GIM (Ghost In the Machine): A Coarse-Grained Reconfigurable Compute-In-Memory Platform for Exploring Machine-Learning Architectures.
Maya BorowiczJames DingWinnie FanZhongqi GaoDavis JacksonAres LuSophia RohlfsenRay SimarPublished in: IPDPS (Workshops) (2024)
Keyphrases
- coarse grained
- fine grained
- machine learning
- multithreading
- protein sequences
- machine learning methods
- single instruction multiple data
- information extraction
- high level
- decision trees
- contact maps
- functional units
- feature selection
- computational biology
- reconfigurable hardware
- bayesian networks
- statistical methods
- shared memory
- hardware implementation
- text classification
- information retrieval systems
- search engine