This patch adds the ARMv8.6 ACLE BFloat16 load intrinsics vld<n>{q}_bf16
as part of the BFloat16 extension.
(https://developer.arm.com/architectures/instruction-sets/simd-isas/neon/intrinsics)
The intrinsics are declared in arm_neon.h .
A new test is added to check assembler output.
This patch depends on the Arm back-end patche.
(https://gcc.gnu.org/ml/gcc-patches/2019-12/msg01448.html)
Tested for regression on arm-none-eabi and armeb-none-eabi. I don't have
commit rights, so if this is ok can someone please commit it for me?
gcc/ChangeLog:
2019-11-14 Delia Burduv <delia.bur...@arm.com>
* config/arm/arm_neon.h (bfloat16_t): New typedef.
(bfloat16x4x2_t): New typedef.
(bfloat16x8x2_t): New typedef.
(bfloat16x4x3_t): New typedef.
(bfloat16x8x3_t): New typedef.
(bfloat16x4x4_t): New typedef.
(bfloat16x8x4_t): New typedef.
(vld2_bf16): New.
(vld2q_bf16): New.
(vld3_bf16): New.
(vld3q_bf16): New.
(vld4_bf16): New.
(vld4q_bf16): New.
(vld2_dup_bf16): New.
(vld2q_dup_bf16): New.
(vld3_dup_bf16): New.
(vld3q_dup_bf16): New.
(vld4_dup_bf16): New.
(vld4q_dup_bf16): New.
* config/arm/arm-builtins.c (E_V2BFmode): New mode.
(VAR13): New.
(arm_simd_types[Bfloat16x2_t]):New type.
* config/arm/arm-modes.def (V2BF): New mode.
* config/arm/arm-simd-builtin-types.def
(Bfloat16x2_t): New entry.
* config/arm/arm_neon_builtins.def
(vld2): Changed to VAR13 and added v4bf, v8bf
(vld2_dup): Changed to VAR8 and added v4bf, v8bf
(vld3): Changed to VAR13 and added v4bf, v8bf
(vld3_dup): Changed to VAR8 and added v4bf, v8bf
(vld4): Changed to VAR13 and added v4bf, v8bf
(vld4_dup): Changed to VAR8 and added v4bf, v8bf
* config/arm/iterators.md (VDXBF): New iterator.
(VQ2BF): New iterator.
(V_elem): Added V4BF, V8BF.
(V_sz_elem): Added V4BF, V8BF.
(V_mode_nunits): Added V4BF, V8BF.
(q): Added V4BF, V8BF.
*config/arm/neon.md (vld2): Used new iterators.
(vld2_dup<mode>): Used new iterators.
(vld2_dupv8bf): New.
(vst3): Used new iterators.
(vst3qa): Used new iterators.
(vst3qb): Used new iterators.
(vld3_dup<mode>): Used new iterators.
(vld3_dupv8bf): New.
(vst4): Used new iterators.
(vst4qa): Used new iterators.
(vst4qb): Used new iterators.
(vld4_dup<mode>): Used new iterators.
(vld4_dupv8bf): New.
gcc/testsuite/ChangeLog:
2019-11-14 Delia Burduv <delia.bur...@arm.com>
* gcc.target/arm/simd/bf16_vldn_1.c: New test.
