Category: Resources
Scalable MCM DNN Accelerator (NVidia)
Scalable Multi-Chip-Module-based Deep Neural Network Accelerator
Computer Architecture Formulas
MCM GPUs (NVidia whitepaper)
Multi-Chip-Module GPUsfor Continued Performance Scalability
Latency Hiding on GPUs (whitepaper)
Understanding Latency Hiding on GPUs
AMD E3 Presentation Slides
All slides from AMD’s E3 presentation
TAGE Predictor (whitepaper)
A case for (partially) TAgged GEometric history length branch prediction
The Accelerator Wall (Whitepaper)
http://parallel.princeton.edu/papers/wall-hpca19.pdf