LUTein: Dense-Sparse Bit-Slice Architecture With Radix-4 LUT-Based Slice-Tensor Processing Units.

Dongseok Im Hoi-Jun Yoo

Published in: HPCA (2024)

Keyphrases

dimensionality reduction
processing units
high dimensional
parallel computing
data formats
computing systems
lookup table
parallel programming
bit parallel
memory access
multiple types
floating point
heterogeneous systems
parallel processing
supervised learning
scheduling problem
real time