Sorry for the confusion, what I meant to say was:
This patch adds the Armv8.6-a ACLE intrinsics for bfcvtn, bfcvtn2 and
bfcvt as part of the BFloat16 extension.
(https://developer.arm.com/architectures/instruction-sets/simd-isas/neon/intrinsics)
The intrinsics are declared in arm_bf16.h and arm_neon.h and the RTL
patterns are defined in aarch64-simd.md.
Tested for regression on aarch64-none-elf and aarch64_be-none-elf. I
don't have commit rights, so if this is ok can someone please commit it
for me?
Here is the updated patch.
Thank you,
Delia
gcc/ChangeLog:
2019-11-06 Delia Burduv <[email protected]>
* config/aarch64/aarch64-simd-builtins.def
(bfcvtn): New built-in function.
(bfcvtn_q): New built-in function.
(bfcvtn2): New built-in function.
(bfcvt): New built-in function.
* config/aarch64/aarch64-simd.md
(aarch64_bfcvtn<q><mode>): New pattern.
(aarch64_bfcvtn2v8bf): New pattern.
(aarch64_bfcvtbf): New pattern.
* config/aarch64/arm_bf16.h (float32_t): New typedef.
(vcvth_bf16_f32): New intrinsic.
* config/aarch64/arm_bf16.h (vcvt_bf16_f32): New intrinsic.
(vcvtq_low_bf16_f32): New intrinsic.
(vcvtq_high_bf16_f32): New intrinsic.
* config/aarch64/iterators.md (V4SF_TO_BF): New mode iterator.
(UNSPEC_BFCVTN): New UNSPEC.
(UNSPEC_BFCVTN2): New UNSPEC.
(UNSPEC_BFCVT): New UNSPEC.
* config/arm/types.md (bf_cvt): New type.
gcc/testsuite/ChangeLog:
2020-01-31 Delia Burduv <[email protected]>
* gcc.target/aarch64/advsimd-intrinsics/bfcvt-compile.c: New
test.
* gcc.target/aarch64/advsimd-intrinsics/bfcvt-nobf16.c: New
test.
* gcc.target/aarch64/advsimd-intrinsics/bfcvt-nosimd.c: New
test.
* gcc.target/aarch64/advsimd-intrinsics/bfcvtnq2-untied.c: New
test.
On 12/23/19 6:30 PM, Richard Sandiford wrote:
> Some of the comments on the BFMMLA/BFMLA[LT] patch apply here too.
>
> Delia Burduv <[email protected]> writes:
>> This patch adds the Armv8.6-a ACLE intrinsics for bfmmla, bfmlalb and
>> bfmlalt as part of the BFloat16 extension.
>
> That's the other patch :-)
>
>> [...]
>> diff --git a/gcc/config/aarch64/aarch64-simd.md
>> b/gcc/config/aarch64/aarch64-simd.md
>> index
>> 55660ae248f4fa75d35ba2949cd4b9d5139ff5f5..ff7a1f5f34a19b05eba48dba96c736dfdfdf7bac
>> 100644
>> --- a/gcc/config/aarch64/aarch64-simd.md
>> +++ b/gcc/config/aarch64/aarch64-simd.md
>> @@ -7027,3 +7027,32 @@
>> "xtn\t%0.<Vntype>, %1.<Vtype>"
>> [(set_attr "type" "neon_shift_imm_narrow_q")]
>> )
>> +
>> +;; bfcvtn
>> +(define_insn "aarch64_bfcvtn<q><mode>"
>> + [(set (match_operand:V4SF_TO_BF 0 "register_operand" "=w")
>> + (unspec:V4SF_TO_BF [(match_operand:V4SF 1 "register_operand" "w")]
>> + UNSPEC_BFCVTN))]
>> + "TARGET_BF16_SIMD"
>> + "bfcvtn\\t%0.4h, %1.4s"
>> + [(set_attr "type" "f_cvt")]
>> +)
>> +
>
> If I've understood the naming convention correctly, the closest type
> seems to be "neon_fp_cvt_narrow_s_q".