diff --git a/gcc/config/arm/arm-builtins.c b/gcc/config/arm/arm-builtins.c
index df09a6bb1fce5f9216337d71cba51a890fd57baf..551d76a44fadc58a35a6155486ec1fb16c959da0 100644
--- a/gcc/config/arm/arm-builtins.c
+++ b/gcc/config/arm/arm-builtins.c
@@ -318,6 +318,7 @@ arm_set_sat_qualifiers[SIMD_MAX_BUILTIN_ARGS]
#define v4bf_UP E_V4BFmode
#define v2si_UP E_V2SImode
#define v2sf_UP E_V2SFmode
+#define v2bf_UP E_V2BFmode
#define di_UP E_DImode
#define v16qi_UP E_V16QImode
#define v8hi_UP E_V8HImode
@@ -381,6 +382,9 @@ typedef struct {
#define VAR12(T, N, A, B, C, D, E, F, G, H, I, J, K, L) \
VAR11 (T, N, A, B, C, D, E, F, G, H, I, J, K) \
VAR1 (T, N, L)
+#define VAR13(T, N, A, B, C, D, E, F, G, H, I, J, K, L, M) \
+ VAR12 (T, N, A, B, C, D, E, F, G, H, I, J, K, L) \
+ VAR1 (T, N, M)
/* The builtin data can be found in arm_neon_builtins.def, arm_vfp_builtins.def
and arm_acle_builtins.def. The entries in arm_neon_builtins.def require
@@ -1013,6 +1017,7 @@ arm_init_simd_builtin_types (void)
arm_simd_types[Float32x4_t].eltype = float_type_node;
/* Init Bfloat vector types with underlying __bf16 scalar type. */
+ arm_simd_types[Bfloat16x2_t].eltype = arm_bf16_type_node;
arm_simd_types[Bfloat16x4_t].eltype = arm_bf16_type_node;
arm_simd_types[Bfloat16x8_t].eltype = arm_bf16_type_node;
diff --git a/gcc/config/arm/arm-modes.def b/gcc/config/arm/arm-modes.def
index 80c3c1a6eb258d116b07ad71fafafc9befb76e8b..9533d177059d98fa2a9e9d1d6321f3d92dad7592 100644
--- a/gcc/config/arm/arm-modes.def
+++ b/gcc/config/arm/arm-modes.def
@@ -80,6 +80,7 @@ VECTOR_MODE (FLOAT, HF, 2); /* V2HF */
FLOAT_MODE (BF, 2, 0);
ADJUST_FLOAT_FORMAT (BF, &arm_bfloat_half_format);
+VECTOR_MODE (FLOAT, BF, 2); /* V2BF. */
VECTOR_MODE (FLOAT, BF, 4); /* V4BF. */
VECTOR_MODE (FLOAT, BF, 8); /* V8BF. */
diff --git a/gcc/config/arm/arm-simd-builtin-types.def b/gcc/config/arm/arm-simd-builtin-types.def
index ee240f85c5618417fff039ec43b81641b187c126..f52f679156d5041ab109909393dc37fda33a390d 100644
--- a/gcc/config/arm/arm-simd-builtin-types.def
+++ b/gcc/config/arm/arm-simd-builtin-types.def
@@ -48,5 +48,6 @@
ENTRY (Float16x8_t, V8HF, none, 128, float16, 19)
ENTRY (Float32x4_t, V4SF, none, 128, float32, 19)
+ ENTRY (Bfloat16x2_t, V2BF, none, 32, bfloat16, 20)
ENTRY (Bfloat16x4_t, V4BF, none, 64, bfloat16, 20)
ENTRY (Bfloat16x8_t, V8BF, none, 128, bfloat16, 20)
diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h
index 71e7568e4315a9354062dee5442ca4af9d9660a9..c47f3cdd2d51066067d2ef341cc12a6db4b6f785 100644
--- a/gcc/config/arm/arm_neon.h
+++ b/gcc/config/arm/arm_neon.h
@@ -91,6 +91,145 @@ typedef float float32_t;
#ifdef __ARM_FEATURE_BF16_VECTOR_ARITHMETIC
typedef __simd128_bfloat16_t bfloat16x8_t;
typedef __simd64_bfloat16_t bfloat16x4_t;
+
+typedef struct bfloat16x4x2_t
+{
+ bfloat16x4_t val[2];
+} bfloat16x4x2_t;
+
+typedef struct bfloat16x8x2_t
+{
+ bfloat16x8_t val[2];
+} bfloat16x8x2_t;
+
+typedef struct bfloat16x4x3_t
+{
+ bfloat16x4_t val[3];
+} bfloat16x4x3_t;
+
+typedef struct bfloat16x8x3_t
+{
+ bfloat16x8_t val[3];
+} bfloat16x8x3_t;
+
+typedef struct bfloat16x4x4_t
+{
+ bfloat16x4_t val[4];
+} bfloat16x4x4_t;
+
+typedef struct bfloat16x8x4_t
+{
+ bfloat16x8_t val[4];
+} bfloat16x8x4_t;
+
+__extension__ extern __inline bfloat16x4x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld2_bf16 (bfloat16_t const * __ptr)
