Flexfloat DL Training Framework
From iis-projects
Contents
Short Description
So far, we have implemented inference of various smaller networks on our PULP-based systems ([pulp-nn]). The data-intensive training of DNN was too memory-hungry to be implemented on our systems. Our latest architecture concept called Manticore includes 4096 snitch cores, is chiplet-based and includes HBM2 memory (see Image).
Recently, industry and academia have started exploring the required computational precision for training. Many state-of-the-art training hardware platforms support by now not only 64-bit and 32-bit floating-point formats, but also 16-bit floating-point formats (binary16 by IEEE and brainfloat). Recent work proposes various training formats such as 8-bit floats.
Status: Available
- Looking for 1 Semester/Master student
- Contact: Gianna Paulin, Tim Fischer
Prerequisites
- Machine Learning
- Python
- C
Prerequisites
- Machine Learning
- Python
- C
Character
- 25% Theory
- 75% Implementation