[PATCH 0/3] [GCC] arm: vst1q_types_xN ACLE intrinsics

[PATCH 0/3] [GCC] arm: vst1q_types_xN ACLE intrinsics

[Ezra.Sitorus]

Add xN variants of vst1q_types intrinsic for AArch32.

[PATCH 1/3] [GCC] arm: vst1q_types_x2 ACLE intrinsics

[Ezra.Sitorus]

From: Ezra Sitorus <ezra.sitorus@arm.com>

This patch is part of a series of patches implementing the _xN variants of the vst1q intrinsic for AArch32.
This patch adds the _x2 variants of the vst1q intrinsic. Tests use xN so that the latter variants (_x3, _x4) could be added.

ACLE documents are at https://developer.arm.com/documentation/ihi0053/latest/
ISA documents are at https://developer.arm.com/documentation/ddi0487/latest/

gcc/ChangeLog:
        * config/arm/arm_neon.h
        (vst1q_u8_x2, vst1q_u16_x2, vst1q_u32_x2, vst1q_u64_x32): New.
        (vst1q_s8_x2, vst1q_s16_x2, vst1q_s32_x2, vst1q_s64_x2): New.
        (vst1q_f16_x2, vst1q_f32_x2): New.
        (vst1q_p8_x2, vst1q_p16_x2, vst1q_p64_x2): New.
        (vst1q_bf16_x2): New.
        * config/arm/arm_neon_builtins.def (vst1<_x2): New entries.
        * config/arm/neon.md (neon_vst1<VMEMX2_q>_x2<VDQX:mode>): Updated from neon_vst1_x2<mode>.
	* config/arm/iterators.md (VMEMX2): New mode iterator.
	    (VMEMX2_q): New mode attribute.

gcc/testsuite/ChangeLog:
        * gcc.target/arm/simd/vst1q_base_xN_1.c: Add new tests.
        * gcc.target/arm/simd/vst1q_bf16_xN_1.c: Add new tests.
        * gcc.target/arm/simd/vst1q_fp16_xN_1.c: Add new tests.
        * gcc.target/arm/simd/vst1q_p64_xN_1.c: Add new tests.
---
 gcc/config/arm/arm_neon.h                     | 114 ++++++++++++++++++
 gcc/config/arm/arm_neon_builtins.def          |   1 +
 gcc/config/arm/iterators.md                   |   6 +
 gcc/config/arm/neon.md                        |   6 +-
 .../gcc.target/arm/simd/vst1q_base_xN_1.c     |  70 +++++++++++
 .../gcc.target/arm/simd/vst1q_bf16_xN_1.c     |  13 ++
 .../gcc.target/arm/simd/vst1q_fp16_xN_1.c     |  13 ++
 .../gcc.target/arm/simd/vst1q_p64_xN_1.c      |  13 ++
 8 files changed, 233 insertions(+), 3 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c
 create mode 100644 gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c
 create mode 100644 gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c
 create mode 100644 gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c

diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h
index 41e645d8352..b8f3fca3060 100644
--- a/gcc/config/arm/arm_neon.h
+++ b/gcc/config/arm/arm_neon.h
@@ -11327,6 +11327,38 @@ vst1_s64_x2 (int64_t * __a, int64x1x2_t __b)
   __builtin_neon_vst1_x2di ((__builtin_neon_di *) __a, __bu.__o);
 }
 
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_s8_x2 (int8_t * __a, int8x16x2_t __b)
+{
+  union { int8x16x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x2v16qi ((__builtin_neon_qi *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_s16_x2 (int16_t * __a, int16x8x2_t __b)
+{
+  union { int16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x2v8hi ((__builtin_neon_hi *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_s32_x2 (int32_t * __a, int32x4x2_t __b)
+{
+  union { int32x4x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x2v4si ((__builtin_neon_si *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_s64_x2 (int64_t * __a, int64x2x2_t __b)
+{
+  union { int64x2x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x2v2di ((__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)
@@ -11656,6 +11688,14 @@ vst1q_p64 (poly64_t * __a, poly64x2_t __b)
   __builtin_neon_vst1v2di ((__builtin_neon_di *) __a, (int64x2_t) __b);
 }
 
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_p64_x2 (poly64_t * __a, poly64x2x2_t __b)
+{
+  union { poly64x2x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x2v2di ((__builtin_neon_di *) __a, __bu.__o);
+}
+
 #pragma GCC pop_options
 __extension__ extern __inline void
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
@@ -11701,6 +11741,24 @@ vst1q_f32 (float32_t * __a, float32x4_t __b)
   __builtin_neon_vst1v4sf ((__builtin_neon_sf *) __a, __b);
 }
 
+#if defined (__ARM_FP16_FORMAT_IEEE) || defined (__ARM_FP16_FORMAT_ALTERNATIVE)
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_f16_x2 (float16_t * __a, float16x8x2_t __b)
+{
+  union { float16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x2v8hf (__a, __bu.__o);
+}
+#endif
+
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_f32_x2 (float32_t * __a, float32x4x2_t __b)
+{
+  union { float32x4x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x2v4sf (__a, __bu.__o);
+}
+
 __extension__ extern __inline void
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vst1q_u8 (uint8_t * __a, uint8x16_t __b)
@@ -11729,6 +11787,38 @@ vst1q_u64 (uint64_t * __a, uint64x2_t __b)
   __builtin_neon_vst1v2di ((__builtin_neon_di *) __a, (int64x2_t) __b);
 }
 
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_u8_x2 (uint8_t * __a, uint8x16x2_t __b)
+{
+  union { uint8x16x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x2v16qi ((__builtin_neon_qi *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_u16_x2 (uint16_t * __a, uint16x8x2_t __b)
+{
+  union { uint16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x2v8hi ((__builtin_neon_hi *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_u32_x2 (uint32_t * __a, uint32x4x2_t __b)
+{
+  union { uint32x4x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x2v4si ((__builtin_neon_si *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_u64_x2 (uint64_t * __a, uint64x2x2_t __b)
+{
+  union { uint64x2x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x2v2di ((__builtin_neon_di *) __a, __bu.__o);
+}
+
 __extension__ extern __inline void
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vst1q_p8 (poly8_t * __a, poly8x16_t __b)
@@ -11743,6 +11833,22 @@ vst1q_p16 (poly16_t * __a, poly16x8_t __b)
   __builtin_neon_vst1v8hi ((__builtin_neon_hi *) __a, (int16x8_t) __b);
 }
 
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_p8_x2 (poly8_t * __a, poly8x16x2_t __b)
+{
+  union { poly8x16x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x2v16qi ((__builtin_neon_qi *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_p16_x2 (poly16_t * __a, poly16x8x2_t __b)
+{
+  union { poly16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x2v8hi ((__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)
@@ -20419,6 +20525,14 @@ vst1q_bf16 (bfloat16_t * __a, bfloat16x8_t __b)
   __builtin_neon_vst1v8bf (__a, __b);
 }
 
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_bf16_x2 (bfloat16_t * __a, bfloat16x8x2_t __b)
+{
+  union { bfloat16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x2v8bf (__a, __bu.__o);
+}
+
 __extension__ extern __inline void
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vst2_bf16 (bfloat16_t * __ptr, bfloat16x4x2_t __val)
diff --git a/gcc/config/arm/arm_neon_builtins.def b/gcc/config/arm/arm_neon_builtins.def
index 95300cb0fe4..496d267fab8 100644
--- a/gcc/config/arm/arm_neon_builtins.def
+++ b/gcc/config/arm/arm_neon_builtins.def
@@ -309,6 +309,7 @@ VAR12 (LOAD1LANE, vld1_lane,
 VAR10 (LOAD1, vld1_dup,
 	v8qi, v4hi, v2si, v2sf, di, v16qi, v8hi, v4si, v4sf, v2di)
 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, vst1_x4, v8qi, v4hi, v2si, di, v4hf, v2sf, v4bf)
 VAR14 (STORE1, vst1,
diff --git a/gcc/config/arm/iterators.md b/gcc/config/arm/iterators.md
index a9803538101..6c5a80d9348 100644
--- a/gcc/config/arm/iterators.md
+++ b/gcc/config/arm/iterators.md
@@ -141,6 +141,9 @@
 ;; Opaque structure types used in table lookups (except vtbl1/vtbx1).
 (define_mode_iterator VTAB [TI EI OI])
 
