search

XiaoMi / nnlib

Fork of https://source.codeaurora.org/quic/hexagon_nn/nnlib
BSD 3-Clause Clear License
54 stars 11 forks source link

What is d32 format? #11

Open apivovarov opened 4 years ago

apivovarov commented 4 years ago

Sorry for posting my question as an issue

Many quantized hexagon_nn ops has _d32 variant. What is D32 format and how it is different from "flat"? e.g.

QuantizedAdd_8p8to8 - elementwisely adds Input A and Input B together. (flat format)
0: Input A data (quint8 tensor)
1: Input B data (quint8 tensor)
...
0: Output data (quint8 tensor)

QuantizedAdd_8p8to8_d32 - Elementwise Add; inputs and output are in d32 format
0: Input A data (qint8)
1: Input B data (qint8)
...
0: Output data (quint8)
lee-bin commented 4 years ago

These two files clarify the format, d32_diagram.png, d32.txt.