+{
+ union { bfloat16x4x2_t __i; __builtin_neon_ti __o; } __rv;
+ __rv.__o = __builtin_neon_vld2v4bf ((const __builtin_neon_hi *) __ptr);
+ return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x8x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld2q_bf16 (const bfloat16_t * __ptr)
+{
+ union { bfloat16x8x2_t __i; __builtin_neon_oi __o; } __rv;
+ __rv.__o = __builtin_neon_vld2v8bf ((const __builtin_neon_hi *) __ptr);
+ return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x4x3_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld3_bf16 (const bfloat16_t * __ptr)
+{
+ union { bfloat16x4x3_t __i; __builtin_neon_ei __o; } __rv;
+ __rv.__o = __builtin_neon_vld3v4bf ((const __builtin_neon_hi *) __ptr);
+ return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x8x3_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld3q_bf16 (const bfloat16_t * __ptr)
+{
+ union { bfloat16x8x3_t __i; __builtin_neon_ci __o; } __rv;
+ __rv.__o = __builtin_neon_vld3v8bf ((const __builtin_neon_hi *) __ptr);
+ return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x4x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld4_bf16 (const bfloat16_t * __ptr)
+{
+ union { bfloat16x4x4_t __i; __builtin_neon_oi __o; } __rv;
+ __rv.__o = __builtin_neon_vld4v4bf ((const __builtin_neon_hi *) __ptr);
+ return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x8x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld4q_bf16 (const bfloat16_t * __ptr)
+{
+ union { bfloat16x8x4_t __i; __builtin_neon_xi __o; } __rv;
+ __rv.__o = __builtin_neon_vld4v8bf ((const __builtin_neon_hi *) __ptr);
+ return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x4x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld2_dup_bf16 (const bfloat16_t * __ptr)
+{
+ union { bfloat16x4x2_t __i; __builtin_neon_ti __o; } __rv;
+ __rv.__o = __builtin_neon_vld2_dupv4bf ((const __builtin_neon_hi *) __ptr);
+ return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x8x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld2q_dup_bf16 (const bfloat16_t * __ptr)
+{
+ union { bfloat16x8x2_t __i; __builtin_neon_oi __o; } __rv;
+ __rv.__o = __builtin_neon_vld2_dupv8bf ((const __builtin_neon_hi *) __ptr);
+ return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x4x3_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld3_dup_bf16 (const bfloat16_t * __ptr)
+{
+ union { bfloat16x4x3_t __i; __builtin_neon_ei __o; } __rv;
+ __rv.__o = __builtin_neon_vld3_dupv4bf ((const __builtin_neon_hi *) __ptr);
+ return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x8x3_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld3q_dup_bf16 (const bfloat16_t * __ptr)
+{
+ union { bfloat16x8x3_t __i; __builtin_neon_ci __o; } __rv;
+ __rv.__o = __builtin_neon_vld3_dupv8bf ((const __builtin_neon_hi *) __ptr);
+ return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x4x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld4_dup_bf16 (const bfloat16_t * __ptr)
+{
+ union { bfloat16x4x4_t __i; __builtin_neon_oi __o; } __rv;
+ __rv.__o = __builtin_neon_vld4_dupv4bf ((const __builtin_neon_hi *) __ptr);
+ return __rv.__i;
+}
+
+__extension__ extern __inline bfloat16x8x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vld4q_dup_bf16 (const bfloat16_t * __ptr)
