diff options
| author | Georgios Pinitas <georgios.pinitas@arm.com> | 2020-02-26 09:58:13 +0000 |
|---|---|---|
| committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2020-03-05 15:15:15 +0000 |
| commit | e8291acc1d9e89c9274d31f0d5bb4779eb95588c (patch) | |
| tree | 5a0fef36d6daabe387174e55b60de54557c75291 /arm_compute/core/NEON/wrapper/intrinsics/cvt.h | |
| parent | aa85cdf22802cb892d7fa422ca505a43d84adb38 (diff) | |
| download | ComputeLibrary-e8291acc1d9e89c9274d31f0d5bb4779eb95588c.tar.gz | |
COMPMID-3152: Initial Bfloat16 support
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: Ie6959e37e13731c86b2ee29392a99a293450a1b4
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2824
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Diffstat (limited to 'arm_compute/core/NEON/wrapper/intrinsics/cvt.h')
| -rw-r--r-- | arm_compute/core/NEON/wrapper/intrinsics/cvt.h | 19 |
1 files changed, 19 insertions, 0 deletions
diff --git a/arm_compute/core/NEON/wrapper/intrinsics/cvt.h b/arm_compute/core/NEON/wrapper/intrinsics/cvt.h index 1f22e09a11..5ea9a5dedd 100644 --- a/arm_compute/core/NEON/wrapper/intrinsics/cvt.h +++ b/arm_compute/core/NEON/wrapper/intrinsics/cvt.h @@ -56,6 +56,25 @@ vcvt(const float32x4_t &a) return vcvtq_s32_f32(a); } +#if defined(__ARM_FEATURE_BF16_VECTOR_ARITHMETIC) || defined(ARM_COMPUTE_FORCE_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_FEATURE_BF16_VECTOR_ARITHMETIC) || defined(ARM_COMPUTE_FORCE_BF16) */ + } // namespace wrapper } // namespace arm_compute #endif /* ARM_COMPUTE_WRAPPER_CVT_H */ |