aarch64: Fold vget_low_* intrinsics to BIT_FIELD_REF [PR102171]

This patch folds vget_low_* intrinsics to BIT_FILED_REF to open up more
optimization opportunities for gimple optimizers.

While we are here, we also remove the vget_low_* definitions from arm_neon.h and
use the new intrinsics framework.

	PR target/102171

gcc/ChangeLog:

	* config/aarch64/aarch64-builtins.cc (AARCH64_SIMD_VGET_LOW_BUILTINS):
	New macro to create definitions for all vget_low intrinsics.
	(VGET_LOW_BUILTIN): Likewise.
	(enum aarch64_builtins): Add vget_low function codes.
	(aarch64_general_fold_builtin): Fold vget_low calls.
	* config/aarch64/aarch64-simd-builtins.def: Delete vget_low builtins.
	* config/aarch64/aarch64-simd.md (aarch64_get_low<mode>): Delete.
	(aarch64_vget_lo_halfv8bf): Likewise.
	* config/aarch64/arm_neon.h (__attribute__): Delete.
	(vget_low_f16): Likewise.
	(vget_low_f32): Likewise.
	(vget_low_f64): Likewise.
	(vget_low_p8): Likewise.
	(vget_low_p16): Likewise.
	(vget_low_p64): Likewise.
	(vget_low_s8): Likewise.
	(vget_low_s16): Likewise.
	(vget_low_s32): Likewise.
	(vget_low_s64): Likewise.
	(vget_low_u8): Likewise.
	(vget_low_u16): Likewise.
	(vget_low_u32): Likewise.
	(vget_low_u64): Likewise.
	(vget_low_bf16): Likewise.

gcc/testsuite/ChangeLog:

	* gcc.target/aarch64/pr113573.c: Replace __builtin_aarch64_get_lowv8hi
	with vget_low_s16.
	* gcc.target/aarch64/vget_low_2.c: New test.
	* gcc.target/aarch64/vget_low_2_be.c: New test.

Signed-off-by: Pengxuan Zheng <quic_pzheng@quicinc.com>

4 files changed, 62 insertions, 131 deletions

diff --git a/gcc/config/aarch64/aarch64-builtins.cc b/gcc/config/aarch64/aarch64-builtins.cc
index 75d21de..11b8880 100644
--- a/gcc/config/aarch64/aarch64-builtins.cc
+++ b/gcc/config/aarch64/aarch64-builtins.cc
@@ -658,6 +658,23 @@ static aarch64_simd_builtin_datum aarch64_simd_builtin_data[] = {
   VREINTERPRET_BUILTINS \
   VREINTERPRETQ_BUILTINS
 
+#define AARCH64_SIMD_VGET_LOW_BUILTINS \
+  VGET_LOW_BUILTIN(f16) \
+  VGET_LOW_BUILTIN(f32) \
+  VGET_LOW_BUILTIN(f64) \
+  VGET_LOW_BUILTIN(p8) \
+  VGET_LOW_BUILTIN(p16) \
+  VGET_LOW_BUILTIN(p64) \
+  VGET_LOW_BUILTIN(s8) \
+  VGET_LOW_BUILTIN(s16) \
+  VGET_LOW_BUILTIN(s32) \
+  VGET_LOW_BUILTIN(s64) \
+  VGET_LOW_BUILTIN(u8) \
+  VGET_LOW_BUILTIN(u16) \
+  VGET_LOW_BUILTIN(u32) \
+  VGET_LOW_BUILTIN(u64) \
+  VGET_LOW_BUILTIN(bf16)
+
 typedef struct
 {
   const char *name;
@@ -697,6 +714,9 @@ typedef struct
 #define VREINTERPRET_BUILTIN(A, B, L) \
   AARCH64_SIMD_BUILTIN_VREINTERPRET##L##_##A##_##B,
 
+#define VGET_LOW_BUILTIN(A) \
+  AARCH64_SIMD_BUILTIN_VGET_LOW_##A,
+
 #undef VAR1
 #define VAR1(T, N, MAP, FLAG, A) \
   AARCH64_SIMD_BUILTIN_##T##_##N##A,
@@ -732,6 +752,7 @@ enum aarch64_builtins
   AARCH64_CRC32_BUILTIN_MAX,
   /* SIMD intrinsic builtins.  */
   AARCH64_SIMD_VREINTERPRET_BUILTINS
+  AARCH64_SIMD_VGET_LOW_BUILTINS
   /* ARMv8.3-A Pointer Authentication Builtins.  */
   AARCH64_PAUTH_BUILTIN_AUTIA1716,
   AARCH64_PAUTH_BUILTIN_PACIA1716,
@@ -823,8 +844,37 @@ static aarch64_fcmla_laneq_builtin_datum aarch64_fcmla_lane_builtin_data[] = {
      && SIMD_INTR_QUAL(A) == SIMD_INTR_QUAL(B) \
   },
 