+;; Opaque structure types for x2 variants of VSTR1/VSTR1Q or VLD1/VLD1Q.
+(define_mode_iterator VMEMX2 [TI OI])
+
 ;; Widenable modes.
 (define_mode_iterator VW [V8QI V4HI V2SI])
 
@@ -1533,6 +1536,9 @@
 ;; vtbl<n> suffix for NEON vector modes.
 (define_mode_attr VTAB_n [(TI "2") (EI "3") (OI "4")])
 
+;; Suffix for x2 variants of vld1 and vst1.
+(define_mode_attr VMEMX2_q [(TI "") (OI "q")])
+
 ;; fp16 or bf16 marker for 16-bit float modes.
 (define_mode_attr fporbf [(HF "fp16") (BF "bf16")])
 
diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md
index f5d583129fa..088277ee6ed 100644
--- a/gcc/config/arm/neon.md
+++ b/gcc/config/arm/neon.md
@@ -5125,9 +5125,9 @@ if (BYTES_BIG_ENDIAN)
 		     UNSPEC_VST1))]
   "TARGET_NEON")
 
-(define_insn "neon_vst1_x2<mode>"
-  [(set (match_operand:TI 0 "neon_struct_operand" "=Um")
-        (unspec:TI [(match_operand:TI 1 "s_register_operand" "w")
+(define_insn "neon_vst1<VMEMX2_q>_x2<VDQX:mode>"
+  [(set (match_operand:VMEMX2 0 "neon_struct_operand" "=Um")
+        (unspec:VMEMX2 [(match_operand:VMEMX2 1 "s_register_operand" "w")
                     (unspec:VDQX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
                    UNSPEC_VST1))]
   "TARGET_NEON"
diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c
new file mode 100644
index 00000000000..232feafade0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c
@@ -0,0 +1,70 @@
+/* { dg-do assemble } */
+/* { dg-require-effective-target arm_neon_ok } */
+/* { dg-options "-save-temps -O2" } */
+/* { dg-add-options arm_neon } */
+
+#include "arm_neon.h"
+
+
+void test_vst1q_u8_x2 (uint8_t * ptr, uint8x16x2_t val)
+{
+    vst1q_u8_x2 (ptr, val);
+}
+
+void test_vst1q_u16_x2 (uint16_t * ptr, uint16x8x2_t val)
+{
+    vst1q_u16_x2 (ptr, val);
+}
+
+void test_vst1q_u32_x2 (uint32_t * ptr, uint32x4x2_t val)
+{
+    vst1q_u32_x2 (ptr, val);
+}
+
+void test_vst1q_u64_x2 (uint64_t * ptr, uint64x2x2_t val)
+{
+    vst1q_u64_x2 (ptr, val);
+}
+
+void test_vst1q_s8_x2 (int8_t * ptr, int8x16x2_t val)
+{
+    vst1q_s8_x2 (ptr, val);
+}
+
+void test_vst1q_s16_x2 (int16_t * ptr, int16x8x2_t val)
+{
+    vst1q_s16_x2 (ptr, val);
+}
+
+void test_vst1q_s32_x2 (int32_t * ptr, int32x4x2_t val)
+{
+    vst1q_s32_x2 (ptr, val);
+}
+
+void test_vst1q_s64_x2 (int64_t * ptr, int64x2x2_t val)
+{
+    vst1q_s64_x2 (ptr, val);
+}
+
+void test_vst1q_f32_x2 (float32_t * ptr, float32x4x2_t val)
+{
+    vst1q_f32_x2 (ptr, val);
+}
+
+void test_vst1q_p8_x2 (poly8_t * ptr, poly8x16x2_t val)
+{
+    vst1q_p8_x2 (ptr, val);
+}
+
+void test_vst1q_p16_x2 (poly16_t * ptr, poly16x8x2_t val)
+{
+    vst1q_p16_x2 (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 {vst1.16\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]+\}, \[r[0-9]+\]\n} 3 } }  */
+
+/* { dg-final { scan-assembler-times {vst1.64\t\{d[0-9]+-d[0-9]+\}, \[r[0-9]+:64\]\n} 2 } }  */
diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c
new file mode 100644
index 00000000000..2a4579f0aae
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c
@@ -0,0 +1,13 @@
+/* { dg-do assemble } */
+/* { dg-require-effective-target arm_v8_2a_bf16_neon_ok } */
+/* { dg-options "-save-temps -O2" } */
+/* { dg-add-options arm_v8_2a_bf16_neon } */
+
+#include "arm_neon.h"
+
+void test_vst1q_bf16_x2 (bfloat16_t * ptr, bfloat16x8x2_t val)
+{
+    vst1q_bf16_x2 (ptr, val);
+}
+
+/* { dg-final { scan-assembler-times {vst1.16\t\{d[0-9]+-d[0-9]+\}, \[r[0-9]+\]\n} 1 } }  */
diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c
new file mode 100644
index 00000000000..61a7e558c48
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c
@@ -0,0 +1,13 @@
+/* { dg-do assemble } */
+/* { dg-require-effective-target arm_neon_fp16_ok } */
+/* { dg-options "-save-temps -O2" } */
+/* { dg-add-options arm_neon_fp16 } */
+
+#include "arm_neon.h"
+
+void test_vst1q_f16_x2 (float16_t * ptr, float16x8x2_t val)
+{
+    vst1q_f16_x2 (ptr, val);
+}
+
+/* { dg-final { scan-assembler-times {vst1.16\t\{d[0-9]+-d[0-9]+\}, \[r[0-9]+\]\n} 1 } }  */
diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c
new file mode 100644
index 00000000000..82f3dad293c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c
@@ -0,0 +1,13 @@
+/* { dg-do assemble } */
+/* { dg-require-effective-target arm_crypto_ok } */
+/* { dg-options "-save-temps -O2" } */
+/* { dg-add-options arm_crypto } */
+
+#include "arm_neon.h"
+
+void test_vst1q_p64_x2 (poly64_t * ptr, poly64x2x2_t val)
+{
+    vst1q_p64_x2 (ptr, val);
+}
+
+/* { dg-final { scan-assembler-times {vst1.64\t\{d[0-9]+-d[0-9]+\}, \[r[0-9]+:64\]\n} 1 } }  */
-- 
2.25.1

[PATCH 2/3] [GCC] arm: vst1q_types_x3 ACLE intrinsics

[Ezra.Sitorus]

From: Ezra Sitorus <ezra.sitorus@arm.com>

This patch is part of a series of patches implementing the _xN variants of the vst1q intrinsic for AArch32.
This patch adds the _x3 variants of the vst1q intrinsic.

ACLE documents are at https://developer.arm.com/documentation/ihi0053/latest/
ISA documents are at https://developer.arm.com/documentation/ddi0487/latest/

gcc/ChangeLog:
        * config/arm/arm_neon.h
        (vst1q_u8_x3, vst1q_u16_x3, vst1q_u32_x3, vst1q_u64_x3): New.
        (vst1q_s8_x3, vst1q_s16_x3, vst1q_s32_x3, vst1q_s64_x3): New.
        (vst1q_f16_x3, vst1q_f32_x3): New.
        (vst1q_p8_x3, vst1q_p16_x3, vst1q_p64_x3): New.
        (vst1q_bf16_x3): New.
        * config/arm/arm_neon_builtins.def (vst1q_x3): New entries.
        * config/arm/neon.md (neon_vst1q_x3<mode>): New.

