@@ -11359,6 +11359,38 @@ vst1q_s64_x2 (int64_t * __a, int64x2x2_t __b)
__builtin_neon_vst1q_x2v2di ((__builtin_neon_di *) __a, __bu.__o);
}
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_s8_x3 (int8_t * __a, int8x16x3_t __b)
+{
+ union { int8x16x3_t __i; __builtin_neon_ci __o; } __bu = { __b };
+ __builtin_neon_vst1q_x3v16qi ((__builtin_neon_qi *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_s16_x3 (int16_t * __a, int16x8x3_t __b)
+{
+ union { int16x8x3_t __i; __builtin_neon_ci __o; } __bu = { __b };
+ __builtin_neon_vst1q_x3v8hi ((__builtin_neon_hi *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_s32_x3 (int32_t * __a, int32x4x3_t __b)
+{
+ union { int32x4x3_t __i; __builtin_neon_ci __o; } __bu = { __b };
+ __builtin_neon_vst1q_x3v4si ((__builtin_neon_si *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_s64_x3 (int64_t * __a, int64x2x3_t __b)
+{
+ union { int64x2x3_t __i; __builtin_neon_ci __o; } __bu = { __b };
+ __builtin_neon_vst1q_x3v2di ((__builtin_neon_di *) __a, __bu.__o);
+}
+
__extension__ extern __inline void
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vst1_s8_x3 (int8_t * __a, int8x8x3_t __b)
@@ -11696,6 +11728,14 @@ vst1q_p64_x2 (poly64_t * __a, poly64x2x2_t __b)
__builtin_neon_vst1q_x2v2di ((__builtin_neon_di *) __a, __bu.__o);
}
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_p64_x3 (poly64_t * __a, poly64x2x3_t __b)
+{
+ union { poly64x2x3_t __i; __builtin_neon_ci __o; } __bu = { __b };
+ __builtin_neon_vst1q_x3v2di ((__builtin_neon_di *) __a, __bu.__o);
+}
+
#pragma GCC pop_options
__extension__ extern __inline void
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
@@ -11759,6 +11799,24 @@ vst1q_f32_x2 (float32_t * __a, float32x4x2_t __b)
__builtin_neon_vst1q_x2v4sf (__a, __bu.__o);
}
+#if defined (__ARM_FP16_FORMAT_IEEE) || defined (__ARM_FP16_FORMAT_ALTERNATIVE)
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_f16_x3 (float16_t * __a, float16x8x3_t __b)
+{
+ union { float16x8x3_t __i; __builtin_neon_ci __o; } __bu = { __b };
+ __builtin_neon_vst1q_x3v8hf (__a, __bu.__o);
+}
+#endif
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_f32_x3 (float32_t * __a, float32x4x3_t __b)
+{
+ union { float32x4x3_t __i; __builtin_neon_ci __o; } __bu = { __b };
+ __builtin_neon_vst1q_x3v4sf (__a, __bu.__o);
+}
+
__extension__ extern __inline void
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vst1q_u8 (uint8_t * __a, uint8x16_t __b)
@@ -11819,6 +11877,38 @@ vst1q_u64_x2 (uint64_t * __a, uint64x2x2_t __b)
__builtin_neon_vst1q_x2v2di ((__builtin_neon_di *) __a, __bu.__o);
}
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_u8_x3 (uint8_t * __a, uint8x16x3_t __b)
+{
+ union { uint8x16x3_t __i; __builtin_neon_ci __o; } __bu = { __b };
+ __builtin_neon_vst1q_x3v16qi ((__builtin_neon_qi *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_u16_x3 (uint16_t * __a, uint16x8x3_t __b)
+{
+ union { uint16x8x3_t __i; __builtin_neon_ci __o; } __bu = { __b };
+ __builtin_neon_vst1q_x3v8hi ((__builtin_neon_hi *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_u32_x3 (uint32_t * __a, uint32x4x3_t __b)
+{
+ union { uint32x4x3_t __i; __builtin_neon_ci __o; } __bu = { __b };
