@@ -373,6 +373,24 @@ arm_binop_none_unone_unone_qualifiers[SIMD_MAX_BUILTIN_ARGS]
#define BINOP_NONE_UNONE_UNONE_QUALIFIERS \
(arm_binop_none_unone_unone_qualifiers)
+static enum arm_type_qualifiers
+arm_binop_unone_unone_imm_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_unsigned, qualifier_unsigned, qualifier_immediate };
+#define BINOP_UNONE_UNONE_IMM_QUALIFIERS \
+ (arm_binop_unone_unone_imm_qualifiers)
+
+static enum arm_type_qualifiers
+arm_binop_unone_unone_unone_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_unsigned, qualifier_unsigned, qualifier_unsigned };
+#define BINOP_UNONE_UNONE_UNONE_QUALIFIERS \
+ (arm_binop_unone_unone_unone_qualifiers)
+
+static enum arm_type_qualifiers
+arm_binop_unone_none_imm_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+ = { qualifier_unsigned, qualifier_none, qualifier_immediate };
+#define BINOP_UNONE_NONE_IMM_QUALIFIERS \
+ (arm_binop_unone_none_imm_qualifiers)
+
/* End of Qualifier for MVE builtins. */
/* void ([T element type] *, T, immediate). */
@@ -207,6 +207,24 @@ typedef struct { uint8x16_t val[4]; } uint8x16x4_t;
#define vcvtq_n_f32_u32(__a, __imm6) __arm_vcvtq_n_f32_u32(__a, __imm6)
#define vcreateq_f16(__a, __b) __arm_vcreateq_f16(__a, __b)
#define vcreateq_f32(__a, __b) __arm_vcreateq_f32(__a, __b)
+#define vcvtq_n_s16_f16(__a, __imm6) __arm_vcvtq_n_s16_f16(__a, __imm6)
+#define vcvtq_n_s32_f32(__a, __imm6) __arm_vcvtq_n_s32_f32(__a, __imm6)
+#define vcvtq_n_u16_f16(__a, __imm6) __arm_vcvtq_n_u16_f16(__a, __imm6)
+#define vcvtq_n_u32_f32(__a, __imm6) __arm_vcvtq_n_u32_f32(__a, __imm6)
+#define vcreateq_u8(__a, __b) __arm_vcreateq_u8(__a, __b)
+#define vcreateq_u16(__a, __b) __arm_vcreateq_u16(__a, __b)
+#define vcreateq_u32(__a, __b) __arm_vcreateq_u32(__a, __b)
+#define vcreateq_u64(__a, __b) __arm_vcreateq_u64(__a, __b)
+#define vcreateq_s8(__a, __b) __arm_vcreateq_s8(__a, __b)
+#define vcreateq_s16(__a, __b) __arm_vcreateq_s16(__a, __b)
+#define vcreateq_s32(__a, __b) __arm_vcreateq_s32(__a, __b)
+#define vcreateq_s64(__a, __b) __arm_vcreateq_s64(__a, __b)
+#define vshrq_n_s8(__a, __imm) __arm_vshrq_n_s8(__a, __imm)
+#define vshrq_n_s16(__a, __imm) __arm_vshrq_n_s16(__a, __imm)
+#define vshrq_n_s32(__a, __imm) __arm_vshrq_n_s32(__a, __imm)
+#define vshrq_n_u8(__a, __imm) __arm_vshrq_n_u8(__a, __imm)
+#define vshrq_n_u16(__a, __imm) __arm_vshrq_n_u16(__a, __imm)
+#define vshrq_n_u32(__a, __imm) __arm_vshrq_n_u32(__a, __imm)
#endif
__extension__ extern __inline void
@@ -753,6 +771,104 @@ __arm_vpnot (mve_pred16_t __a)
return __builtin_mve_vpnothi (__a);
}
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcreateq_u8 (uint64_t __a, uint64_t __b)
+{
+ return __builtin_mve_vcreateq_uv16qi (__a, __b);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcreateq_u16 (uint64_t __a, uint64_t __b)
+{
+ return __builtin_mve_vcreateq_uv8hi (__a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcreateq_u32 (uint64_t __a, uint64_t __b)
+{
+ return __builtin_mve_vcreateq_uv4si (__a, __b);
+}
+
+__extension__ extern __inline uint64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcreateq_u64 (uint64_t __a, uint64_t __b)
+{
+ return __builtin_mve_vcreateq_uv2di (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcreateq_s8 (uint64_t __a, uint64_t __b)
+{
+ return __builtin_mve_vcreateq_sv16qi (__a, __b);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcreateq_s16 (uint64_t __a, uint64_t __b)
+{
+ return __builtin_mve_vcreateq_sv8hi (__a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcreateq_s32 (uint64_t __a, uint64_t __b)
+{
+ return __builtin_mve_vcreateq_sv4si (__a, __b);