gcc/testsuite/ChangeLog:
        * gcc.target/arm/simd/vst1q_base_xN_1.c: Add new tests.
        * gcc.target/arm/simd/vst1q_bf16_xN_1.c: Add new tests.
        * gcc.target/arm/simd/vst1q_fp16_xN_1.c: Add new tests.
        * gcc.target/arm/simd/vst1q_p64_xN_1.c: Add new tests.
---
 gcc/config/arm/arm_neon.h                     | 114 ++++++++++++++++++
 gcc/config/arm/arm_neon_builtins.def          |   1 +
 gcc/config/arm/neon.md                        |  24 ++++
 .../gcc.target/arm/simd/vst1q_base_xN_1.c     |  60 +++++++++
 .../gcc.target/arm/simd/vst1q_bf16_xN_1.c     |   6 +
 .../gcc.target/arm/simd/vst1q_fp16_xN_1.c     |   6 +
 .../gcc.target/arm/simd/vst1q_p64_xN_1.c      |   6 +
 7 files changed, 217 insertions(+)

diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h
index b8f3fca3060..46ee888410f 100644
--- a/gcc/config/arm/arm_neon.h
+++ b/gcc/config/arm/arm_neon.h
@@ -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)
diff --git a/gcc/config/arm/arm_neon_builtins.def b/gcc/config/arm/arm_neon_builtins.def
index 496d267fab8..b1886372a1f 100644
--- a/gcc/config/arm/arm_neon_builtins.def
+++ b/gcc/config/arm/arm_neon_builtins.def
@@ -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,
diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md
index 088277ee6ed..b69ed24c018 100644
--- a/gcc/config/arm/neon.md
+++ b/gcc/config/arm/neon.md
@@ -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")
diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c
index 232feafade0..ba30fda514f 100644
--- a/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c
+++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c
@@ -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 } }  */
diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c
index 2a4579f0aae..2593c31c756 100644
--- a/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c
+++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c
@@ -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
diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c
index 61a7e558c48..28e949b557a 100644
--- a/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c
+++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c
@@ -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 } }  */
diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c
index 82f3dad293c..7878d936b9f 100644
--- a/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c
+++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c
@@ -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 } }  */
-- 
2.25.1

[PATCH 3/3] [GCC] arm: vst1q_types_x4 ACLE intrinsics

[Ezra.Sitorus]

From: Ezra Sitorus <ezra.sitorus@arm.com>

This patch is part of a series of patches implementing the _xN variants of the vst1q intrinsic for AArch32.
This patch adds the _x4 variants of the vst1q intrinsic.

ACLE documents are at https://developer.arm.com/documentation/ihi0053/latest/
ISA documents are at https://developer.arm.com/documentation/ddi0487/latest/

gcc/ChangeLog:
    * config/arm/arm_neon.h
    (vst1q_u8_x4, vst1q_u16_x4, vst1q_u32_x4, vst1q_u64_x4): New.
    (vst1q_s8_x4, vst1q_s16_x4, vst1q_s32_x4, vst1q_s64_x4): New.
    (vst1q_f16_x4, vst1q_f32_x4): New.
    (vst1q_p8_x4, vst1q_p16_x4, vst1q_p64_x4): New.
    (vst1q_bf16_x4): New.
    * config/arm/arm_neon_builtins.def (vst1q_x4): New entries.
    * config/arm/neon.md (neon_vst1q_x4<mode>): New.

gcc/testsuite/ChangeLog:
    * gcc.target/arm/simd/vst1q_base_xN_1.c: Add new tests.
    * gcc.target/arm/simd/vst1q_bf16_xN_1.c: Add new tests.
    * gcc.target/arm/simd/vst1q_fp16_xN_1.c: Add new tests.
    * gcc.target/arm/simd/vst1q_p64_xN_1.c: Add new tests.
---
 gcc/config/arm/arm_neon.h                     | 114 ++++++++++++++++++
 gcc/config/arm/arm_neon_builtins.def          |   1 +
 gcc/config/arm/neon.md                        |  26 ++++
 .../gcc.target/arm/simd/vst1q_base_xN_1.c     |  59 +++++++++
 .../gcc.target/arm/simd/vst1q_bf16_xN_1.c     |   8 +-
 .../gcc.target/arm/simd/vst1q_fp16_xN_1.c     |   6 +
 .../gcc.target/arm/simd/vst1q_p64_xN_1.c      |   6 +
 7 files changed, 219 insertions(+), 1 deletion(-)

diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h
index 46ee888410f..df3e23b6e95 100644
--- a/gcc/config/arm/arm_neon.h
+++ b/gcc/config/arm/arm_neon.h
@@ -11391,6 +11391,38 @@ vst1q_s64_x3 (int64_t * __a, int64x2x3_t __b)
   __builtin_neon_vst1q_x3v2di ((__builtin_neon_di *) __a, __bu.__o);
 }
 
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_s8_x4 (int8_t * __a, int8x16x4_t __b)
+{
+  union { int8x16x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x4v16qi ((__builtin_neon_qi *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_s16_x4 (int16_t * __a, int16x8x4_t __b)
+{
+  union { int16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x4v8hi ((__builtin_neon_hi *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_s32_x4 (int32_t * __a, int32x4x4_t __b)
+{
+  union { int32x4x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x4v4si ((__builtin_neon_si *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_s64_x4 (int64_t * __a, int64x2x4_t __b)
+{
+  union { int64x2x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x4v2di ((__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)
@@ -11736,6 +11768,14 @@ vst1q_p64_x3 (poly64_t * __a, poly64x2x3_t __b)
   __builtin_neon_vst1q_x3v2di ((__builtin_neon_di *) __a, __bu.__o);
 }
 
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_p64_x4 (poly64_t * __a, poly64x2x4_t __b)
+{
+  union { poly64x2x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x4v2di ((__builtin_neon_di *) __a, __bu.__o);
+}
+
 #pragma GCC pop_options
 __extension__ extern __inline void
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
@@ -11817,6 +11857,24 @@ vst1q_f32_x3 (float32_t * __a, float32x4x3_t __b)
   __builtin_neon_vst1q_x3v4sf (__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_x4 (float16_t * __a, float16x8x4_t __b)
+{
+  union { float16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x4v8hf (__a, __bu.__o);
+}
+#endif
+
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_f32_x4 (float32_t * __a, float32x4x4_t __b)
+{
+  union { float32x4x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x4v4sf (__a, __bu.__o);
+}
+
 __extension__ extern __inline void
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vst1q_u8 (uint8_t * __a, uint8x16_t __b)
@@ -11909,6 +11967,38 @@ vst1q_u64_x3 (uint64_t * __a, uint64x2x3_t __b)
   __builtin_neon_vst1q_x3v2di ((__builtin_neon_di *) __a, __bu.__o);
 }
 
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_u8_x4 (uint8_t * __a, uint8x16x4_t __b)
+{
+  union { uint8x16x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x4v16qi ((__builtin_neon_qi *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_u16_x4 (uint16_t * __a, uint16x8x4_t __b)
+{
+  union { uint16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x4v8hi ((__builtin_neon_hi *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_u32_x4 (uint32_t * __a, uint32x4x4_t __b)
+{
+  union { uint32x4x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x4v4si ((__builtin_neon_si *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_u64_x4 (uint64_t * __a, uint64x2x4_t __b)
+{
+  union { uint64x2x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x4v2di ((__builtin_neon_di *) __a, __bu.__o);
+}
+
 __extension__ extern __inline void
 __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
 vst1q_p8 (poly8_t * __a, poly8x16_t __b)
@@ -11955,6 +12045,22 @@ vst1q_p16_x3 (poly16_t * __a, poly16x8x3_t __b)
   __builtin_neon_vst1q_x3v8hi ((__builtin_neon_hi *) __a, __bu.__o);
 }
 
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_p8_x4 (poly8_t * __a, poly8x16x4_t __b)
+{
+  union { poly8x16x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x4v16qi ((__builtin_neon_qi *) __a, __bu.__o);
+}
+
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_p16_x4 (poly16_t * __a, poly16x8x4_t __b)
+{
+  union { poly16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x4v8hi ((__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)
@@ -20647,6 +20753,14 @@ vst1q_bf16_x3 (bfloat16_t * __a, bfloat16x8x3_t __b)
   __builtin_neon_vst1q_x3v8bf (__a, __bu.__o);
 }
 