+#undef VGET_LOW_BUILTIN
+#define VGET_LOW_BUILTIN(A) \
+  {"vget_low_" #A, \
+   AARCH64_SIMD_BUILTIN_VGET_LOW_##A, \
+   2, \
+   { SIMD_INTR_MODE(A, d), SIMD_INTR_MODE(A, q) }, \
+   { SIMD_INTR_QUAL(A), SIMD_INTR_QUAL(A) }, \
+   FLAG_AUTO_FP, \
+   false \
+  },
+
+#define AARCH64_SIMD_VGET_LOW_BUILTINS \
+  VGET_LOW_BUILTIN(f16) \
+  VGET_LOW_BUILTIN(f32) \
+  VGET_LOW_BUILTIN(f64) \
+  VGET_LOW_BUILTIN(p8) \
+  VGET_LOW_BUILTIN(p16) \
+  VGET_LOW_BUILTIN(p64) \
+  VGET_LOW_BUILTIN(s8) \
+  VGET_LOW_BUILTIN(s16) \
+  VGET_LOW_BUILTIN(s32) \
+  VGET_LOW_BUILTIN(s64) \
+  VGET_LOW_BUILTIN(u8) \
+  VGET_LOW_BUILTIN(u16) \
+  VGET_LOW_BUILTIN(u32) \
+  VGET_LOW_BUILTIN(u64) \
+  VGET_LOW_BUILTIN(bf16)
+
 static const aarch64_simd_intrinsic_datum aarch64_simd_intrinsic_data[] = {
   AARCH64_SIMD_VREINTERPRET_BUILTINS
+  AARCH64_SIMD_VGET_LOW_BUILTINS
 };
 
 
@@ -3216,6 +3266,9 @@ aarch64_fold_builtin_lane_check (tree arg0, tree arg1, tree arg2)
 #define VREINTERPRET_BUILTIN(A, B, L) \
   case AARCH64_SIMD_BUILTIN_VREINTERPRET##L##_##A##_##B:
 
+#undef VGET_LOW_BUILTIN
+#define VGET_LOW_BUILTIN(A) \
+  case AARCH64_SIMD_BUILTIN_VGET_LOW_##A:
 
 /* Try to fold a call to the built-in function with subcode FCODE.  The
    function is passed the N_ARGS arguments in ARGS and it returns a value
@@ -3235,6 +3288,13 @@ aarch64_general_fold_builtin (unsigned int fcode, tree type,
 	return fold_build1 (FLOAT_EXPR, type, args[0]);
       AARCH64_SIMD_VREINTERPRET_BUILTINS
 	return fold_build1 (VIEW_CONVERT_EXPR, type, args[0]);
+      AARCH64_SIMD_VGET_LOW_BUILTINS
+	{
+	  auto pos = BYTES_BIG_ENDIAN ? 64 : 0;
+
+	  return fold_build3 (BIT_FIELD_REF, type, args[0], bitsize_int (64),
+			      bitsize_int (pos));
+	}
       case AARCH64_SIMD_BUILTIN_LANE_CHECK:
 	gcc_assert (n_args == 3);
 	if (aarch64_fold_builtin_lane_check (args[0], args[1], args[2]))
diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def
index da16f60..a9f0558 100644
--- a/gcc/config/aarch64/aarch64-simd-builtins.def
+++ b/gcc/config/aarch64/aarch64-simd-builtins.def
@@ -65,8 +65,6 @@
   BUILTIN_VS (UNOP, ctz, 2, NONE)
   BUILTIN_VB (UNOP, popcount, 2, NONE)
 
-  /* Implemented by aarch64_get_low<mode>.  */
-  BUILTIN_VQMOV (UNOP, get_low, 0, AUTO_FP)
   /* Implemented by aarch64_get_high<mode>.  */
   BUILTIN_VQMOV (UNOP, get_high, 0, AUTO_FP)
 
@@ -960,8 +958,7 @@
   VAR1 (QUADOP_LANE, bfmlalb_lane_q, 0, FP, v4sf)
   VAR1 (QUADOP_LANE, bfmlalt_lane_q, 0, FP, v4sf)
 
-  /* Implemented by aarch64_vget_lo/hi_halfv8bf.  */
-  VAR1 (UNOP, vget_lo_half, 0, AUTO_FP, v8bf)
+  /* Implemented by aarch64_vget_hi_halfv8bf.  */
   VAR1 (UNOP, vget_hi_half, 0, AUTO_FP, v8bf)
 
   /* Implemented by aarch64_simd_<sur>mmlav16qi.  */
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index 16b7445d..875ea52 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -288,17 +288,6 @@
   }
 )
 