>
>> +(define_insn "aarch64_bfcvtn2v8bf"
>> + [(set (match_operand:V8BF 0 "register_operand" "=w")
>> + (unspec:V8BF [(match_operand:V8BF 1 "register_operand" "w")
>> + (match_operand:V4SF 2 "register_operand" "w")]
>> + UNSPEC_BFCVTN2))]
>> + "TARGET_BF16_SIMD"
>> + "bfcvtn2\\t%0.8h, %2.4s"
>> + [(set_attr "type" "f_cvt")]
>> +)
>
> Same here.
>
> The constraint on operand 1 needs to be "0", otherwise operands 1 and 0
> could end up in different registers. You could test for this using
> something like:
>
> bfloat16x8_t test_bfcvtnq2_untied (bfloat16x8_t unused, bfloat16x8_t inactive,
> float32x4_t a)
> {
> return vcvtq_high_bf16_f32 (inactive, a);
> }
>
> which when compiled at -O should produce something like:
>
> /*
> **test_bfcvtnq2_untied:
> ** mov v0\.8h, v1\.8h
> ** bfcvtn2 v0\.8h, v2\.4s
> ** ret
> */
>
> (Completely untested, the code above is probably wrong.)
>
>> +
>> +(define_insn "aarch64_bfcvtbf"
>> + [(set (match_operand:BF 0 "register_operand" "=w")
>> + (unspec:BF [(match_operand:SF 1 "register_operand" "w")]
>> + UNSPEC_BFCVT))]
>> + "TARGET_BF16_SIMD"
>
> I think this just needs the scalar macro rather than *_SIMD.
>
>> + "bfcvt\\t%h0, %s1"
>> + [(set_attr "type" "f_cvt")]
>> +)
>> diff --git a/gcc/config/aarch64/arm_bf16.h b/gcc/config/aarch64/arm_bf16.h
>> index
>> aedb0972735ce549fac1870bacd1ef3101e8fd26..1b9ab3690d35e153cd4f24b9e3bbb5b4cc4b4f4d
>> 100644
>> --- a/gcc/config/aarch64/arm_bf16.h
>> +++ b/gcc/config/aarch64/arm_bf16.h
>> @@ -34,7 +34,15 @@
>> #ifdef __ARM_FEATURE_BF16_SCALAR_ARITHMETIC
>>
>> typedef __bf16 bfloat16_t;
>> -
>> +typedef float float32_t;
>> +
>> +__extension__ extern __inline bfloat16_t
>> +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>> +vcvth_bf16_f32 \
>> + (float32_t __a)
>
> No need for the line break here.
>
>> +{
>> + return __builtin_aarch64_bfcvtbf (__a);
>> +}
>>
>> #endif
>> #pragma GCC pop_options
>> diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
>> index
>> 6cdbf381f0156ed993f03b847228b36ebbdd14f8..120f4b7d8827aee51834e75aeaa6ab8f8451980e
>> 100644
>> --- a/gcc/config/aarch64/arm_neon.h
>> +++ b/gcc/config/aarch64/arm_neon.h
>> @@ -34610,6 +34610,35 @@ vrnd64xq_f64 (float64x2_t __a)
>>
>> #include "arm_bf16.h"
>>
>> +#pragma GCC push_options
>> +#pragma GCC target ("arch=armv8.2-a+bf16")
>> +#ifdef __ARM_FEATURE_BF16_VECTOR_ARITHMETIC
>> +
>> +__extension__ extern __inline bfloat16x4_t
>> +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>> +vcvt_bf16_f32 (float32x4_t __a)
>> +{
>> + return __builtin_aarch64_bfcvtnv4bf (__a);
>> +
>> +}
>
> Nit: extra blank line.