+__extension__ extern __inline void
+__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
+vst1q_bf16_x4 (bfloat16_t * __a, bfloat16x8x4_t __b)
+{
+  union { bfloat16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
+  __builtin_neon_vst1q_x4v8bf (__a, __bu.__o);
+}
+
 __extension__ extern __inline void
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vst2_bf16 (bfloat16_t * __ptr, bfloat16x4x2_t __val)
diff --git a/gcc/config/arm/arm_neon_builtins.def b/gcc/config/arm/arm_neon_builtins.def
index b1886372a1f..12f78800588 100644
--- a/gcc/config/arm/arm_neon_builtins.def
+++ b/gcc/config/arm/arm_neon_builtins.def
@@ -313,6 +313,7 @@ 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)
+VAR7 (STORE1, vst1q_x4, v16qi, v8hi, v4si, v2di, v8hf, v4sf, v8bf)
 VAR14 (STORE1, vst1,
         v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf, v2di,
         v4bf, v8bf)
diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md
index b69ed24c018..2fa4f85b820 100644
--- a/gcc/config/arm/neon.md
+++ b/gcc/config/arm/neon.md
@@ -5169,6 +5169,32 @@ if (BYTES_BIG_ENDIAN)
   [(set_attr "type" "neon_store1_3reg<q>")]
 )
 
+(define_insn "neon_vst1q_x4<mode>"
+  [(set (match_operand:XI 0 "neon_struct_operand" "=Um")
+        (unspec:XI [(match_operand:XI 1 "s_register_operand" "w")
+                    (unspec:VDQX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+                   UNSPEC_VST1))]
+  "TARGET_NEON"
+{
+  int regno = REGNO (operands[1]);
+  rtx ops[5];
+  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);
+  ops[4] = gen_rtx_REG (DImode, regno + 6);
+  output_asm_insn ("vst1.<V_sz_elem>\t{%P1, %P2, %P3, %P4}, %A0", ops);
+
+  ops[1] = gen_rtx_REG (DImode, regno + 8);
+  ops[2] = gen_rtx_REG (DImode, regno + 10);
+  ops[3] = gen_rtx_REG (DImode, regno + 12);
+  ops[4] = gen_rtx_REG (DImode, regno + 14);
+  output_asm_insn ("vst1.<V_sz_elem>\t{%P1, %P2, %P3, %P4}, %A0", ops);
+  return "";
+}
+  [(set_attr "type" "neon_store1_4reg<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")
diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c
index ba30fda514f..461aae3af62 100644
--- a/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c
+++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c
@@ -116,15 +116,74 @@ void test_vst1q_p16_x3 (poly16_t * ptr, poly16x8x3_t val)
     vst1q_p16_x3 (ptr, val);
 }
 
+void test_vst1q_u8_x4 (uint8_t * ptr, uint8x16x4_t val)
+{
+    vst1q_u8_x4 (ptr, val);
+}
+
+void test_vst1q_u16_x4 (uint16_t * ptr, uint16x8x4_t val)
+{
+    vst1q_u16_x4 (ptr, val);
+}
+
+void test_vst1q_u32_x4 (uint32_t * ptr, uint32x4x4_t val)
+{
+    vst1q_u32_x4 (ptr, val);
+}
+
+void test_vst1q_u64_x4 (uint64_t * ptr, uint64x2x4_t val)
+{
+    vst1q_u64_x4 (ptr, val);
+}
+
+void test_vst1q_s8_x4 (int8_t * ptr, int8x16x4_t val)
+{
+    vst1q_s8_x4 (ptr, val);
+}
+
+void test_vst1q_s16_x4 (int16_t * ptr, int16x8x4_t val)
+{
+    vst1q_s16_x4 (ptr, val);
+}
+
+void test_vst1q_s32_x4 (int32_t * ptr, int32x4x4_t val)
+{
+    vst1q_s32_x4 (ptr, val);
+}
+
+void test_vst1q_s64_x4 (int64_t * ptr, int64x2x4_t val)
+{
+    vst1q_s64_x4 (ptr, val);
+}
+
+void test_vst1q_f32_x4 (float32_t * ptr, float32x4x4_t val)
+{
+    vst1q_f32_x4 (ptr, val);
+}
+
+void test_vst1q_p8_x4 (poly8_t * ptr, poly8x16x4_t val)
+{
+    vst1q_p8_x4 (ptr, val);
+}
+
+void test_vst1q_p16_x4 (poly16_t * ptr, poly16x8x4_t val)
+{
+    vst1q_p16_x4 (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 {vst1.8\t\{d[0-9]+, 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 {vst1.16\t\{d[0-9]+, 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 {vst1.32\t\{d[0-9]+, 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 } }  */
+/* { dg-final { scan-assembler-times {vst1.64\t\{d[0-9]+, d[0-9]+, d[0-9]+, d[0-9]+\}, \[r[0-9]+:64\]\n} 4 } }  */
diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c
index 2593c31c756..84fa8509db8 100644
--- a/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c
+++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c
@@ -15,5 +15,11 @@ void test_vst1q_bf16_x3 (bfloat16_t * ptr, bfloat16x8x3_t val)
     vst1q_bf16_x3 (ptr, val);
 }
 
+void test_vst1q_bf16_x4 (bfloat16_t * ptr, bfloat16x8x4_t val)
+{
+    vst1q_bf16_x4 (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
+/* { dg-final { scan-assembler-times {vst1.16\t\{d[0-9]+, d[0-9]+, d[0-9]+\}, \[r[0-9]+\]\n} 2 } }  */
+/* { dg-final { scan-assembler-times {vst1.16\t\{d[0-9]+, d[0-9]+, d[0-9]+, d[0-9]+\}, \[r[0-9]+\]\n} 2 } }  */
\ No newline at end of file
diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c
index 28e949b557a..5b13edf9998 100644
--- a/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c
+++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c
@@ -15,5 +15,11 @@ void test_vst1q_f16_x3 (float16_t * ptr, float16x8x3_t val)
     vst1q_f16_x3 (ptr, val);
 }
 
+void test_vst1q_f16_x4 (float16_t * ptr, float16x8x4_t val)
+{
+    vst1q_f16_x4 (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 } }  */
+/* { dg-final { scan-assembler-times {vst1.16\t\{d[0-9]+, d[0-9]+, d[0-9]+, d[0-9]+\}, \[r[0-9]+\]\n} 2 } }  */
diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c
index 7878d936b9f..f49917d5ec8 100644
--- a/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c
+++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c
@@ -15,5 +15,11 @@ void test_vst1q_p64_x3 (poly64_t * ptr, poly64x2x3_t val)
     vst1q_p64_x3 (ptr, val);
 }
 
+void test_vst1q_p64_x4 (poly64_t * ptr, poly64x2x4_t val)
+{
+    vst1q_p64_x4 (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 } }  */
+/* { dg-final { scan-assembler-times {vst1.64\t\{d[0-9]+, d[0-9]+, d[0-9]+, d[0-9]+\}, \[r[0-9]+:64\]\n} 2 } }  */
-- 
2.25.1

Re: [PATCH 1/3] [GCC] arm: vst1q_types_x2 ACLE intrinsics

[Richard Earnshaw]

On 10/10/2023 15:04, Ezra.Sitorus@arm.com wrote:
> From: Ezra Sitorus <ezra.sitorus@arm.com>
> 
> This patch is part of a series of patches implementing the _xN variants of the vst1q intrinsic for AArch32.
> This patch adds the _x2 variants of the vst1q intrinsic. Tests use xN so that the latter variants (_x3, _x4) could be added.
> 
> ACLE documents are at https://developer.arm.com/documentation/ihi0053/latest/
> ISA documents are at https://developer.arm.com/documentation/ddi0487/latest/
> 
> gcc/ChangeLog:
>          * config/arm/arm_neon.h
>          (vst1q_u8_x2, vst1q_u16_x2, vst1q_u32_x2, vst1q_u64_x32): New.

The same issues that I noted on the previous set apply here too.

Otherwise OK.

R.