+}
+
+__extension__ extern __inline int64x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcreateq_s64 (uint64_t __a, uint64_t __b)
+{
+ return __builtin_mve_vcreateq_sv2di (__a, __b);
+}
+
+__extension__ extern __inline int8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq_n_s8 (int8x16_t __a, const int __imm)
+{
+ return __builtin_mve_vshrq_n_sv16qi (__a, __imm);
+}
+
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq_n_s16 (int16x8_t __a, const int __imm)
+{
+ return __builtin_mve_vshrq_n_sv8hi (__a, __imm);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq_n_s32 (int32x4_t __a, const int __imm)
+{
+ return __builtin_mve_vshrq_n_sv4si (__a, __imm);
+}
+
+__extension__ extern __inline uint8x16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq_n_u8 (uint8x16_t __a, const int __imm)
+{
+ return __builtin_mve_vshrq_n_uv16qi (__a, __imm);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq_n_u16 (uint16x8_t __a, const int __imm)
+{
+ return __builtin_mve_vshrq_n_uv8hi (__a, __imm);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vshrq_n_u32 (uint32x4_t __a, const int __imm)
+{
+ return __builtin_mve_vshrq_n_uv4si (__a, __imm);
+}
+
#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */
__extension__ extern __inline void
@@ -1165,6 +1281,34 @@ __arm_vcreateq_f32 (uint64_t __a, uint64_t __b)
return __builtin_mve_vcreateq_fv4sf (__a, __b);
}
+__extension__ extern __inline int16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_n_s16_f16 (float16x8_t __a, const int __imm6)
+{
+ return __builtin_mve_vcvtq_n_from_f_sv8hi (__a, __imm6);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_n_s32_f32 (float32x4_t __a, const int __imm6)
+{
+ return __builtin_mve_vcvtq_n_from_f_sv4si (__a, __imm6);
+}
+
+__extension__ extern __inline uint16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_n_u16_f16 (float16x8_t __a, const int __imm6)
+{
+ return __builtin_mve_vcvtq_n_from_f_uv8hi (__a, __imm6);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+__arm_vcvtq_n_u32_f32 (float32x4_t __a, const int __imm6)
+{
+ return __builtin_mve_vcvtq_n_from_f_uv4si (__a, __imm6);
+}
+
#endif
enum {
@@ -1598,6 +1742,16 @@ extern void *__ARM_undef;
int (*)[__ARM_mve_type_int16x8_t]: __arm_vqnegq_s16 (__ARM_mve_coerce(__p0, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t]: __arm_vqnegq_s32 (__ARM_mve_coerce(__p0, int32x4_t)));})
+#define vshrq(p0,p1) __arm_vshrq(p0,p1)
+#define __arm_vshrq(p0,p1) ({ __typeof(p0) __p0 = (p0); \
+ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
+ int (*)[__ARM_mve_type_int8x16_t]: __arm_vshrq_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), p1), \
+ int (*)[__ARM_mve_type_int16x8_t]: __arm_vshrq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), p1), \
+ int (*)[__ARM_mve_type_int32x4_t]: __arm_vshrq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), p1), \
+ int (*)[__ARM_mve_type_uint8x16_t]: __arm_vshrq_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), p1), \
+ int (*)[__ARM_mve_type_uint16x8_t]: __arm_vshrq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), p1), \
+ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vshrq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), p1));})
+
#endif /* MVE Floating point. */
#ifdef __cplusplus
@@ -6,7 +6,7 @@
GCC is free software; you can redistribute it and/or modify it
under the terms of the GNU General Public License as published
- by the Free Software Foundation; either version 3, or (at your
+ by the Free Software Foundation; either version 3, or (at your
option) any later version.