>
>> +
>> +__extension__ extern __inline bfloat16x8_t
>> +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>> +vcvtq_low_bf16_f32 (float32x4_t __a)
>> +{
>> + return __builtin_aarch64_bfcvtn_qv8bf (__a);
>> +}
>> +
>> +__extension__ extern __inline bfloat16x8_t
>> +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
>> +vcvtq_high_bf16_f32 (bfloat16x8_t __inactive, float32x4_t __a)
>> +{
>> + return __builtin_aarch64_bfcvtn2v8bf (__inactive, __a);
>> +}
>> +
>> +#endif
>> +#pragma GCC pop_options
>> +
>> #pragma GCC pop_options
>>
>> #undef __aarch64_vget_lane_any
>> diff --git a/gcc/config/aarch64/iterators.md
>> b/gcc/config/aarch64/iterators.md
>> index
>> 931166da5e47302afe810498eea9c8c2ab89b9de..f9f0bafb1eca4da42e564224fca1fd43d89f6ed1
>> 100644
>> --- a/gcc/config/aarch64/iterators.md
>> +++ b/gcc/config/aarch64/iterators.md
>> @@ -431,6 +431,9 @@
>> ;; SVE predicate modes that control 16-bit, 32-bit or 64-bit elements.
>> (define_mode_iterator PRED_HSD [VNx8BI VNx4BI VNx2BI])
>>
>> +;; Bfloat16 modes to which V4SF can be converted
>> +(define_mode_iterator V4SF_TO_BF [V4BF V8BF])
>> +
>> ;; ------------------------------------------------------------------
>> ;; Unspec enumerations for Advance SIMD. These could well go into
>> ;; aarch64.md but for their use in int_iterators here.
>> @@ -673,6 +676,9 @@
>> UNSPEC_UMULHS ; Used in aarch64-sve2.md.
>> UNSPEC_UMULHRS ; Used in aarch64-sve2.md.
>> UNSPEC_ASRD ; Used in aarch64-sve.md.
>> + UNSPEC_BFCVTN ; Used in aarch64-simd.md.
>> + UNSPEC_BFCVTN2 ; Used in aarch64-simd.md.
>> + UNSPEC_BFCVT ; Used in aarch64-simd.md.
>> ])
>>
>> ;; ------------------------------------------------------------------
>> diff --git a/gcc/config/arm/types.md b/gcc/config/arm/types.md
>> index
>> df39522f2ad63a52c910b1a6bcc7aa13aaf5d021..dbcb4d58798d7f51b1b8310cd446c58317d7b50d
>> 100644
>> --- a/gcc/config/arm/types.md
>> +++ b/gcc/config/arm/types.md
>> @@ -1097,7 +1097,8 @@
>> crypto_sm4,\
>> coproc,\
>> tme,\
>> - memtag"
>> + memtag,\
>> + bf_cvt"
>
> This doesn't seem to be used.
>
>> diff --git
>> a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvt-compile.c
>> b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvt-compile.c
>> new file mode 100644
>> index
>> 0000000000000000000000000000000000000000..ebe5b578c1fa82a6f2a166d55c7dc7e905b87135
>> --- /dev/null
>> +++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvt-compile.c
>> @@ -0,0 +1,56 @@
>> +/* { dg-do assemble { target { aarch64*-*-* } } } */
>> +/* { dg-require-effective-target arm_v8_2a_bf16_neon_ok } */
>> +/* { dg-add-options arm_v8_2a_bf16_neon } */
>> +/* { dg-additional-options "-save-temps" } */
>> +/* { dg-final { check-function-bodies "**" "" "-DCHECK_ASM" } } */
>> +
>> +#include <arm_neon.h>
>> +
>> +/*
>> +**test_bfcvtn:
>> +** ...
>> +** bfcvtn\tv[0-9]+.4h, v[0-9]+.4s
>> +** ...
>> +*/
>> +bfloat16x4_t test_bfcvtn (float32x4_t a)
>> +{
>> + return vcvt_bf16_f32 (a);
>> +}
>> +
>> +/*
>> +**test_bfcvtnq:
>> +** ...
>> +** bfcvtn v[0-9]+.4h, v[0-9]+.4s
>> +** ...
>> +*/
>> +bfloat16x8_t test_bfcvtnq (float32x4_t a)
>> +{
>> + return vcvtq_low_bf16_f32 (a);
>> +}
>> +
>> +/*
>> +**test_bfcvtnq2:
>> +** ...