>          (vst1q_s8_x2, vst1q_s16_x2, vst1q_s32_x2, vst1q_s64_x2): New.
>          (vst1q_f16_x2, vst1q_f32_x2): New.
>          (vst1q_p8_x2, vst1q_p16_x2, vst1q_p64_x2): New.
>          (vst1q_bf16_x2): New.
>          * config/arm/arm_neon_builtins.def (vst1<_x2): New entries.
>          * config/arm/neon.md (neon_vst1<VMEMX2_q>_x2<VDQX:mode>): Updated from neon_vst1_x2<mode>.
> 	* config/arm/iterators.md (VMEMX2): New mode iterator.
> 	    (VMEMX2_q): New mode attribute.
> 
> gcc/testsuite/ChangeLog:
>          * gcc.target/arm/simd/vst1q_base_xN_1.c: Add new tests.
>          * gcc.target/arm/simd/vst1q_bf16_xN_1.c: Add new tests.
>          * gcc.target/arm/simd/vst1q_fp16_xN_1.c: Add new tests.
>          * gcc.target/arm/simd/vst1q_p64_xN_1.c: Add new tests.
> ---
>   gcc/config/arm/arm_neon.h                     | 114 ++++++++++++++++++
>   gcc/config/arm/arm_neon_builtins.def          |   1 +
>   gcc/config/arm/iterators.md                   |   6 +
>   gcc/config/arm/neon.md                        |   6 +-
>   .../gcc.target/arm/simd/vst1q_base_xN_1.c     |  70 +++++++++++
>   .../gcc.target/arm/simd/vst1q_bf16_xN_1.c     |  13 ++
>   .../gcc.target/arm/simd/vst1q_fp16_xN_1.c     |  13 ++
>   .../gcc.target/arm/simd/vst1q_p64_xN_1.c      |  13 ++
>   8 files changed, 233 insertions(+), 3 deletions(-)
>   create mode 100644 gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c
>   create mode 100644 gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c
>   create mode 100644 gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c
>   create mode 100644 gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c
> 
> diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h
> index 41e645d8352..b8f3fca3060 100644
> --- a/gcc/config/arm/arm_neon.h
> +++ b/gcc/config/arm/arm_neon.h
> @@ -11327,6 +11327,38 @@ vst1_s64_x2 (int64_t * __a, int64x1x2_t __b)
>     __builtin_neon_vst1_x2di ((__builtin_neon_di *) __a, __bu.__o);
>   }
>   
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_s8_x2 (int8_t * __a, int8x16x2_t __b)
> +{
> +  union { int8x16x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x2v16qi ((__builtin_neon_qi *) __a, __bu.__o);
> +}
> +
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_s16_x2 (int16_t * __a, int16x8x2_t __b)
> +{
> +  union { int16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x2v8hi ((__builtin_neon_hi *) __a, __bu.__o);
> +}
> +
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_s32_x2 (int32_t * __a, int32x4x2_t __b)
> +{
> +  union { int32x4x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x2v4si ((__builtin_neon_si *) __a, __bu.__o);
> +}
> +
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_s64_x2 (int64_t * __a, int64x2x2_t __b)
> +{
> +  union { int64x2x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x2v2di ((__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)
> @@ -11656,6 +11688,14 @@ vst1q_p64 (poly64_t * __a, poly64x2_t __b)
>     __builtin_neon_vst1v2di ((__builtin_neon_di *) __a, (int64x2_t) __b);
>   }
>   
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_p64_x2 (poly64_t * __a, poly64x2x2_t __b)
> +{
> +  union { poly64x2x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x2v2di ((__builtin_neon_di *) __a, __bu.__o);
> +}
> +
>   #pragma GCC pop_options
>   __extension__ extern __inline void
>   __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> @@ -11701,6 +11741,24 @@ vst1q_f32 (float32_t * __a, float32x4_t __b)
>     __builtin_neon_vst1v4sf ((__builtin_neon_sf *) __a, __b);
>   }
>   
> +#if defined (__ARM_FP16_FORMAT_IEEE) || defined (__ARM_FP16_FORMAT_ALTERNATIVE)
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_f16_x2 (float16_t * __a, float16x8x2_t __b)
> +{
> +  union { float16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x2v8hf (__a, __bu.__o);
> +}
> +#endif
> +
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_f32_x2 (float32_t * __a, float32x4x2_t __b)
> +{
> +  union { float32x4x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x2v4sf (__a, __bu.__o);
> +}
> +
>   __extension__ extern __inline void
>   __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
>   vst1q_u8 (uint8_t * __a, uint8x16_t __b)
> @@ -11729,6 +11787,38 @@ vst1q_u64 (uint64_t * __a, uint64x2_t __b)
>     __builtin_neon_vst1v2di ((__builtin_neon_di *) __a, (int64x2_t) __b);
>   }
>   
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_u8_x2 (uint8_t * __a, uint8x16x2_t __b)
> +{
> +  union { uint8x16x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x2v16qi ((__builtin_neon_qi *) __a, __bu.__o);
> +}
> +
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_u16_x2 (uint16_t * __a, uint16x8x2_t __b)
> +{
> +  union { uint16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x2v8hi ((__builtin_neon_hi *) __a, __bu.__o);
> +}
> +
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_u32_x2 (uint32_t * __a, uint32x4x2_t __b)
> +{
> +  union { uint32x4x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x2v4si ((__builtin_neon_si *) __a, __bu.__o);
> +}
> +
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_u64_x2 (uint64_t * __a, uint64x2x2_t __b)
> +{
> +  union { uint64x2x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x2v2di ((__builtin_neon_di *) __a, __bu.__o);
> +}
> +
>   __extension__ extern __inline void
>   __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
>   vst1q_p8 (poly8_t * __a, poly8x16_t __b)
> @@ -11743,6 +11833,22 @@ vst1q_p16 (poly16_t * __a, poly16x8_t __b)
>     __builtin_neon_vst1v8hi ((__builtin_neon_hi *) __a, (int16x8_t) __b);
>   }
>   
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_p8_x2 (poly8_t * __a, poly8x16x2_t __b)
> +{
> +  union { poly8x16x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x2v16qi ((__builtin_neon_qi *) __a, __bu.__o);
> +}
> +
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_p16_x2 (poly16_t * __a, poly16x8x2_t __b)
> +{
> +  union { poly16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x2v8hi ((__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)
> @@ -20419,6 +20525,14 @@ vst1q_bf16 (bfloat16_t * __a, bfloat16x8_t __b)