GCC is distributed in the hope that it will be useful, but WITHOUT
@@ -81,3 +81,9 @@ VAR2 (BINOP_NONE_NONE_NONE, vbrsrq_n_f, v8hf, v4sf)
VAR2 (BINOP_NONE_NONE_IMM, vcvtq_n_to_f_s, v8hf, v4sf)
VAR2 (BINOP_NONE_UNONE_IMM, vcvtq_n_to_f_u, v8hf, v4sf)
VAR2 (BINOP_NONE_UNONE_UNONE, vcreateq_f, v8hf, v4sf)
+VAR2 (BINOP_UNONE_NONE_IMM, vcvtq_n_from_f_u, v8hi, v4si)
+VAR2 (BINOP_NONE_NONE_IMM, vcvtq_n_from_f_s, v8hi, v4si)
+VAR4 (BINOP_UNONE_UNONE_UNONE, vcreateq_u, v16qi, v8hi, v4si, v2di)
+VAR4 (BINOP_NONE_UNONE_UNONE, vcreateq_s, v16qi, v8hi, v4si, v2di)
+VAR3 (BINOP_UNONE_UNONE_IMM, vshrq_n_u, v16qi, v8hi, v4si)
+VAR3 (BINOP_NONE_NONE_IMM, vshrq_n_s, v16qi, v8hi, v4si)
@@ -35,7 +35,7 @@
;; in ARM/Thumb-2 state: Da, Db, Dc, Dd, Dn, DN, Dm, Dl, DL, Do, Dv, Dy, Di,
;; Dt, Dp, Dz, Tu
;; in Thumb-1 state: Pa, Pb, Pc, Pd, Pe
-;; in Thumb-2 state: Ha, Pj, PJ, Ps, Pt, Pu, Pv, Pw, Px, Py, Pz, Rd
+;; in Thumb-2 state: Ha, Pj, PJ, Ps, Pt, Pu, Pv, Pw, Px, Py, Pz, Rd, Rf, Rb
;; in all states: Pf, Pg, UM, U1
;; The following memory constraints have been used:
@@ -56,6 +56,16 @@
(and (match_code "const_int")
(match_test "TARGET_HAVE_MVE && ival >= 1 && ival <= 16")))
+(define_constraint "Rb"
+ "@internal In Thumb-2 state a constant in range 1 to 8"
+ (and (match_code "const_int")
+ (match_test "TARGET_HAVE_MVE && ival >= 1 && ival <= 8")))
+
+(define_constraint "Rf"
+ "@internal In Thumb-2 state a constant in range 1 to 32"
+ (and (match_code "const_int")
+ (match_test "TARGET_HAVE_MVE && ival >= 1 && ival <= 32")))
+
(define_register_constraint "t" "TARGET_32BIT ? VFP_LO_REGS : NO_REGS"
"The VFP registers @code{s0}-@code{s31}.")
@@ -22,6 +22,7 @@
(define_mode_iterator MVE_types [V16QI V8HI V4SI V2DI TI V8HF V4SF V2DF])
(define_mode_iterator MVE_VLD_ST [V16QI V8HI V4SI V8HF V4SF])
(define_mode_iterator MVE_0 [V8HF V4SF])
+(define_mode_iterator MVE_1 [V16QI V8HI V4SI V2DI])
(define_mode_iterator MVE_3 [V16QI V8HI])
(define_mode_iterator MVE_2 [V16QI V8HI V4SI])
(define_mode_iterator MVE_5 [V8HI V4SI])
@@ -38,7 +39,8 @@
VCVTPQ_U VCVTNQ_S VCVTNQ_U VCVTMQ_S VCVTMQ_U
VADDLVQ_U VCTP8Q VCTP16Q VCTP32Q VCTP64Q VPNOT
VCREATEQ_F VCVTQ_N_TO_F_S VCVTQ_N_TO_F_U VBRSRQ_N_F
- VSUBQ_N_F])
+ VSUBQ_N_F VCREATEQ_U VCREATEQ_S VSHRQ_N_S VSHRQ_N_U
+ VCVTQ_N_FROM_F_S VCVTQ_N_FROM_F_U])
(define_mode_attr MVE_CNVT [(V8HI "V8HF") (V4SI "V4SF")
(V8HF "V8HI") (V4SF "V4SI")])
@@ -55,10 +57,16 @@
(VCVTNQ_U "u") (VCVTMQ_S "s") (VCVTMQ_U "u")
(VCLZQ_U "u") (VCLZQ_S "s") (VREV32Q_U "u")
(VREV32Q_S "s") (VADDLVQ_U "u") (VADDLVQ_S "s")
- (VCVTQ_N_TO_F_S "s") (VCVTQ_N_TO_F_U "u")])
+ (VCVTQ_N_TO_F_S "s") (VCVTQ_N_TO_F_U "u")
