diff options
author | Pablo Marquez Tello <pablo.tello@arm.com> | 2022-12-19 17:12:53 +0000 |
---|---|---|
committer | Pablo Marquez Tello <pablo.tello@arm.com> | 2022-12-21 08:28:34 +0000 |
commit | 9d7b690fd886bcc514a6aa8d17d53e25e3500a33 (patch) | |
tree | fa5c965eec259859716c4e224e96d33eac1b1731 /src/core/NEON/wrapper | |
parent | b84e25313e5dc7acbc03623e1e071e845047c111 (diff) | |
download | ComputeLibrary-9d7b690fd886bcc514a6aa8d17d53e25e3500a33.tar.gz |
Fixed various mismatches in CpuCastKernel
* Fixes various mismatches when converting FP32 to BF16 and
BF16 to FP32
* Fixed segfault when trying logging=1 and trying to log BF16
* Resolves MLCE-979
Change-Id: Ie517d0b7411b4e3a7fecdee588f0e073d290625a
Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8830
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/NEON/wrapper')
-rw-r--r-- | src/core/NEON/wrapper/intrinsics/cvt.h | 20 |
1 files changed, 0 insertions, 20 deletions
diff --git a/src/core/NEON/wrapper/intrinsics/cvt.h b/src/core/NEON/wrapper/intrinsics/cvt.h index baad1319b2..c75d43dbf2 100644 --- a/src/core/NEON/wrapper/intrinsics/cvt.h +++ b/src/core/NEON/wrapper/intrinsics/cvt.h @@ -87,26 +87,6 @@ vcvta(const float32x4_t &a) return vcvtaq_s32_f32(a); } #endif //__aarch64__ - -#if defined(ARM_COMPUTE_ENABLE_BF16) -/** Convert 2x128-bit floating point vectors into 1x128-bit bfloat16 vector - * - * @param[in] inptr Pointer to the input memory to load values from - * @param[in,out] outptr Pointer to the output memory to store values to - */ -inline void vcvt_bf16_f32(const float *inptr, uint16_t *outptr) -{ - __asm __volatile( - "ldp q0, q1, [%[inptr]]\n" - ".inst 0xea16800\n" // BFCVTN v0, v0 - ".inst 0x4ea16820\n" // BFCVTN2 v0, v1 - "str q0, [%[outptr]]\n" - : [inptr] "+r"(inptr) - : [outptr] "r"(outptr) - : "v0", "v1", "memory"); -} -#endif /* defined(ARM_COMPUTE_ENABLE_BF16) */ - } // namespace wrapper } // namespace arm_compute #endif /* ARM_COMPUTE_WRAPPER_CVT_H */ |