi *)
__base, __offset, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset_z_s32 (int8_t const * __base, uint32x4_t __offset,
mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_gather_offset_z_sv4si ((__builtin_neon_qi *)
__base, __offset, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset_z_s16 (int8_t const * __base, uint16x8_t __offset,
mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_gather_offset_z_sv8hi ((__builtin_neon_qi *)
__base, __offset, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset_z_u8 (uint8_t const * __base, uint8x16_t __offset,
mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_gather_offset_z_uv16qi ((__builtin_neon_qi *)
__base, __offset, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset_z_u32 (uint8_t const * __base, uint32x4_t __offset,
mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_gather_offset_z_uv4si ((__builtin_neon_qi *)
__base, __offset, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_gather_offset_z_u16 (uint8_t const * __base, uint16x8_t __offset,
mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_gather_offset_z_uv8hi ((__builtin_neon_qi *)
__base, __offset, __p);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_z_s8 (int8_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_z_sv16qi ((__builtin_neon_qi *) __base, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_z_s32 (int8_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_z_sv4si ((__builtin_neon_qi *) __base, __p);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_z_s16 (int8_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_z_sv8hi ((__builtin_neon_qi *) __base, __p);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_z_u8 (uint8_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_z_uv16qi ((__builtin_neon_qi *) __base, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_z_u32 (uint8_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_z_uv4si ((__builtin_neon_qi *) __base, __p);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrbq_z_u16 (uint8_t const * __base, mve_pred16_t __p)
+{
+ return __builtin_mve_vldrbq_z_uv8hi ((__builtin_neon_qi *) __base, __p);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_gather_base_z_s32 (uint32x4_t __addr, const int __offset,
mve_pred16_t __p)
+{
+ return __builtin_mve_vldrwq_gather_base_z_sv4si (__addr, __offset, __p);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vldrwq_gather_base_z_u32 (uint32x4_t __addr, const int __offset,
mve_pred16_t __p)
+{
+ return __builtin_mve_vldrwq_gather_base_z_uv4si (__addr, __offset, __p);
+}
+
#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */
__extension__ extern __inline void
@@ -13471,6 +13584,7 @@ __arm_vsubq_m_n_f16 (float16x8_t __inactive,
float16x8_t __a, float16_t __b, mve
{
return __builtin_mve_vsubq_m_n_fv8hf (__inactive, __a, __b, __p);
}
+
#endif
enum {
@@ -17946,6 +18060,17 @@ extern void *__ARM_undef;
int (*)[__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_base_p_s32 (p0, p1,
__ARM_mve_coerce(__p2, int32x4_t), p3), \
int (*)[__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_base_p_u32 (p0, p1,
__ARM_mve_coerce(__p2, uint32x4_t), p3));})
+#define vldrbq_gather_offset_z(p0,p1,p2) __arm_vldrbq_gather_offset_z(p0,p1,p2)
+#define __arm_vldrbq_gather_offset_z(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
+ __typeof(p1) __p1 = (p1); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
+ int (*)[__ARM_mve_type_int8_t_const_ptr][__ARM_mve_type_uint8x16_t]:
__arm_vldrbq_gather_offset_z_s8 (__ARM_mve_coerce(__p0, int8_t const *),
__ARM_mve_coerce(__p1, uint8x16_t), p2), \
+ int (*)[__ARM_mve_type_int8_t_const_ptr][__ARM_mve_type_uint16x8_t]:
__arm_vldrbq_gather_offset_z_s16 (__ARM_mve_coerce(__p0, int8_t const *),
__ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_int8_t_const_ptr][__ARM_mve_type_uint32x4_t]:
__arm_vldrbq_gather_offset_z_s32 (__ARM_mve_coerce(__p0, int8_t const *),
__ARM_mve_coerce(__p1, uint32x4_t), p2), \
+ int (*)[__ARM_mve_type_uint8_t_const_ptr][__ARM_mve_type_uint8x16_t]:
__arm_vldrbq_gather_offset_z_u8 (__ARM_mve_coerce(__p0, uint8_t const *),
__ARM_mve_coerce(__p1, uint8x16_t), p2), \
+ int (*)[__ARM_mve_type_uint8_t_const_ptr][__ARM_mve_type_uint16x8_t]:
__arm_vldrbq_gather_offset_z_u16 (__ARM_mve_coerce(__p0, uint8_t const *),
__ARM_mve_coerce(__p1, uint16x8_t), p2), \
+ int (*)[__ARM_mve_type_uint8_t_const_ptr][__ARM_mve_type_uint32x4_t]:
__arm_vldrbq_gather_offset_z_u32 (__ARM_mve_coerce(__p0, uint8_t const *),
__ARM_mve_coerce(__p1, uint32x4_t), p2));})
+
#endif /* MVE Floating point. */
#ifdef __cplusplus
diff --git a/gcc/config/arm/arm_mve_builtins.def
b/gcc/config/arm/arm_mve_builtins.def
index
dc22c2f599702be5a4c4481033d3f413abf6d1c5..45b00e889cfe716a2c70fb86d72eb9a4c411b70d
100644
--- a/gcc/config/arm/arm_mve_builtins.def
+++ b/gcc/config/arm/arm_mve_builtins.def
@@ -703,3 +703,9 @@ VAR3 (STRSS_P, vstrbq_scatter_offset_p_s, v16qi, v8hi, v4si)
VAR3 (STRSU_P, vstrbq_scatter_offset_p_u, v16qi, v8hi, v4si)
VAR1 (STRSBS_P, vstrwq_scatter_base_p_s, v4si)
VAR1 (STRSBU_P, vstrwq_scatter_base_p_u, v4si)
