Mix-GEMM: An efficient HW-SW Architecture for Mixed-Precision Quantized Deep Neural Networks Inference on Edge Devices.
Enrico ReggianiAlessandro PappalardoMax DoblasMiquel MoretóMauro OlivieriOsman Sabri UnsalAdrián CristalPublished in: HPCA (2023)
Keyphrases
- hw sw
- hardware software
- neural network
- embedded systems
- design methodology
- hardware and software
- multi layer
- hardware software co design
- fuzzy neural network
- pattern recognition
- back propagation
- artificial neural networks
- real time
- multilayer perceptron
- fuzzy logic
- resource management
- query processing
- user interface
- case study