+{
+ union { bfloat16x8x4_t __i; __builtin_neon_xi __o; } __rv;
+ __rv.__o = __builtin_neon_vld4_dupv8bf ((const __builtin_neon_hi *) __ptr);
+ return __rv.__i;
+}
+
#endif
#pragma GCC pop_options
#pragma GCC pop_options
diff --git a/gcc/config/arm/arm_neon_builtins.def b/gcc/config/arm/arm_neon_builtins.def
index bcccf93f7fa2750e9006e5856efecbec0fb331b9..b9b56fc3d8b767eac0734d75e3fc5b61188ddca7 100644
--- a/gcc/config/arm/arm_neon_builtins.def
+++ b/gcc/config/arm/arm_neon_builtins.def
@@ -320,29 +320,29 @@ VAR12 (STORE1, vst1,
v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf, v2di)
VAR12 (STORE1LANE, vst1_lane,
v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf, v2di)
-VAR11 (LOAD1, vld2,
- v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf)
+VAR13 (LOAD1, vld2,
+ v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf, v4bf, v8bf)
VAR9 (LOAD1LANE, vld2_lane,
v8qi, v4hi, v4hf, v2si, v2sf, v8hi, v8hf, v4si, v4sf)
-VAR6 (LOAD1, vld2_dup, v8qi, v4hi, v4hf, v2si, v2sf, di)
+VAR8 (LOAD1, vld2_dup, v8qi, v4hi, v4hf, v2si, v2sf, di, v4bf, v8bf)
VAR11 (STORE1, vst2,
v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf)
VAR9 (STORE1LANE, vst2_lane,
v8qi, v4hi, v4hf, v2si, v2sf, v8hi, v8hf, v4si, v4sf)
-VAR11 (LOAD1, vld3,
- v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf)
+VAR13 (LOAD1, vld3,
+ v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf, v4bf, v8bf)
VAR9 (LOAD1LANE, vld3_lane,
v8qi, v4hi, v4hf, v2si, v2sf, v8hi, v8hf, v4si, v4sf)
-VAR6 (LOAD1, vld3_dup, v8qi, v4hi, v4hf, v2si, v2sf, di)
+VAR8 (LOAD1, vld3_dup, v8qi, v4hi, v4hf, v2si, v2sf, di, v4bf, v8bf)
VAR11 (STORE1, vst3,
v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf)
VAR9 (STORE1LANE, vst3_lane,
v8qi, v4hi, v4hf, v2si, v2sf, v8hi, v8hf, v4si, v4sf)
-VAR11 (LOAD1, vld4,
- v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf)
+VAR13 (LOAD1, vld4,
+ v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf, v4bf, v8bf)
VAR9 (LOAD1LANE, vld4_lane,
v8qi, v4hi, v4hf, v2si, v2sf, v8hi, v8hf, v4si, v4sf)
-VAR6 (LOAD1, vld4_dup, v8qi, v4hi, v4hf, v2si, v2sf, di)
+VAR8 (LOAD1, vld4_dup, v8qi, v4hi, v4hf, v2si, v2sf, di, v4bf, v8bf)
VAR11 (STORE1, vst4,
v8qi, v4hi, v4hf, v2si, v2sf, di, v16qi, v8hi, v8hf, v4si, v4sf)
VAR9 (STORE1LANE, vst4_lane,
diff --git a/gcc/config/arm/iterators.md b/gcc/config/arm/iterators.md
index 439021fa0733ac31706287c4f98d62b080afc3a1..f8b98bd57af223cacba05907d25e3d4b9d58eb8a 100644
--- a/gcc/config/arm/iterators.md
+++ b/gcc/config/arm/iterators.md
@@ -86,6 +86,12 @@
;; Double-width vector modes plus 64-bit elements.
(define_mode_iterator VDX [V8QI V4HI V4HF V2SI V2SF DI])
+;; Double-width vector modes plus 64-bit elements and V4BF.
+(define_mode_iterator VDXBF [V8QI V4HI V4HF V2SI V2SF DI (V4BF "TARGET_BF16_SIMD")])
+
+;; Double-width vector modes plus 64-bit elements, V4BF and V8BF.
+(define_mode_iterator VDXBF2 [V8QI V4HI V4HF V2SI V2SF DI (V4BF "TARGET_BF16_SIMD") (V8BF ("TARGET_BF16_SIMD"))])
+
;; Double-width vector modes plus 64-bit elements,
;; with V4BFmode added, suitable for moves.
(define_mode_iterator VDXMOV [V8QI V4HI V4HF V4BF V2SI V2SF DI])
@@ -102,6 +108,9 @@
;; Quad-width vector modes, including V8HF.
(define_mode_iterator VQ2 [V16QI V8HI V8HF V4SI V4SF])
+;; Quad-width vector modes, including V8HF and V8BF.