>> +** bfcvtn v[0-9]+.4h, v[0-9]+.4s
>> +** ...
>> +*/
>> +bfloat16x8_t test_bfcvtnq2 (bfloat16x8_t inactive, float32x4_t a)
>> +{
>> + return vcvtq_high_bf16_f32 (inactive, a);
>> +}
>> +
>> +/*
>> +**test_bfcvt:
>> +** ...
>> +** bfcvt h[0-9]+, s[0-9]+
>> +** ...
>> +*/
>> +bfloat16_t test_bfcvt (float32_t a)
>> +{
>> + return vcvth_bf16_f32 (a);
>> +}
>> +
>> +/* { dg-final { scan-assembler {bfcvtn\tv[0-9]+.4h, v[0-9]+.4s} } } */
>> +/* { dg-final { scan-assembler {bfcvtn\tv[0-9]+.4h, v[0-9]+.4s} } } */
>> +/* { dg-final { scan-assembler {bfcvtn\tv[0-9]+.4h, v[0-9]+.4s} } } */
>> +/* { dg-final { scan-assembler {bfcvt\th[0-9]+, s[0-9]+} } } */
>
> Same comments as for the BFMMLA/BFMLA[BT] tests.
>
> As well as testing all these combinations for the SIMD case,
> it would be good to have a direct arm_bf16.h-only test for:
>
> #pragma GCC target "arch=armv8.2-a+bf16+nosimd"
>
> test_bfcvt should still work in that case.
>
> It would also be good to have a test that test_bfcvt reports
> an appropriate error if compiled after:
>
> #pragma GCC target "arch=armv8.2-a+nobf16"
>
> Thanks,
> Richard
>
diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def
index a118f4f121de067c0a80f691b852247b0ab27f7a..c1e364b4d1cb7a207c1de5a409a08e18a405a107 100644
--- a/gcc/config/aarch64/aarch64-simd-builtins.def
+++ b/gcc/config/aarch64/aarch64-simd-builtins.def
@@ -692,3 +692,9 @@
VAR2 (TERNOP, bfdot, 0, v2sf, v4sf)
VAR2 (QUADOP_LANE_PAIR, bfdot_lane, 0, v2sf, v4sf)
VAR2 (QUADOP_LANE_PAIR, bfdot_laneq, 0, v2sf, v4sf)
+
+ /* Implemented by aarch64_bfcvtn{q}{2}<mode> */
+ VAR1 (UNOP, bfcvtn, 0, v4bf)
+ VAR1 (UNOP, bfcvtn_q, 0, v8bf)
+ VAR1 (BINOP, bfcvtn2, 0, v8bf)
+ VAR1 (UNOP, bfcvt, 0, bf)
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index 97f46f96968a6bc2f93bbc812931537b819b3b19..111e48ea6b70548158ba696d997a2f2fc3cb2769 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -7091,3 +7091,32 @@
}
[(set_attr "type" "neon_dot<VDQSF:q>")]
)
+
+;; bfcvtn
+(define_insn "aarch64_bfcvtn<q><mode>"
+ [(set (match_operand:V4SF_TO_BF 0 "register_operand" "=w")
+ (unspec:V4SF_TO_BF [(match_operand:V4SF 1 "register_operand" "w")]
+ UNSPEC_BFCVTN))]
+ "TARGET_BF16_SIMD"
+ "bfcvtn\\t%0.4h, %1.4s"
+ [(set_attr "type" "neon_fp_cvt_narrow_s_q")]
+)
+
+(define_insn "aarch64_bfcvtn2v8bf"
+ [(set (match_operand:V8BF 0 "register_operand" "=w")
+ (unspec:V8BF [(match_operand:V8BF 1 "register_operand" "0")
+ (match_operand:V4SF 2 "register_operand" "w")]
+ UNSPEC_BFCVTN2))]
+ "TARGET_BF16_SIMD"
+ "bfcvtn2\\t%0.8h, %2.4s"
+ [(set_attr "type" "neon_fp_cvt_narrow_s_q")]
+)
+
+(define_insn "aarch64_bfcvtbf"
+ [(set (match_operand:BF 0 "register_operand" "=w")
