diff options
author | Antonio Sanchez <cantonios@google.com> | 2020-12-02 14:00:57 -0800 |
---|---|---|
committer | Antonio Sanchez <cantonios@google.com> | 2020-12-04 10:16:29 -0800 |
commit | e2f21465fea76a80966f12a20d0be36597f19b44 (patch) | |
tree | 1ae9b0e3ae489b028902166a343f796d196fde82 /Eigen/src/Core/arch/Default/Half.h | |
parent | 305b8bd2777bda99f65791468f305b76021bf579 (diff) |
Special function implementations for half/bfloat16 packets.
Current implementations fail to consider half-float packets, only
half-float scalars. Added specializations for packets on AVX, AVX512 and
NEON. Added tests to `special_packetmath`.
The current `special_functions` tests would fail for half and bfloat16 due to
lack of precision. The NEON tests also fail with precision issues and
due to different handling of `sqrt(inf)`, so special functions bessel, ndtri
have been disabled.
Tested with AVX, AVX512.
Diffstat (limited to 'Eigen/src/Core/arch/Default/Half.h')
-rw-r--r-- | Eigen/src/Core/arch/Default/Half.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/Eigen/src/Core/arch/Default/Half.h b/Eigen/src/Core/arch/Default/Half.h index b9a8a46aa..76156c416 100644 --- a/Eigen/src/Core/arch/Default/Half.h +++ b/Eigen/src/Core/arch/Default/Half.h @@ -58,7 +58,7 @@ #define F16_PACKET_FUNCTION(PACKET_F, PACKET_F16, METHOD) \ template <> \ - EIGEN_DEFINE_FUNCTION_ALLOWING_MULTIPLE_DEFINITIONS EIGEN_UNUSED \ + EIGEN_STRONG_INLINE EIGEN_DEVICE_FUNC EIGEN_UNUSED \ PACKET_F16 METHOD<PACKET_F16>(const PACKET_F16& _x) { \ return float2half(METHOD<PACKET_F>(half2float(_x))); \ } |