01-05-2021, 10:53 AM
Good question.
When you have combined operations (i.e. Multiply and Accumulate or Dot Product), you could either truncate/round after each (sub)operation or you could allow larger bit-widths in the intermediate levels and then truncate/round at the end. Especially with shorter bit-widths, the difference in overall accuracy actually justifies the slightly larger internal multipliers.
When you have combined operations (i.e. Multiply and Accumulate or Dot Product), you could either truncate/round after each (sub)operation or you could allow larger bit-widths in the intermediate levels and then truncate/round at the end. Especially with shorter bit-widths, the difference in overall accuracy actually justifies the slightly larger internal multipliers.
Visit pulp-platform.org and follow us on twitter @pulp_platform