+ (unspec:BF [(match_operand:SF 1 "register_operand" "w")]
+ UNSPEC_BFCVT))]
+ "TARGET_BF16_FP"
+ "bfcvt\\t%h0, %s1"
+ [(set_attr "type" "f_cvt")]
+)
diff --git a/gcc/config/aarch64/arm_bf16.h b/gcc/config/aarch64/arm_bf16.h
index 3759c0d1cb449a7f0125cc2a1433127564d66622..fb2150e1d60a590046e2c034422021aafc721e23 100644
--- a/gcc/config/aarch64/arm_bf16.h
+++ b/gcc/config/aarch64/arm_bf16.h
@@ -28,5 +28,13 @@
#define _AARCH64_BF16_H_
typedef __bf16 bfloat16_t;
+typedef float float32_t;
+
+__extension__ extern __inline bfloat16_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vcvth_bf16_f32 (float32_t __a)
+{
+ return __builtin_aarch64_bfcvtbf (__a);
+}
#endif
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 7f05c3f9eca844b0e7b824a191223a4906c825b1..36f82743231a7160050695267e75a08e0cd73e03 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -34660,6 +34660,27 @@ vbfdotq_laneq_f32 (float32x4_t __r, bfloat16x8_t __a, bfloat16x8_t __b,
return __builtin_aarch64_bfdot_laneqv4sf (__r, __a, __b, __index);
}
+__extension__ extern __inline bfloat16x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vcvt_bf16_f32 (float32x4_t __a)
+{
+ return __builtin_aarch64_bfcvtnv4bf (__a);
+}
+
+__extension__ extern __inline bfloat16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vcvtq_low_bf16_f32 (float32x4_t __a)
+{
+ return __builtin_aarch64_bfcvtn_qv8bf (__a);
+}
+
+__extension__ extern __inline bfloat16x8_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vcvtq_high_bf16_f32 (bfloat16x8_t __inactive, float32x4_t __a)
+{
+ return __builtin_aarch64_bfcvtn2v8bf (__inactive, __a);
+}
+
#pragma GCC pop_options
/* AdvSIMD 8-bit Integer Matrix Multiply (I8MM) intrinsics. */
diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md
index fc973086cb91ae0dc54eeeb0b832d522539d7982..9f25d4805d2d78025885f573176296e71f74f447 100644
--- a/gcc/config/aarch64/iterators.md
+++ b/gcc/config/aarch64/iterators.md
@@ -455,6 +455,9 @@
;; SVE predicate modes that control 16-bit, 32-bit or 64-bit elements.
(define_mode_iterator PRED_HSD [VNx8BI VNx4BI VNx2BI])
+;; Bfloat16 modes to which V4SF can be converted
+(define_mode_iterator V4SF_TO_BF [V4BF V8BF])
+
;; ------------------------------------------------------------------
;; Unspec enumerations for Advance SIMD. These could well go into
;; aarch64.md but for their use in int_iterators here.
@@ -808,6 +811,9 @@
UNSPEC_USDOT ; Used in aarch64-simd.md.
UNSPEC_SUDOT ; Used in aarch64-simd.md.
UNSPEC_BFDOT ; Used in aarch64-simd.md.
+ UNSPEC_BFCVTN ; Used in aarch64-simd.md.
+ UNSPEC_BFCVTN2 ; Used in aarch64-simd.md.
+ UNSPEC_BFCVT ; Used in aarch64-simd.md.