+ (VCREATEQ_U "u") (VCREATEQ_S "s") (VSHRQ_N_S "s")
+ (VSHRQ_N_U "u") (VCVTQ_N_FROM_F_S "s")
+ (VCVTQ_N_FROM_F_U "u")])
(define_int_attr mode1 [(VCTP8Q "8") (VCTP16Q "16") (VCTP32Q "32")
(VCTP64Q "64")])
+(define_mode_attr MVE_pred2 [(V16QI "mve_imm_8") (V8HI "mve_imm_16")
+ (V4SI "mve_imm_32")])
+(define_mode_attr MVE_constraint2 [(V16QI "Rb") (V8HI "Rd") (V4SI "Rf")])
(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])
@@ -79,6 +87,9 @@
(define_int_iterator VADDLVQ [VADDLVQ_U VADDLVQ_S])
(define_int_iterator VCTPQ [VCTP8Q VCTP16Q VCTP32Q VCTP64Q])
(define_int_iterator VCVTQ_N_TO_F [VCVTQ_N_TO_F_S VCVTQ_N_TO_F_U])
+(define_int_iterator VCREATEQ [VCREATEQ_U VCREATEQ_S])
+(define_int_iterator VSHRQ_N [VSHRQ_N_S VSHRQ_N_U])
+(define_int_iterator VCVTQ_N_FROM_F [VCVTQ_N_FROM_F_S VCVTQ_N_FROM_F_U])
(define_insn "*mve_mov<mode>"
[(set (match_operand:MVE_types 0 "s_register_operand" "=w,w,r,w,w,r,w")
@@ -743,3 +754,48 @@
"vmov %q0[2], %q0[0], %Q2, %Q1\;vmov %q0[3], %q0[1], %R2, %R1"
[(set_attr "type" "mve_move")
(set_attr "length""8")])
+
+;;
+;; [vcreateq_u, vcreateq_s])
+;;
+(define_insn "mve_vcreateq_<supf><mode>"
+ [
+ (set (match_operand:MVE_1 0 "s_register_operand" "=w")
+ (unspec:MVE_1 [(match_operand:DI 1 "s_register_operand" "r")
+ (match_operand:DI 2 "s_register_operand" "r")]
+ VCREATEQ))
+ ]
+ "TARGET_HAVE_MVE"
+ "vmov %q0[2], %q0[0], %Q2, %Q1\;vmov %q0[3], %q0[1], %R2, %R1"
+ [(set_attr "type" "mve_move")
+ (set_attr "length""8")])
+
+;;
+;; [vshrq_n_s, vshrq_n_u])
+;;
+(define_insn "mve_vshrq_n_<supf><mode>"
+ [
+ (set (match_operand:MVE_2 0 "s_register_operand" "=w")
+ (unspec:MVE_2 [(match_operand:MVE_2 1 "s_register_operand" "w")
+ (match_operand:SI 2 "<MVE_pred2>" "<MVE_constraint2>")]
+ VSHRQ_N))
+ ]
+ "TARGET_HAVE_MVE"
+ "vshr.<supf>%#<V_sz_elem>\t%q0, %q1, %2"
+ [(set_attr "type" "mve_move")
+])
+
+;;
+;; [vcvtq_n_from_f_s, vcvtq_n_from_f_u])
+;;
+(define_insn "mve_vcvtq_n_from_f_<supf><mode>"
+ [
+ (set (match_operand:MVE_5 0 "s_register_operand" "=w")
+ (unspec:MVE_5 [(match_operand:<MVE_CNVT> 1 "s_register_operand" "w")
+ (match_operand:SI 2 "mve_imm_16" "Rd")]
+ VCVTQ_N_FROM_F))
+ ]
+ "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
+ "vcvt.<supf>%#<V_sz_elem>.f%#<V_sz_elem>\t%q0, %q1, %2"
+ [(set_attr "type" "mve_move")
+])
@@ -35,6 +35,14 @@
(define_predicate "mve_imm_16"
(match_test "satisfies_constraint_Rd (op)"))
+;; True for immediates in the range of 1 to 8 for MVE.
+(define_predicate "mve_imm_8"
+ (match_test "satisfies_constraint_Rb (op)"))
+
+;; True for immediates in the range of 1 to 32 for MVE.