>     __builtin_neon_vst1v8bf (__a, __b);
>   }
>   
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_bf16_x2 (bfloat16_t * __a, bfloat16x8x2_t __b)
> +{
> +  union { bfloat16x8x2_t __i; __builtin_neon_oi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x2v8bf (__a, __bu.__o);
> +}
> +
>   __extension__ extern __inline void
>   __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>   vst2_bf16 (bfloat16_t * __ptr, bfloat16x4x2_t __val)
> diff --git a/gcc/config/arm/arm_neon_builtins.def b/gcc/config/arm/arm_neon_builtins.def
> index 95300cb0fe4..496d267fab8 100644
> --- a/gcc/config/arm/arm_neon_builtins.def
> +++ b/gcc/config/arm/arm_neon_builtins.def
> @@ -309,6 +309,7 @@ VAR12 (LOAD1LANE, vld1_lane,
>   VAR10 (LOAD1, vld1_dup,
>   	v8qi, v4hi, v2si, v2sf, di, v16qi, v8hi, v4si, v4sf, v2di)
>   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, vst1_x4, v8qi, v4hi, v2si, di, v4hf, v2sf, v4bf)
>   VAR14 (STORE1, vst1,
> diff --git a/gcc/config/arm/iterators.md b/gcc/config/arm/iterators.md
> index a9803538101..6c5a80d9348 100644
> --- a/gcc/config/arm/iterators.md
> +++ b/gcc/config/arm/iterators.md
> @@ -141,6 +141,9 @@
>   ;; Opaque structure types used in table lookups (except vtbl1/vtbx1).
>   (define_mode_iterator VTAB [TI EI OI])
>   
> +;; Opaque structure types for x2 variants of VSTR1/VSTR1Q or VLD1/VLD1Q.
> +(define_mode_iterator VMEMX2 [TI OI])
> +
>   ;; Widenable modes.
>   (define_mode_iterator VW [V8QI V4HI V2SI])
>   
> @@ -1533,6 +1536,9 @@
>   ;; vtbl<n> suffix for NEON vector modes.
>   (define_mode_attr VTAB_n [(TI "2") (EI "3") (OI "4")])
>   
> +;; Suffix for x2 variants of vld1 and vst1.
> +(define_mode_attr VMEMX2_q [(TI "") (OI "q")])
> +
>   ;; fp16 or bf16 marker for 16-bit float modes.
>   (define_mode_attr fporbf [(HF "fp16") (BF "bf16")])
>   
> diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md
> index f5d583129fa..088277ee6ed 100644
> --- a/gcc/config/arm/neon.md
> +++ b/gcc/config/arm/neon.md
> @@ -5125,9 +5125,9 @@ if (BYTES_BIG_ENDIAN)
>   		     UNSPEC_VST1))]
>     "TARGET_NEON")
>   
> -(define_insn "neon_vst1_x2<mode>"
> -  [(set (match_operand:TI 0 "neon_struct_operand" "=Um")
> -        (unspec:TI [(match_operand:TI 1 "s_register_operand" "w")
> +(define_insn "neon_vst1<VMEMX2_q>_x2<VDQX:mode>"
> +  [(set (match_operand:VMEMX2 0 "neon_struct_operand" "=Um")
> +        (unspec:VMEMX2 [(match_operand:VMEMX2 1 "s_register_operand" "w")
>                       (unspec:VDQX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
>                      UNSPEC_VST1))]
>     "TARGET_NEON"
> diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c
> new file mode 100644
> index 00000000000..232feafade0
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c
> @@ -0,0 +1,70 @@
> +/* { dg-do assemble } */
> +/* { dg-require-effective-target arm_neon_ok } */
> +/* { dg-options "-save-temps -O2" } */
> +/* { dg-add-options arm_neon } */
> +
> +#include "arm_neon.h"
> +
> +
> +void test_vst1q_u8_x2 (uint8_t * ptr, uint8x16x2_t val)
> +{
> +    vst1q_u8_x2 (ptr, val);
> +}
> +
> +void test_vst1q_u16_x2 (uint16_t * ptr, uint16x8x2_t val)
> +{
> +    vst1q_u16_x2 (ptr, val);
> +}
> +
> +void test_vst1q_u32_x2 (uint32_t * ptr, uint32x4x2_t val)
> +{
> +    vst1q_u32_x2 (ptr, val);
> +}
> +
> +void test_vst1q_u64_x2 (uint64_t * ptr, uint64x2x2_t val)
> +{
> +    vst1q_u64_x2 (ptr, val);
> +}
> +
> +void test_vst1q_s8_x2 (int8_t * ptr, int8x16x2_t val)
> +{
> +    vst1q_s8_x2 (ptr, val);
> +}
> +
> +void test_vst1q_s16_x2 (int16_t * ptr, int16x8x2_t val)
> +{
> +    vst1q_s16_x2 (ptr, val);
> +}
> +
> +void test_vst1q_s32_x2 (int32_t * ptr, int32x4x2_t val)
> +{
> +    vst1q_s32_x2 (ptr, val);
> +}
> +
> +void test_vst1q_s64_x2 (int64_t * ptr, int64x2x2_t val)
> +{
> +    vst1q_s64_x2 (ptr, val);
> +}
> +
> +void test_vst1q_f32_x2 (float32_t * ptr, float32x4x2_t val)
> +{
> +    vst1q_f32_x2 (ptr, val);
> +}
> +
> +void test_vst1q_p8_x2 (poly8_t * ptr, poly8x16x2_t val)
> +{
> +    vst1q_p8_x2 (ptr, val);
> +}
> +
> +void test_vst1q_p16_x2 (poly16_t * ptr, poly16x8x2_t val)
> +{
> +    vst1q_p16_x2 (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 {vst1.16\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]+\}, \[r[0-9]+\]\n} 3 } }  */
> +
> +/* { dg-final { scan-assembler-times {vst1.64\t\{d[0-9]+-d[0-9]+\}, \[r[0-9]+:64\]\n} 2 } }  */
> diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c
> new file mode 100644
> index 00000000000..2a4579f0aae
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c
> @@ -0,0 +1,13 @@
> +/* { dg-do assemble } */
> +/* { dg-require-effective-target arm_v8_2a_bf16_neon_ok } */
> +/* { dg-options "-save-temps -O2" } */
> +/* { dg-add-options arm_v8_2a_bf16_neon } */
> +
> +#include "arm_neon.h"
> +
> +void test_vst1q_bf16_x2 (bfloat16_t * ptr, bfloat16x8x2_t val)
> +{
> +    vst1q_bf16_x2 (ptr, val);
> +}
> +
> +/* { dg-final { scan-assembler-times {vst1.16\t\{d[0-9]+-d[0-9]+\}, \[r[0-9]+\]\n} 1 } }  */
> diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c
> new file mode 100644
> index 00000000000..61a7e558c48
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c
> @@ -0,0 +1,13 @@
> +/* { dg-do assemble } */
> +/* { dg-require-effective-target arm_neon_fp16_ok } */
> +/* { dg-options "-save-temps -O2" } */
> +/* { dg-add-options arm_neon_fp16 } */
> +
> +#include "arm_neon.h"
> +
> +void test_vst1q_f16_x2 (float16_t * ptr, float16x8x2_t val)
> +{
> +    vst1q_f16_x2 (ptr, val);
> +}
> +
> +/* { dg-final { scan-assembler-times {vst1.16\t\{d[0-9]+-d[0-9]+\}, \[r[0-9]+\]\n} 1 } }  */
> diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c
> new file mode 100644
> index 00000000000..82f3dad293c
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c
> @@ -0,0 +1,13 @@
> +/* { dg-do assemble } */
> +/* { dg-require-effective-target arm_crypto_ok } */
> +/* { dg-options "-save-temps -O2" } */
> +/* { dg-add-options arm_crypto } */
> +
> +#include "arm_neon.h"
> +
> +void test_vst1q_p64_x2 (poly64_t * ptr, poly64x2x2_t val)
> +{
> +    vst1q_p64_x2 (ptr, val);
> +}
> +
> +/* { dg-final { scan-assembler-times {vst1.64\t\{d[0-9]+-d[0-9]+\}, \[r[0-9]+:64\]\n} 1 } }  */

