Published June 27, 2023 | Version v1
Report Open

Implementation of CUDA kernels with cppPosit and BFLOAT16

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