+(define_mode_iterator VQ2BF [V16QI V8HI V8HF V4SI V4SF (V8BF "TARGET_BF16_SIMD")])
+
;; Quad-width vector modes with 16- or 32-bit elements
(define_mode_iterator VQ_HS [V8HI V8HF V4SI V4SF])
@@ -546,6 +555,7 @@
(define_mode_attr V_two_elem [(V8QI "HI") (V16QI "HI")
(V4HI "SI") (V8HI "SI")
(V4HF "SF") (V8HF "SF")
+ (V4BF "V2BF") (V8BF "V2BF")
(V2SI "V2SI") (V4SI "V2SI")
(V2SF "V2SF") (V4SF "V2SF")
(DI "V2DI") (V2DI "V2DI")])
@@ -566,6 +576,7 @@
(define_mode_attr V_three_elem [(V8QI "BLK") (V16QI "BLK")
(V4HI "BLK") (V8HI "BLK")
(V4HF "BLK") (V8HF "BLK")
+ (V4BF "BLK") (V8BF "BLK")
(V2SI "BLK") (V4SI "BLK")
(V2SF "BLK") (V4SF "BLK")
(DI "EI") (V2DI "EI")])
@@ -574,6 +585,7 @@
(define_mode_attr V_four_elem [(V8QI "SI") (V16QI "SI")
(V4HI "V4HI") (V8HI "V4HI")
(V4HF "V4HF") (V8HF "V4HF")
+ (V4BF "V4BF") (V8BF "V4BF")
(V2SI "V4SI") (V4SI "V4SI")
(V2SF "V4SF") (V4SF "V4SF")
(DI "OI") (V2DI "OI")])
@@ -697,6 +709,7 @@
(V2SI "32") (V4SI "32")
(DI "64") (V2DI "64")
(V4HF "16") (V8HF "16")
+ (V4BF "16") (V8BF "16")
(V2SF "32") (V4SF "32")])
(define_mode_attr V_elem_ch [(V8QI "b") (V16QI "b")
@@ -772,6 +785,7 @@
(define_mode_attr V_mode_nunits [(V8QI "8") (V16QI "16")
(V4HF "4") (V8HF "8")
(V4HI "4") (V8HI "8")
+ (V4BF "4") (V8BF "8")
(V2SI "2") (V4SI "4")
(V2SF "2") (V4SF "4")
(DI "1") (V2DI "2")
diff --git a/gcc/config/arm/neon.md b/gcc/config/arm/neon.md
index b724aab65f720bf0e48bb828f0874426effd235c..4109e7f84838e48eebd95290eeeefc9d3e48ec7d 100644
--- a/gcc/config/arm/neon.md
+++ b/gcc/config/arm/neon.md
@@ -5383,7 +5383,7 @@ if (BYTES_BIG_ENDIAN)
(define_insn "neon_vld2<mode>"
[(set (match_operand:TI 0 "s_register_operand" "=w")
(unspec:TI [(match_operand:TI 1 "neon_struct_operand" "Um")
- (unspec:VDX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ (unspec:VDXBF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
UNSPEC_VLD2))]
"TARGET_NEON"
{
@@ -5408,7 +5408,7 @@ if (BYTES_BIG_ENDIAN)
(define_insn "neon_vld2<mode>"
[(set (match_operand:OI 0 "s_register_operand" "=w")
(unspec:OI [(match_operand:OI 1 "neon_struct_operand" "Um")
- (unspec:VQ2 [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ (unspec:VQ2BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
UNSPEC_VLD2))]
"TARGET_NEON"
"vld2.<V_sz_elem>\t%h0, %A1"
@@ -5471,7 +5471,7 @@ if (BYTES_BIG_ENDIAN)
(define_insn "neon_vld2_dup<mode>"
[(set (match_operand:TI 0 "s_register_operand" "=w")
(unspec:TI [(match_operand:<V_two_elem> 1 "neon_struct_operand" "Um")
- (unspec:VDX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ (unspec:VDXBF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
UNSPEC_VLD2_DUP))]
"TARGET_NEON"
{
@@ -5486,6 +5486,27 @@ if (BYTES_BIG_ENDIAN)
(const_string "neon_load1_1reg<q>")))]
)
+(define_insn "neon_vld2_dupv8bf"
+ [(set (match_operand:OI 0 "s_register_operand" "=w")
+ (unspec:OI [(match_operand:V2BF 1 "neon_struct_operand" "Um")
+ (unspec:V8BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ UNSPEC_VLD2_DUP))]
+ "TARGET_BF16_SIMD"
+ {
+ rtx ops[5];
+ int tabbase = REGNO (operands[0]);
+
+ ops[4] = operands[1];
+ ops[0] = gen_rtx_REG (V4BFmode, tabbase);
+ ops[1] = gen_rtx_REG (V4BFmode, tabbase + 2);