Re: [PATCH 2/3] [GCC] arm: vst1q_types_x3 ACLE intrinsics

[Richard Earnshaw]

On 10/10/2023 15:04, Ezra.Sitorus@arm.com wrote:
> From: Ezra Sitorus <ezra.sitorus@arm.com>
> 
> This patch is part of a series of patches implementing the _xN variants of the vst1q intrinsic for AArch32.
> This patch adds the _x3 variants of the vst1q intrinsic.

OK, but format lines to <= 70 columns please.

R.
> 
> ACLE documents are at https://developer.arm.com/documentation/ihi0053/latest/
> ISA documents are at https://developer.arm.com/documentation/ddi0487/latest/
> 
> gcc/ChangeLog:
>          * config/arm/arm_neon.h
>          (vst1q_u8_x3, vst1q_u16_x3, vst1q_u32_x3, vst1q_u64_x3): New.
>          (vst1q_s8_x3, vst1q_s16_x3, vst1q_s32_x3, vst1q_s64_x3): New.
>          (vst1q_f16_x3, vst1q_f32_x3): New.
>          (vst1q_p8_x3, vst1q_p16_x3, vst1q_p64_x3): New.
>          (vst1q_bf16_x3): New.
>          * config/arm/arm_neon_builtins.def (vst1q_x3): New entries.
>          * config/arm/neon.md (neon_vst1q_x3<mode>): New.
> 
> gcc/testsuite/ChangeLog:
>          * gcc.target/arm/simd/vst1q_base_xN_1.c: Add new tests.
>          * gcc.target/arm/simd/vst1q_bf16_xN_1.c: Add new tests.
>          * gcc.target/arm/simd/vst1q_fp16_xN_1.c: Add new tests.
>          * gcc.target/arm/simd/vst1q_p64_xN_1.c: Add new tests.
> ---
>   gcc/config/arm/arm_neon.h                     | 114 ++++++++++++++++++
>   gcc/config/arm/arm_neon_builtins.def          |   1 +
>   gcc/config/arm/neon.md                        |  24 ++++
>   .../gcc.target/arm/simd/vst1q_base_xN_1.c     |  60 +++++++++
>   .../gcc.target/arm/simd/vst1q_bf16_xN_1.c     |   6 +
>   .../gcc.target/arm/simd/vst1q_fp16_xN_1.c     |   6 +
>   .../gcc.target/arm/simd/vst1q_p64_xN_1.c      |   6 +
>   7 files changed, 217 insertions(+)
> 
> diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h
> index b8f3fca3060..46ee888410f 100644
> --- a/gcc/config/arm/arm_neon.h
> +++ b/gcc/config/arm/arm_neon.h
> @@ -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)
> diff --git a/gcc/config/arm/arm_neon_builtins.def b/gcc/config/arm/arm_neon_builtins.def
> index 496d267fab8..b1886372a1f 100644
> --- a/gcc/config/arm/arm_neon_builtins.def
> +++ b/gcc/config/arm/arm_neon_builtins.def
> @@ -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,
> diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md
> index 088277ee6ed..b69ed24c018 100644
> --- a/gcc/config/arm/neon.md
> +++ b/gcc/config/arm/neon.md
> @@ -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")
> diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c
> index 232feafade0..ba30fda514f 100644
> --- a/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c
> +++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c
> @@ -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 } }  */
> diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c
> index 2a4579f0aae..2593c31c756 100644
> --- a/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c
> +++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c
> @@ -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
> diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c
> index 61a7e558c48..28e949b557a 100644
> --- a/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c
> +++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c
> @@ -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 } }  */
> diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c
> index 82f3dad293c..7878d936b9f 100644
> --- a/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c
> +++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c
> @@ -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 } }  */

Re: [PATCH 3/3] [GCC] arm: vst1q_types_x4 ACLE intrinsics

[Richard Earnshaw]

On 10/10/2023 15:04, Ezra.Sitorus@arm.com wrote:
> From: Ezra Sitorus <ezra.sitorus@arm.com>
> 
> This patch is part of a series of patches implementing the _xN variants of the vst1q intrinsic for AArch32.
> This patch adds the _x4 variants of the vst1q intrinsic.

OK, but see earlier comments about formatting.

R.

