2025-07-24 –, Main Room 2
The IEEE has a working group drafting a standard for Floating-point Arithmetic Formats in Machine Learning. This talk explains one approach to implementing these multi-format microfloat representations. The presentation covers specific implementation approaches adopted and design advantages found with Julia.
The IEEE has a working group to draft a standard for Floating-point arithmetic formats in Machine Learning ( https://standards.ieee.org/ieee/3109/11165/ ). This talk explains one approach to the multi-format implementation while discussing advantages found in using Julia. Reference material is given in a current public report ( https://github.com/P3109/Public/tree/main/Shared%20Reports ).
Julia Innovator