+ ops[2] = gen_rtx_REG (V4BFmode, tabbase + 4);
+ ops[3] = gen_rtx_REG (V4BFmode, tabbase + 6);
+ output_asm_insn ("vld2.16\t{%P0, %P1, %P2, %P3}, %A4", ops);
+ return "";
+ }
+ [(set_attr "type" "neon_load2_all_lanes_q")]
+)
+
(define_expand "vec_store_lanesti<mode>"
[(set (match_operand:TI 0 "neon_struct_operand")
(unspec:TI [(match_operand:TI 1 "s_register_operand")
@@ -5592,7 +5613,7 @@ if (BYTES_BIG_ENDIAN)
(define_insn "neon_vld3<mode>"
[(set (match_operand:EI 0 "s_register_operand" "=w")
(unspec:EI [(match_operand:EI 1 "neon_struct_operand" "Um")
- (unspec:VDX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ (unspec:VDXBF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
UNSPEC_VLD3))]
"TARGET_NEON"
{
@@ -5620,7 +5641,7 @@ if (BYTES_BIG_ENDIAN)
(define_expand "neon_vld3<mode>"
[(match_operand:CI 0 "s_register_operand")
(match_operand:CI 1 "neon_struct_operand")
- (unspec:VQ2 [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ (unspec:VQ2BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
"TARGET_NEON"
{
rtx mem;
@@ -5635,7 +5656,7 @@ if (BYTES_BIG_ENDIAN)
(define_insn "neon_vld3qa<mode>"
[(set (match_operand:CI 0 "s_register_operand" "=w")
(unspec:CI [(match_operand:EI 1 "neon_struct_operand" "Um")
- (unspec:VQ2 [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ (unspec:VQ2BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
UNSPEC_VLD3A))]
"TARGET_NEON"
{
@@ -5655,7 +5676,7 @@ if (BYTES_BIG_ENDIAN)
[(set (match_operand:CI 0 "s_register_operand" "=w")
(unspec:CI [(match_operand:EI 1 "neon_struct_operand" "Um")
(match_operand:CI 2 "s_register_operand" "0")
- (unspec:VQ2 [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ (unspec:VQ2BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
UNSPEC_VLD3B))]
"TARGET_NEON"
{
@@ -5732,7 +5753,7 @@ if (BYTES_BIG_ENDIAN)
(define_insn "neon_vld3_dup<mode>"
[(set (match_operand:EI 0 "s_register_operand" "=w")
(unspec:EI [(match_operand:<V_three_elem> 1 "neon_struct_operand" "Um")
- (unspec:VDX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ (unspec:VDXBF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
UNSPEC_VLD3_DUP))]
"TARGET_NEON"
{
@@ -5755,6 +5776,26 @@ if (BYTES_BIG_ENDIAN)
(const_string "neon_load3_all_lanes<q>")
(const_string "neon_load1_1reg<q>")))])
+(define_insn "neon_vld3_dupv8bf"
+ [(set (match_operand:CI 0 "s_register_operand" "=w")
+ (unspec:CI [(match_operand:V2BF 1 "neon_struct_operand" "Um")
+ (unspec:V8BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ UNSPEC_VLD2_DUP))]
+ "TARGET_BF16_SIMD"
+ {
+ rtx ops[4];
+ int tabbase = REGNO (operands[0]);
+
+ ops[3] = operands[1];
+ ops[0] = gen_rtx_REG (V4BFmode, tabbase);
+ ops[1] = gen_rtx_REG (V4BFmode, tabbase + 2);
+ ops[2] = gen_rtx_REG (V4BFmode, tabbase + 4);
+ output_asm_insn ("vld3.16\t{%P0[], %P1[], %P2[]}, %A3", ops);
+ return "";
+ }
+ [(set_attr "type" "neon_load3_all_lanes_q")]
+)
+
(define_expand "vec_store_lanesei<mode>"
[(set (match_operand:EI 0 "neon_struct_operand")
(unspec:EI [(match_operand:EI 1 "s_register_operand")
@@ -5910,7 +5951,7 @@ if (BYTES_BIG_ENDIAN)
(define_insn "neon_vld4<mode>"
[(set (match_operand:OI 0 "s_register_operand" "=w")