+VAR1 (LDRGBS_Z, vldrwq_gather_base_z_s, v4si)
+VAR1 (LDRGBU_Z, vldrwq_gather_base_z_u, v4si)
+VAR3 (LDRGS_Z, vldrbq_gather_offset_z_s, v16qi, v8hi, v4si)
+VAR3 (LDRGU_Z, vldrbq_gather_offset_z_u, v16qi, v8hi, v4si)
+VAR3 (LDRS_Z, vldrbq_z_s, v16qi, v8hi, v4si)
+VAR3 (LDRU_Z, vldrbq_z_u, v16qi, v8hi, v4si)
diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md
index
266a7f830285521fd225c8b07bc15e412b7bab61..05b94e4ee283da427aee18c7223bf5ff4b0e1e4a
100644
--- a/gcc/config/arm/mve.md
+++ b/gcc/config/arm/mve.md
@@ -8135,3 +8135,69 @@
return "";
}
[(set_attr "length" "8")])
+
+;;
+;; [vldrbq_gather_offset_z_s vldrbq_gather_offset_z_u]
+;;
+(define_insn "mve_vldrbq_gather_offset_z_<supf><mode>"
+ [(set (match_operand:MVE_2 0 "s_register_operand" "=&w")
+ (unspec:MVE_2 [(match_operand:<MVE_B_ELEM> 1 "memory_operand" "Us")
+ (match_operand:MVE_2 2 "s_register_operand" "w")
+ (match_operand:HI 3 "vpr_register_operand" "Up")]
+ VLDRBGOQ))
+ ]
+ "TARGET_HAVE_MVE"
+{
+ rtx ops[4];
+ ops[0] = operands[0];
+ ops[1] = operands[1];
+ ops[2] = operands[2];
+ ops[3] = operands[3];
+ if (!strcmp ("<supf>","s") && <V_sz_elem> == 8)
+ output_asm_insn ("vpst\n\tvldrbt.u8\t%q0, [%m1, %q2]",ops);
+ else
+ output_asm_insn ("vpst\n\tvldrbt.<supf><V_sz_elem>\t%q0, [%m1, %q2]",ops);
+ return "";
+}
+ [(set_attr "length" "8")])
+
+;;
+;; [vldrbq_z_s vldrbq_z_u]
+;;
+(define_insn "mve_vldrbq_z_<supf><mode>"
+ [(set (match_operand:MVE_2 0 "s_register_operand" "=w")
+ (unspec:MVE_2 [(match_operand:<MVE_B_ELEM> 1 "memory_operand" "Us")
+ (match_operand:HI 2 "vpr_register_operand" "Up")]
+ VLDRBQ))
+ ]
+ "TARGET_HAVE_MVE"
+{
+ rtx ops[2];
+ int regno = REGNO (operands[0]);
+ ops[0] = gen_rtx_REG (TImode, regno);
+ ops[1] = operands[1];
+ output_asm_insn ("vpst\n\tvldrbt.<supf><V_sz_elem>\t%q0, %E1",ops);
+ return "";
+}
+ [(set_attr "length" "8")])
+
+;;
+;; [vldrwq_gather_base_z_s vldrwq_gather_base_z_u]
+;;
+(define_insn "mve_vldrwq_gather_base_z_<supf>v4si"
+ [(set (match_operand:V4SI 0 "s_register_operand" "=&w")
+ (unspec:V4SI [(match_operand:V4SI 1 "s_register_operand" "w")
+ (match_operand:SI 2 "immediate_operand" "i")
+ (match_operand:HI 3 "vpr_register_operand" "Up")]
+ VLDRWGBQ))
+ ]
+ "TARGET_HAVE_MVE"
+{
+ rtx ops[3];
+ ops[0] = operands[0];
+ ops[1] = operands[1];
+ ops[2] = operands[2];
+ output_asm_insn ("vpst\n\tvldrwt.u32\t%q0, [%q1, %2]",ops);
+ return "";
+}
+ [(set_attr "length" "8")])
diff --git
a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s16.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s16.c
new file mode 100644
index
0000000000000000000000000000000000000000..ce1b2b241989449e0bfee0f5a378eb9b5a3e250a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s16.c
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int16x8_t
+foo (int8_t const * base, uint16x8_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z_s16 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.s16" } } */
+
+int16x8_t
+foo1 (int8_t const * base, uint16x8_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.s16" } } */
diff --git
a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s32.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s32.c
new file mode 100644
index
0000000000000000000000000000000000000000..b79e1c8961cb52b4e16351064ee8f2e1be1baae5
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s32.c
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int32x4_t
+foo (int8_t const * base, uint32x4_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z_s32 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.s32" } } */
+
+int32x4_t
+foo1 (int8_t const * base, uint32x4_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.s32" } } */
diff --git
a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s8.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s8.c
new file mode 100644
index
0000000000000000000000000000000000000000..816634a7086ce290048a669144e715de03eed71c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_s8.c
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int8x16_t
+foo (int8_t const * base, uint8x16_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z_s8 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u8" } } */
+
+int8x16_t
+foo1 (int8_t const * base, uint8x16_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u8" } } */
diff --git
a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u16.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u16.c
new file mode 100644
index
0000000000000000000000000000000000000000..67722400bb04be883b89d3a882023ef18b1e1c7d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u16.c
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint16x8_t
+foo (uint8_t const * base, uint16x8_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z_u16 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u16" } } */
+
+uint16x8_t
+foo1 (uint8_t const * base, uint16x8_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u16" } } */
diff --git
a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u32.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u32.c
new file mode 100644
index