-(define_expand "aarch64_get_low<mode>"
-  [(match_operand:<VHALF> 0 "register_operand")
-   (match_operand:VQMOV 1 "register_operand")]
-  "TARGET_FLOAT"
-  {
-    rtx lo = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, false);
-    emit_insn (gen_aarch64_get_half<mode> (operands[0], operands[1], lo));
-    DONE;
-  }
-)
-
 (define_expand "aarch64_get_high<mode>"
   [(match_operand:<VHALF> 0 "register_operand")
    (match_operand:VQMOV 1 "register_operand")]
@@ -9774,17 +9763,7 @@
   [(set_attr "type" "neon_dot<VDQSF:q>")]
 )
 
-;; vget_low/high_bf16
-(define_expand "aarch64_vget_lo_halfv8bf"
-  [(match_operand:V4BF 0 "register_operand")
-   (match_operand:V8BF 1 "register_operand")]
-  "TARGET_BF16_SIMD"
-{
-  rtx p = aarch64_simd_vect_par_cnst_half (V8BFmode, 8, false);
-  emit_insn (gen_aarch64_get_halfv8bf (operands[0], operands[1], p));
-  DONE;
-})
-
+;; vget_high_bf16
 (define_expand "aarch64_vget_hi_halfv8bf"
   [(match_operand:V4BF 0 "register_operand")
    (match_operand:V8BF 1 "register_operand")]
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 0ee325d..92c2c53 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -3029,104 +3029,6 @@ vsetq_lane_u64 (uint64_t __elem, uint64x2_t __vec, const int __index)
 
 __extension__ extern __inline float16x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-vget_low_f16 (float16x8_t __a)
-{
-  return __builtin_aarch64_get_lowv8hf (__a);
-}
-
-__extension__ extern __inline float32x2_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-vget_low_f32 (float32x4_t __a)
-{
-  return __builtin_aarch64_get_lowv4sf (__a);
-}
-
-__extension__ extern __inline float64x1_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-vget_low_f64 (float64x2_t __a)
-{
-  return (float64x1_t) {__builtin_aarch64_get_lowv2df (__a)};
-}
-
-__extension__ extern __inline poly8x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-vget_low_p8 (poly8x16_t __a)
-{
-  return (poly8x8_t) __builtin_aarch64_get_lowv16qi ((int8x16_t) __a);
-}
-
-__extension__ extern __inline poly16x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-vget_low_p16 (poly16x8_t __a)
-{
-  return (poly16x4_t) __builtin_aarch64_get_lowv8hi ((int16x8_t) __a);
-}
-
-__extension__ extern __inline poly64x1_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-vget_low_p64 (poly64x2_t __a)
-{
-  return (poly64x1_t) __builtin_aarch64_get_lowv2di ((int64x2_t) __a);
-}
-
-__extension__ extern __inline int8x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-vget_low_s8 (int8x16_t __a)
-{
-  return  __builtin_aarch64_get_lowv16qi (__a);
-}
-
-__extension__ extern __inline int16x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-vget_low_s16 (int16x8_t __a)
-{
-  return  __builtin_aarch64_get_lowv8hi (__a);
-}
-
-__extension__ extern __inline int32x2_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-vget_low_s32 (int32x4_t __a)
-{
-  return  __builtin_aarch64_get_lowv4si (__a);
-}
-
-__extension__ extern __inline int64x1_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-vget_low_s64 (int64x2_t __a)
-{
-  return  (int64x1_t) {__builtin_aarch64_get_lowv2di (__a)};
-}
-
-__extension__ extern __inline uint8x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-vget_low_u8 (uint8x16_t __a)
-{
-  return (uint8x8_t) __builtin_aarch64_get_lowv16qi ((int8x16_t) __a);
-}
-
-__extension__ extern __inline uint16x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-vget_low_u16 (uint16x8_t __a)
-{
-  return (uint16x4_t) __builtin_aarch64_get_lowv8hi ((int16x8_t) __a);
-}
-
-__extension__ extern __inline uint32x2_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-vget_low_u32 (uint32x4_t __a)
-{
-  return (uint32x2_t) __builtin_aarch64_get_lowv4si ((int32x4_t) __a);
-}
-
-__extension__ extern __inline uint64x1_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-vget_low_u64 (uint64x2_t __a)
-{
-  return (uint64x1_t) {__builtin_aarch64_get_lowv2di ((int64x2_t) __a)};
-}
-
-__extension__ extern __inline float16x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vget_high_f16 (float16x8_t __a)
 {
   return __builtin_aarch64_get_highv8hf (__a);
@@ -28481,13 +28383,6 @@ vbfmlaltq_laneq_f32 (float32x4_t __r, bfloat16x8_t __a, bfloat16x8_t __b,
 
 __extension__ extern __inline bfloat16x4_t
 __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-vget_low_bf16 (bfloat16x8_t __a)
-{
-  return __builtin_aarch64_vget_lo_halfv8bf (__a);
-}
-
-__extension__ extern __inline bfloat16x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
 vget_high_bf16 (bfloat16x8_t __a)
 {
   return __builtin_aarch64_vget_hi_halfv8bf (__a);