(unspec:OI [(match_operand:OI 1 "neon_struct_operand" "Um")
- (unspec:VDX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ (unspec:VDXBF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
UNSPEC_VLD4))]
"TARGET_NEON"
{
@@ -5938,7 +5979,7 @@ if (BYTES_BIG_ENDIAN)
(define_expand "neon_vld4<mode>"
[(match_operand:XI 0 "s_register_operand")
(match_operand:XI 1 "neon_struct_operand")
- (unspec:VQ2 [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ (unspec:VQ2BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
"TARGET_NEON"
{
rtx mem;
@@ -5953,7 +5994,7 @@ if (BYTES_BIG_ENDIAN)
(define_insn "neon_vld4qa<mode>"
[(set (match_operand:XI 0 "s_register_operand" "=w")
(unspec:XI [(match_operand:OI 1 "neon_struct_operand" "Um")
- (unspec:VQ2 [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ (unspec:VQ2BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
UNSPEC_VLD4A))]
"TARGET_NEON"
{
@@ -5974,7 +6015,7 @@ if (BYTES_BIG_ENDIAN)
[(set (match_operand:XI 0 "s_register_operand" "=w")
(unspec:XI [(match_operand:OI 1 "neon_struct_operand" "Um")
(match_operand:XI 2 "s_register_operand" "0")
- (unspec:VQ2 [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ (unspec:VQ2BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
UNSPEC_VLD4B))]
"TARGET_NEON"
{
@@ -6054,7 +6095,7 @@ if (BYTES_BIG_ENDIAN)
(define_insn "neon_vld4_dup<mode>"
[(set (match_operand:OI 0 "s_register_operand" "=w")
(unspec:OI [(match_operand:<V_four_elem> 1 "neon_struct_operand" "Um")
- (unspec:VDX [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ (unspec:VDXBF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
UNSPEC_VLD4_DUP))]
"TARGET_NEON"
{
@@ -6080,6 +6121,27 @@ if (BYTES_BIG_ENDIAN)
(const_string "neon_load1_1reg<q>")))]
)
+(define_insn "neon_vld4_dupv8bf"
+ [(set (match_operand:XI 0 "s_register_operand" "=w")
+ (unspec:XI [(match_operand:V2BF 1 "neon_struct_operand" "Um")
+ (unspec:V8BF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
+ UNSPEC_VLD2_DUP))]
+ "TARGET_BF16_SIMD"
+ {
+ rtx ops[5];
+ int tabbase = REGNO (operands[0]);
+
+ ops[4] = operands[1];
+ ops[0] = gen_rtx_REG (V4BFmode, tabbase);
+ ops[1] = gen_rtx_REG (V4BFmode, tabbase + 2);
+ ops[2] = gen_rtx_REG (V4BFmode, tabbase + 4);
+ ops[3] = gen_rtx_REG (V4BFmode, tabbase + 6);
+ output_asm_insn ("vld4.16\t{%P0[], %P1[], %P2[], %P3[]}, %A4", ops);
+ return "";
+ }
+ [(set_attr "type" "neon_load4_all_lanes_q")]
+)
+
(define_expand "vec_store_lanesoi<mode>"
[(set (match_operand:OI 0 "neon_struct_operand")
(unspec:OI [(match_operand:OI 1 "s_register_operand")
diff --git a/gcc/testsuite/gcc.target/arm/simd/bf16_vldn_1.c b/gcc/testsuite/gcc.target/arm/simd/bf16_vldn_1.c
new file mode 100644
index 0000000000000000000000000000000000000000..8db8dfbe28d2136bd2d943e2aae80e32cea34133
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/bf16_vldn_1.c
@@ -0,0 +1,152 @@
+/* { dg-do assemble } */
+/* { dg-options "-save-temps" } */
+/* { dg-require-effective-target arm_v8_2a_bf16_neon_ok } */
+/* { dg-add-options arm_v8_2a_bf16_neon } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#include "arm_neon.h"
+
+
+/*
+**test_vld2_bf16:
+** ...
+** vld2.16\t{d[0-9]+-d[0-9]+}, \[r[0-9]+\]
+** ...