0000000000000000000000000000000000000000..ed174404330e13e017edd07883dbdb261300f23b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u32.c
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint32x4_t
+foo (uint8_t const * base, uint32x4_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z_u32 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u32" } } */
+
+uint32x4_t
+foo1 (uint8_t const * base, uint32x4_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u32" } } */
diff --git
a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u8.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u8.c
new file mode 100644
index
0000000000000000000000000000000000000000..1ac9f4ee3669222020b6de6b8e89463128b61acd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_z_u8.c
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint8x16_t
+foo (uint8_t const * base, uint8x16_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z_u8 (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u8" } } */
+
+uint8x16_t
+foo1 (uint8_t const * base, uint8x16_t offset, mve_pred16_t p)
+{
+ return vldrbq_gather_offset_z (base, offset, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u8" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_s16.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_s16.c
new file mode 100644
index
0000000000000000000000000000000000000000..4fd604ed27da1d686f60b76c6a66a5377b32ed3c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_s16.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int16x8_t
+foo (int8_t const * base, mve_pred16_t p)
+{
+ return vldrbq_z_s16 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.s16" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_s32.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_s32.c
new file mode 100644
index
0000000000000000000000000000000000000000..faae9e17c15cc60d72a582e4f341dd2e132c4f7e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_s32.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int32x4_t
+foo (int8_t const * base, mve_pred16_t p)
+{
+ return vldrbq_z_s32 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.s32" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_s8.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_s8.c
new file mode 100644
index
0000000000000000000000000000000000000000..1bb0bed237f936739395d48be9509393a888ae3d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_s8.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int8x16_t
+foo (int8_t const * base, mve_pred16_t p)
+{
+ return vldrbq_z_s8 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.s8" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_u16.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_u16.c
new file mode 100644
index
0000000000000000000000000000000000000000..50e18a3cecc98fe83727b9256e14e8dd1088aa61
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_u16.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint16x8_t
+foo (uint8_t const * base, mve_pred16_t p)
+{
+ return vldrbq_z_u16 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u16" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_u32.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_u32.c
new file mode 100644
index
0000000000000000000000000000000000000000..78590dda496acb26d8eeff273932541f7f1a3869
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_u32.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint32x4_t
+foo (uint8_t const * base, mve_pred16_t p)
+{
+ return vldrbq_z_u32 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u32" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_u8.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_u8.c
new file mode 100644
index
0000000000000000000000000000000000000000..54192ae94af60bbb2525d0f3dc830d603de69fb6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_z_u8.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint8x16_t
+foo (uint8_t const * base, mve_pred16_t p)
+{
+ return vldrbq_z_u8 (base, p);
+}
+
+/* { dg-final { scan-assembler "vldrbt.u8" } } */
diff --git
a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_z_s32.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_z_s32.c
new file mode 100644
index
0000000000000000000000000000000000000000..3bb1ba826f309e53810aa675e5442d2aeb15f4b1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_z_s32.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int32x4_t
+foo (uint32x4_t addr, mve_pred16_t p)
+{
+ return vldrwq_gather_base_z_s32 (addr, 4, p);
+}
+
+/* { dg-final { scan-assembler "vldrwt.u32" } } */
diff --git
a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_z_u32.c
b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_z_u32.c
new file mode 100644
index
0000000000000000000000000000000000000000..2a92e4d915fb77c42efd9be0ab04f43dc836a4d4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_z_u32.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" }
*/
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint32x4_t
+foo (uint32x4_t addr, mve_pred16_t p)
+{
+ return vldrwq_gather_base_z_u32 (addr, 4, p);
+}
+
+/* { dg-final { scan-assembler "vldrwt.u32" } } */
