Completed
So, we should amortize data movement
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
What Can In-memory Computing Deliver and What Are the Barriers - tinyML Summit 2019
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 The memory wall Separating memory from compute fundamentally raises a communicatio
- 3 So, we should amortize data movement
- 4 In-memory computing (IMC)
- 5 The basic tradeoffs
- 6 IMC as a spatial architecture
- 7 Where does IMC stand today?
- 8 analog computation
- 9 Algorithmic co-design(?)
- 10 programmability
- 11 efficient application mappings
- 12 Path forward: charge-domain analog computin
- 13 2.4Mb, 64-tile IMC
- 14 Programmable IMC
- 15 Bit-scalable mixed-signal compute
- 16 Development board
- 17 Design flow
- 18 Demonstrations
- 19 Conclusions
