이론 관련/컴퓨터 관련
fp16
구차니
2021. 5. 10. 20:08
float가 대개 32bit
double이 대개 64bit 인데
fp16이라고 16bit짜리 half precision float point라는게 존재하네..
They can express values in the range ±65,504, with the minimum value above 1 being 1 + 1/1024.
In the IEEE 754-2008 standard, the 16-bit base-2 format is referred to as binary16. It is intended for storage of floating-point values in applications where higher precision is not essential for performing arithmetic computations.
[링크 : https://en.wikipedia.org/wiki/Half-precision_floating-point_format]