])
;; ------------------------------------------------------------------
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvt-compile.c b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvt-compile.c
new file mode 100644
index 0000000000000000000000000000000000000000..ffb5305e2e5ea1aadae07e82fd8ed6f9f247c1a9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvt-compile.c
@@ -0,0 +1,48 @@
+/* { dg-do assemble { target { aarch64*-*-* } } } */
+/* { dg-require-effective-target arm_v8_2a_bf16_neon_ok } */
+/* { dg-add-options arm_v8_2a_bf16_neon } */
+/* { dg-additional-options "-save-temps" } */
+/* { dg-final { check-function-bodies "**" "" {-O[^0]} } } */
+/* { dg-skip-if "" { *-*-* } { "-fno-fat-lto-objects" } } */
+
+#include <arm_neon.h>
+
+/*
+**test_bfcvtn:
+** bfcvtn\tv0.4h, v0.4s
+** ret
+*/
+bfloat16x4_t test_bfcvtn (float32x4_t a)
+{
+ return vcvt_bf16_f32 (a);
+}
+
+/*
+**test_bfcvtnq:
+** bfcvtn\tv0.4h, v0.4s
+** ret
+*/
+bfloat16x8_t test_bfcvtnq (float32x4_t a)
+{
+ return vcvtq_low_bf16_f32 (a);
+}
+
+/*
+**test_bfcvtnq2:
+** bfcvtn2\tv0.8h, v1.4s
+** ret
+*/
+bfloat16x8_t test_bfcvtnq2 (bfloat16x8_t inactive, float32x4_t a)
+{
+ return vcvtq_high_bf16_f32 (inactive, a);
+}
+
+/*
+**test_bfcvt:
+** bfcvt\th0, s0
+** ret
+*/
+bfloat16_t test_bfcvt (float32_t a)
+{
+ return vcvth_bf16_f32 (a);
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvt-nobf16.c b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvt-nobf16.c
new file mode 100644
index 0000000000000000000000000000000000000000..b3b6db12358677b2f34169214241318e5d0d764f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvt-nobf16.c
@@ -0,0 +1,10 @@
+/* { dg-do assemble { target { aarch64*-*-* } } } */
+/* { dg-additional-options "-march=armv8.2-a+nobf16" } */
+
+#include <arm_neon.h>
+
+bfloat16x4_t test_bfcvtn (float32x4_t a)
+{
+ /* { dg-error "inlining failed .* 'vcvt_bf16_f32" "" { target *-*-* } 0 } */
+ return vcvt_bf16_f32 (a);
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvt-nosimd.c b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvt-nosimd.c
new file mode 100644
index 0000000000000000000000000000000000000000..8d7dffe16275de60e884c449afa0fea0b1af6081
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvt-nosimd.c
@@ -0,0 +1,15 @@
+/* { dg-do assemble { target { aarch64*-*-* } } } */
+/* { dg-additional-options "-save-temps -march=armv8.2-a+bf16+nosimd" } */
+/* { dg-final { check-function-bodies "**" "" "-DCHECK_ASM" } } */
+
+#include <arm_neon.h>
+
+/*
+**test_bfcvt:
+** bfcvt\th0, s0
+** ret
+*/
+bfloat16_t test_bfcvt (float32_t a)
+{
+ return vcvth_bf16_f32 (a);
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvtnq2-untied.c b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvtnq2-untied.c
new file mode 100644
index 0000000000000000000000000000000000000000..7d2cef68438da83e386fa02753d018242a74a452
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/bfcvtnq2-untied.c
@@ -0,0 +1,20 @@
+/* { dg-do assemble { target { aarch64*-*-* } } } */
+/* { dg-require-effective-target arm_v8_2a_bf16_neon_ok } */
+/* { dg-add-options arm_v8_2a_bf16_neon } */
+/* { dg-additional-options "-save-temps" } */
+/* { dg-final { check-function-bodies "**" "" {-O[^0]} } } */
+/* { dg-skip-if "" { *-*-* } { "-fno-fat-lto-objects" } } */
+
+#include <arm_neon.h>
+
+/*
+**test_bfcvtnq2_untied:
+** mov\tv0.16b, v1.16b
+** bfcvtn2\tv0.8h, v2.4s
+** ret
+*/
+bfloat16x8_t test_bfcvtnq2_untied (bfloat16x8_t unused, bfloat16x8_t inactive,
+ float32x4_t a)
+{
+ return vcvtq_high_bf16_f32 (inactive, a);
+}