+*/
+bfloat16x4x2_t
+test_vld2_bf16 (bfloat16_t * ptr)
+{
+ vld2_bf16 (ptr);
+}
+
+/*
+**test_vld2q_bf16:
+** ...
+** vld2.16\t{d[0-9]+-d[0-9]+}, \[r[0-9]+\]
+** ...
+*/
+bfloat16x8x2_t
+test_vld2q_bf16 (bfloat16_t * ptr)
+{
+ vld2q_bf16 (ptr);
+}
+
+/*
+**test_vld2_dup_bf16:
+** ...
+** vld2.16\t{d[0-9]+\[\], d[0-9]+\[\]}, \[r[0-9]+\]
+** ...
+*/
+bfloat16x4x2_t
+test_vld2_dup_bf16 (bfloat16_t * ptr)
+{
+ vld2_dup_bf16 (ptr);
+}
+
+/*
+**test_vld2q_dup_bf16:
+** ...
+** vld2.16\t{d[0-9]+, d[0-9]+, d[0-9]+, d[0-9]+}, \[r3\]
+** ...
+*/
+bfloat16x8x2_t
+test_vld2q_dup_bf16 (bfloat16_t * ptr)
+{
+ vld2q_dup_bf16 (ptr);
+}
+
+/*
+**test_vld3_bf16:
+** ...
+** vld3.16\t{d[0-9]+-d[0-9]+}, \[r[0-9]+\]
+** ...
+*/
+bfloat16x4x3_t
+test_vld3_bf16 (bfloat16_t * ptr)
+{
+ vld3_bf16 (ptr);
+}
+
+/*
+**test_vld3q_bf16:
+** ...
+** vld3.16\t{d[0-9]+, d[0-9]+, d[0-9]+}, \[r[0-9]+\]
+** ...
+*/
+bfloat16x8x3_t
+test_vld3q_bf16 (bfloat16_t * ptr)
+{
+ vld3q_bf16 (ptr);
+}
+
+/*
+**test_vld3_dup_bf16:
+** ...
+** vld3.16\t{d[0-9]+\[\], d[0-9]+\[\], d[0-9]+\[\]}, \[r[0-9]+\]
+** ...
+*/
+bfloat16x4x3_t
+test_vld3_dup_bf16 (bfloat16_t * ptr)
+{
+ vld3_dup_bf16 (ptr);
+}
+
+/*
+**test_vld3q_dup_bf16:
+** ...
+** vld3.16\t{d[0-9]+\[\], d[0-9]+\[\], d[0-9]+\[\]}, \[r[0-9]+\]
+** ...
+*/
+bfloat16x8x3_t
+test_vld3q_dup_bf16 (bfloat16_t * ptr)
+{
+ vld3q_dup_bf16 (ptr);
+}
+
+/*
+**test_vld4_bf16:
+** ...
+** vld4.16\t{d[0-9]+-d[0-9]+}, \[r[0-9]+\]
+** ...
+*/
+bfloat16x4x4_t
+test_vld4_bf16 (bfloat16_t * ptr)
+{
+ vld4_bf16 (ptr);
+}
+
+/*
+**test_vld4q_bf16:
+** ...
+** vld4.16\t{d[0-9]+, d[0-9]+, d[0-9]+, d[0-9]+}, \[r[0-9]+\]
+** ...
+*/
+bfloat16x8x4_t
+test_vld4q_bf16 (bfloat16_t * ptr)
+{
+ vld4q_bf16 (ptr);
+}
+
+/*
+**test_vld4_dup_bf16:
+** ...
+** vld4.16\t{d[0-9]+\[\], d[0-9]+\[\], d[0-9]+\[\], d[0-9]+\[\]}, \[r[0-9]+\]
+** ...
+*/
+bfloat16x4x4_t
+test_vld4_dup_bf16 (bfloat16_t * ptr)
+{
+ vld4_dup_bf16 (ptr);
+}
+
+/*
+**test_vld4q_dup_bf16:
+** ...
+** vld4.16\t{d[0-9]+\[\], d[0-9]+\[\], d[0-9]+\[\], d[0-9]+\[\]}, \[r[0-9]+\]
+** ...
+*/
+bfloat16x4x4_t
+test_vld4q_dup_bf16 (bfloat16_t * ptr)
+{
+ vld4q_dup_bf16 (ptr);
+}
