Published June 27, 2023
| Version v1
Report
Open
Implementation of CUDA kernels with cppPosit and BFLOAT16
Authors/Creators
Description
This report details adding CUDA support to the cppPosit library for floating point numbers representation and comparing its performance against BFLOAT16 and IEEE floats. It's been developed in 2022 at the university of Pisa.
Files
seai_2022_r4.pdf
Files
(758.8 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:c467c5a0b8da0fae952c163cbc3a8226
|
758.8 kB | Preview Download |