> 
> ACLE documents are at https://developer.arm.com/documentation/ihi0053/latest/
> ISA documents are at https://developer.arm.com/documentation/ddi0487/latest/
> 
> gcc/ChangeLog:
>      * config/arm/arm_neon.h
>      (vst1q_u8_x4, vst1q_u16_x4, vst1q_u32_x4, vst1q_u64_x4): New.
>      (vst1q_s8_x4, vst1q_s16_x4, vst1q_s32_x4, vst1q_s64_x4): New.
>      (vst1q_f16_x4, vst1q_f32_x4): New.
>      (vst1q_p8_x4, vst1q_p16_x4, vst1q_p64_x4): New.
>      (vst1q_bf16_x4): New.
>      * config/arm/arm_neon_builtins.def (vst1q_x4): New entries.
>      * config/arm/neon.md (neon_vst1q_x4<mode>): New.
> 
> gcc/testsuite/ChangeLog:
>      * gcc.target/arm/simd/vst1q_base_xN_1.c: Add new tests.
>      * gcc.target/arm/simd/vst1q_bf16_xN_1.c: Add new tests.
>      * gcc.target/arm/simd/vst1q_fp16_xN_1.c: Add new tests.
>      * gcc.target/arm/simd/vst1q_p64_xN_1.c: Add new tests.
> ---
>   gcc/config/arm/arm_neon.h                     | 114 ++++++++++++++++++
>   gcc/config/arm/arm_neon_builtins.def          |   1 +
>   gcc/config/arm/neon.md                        |  26 ++++
>   .../gcc.target/arm/simd/vst1q_base_xN_1.c     |  59 +++++++++
>   .../gcc.target/arm/simd/vst1q_bf16_xN_1.c     |   8 +-
>   .../gcc.target/arm/simd/vst1q_fp16_xN_1.c     |   6 +
>   .../gcc.target/arm/simd/vst1q_p64_xN_1.c      |   6 +
>   7 files changed, 219 insertions(+), 1 deletion(-)
> 
> diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h
> index 46ee888410f..df3e23b6e95 100644
> --- a/gcc/config/arm/arm_neon.h
> +++ b/gcc/config/arm/arm_neon.h
> @@ -11391,6 +11391,38 @@ vst1q_s64_x3 (int64_t * __a, int64x2x3_t __b)
>     __builtin_neon_vst1q_x3v2di ((__builtin_neon_di *) __a, __bu.__o);
>   }
>   
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_s8_x4 (int8_t * __a, int8x16x4_t __b)
> +{
> +  union { int8x16x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x4v16qi ((__builtin_neon_qi *) __a, __bu.__o);
> +}
> +
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_s16_x4 (int16_t * __a, int16x8x4_t __b)
> +{
> +  union { int16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x4v8hi ((__builtin_neon_hi *) __a, __bu.__o);
> +}
> +
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_s32_x4 (int32_t * __a, int32x4x4_t __b)
> +{
> +  union { int32x4x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x4v4si ((__builtin_neon_si *) __a, __bu.__o);
> +}
> +
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_s64_x4 (int64_t * __a, int64x2x4_t __b)
> +{
> +  union { int64x2x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x4v2di ((__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)
> @@ -11736,6 +11768,14 @@ vst1q_p64_x3 (poly64_t * __a, poly64x2x3_t __b)
>     __builtin_neon_vst1q_x3v2di ((__builtin_neon_di *) __a, __bu.__o);
>   }
>   
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_p64_x4 (poly64_t * __a, poly64x2x4_t __b)
> +{
> +  union { poly64x2x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x4v2di ((__builtin_neon_di *) __a, __bu.__o);
> +}
> +
>   #pragma GCC pop_options
>   __extension__ extern __inline void
>   __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> @@ -11817,6 +11857,24 @@ vst1q_f32_x3 (float32_t * __a, float32x4x3_t __b)
>     __builtin_neon_vst1q_x3v4sf (__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_x4 (float16_t * __a, float16x8x4_t __b)
> +{
> +  union { float16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x4v8hf (__a, __bu.__o);
> +}
> +#endif
> +
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_f32_x4 (float32_t * __a, float32x4x4_t __b)
> +{
> +  union { float32x4x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x4v4sf (__a, __bu.__o);
> +}
> +
>   __extension__ extern __inline void
>   __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
>   vst1q_u8 (uint8_t * __a, uint8x16_t __b)
> @@ -11909,6 +11967,38 @@ vst1q_u64_x3 (uint64_t * __a, uint64x2x3_t __b)
>     __builtin_neon_vst1q_x3v2di ((__builtin_neon_di *) __a, __bu.__o);
>   }
>   
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_u8_x4 (uint8_t * __a, uint8x16x4_t __b)
> +{
> +  union { uint8x16x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x4v16qi ((__builtin_neon_qi *) __a, __bu.__o);
> +}
> +
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_u16_x4 (uint16_t * __a, uint16x8x4_t __b)
> +{
> +  union { uint16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x4v8hi ((__builtin_neon_hi *) __a, __bu.__o);
> +}
> +
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_u32_x4 (uint32_t * __a, uint32x4x4_t __b)
> +{
> +  union { uint32x4x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x4v4si ((__builtin_neon_si *) __a, __bu.__o);
> +}
> +
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_u64_x4 (uint64_t * __a, uint64x2x4_t __b)
> +{
> +  union { uint64x2x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x4v2di ((__builtin_neon_di *) __a, __bu.__o);
> +}
> +
>   __extension__ extern __inline void
>   __attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
>   vst1q_p8 (poly8_t * __a, poly8x16_t __b)
> @@ -11955,6 +12045,22 @@ vst1q_p16_x3 (poly16_t * __a, poly16x8x3_t __b)
>     __builtin_neon_vst1q_x3v8hi ((__builtin_neon_hi *) __a, __bu.__o);
>   }
>   
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_p8_x4 (poly8_t * __a, poly8x16x4_t __b)
> +{
> +  union { poly8x16x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x4v16qi ((__builtin_neon_qi *) __a, __bu.__o);
> +}
> +
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_p16_x4 (poly16_t * __a, poly16x8x4_t __b)
> +{
> +  union { poly16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x4v8hi ((__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)
> @@ -20647,6 +20753,14 @@ vst1q_bf16_x3 (bfloat16_t * __a, bfloat16x8x3_t __b)
>     __builtin_neon_vst1q_x3v8bf (__a, __bu.__o);
>   }
>   
> +__extension__ extern __inline void
> +__attribute__  ((__always_inline__, __gnu_inline__, __artificial__))
> +vst1q_bf16_x4 (bfloat16_t * __a, bfloat16x8x4_t __b)
> +{
> +  union { bfloat16x8x4_t __i; __builtin_neon_xi __o; } __bu = { __b };
> +  __builtin_neon_vst1q_x4v8bf (__a, __bu.__o);
> +}
> +
>   __extension__ extern __inline void
>   __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>   vst2_bf16 (bfloat16_t * __ptr, bfloat16x4x2_t __val)
> diff --git a/gcc/config/arm/arm_neon_builtins.def b/gcc/config/arm/arm_neon_builtins.def
> index b1886372a1f..12f78800588 100644
> --- a/gcc/config/arm/arm_neon_builtins.def
> +++ b/gcc/config/arm/arm_neon_builtins.def
> @@ -313,6 +313,7 @@ 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)
> +VAR7 (STORE1, vst1q_x4, v16qi, v8hi, v4si, v2di, v8hf, v4sf, v8bf)
>   VAR14 (STORE1, vst1,
>           v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf, v2di,
>           v4bf, v8bf)
> diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md
> index b69ed24c018..2fa4f85b820 100644
> --- a/gcc/config/arm/neon.md
> +++ b/gcc/config/arm/neon.md
> @@ -5169,6 +5169,32 @@ if (BYTES_BIG_ENDIAN)
>     [(set_attr "type" "neon_store1_3reg<q>")]
>   )
>   
> +(define_insn "neon_vst1q_x4<mode>"
> +  [(set (match_operand:XI 0 "neon_struct_operand" "=Um")
> +        (unspec:XI [(match_operand:XI 1 "s_register_operand" "w")
> +                    (unspec:VDQX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
> +                   UNSPEC_VST1))]
> +  "TARGET_NEON"
> +{
> +  int regno = REGNO (operands[1]);
> +  rtx ops[5];
> +  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);
> +  ops[4] = gen_rtx_REG (DImode, regno + 6);
> +  output_asm_insn ("vst1.<V_sz_elem>\t{%P1, %P2, %P3, %P4}, %A0", ops);
> +
> +  ops[1] = gen_rtx_REG (DImode, regno + 8);
> +  ops[2] = gen_rtx_REG (DImode, regno + 10);
> +  ops[3] = gen_rtx_REG (DImode, regno + 12);
> +  ops[4] = gen_rtx_REG (DImode, regno + 14);
> +  output_asm_insn ("vst1.<V_sz_elem>\t{%P1, %P2, %P3, %P4}, %A0", ops);
> +  return "";
> +}
> +  [(set_attr "type" "neon_store1_4reg<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")
> diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c
> index ba30fda514f..461aae3af62 100644
> --- a/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c
> +++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_base_xN_1.c
> @@ -116,15 +116,74 @@ void test_vst1q_p16_x3 (poly16_t * ptr, poly16x8x3_t val)
>       vst1q_p16_x3 (ptr, val);
>   }
>   
> +void test_vst1q_u8_x4 (uint8_t * ptr, uint8x16x4_t val)
> +{
> +    vst1q_u8_x4 (ptr, val);
> +}
> +
> +void test_vst1q_u16_x4 (uint16_t * ptr, uint16x8x4_t val)
> +{
> +    vst1q_u16_x4 (ptr, val);
> +}
> +
> +void test_vst1q_u32_x4 (uint32_t * ptr, uint32x4x4_t val)
> +{
> +    vst1q_u32_x4 (ptr, val);
> +}
> +
> +void test_vst1q_u64_x4 (uint64_t * ptr, uint64x2x4_t val)
> +{
> +    vst1q_u64_x4 (ptr, val);
> +}
> +
> +void test_vst1q_s8_x4 (int8_t * ptr, int8x16x4_t val)
> +{
> +    vst1q_s8_x4 (ptr, val);
> +}
> +
> +void test_vst1q_s16_x4 (int16_t * ptr, int16x8x4_t val)
> +{
> +    vst1q_s16_x4 (ptr, val);
> +}
> +
> +void test_vst1q_s32_x4 (int32_t * ptr, int32x4x4_t val)
> +{
> +    vst1q_s32_x4 (ptr, val);
> +}
> +
> +void test_vst1q_s64_x4 (int64_t * ptr, int64x2x4_t val)
> +{
> +    vst1q_s64_x4 (ptr, val);
> +}
> +
> +void test_vst1q_f32_x4 (float32_t * ptr, float32x4x4_t val)
> +{
> +    vst1q_f32_x4 (ptr, val);
> +}
> +
> +void test_vst1q_p8_x4 (poly8_t * ptr, poly8x16x4_t val)
> +{
> +    vst1q_p8_x4 (ptr, val);
> +}
> +
> +void test_vst1q_p16_x4 (poly16_t * ptr, poly16x8x4_t val)
> +{
> +    vst1q_p16_x4 (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 {vst1.8\t\{d[0-9]+, 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 {vst1.16\t\{d[0-9]+, 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 {vst1.32\t\{d[0-9]+, 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 } }  */
> +/* { dg-final { scan-assembler-times {vst1.64\t\{d[0-9]+, d[0-9]+, d[0-9]+, d[0-9]+\}, \[r[0-9]+:64\]\n} 4 } }  */
> diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c
> index 2593c31c756..84fa8509db8 100644
> --- a/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c
> +++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_bf16_xN_1.c
> @@ -15,5 +15,11 @@ void test_vst1q_bf16_x3 (bfloat16_t * ptr, bfloat16x8x3_t val)
>       vst1q_bf16_x3 (ptr, val);
>   }
>   
> +void test_vst1q_bf16_x4 (bfloat16_t * ptr, bfloat16x8x4_t val)
> +{
> +    vst1q_bf16_x4 (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
> +/* { dg-final { scan-assembler-times {vst1.16\t\{d[0-9]+, d[0-9]+, d[0-9]+\}, \[r[0-9]+\]\n} 2 } }  */
> +/* { dg-final { scan-assembler-times {vst1.16\t\{d[0-9]+, d[0-9]+, d[0-9]+, d[0-9]+\}, \[r[0-9]+\]\n} 2 } }  */
> \ No newline at end of file
> diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c
> index 28e949b557a..5b13edf9998 100644
> --- a/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c
> +++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_fp16_xN_1.c
> @@ -15,5 +15,11 @@ void test_vst1q_f16_x3 (float16_t * ptr, float16x8x3_t val)
>       vst1q_f16_x3 (ptr, val);
>   }
>   
> +void test_vst1q_f16_x4 (float16_t * ptr, float16x8x4_t val)
> +{
> +    vst1q_f16_x4 (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 } }  */
> +/* { dg-final { scan-assembler-times {vst1.16\t\{d[0-9]+, d[0-9]+, d[0-9]+, d[0-9]+\}, \[r[0-9]+\]\n} 2 } }  */
> diff --git a/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c b/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c
> index 7878d936b9f..f49917d5ec8 100644
> --- a/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c
> +++ b/gcc/testsuite/gcc.target/arm/simd/vst1q_p64_xN_1.c
> @@ -15,5 +15,11 @@ void test_vst1q_p64_x3 (poly64_t * ptr, poly64x2x3_t val)
>       vst1q_p64_x3 (ptr, val);
>   }
>   
> +void test_vst1q_p64_x4 (poly64_t * ptr, poly64x2x4_t val)
> +{
> +    vst1q_p64_x4 (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 } }  */
> +/* { dg-final { scan-assembler-times {vst1.64\t\{d[0-9]+, d[0-9]+, d[0-9]+, d[0-9]+\}, \[r[0-9]+:64\]\n} 2 } }  */