Newton: A DRAM-maker's Accelerator-in-Memory (AiM) Architecture for Machine Learning.
Mingxuan HeChoungki SongIlkon KimChunseok JeongSeho KimIl ParkMithuna ThottethodiT. N. VijaykumarPublished in: MICRO (2020)
Keyphrases
- machine learning
- main memory
- memory subsystem
- embedded dram
- dynamic random access memory
- memory hierarchy
- level parallelism
- random access memory
- management system
- real time
- knowledge acquisition
- software architecture
- memory access
- memory usage
- text classification
- support vector machine
- interior point methods
- data mining
- computer vision
- decision trees
- data structure
- computer science
- external memory
- database management systems
- memory space
- parallel implementation
- text mining
- input output
- past experience
- processing elements
- memory management
- associative memory
- reinforcement learning
- feature selection
- machine learning algorithms