+ __builtin_neon_vst1q_x3v4si ((__builtin_neon_si *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_u64_x3 (uint64_t * __a, uint64x2x3_t __b)
+{
+ union { uint64x2x3_t __i; __builtin_neon_ci __o; } __bu = { __b };
+ __builtin_neon_vst1q_x3v2di ((__builtin_neon_di *) __a, __bu.__o);
+}
+
__extension__ extern __inline void
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vst1q_p8 (poly8_t * __a, poly8x16_t __b)
@@ -11849,6 +11939,22 @@ vst1q_p16_x2 (poly16_t * __a, poly16x8x2_t __b)
__builtin_neon_vst1q_x2v8hi ((__builtin_neon_hi *) __a, __bu.__o);
}
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_p8_x3 (poly8_t * __a, poly8x16x3_t __b)
+{
+ union { poly8x16x3_t __i; __builtin_neon_ci __o; } __bu = { __b };
+ __builtin_neon_vst1q_x3v16qi ((__builtin_neon_qi *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_p16_x3 (poly16_t * __a, poly16x8x3_t __b)
+{
+ union { poly16x8x3_t __i; __builtin_neon_ci __o; } __bu = { __b };
+ __builtin_neon_vst1q_x3v8hi ((__builtin_neon_hi *) __a, __bu.__o);
+}
+
__extension__ extern __inline void
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vst1_lane_s8 (int8_t * __a, int8x8_t __b, const int __c)
@@ -20533,6 +20639,14 @@ vst1q_bf16_x2 (bfloat16_t * __a, bfloat16x8x2_t __b)
__builtin_neon_vst1q_x2v8bf (__a, __bu.__o);
}
+__extension__ extern __inline void
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_bf16_x3 (bfloat16_t * __a, bfloat16x8x3_t __b)
+{
+ union { bfloat16x8x3_t __i; __builtin_neon_ci __o; } __bu = { __b };
+ __builtin_neon_vst1q_x3v8bf (__a, __bu.__o);
+}
+
__extension__ extern __inline void
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vst2_bf16 (bfloat16_t * __ptr, bfloat16x4x2_t __val)
@@ -311,6 +311,7 @@ VAR10 (LOAD1, vld1_dup,
VAR7 (STORE1, vst1_x2, v8qi, v4hi, v2si, di, v4hf, v2sf, v4bf)
VAR7 (STORE1, vst1q_x2, v16qi, v8hi, v4si, v2di, v8hf, v4sf, v8bf)
VAR7 (STORE1, vst1_x3, v8qi, v4hi, v2si, di, v4hf, v2sf, v4bf)
+VAR7 (STORE1, vst1q_x3, v16qi, v8hi, v4si, v2di, v8hf, v4sf, v8bf)
VAR7 (STORE1, vst1_x4, v8qi, v4hi, v2si, di, v4hf, v2sf, v4bf)
VAR14 (STORE1, vst1,
v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf, v2di,
@@ -5145,6 +5145,30 @@ if (BYTES_BIG_ENDIAN)
[(set_attr "type" "neon_store1_3reg<q>")]
)
+(define_insn "neon_vst1q_x3<mode>"
+ [(set (match_operand:CI 0 "neon_struct_operand" "=Um")
+ (unspec:CI [(match_operand:CI 1 "s_register_operand" "w")
+ (unspec:VDQX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ UNSPEC_VST1))]
+ "TARGET_NEON"
+{
+ int regno = REGNO (operands[1]);
+ rtx ops[4];
+ ops[0] = operands[0];
+ ops[1] = gen_rtx_REG (DImode, regno);
+ ops[2] = gen_rtx_REG (DImode, regno + 2);
+ ops[3] = gen_rtx_REG (DImode, regno + 4);
+ output_asm_insn ("vst1.<V_sz_elem>\t{%P1, %P2, %P3}, %A0", ops);
+
+ ops[1] = gen_rtx_REG (DImode, regno + 6);
+ ops[2] = gen_rtx_REG (DImode, regno + 8);
+ ops[3] = gen_rtx_REG (DImode, regno + 10);
+ output_asm_insn ("vst1.<V_sz_elem>\t{%P1, %P2, %P3}, %A0", ops);
+ return "";
+}
+ [(set_attr "type" "neon_store1_3reg<q>")]
+)
+
(define_insn "neon_vst1_x4<mode>"
[(set (match_operand:OI 0 "neon_struct_operand" "=Um")