+(define_predicate "mve_imm_32"
+ (match_test "satisfies_constraint_Rf (op)"))
+
; Predicate for stack protector guard's address in
; stack_protect_combined_set_insn and stack_protect_combined_test_insn patterns
(define_predicate "guard_addr_operand"
new file mode 100644
@@ -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 (uint64_t a, uint64_t b)
+{
+ return vcreateq_s16 (a, b);
+}
+
+/* { dg-final { scan-assembler "vmov" } } */
new file mode 100644
@@ -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 (uint64_t a, uint64_t b)
+{
+ return vcreateq_s32 (a, b);
+}
+
+/* { dg-final { scan-assembler "vmov" } } */
new file mode 100644
@@ -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"
+
+int64x2_t
+foo (uint64_t a, uint64_t b)
+{
+ return vcreateq_s64 (a, b);
+}
+
+/* { dg-final { scan-assembler "vmov" } } */
new file mode 100644
@@ -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 (uint64_t a, uint64_t b)
+{
+ return vcreateq_s8 (a, b);
+}
+
+/* { dg-final { scan-assembler "vmov" } } */
new file mode 100644
@@ -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 (uint64_t a, uint64_t b)
+{
+ return vcreateq_u16 (a, b);
+}
+
+/* { dg-final { scan-assembler "vmov" } } */
new file mode 100644
@@ -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 (uint64_t a, uint64_t b)
+{
+ return vcreateq_u32 (a, b);
+}
+
+/* { dg-final { scan-assembler "vmov" } } */
new file mode 100644
@@ -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"
+
+uint64x2_t
+foo (uint64_t a, uint64_t b)
+{
+ return vcreateq_u64 (a, b);
+}
+
+/* { dg-final { scan-assembler "vmov" } } */
new file mode 100644
@@ -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 (uint64_t a, uint64_t b)
+{
+ return vcreateq_u8 (a, b);
+}
+
+/* { dg-final { scan-assembler "vmov" } } */
new file mode 100644
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve.fp -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int16x8_t
+foo (float16x8_t a)
+{
+ return vcvtq_n_s16_f16 (a, 1);
+}
+
+/* { dg-final { scan-assembler "vcvt.s16.f16" } } */
new file mode 100644
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve.fp -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int32x4_t
+foo (float32x4_t a)
+{
+ return vcvtq_n_s32_f32 (a, 1);
+}
+
+/* { dg-final { scan-assembler "vcvt.s32.f32" } } */
new file mode 100644
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve.fp -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint16x8_t
+foo (float16x8_t a)
+{
+ return vcvtq_n_u16_f16 (a, 1);
+}
+
+/* { dg-final { scan-assembler "vcvt.u16.f16" } } */
new file mode 100644
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve.fp -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint32x4_t
+foo (float32x4_t a)
+{
+ return vcvtq_n_u32_f32 (a, 1);
+}
+
+/* { dg-final { scan-assembler "vcvt.u32.f32" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int16x8_t
+foo (int16x8_t a)
+{
+ return vshrq_n_s16 (a, 16);
+}
+
+/* { dg-final { scan-assembler "vshr.s16" } } */
+
+int16x8_t
+foo1 (int16x8_t a)
+{
+ return vshrq (a, 16);
+}
+
+/* { dg-final { scan-assembler "vshr.s16" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int32x4_t
+foo (int32x4_t a)
+{
+ return vshrq_n_s32 (a, 32);
+}
+
+/* { dg-final { scan-assembler "vshr.s32" } } */
+
+int32x4_t
+foo1 (int32x4_t a)
+{
+ return vshrq (a, 32);
+}
+
+/* { dg-final { scan-assembler "vshr.s32" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+int8x16_t
+foo (int8x16_t a)
+{
+ return vshrq_n_s8 (a, 8);
+}
+
+/* { dg-final { scan-assembler "vshr.s8" } } */
+
+int8x16_t
+foo1 (int8x16_t a)
+{
+ return vshrq (a, 8);
+}
+
+/* { dg-final { scan-assembler "vshr.s8" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint16x8_t
+foo (uint16x8_t a)
+{
+ return vshrq_n_u16 (a, 16);
+}
+
+/* { dg-final { scan-assembler "vshr.u16" } } */
+
+uint16x8_t
+foo1 (uint16x8_t a)
+{
+ return vshrq (a, 16);
+}
+
+/* { dg-final { scan-assembler "vshr.u16" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint32x4_t
+foo (uint32x4_t a)
+{
+ return vshrq_n_u32 (a, 32);
+}
+
+/* { dg-final { scan-assembler "vshr.u32" } } */
+
+uint32x4_t
+foo1 (uint32x4_t a)
+{
+ return vshrq (a, 32);
+}
+
+/* { dg-final { scan-assembler "vshr.u32" } } */
new file mode 100644
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */
+/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */
+
+#include "arm_mve.h"
+
+uint8x16_t
+foo (uint8x16_t a)
+{
+ return vshrq_n_u8 (a, 8);
+}
+
+/* { dg-final { scan-assembler "vshr.u8" } } */
+
+uint8x16_t
+foo1 (uint8x16_t a)
+{
+ return vshrq (a, 8);
+}
+
+/* { dg-final { scan-assembler "vshr.u8" } } */