(unspec:OI [(match_operand:OI 1 "s_register_operand" "w")
@@ -61,10 +61,70 @@ void test_vst1q_p16_x2 (poly16_t * ptr, poly16x8x2_t val)
vst1q_p16_x2 (ptr, val);
}
+void test_vst1q_u8_x3 (uint8_t * ptr, uint8x16x3_t val)
+{
+ vst1q_u8_x3 (ptr, val);
+}
+
+void test_vst1q_u16_x3 (uint16_t * ptr, uint16x8x3_t val)
+{
+ vst1q_u16_x3 (ptr, val);
+}
+
+void test_vst1q_u32_x3 (uint32_t * ptr, uint32x4x3_t val)
+{
+ vst1q_u32_x3 (ptr, val);
+}
+
+void test_vst1q_u64_x3 (uint64_t * ptr, uint64x2x3_t val)
+{
+ vst1q_u64_x3 (ptr, val);
+}
+
+void test_vst1q_s8_x3 (int8_t * ptr, int8x16x3_t val)
+{
+ vst1q_s8_x3 (ptr, val);
+}
+
+void test_vst1q_s16_x3 (int16_t * ptr, int16x8x3_t val)
+{
+ vst1q_s16_x3 (ptr, val);
+}
+
+void test_vst1q_s32_x3 (int32_t * ptr, int32x4x3_t val)
+{
+ vst1q_s32_x3 (ptr, val);
+}
+
+void test_vst1q_s64_x3 (int64_t * ptr, int64x2x3_t val)
+{
+ vst1q_s64_x3 (ptr, val);
+}
+
+void test_vst1q_f32_x3 (float32_t * ptr, float32x4x3_t val)
+{
+ vst1q_f32_x3 (ptr, val);
+}
+
+void test_vst1q_p8_x3 (poly8_t * ptr, poly8x16x3_t val)
+{
+ vst1q_p8_x3 (ptr, val);
+}
+
+void test_vst1q_p16_x3 (poly16_t * ptr, poly16x8x3_t val)
+{
+ vst1q_p16_x3 (ptr, val);
+}
+
+
/* { dg-final { scan-assembler-times {vst1.8\t\{d[0-9]+-d[0-9]+\}, \[r[0-9]+\]\n} 3 } } */
+/* { dg-final { scan-assembler-times {vst1.8\t\{d[0-9]+, d[0-9]+, d[0-9]+\}, \[r[0-9]+\]\n} 6 } } */
/* { dg-final { scan-assembler-times {vst1.16\t\{d[0-9]+-d[0-9]+\}, \[r[0-9]+\]\n} 3 } } */
+/* { dg-final { scan-assembler-times {vst1.16\t\{d[0-9]+, d[0-9]+, d[0-9]+\}, \[r[0-9]+\]\n} 6 } } */
/* { dg-final { scan-assembler-times {vst1.32\t\{d[0-9]+-d[0-9]+\}, \[r[0-9]+\]\n} 3 } } */
+/* { dg-final { scan-assembler-times {vst1.32\t\{d[0-9]+, d[0-9]+, d[0-9]+\}, \[r[0-9]+\]\n} 6 } } */
/* { dg-final { scan-assembler-times {vst1.64\t\{d[0-9]+-d[0-9]+\}, \[r[0-9]+:64\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {vst1.64\t\{d[0-9]+, d[0-9]+, d[0-9]+\}, \[r[0-9]+:64\]\n} 4 } } */
@@ -10,4 +10,10 @@ void test_vst1q_bf16_x2 (bfloat16_t * ptr, bfloat16x8x2_t val)
vst1q_bf16_x2 (ptr, val);
}
+void test_vst1q_bf16_x3 (bfloat16_t * ptr, bfloat16x8x3_t val)
+{
+ vst1q_bf16_x3 (ptr, val);
+}
+
/* { dg-final { scan-assembler-times {vst1.16\t\{d[0-9]+-d[0-9]+\}, \[r[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {vst1.16\t\{d[0-9]+, d[0-9]+, d[0-9]+\}, \[r[0-9]+\]\n} 2 } } */
\ No newline at end of file
@@ -10,4 +10,10 @@ void test_vst1q_f16_x2 (float16_t * ptr, float16x8x2_t val)
vst1q_f16_x2 (ptr, val);
}
+void test_vst1q_f16_x3 (float16_t * ptr, float16x8x3_t val)
+{
+ vst1q_f16_x3 (ptr, val);
+}
+
/* { dg-final { scan-assembler-times {vst1.16\t\{d[0-9]+-d[0-9]+\}, \[r[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {vst1.16\t\{d[0-9]+, d[0-9]+, d[0-9]+\}, \[r[0-9]+\]\n} 2 } } */
@@ -10,4 +10,10 @@ void test_vst1q_p64_x2 (poly64_t * ptr, poly64x2x2_t val)
vst1q_p64_x2 (ptr, val);
}
+void test_vst1q_p64_x3 (poly64_t * ptr, poly64x2x3_t val)
+{
+ vst1q_p64_x3 (ptr, val);
+}
+
/* { dg-final { scan-assembler-times {vst1.64\t\{d[0-9]+-d[0-9]+\}, \[r[0-9]+:64\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {vst1.64\t\{d[0-9]+, d[0-9]+, d[0-9]+\}, \[r[0-9]+:64\]\n} 2 } } */