Class (Tentative) Tirgul (Tentative)
1 Intro - Machine learning CUDA I
2 xNN - CNN, RNN, GNN, etc CUDA II
3 training - the use of CPUs Pytorch + CUDA
4 the use of GPUs Performance and power counters
5 GPU optimizations Pytorch CUDA II
6 Sparsity, pruning and compression Sparse data structures and algorithms
7 Inference Binarization and quantization Libraries for Binarization and quantization on CPU
8 Support for low power Libraries for Binarization and quantization on GPUs
9 Introduction to FPGA and ASIC Setting the FPGA environment PYNQ
10 Binarization and quantization on FPGA Topics for final work
11 Support for GNN - I Running Pytorch examples on FPGA
12 Support for GNN - II FIND on PINQ
13 Put it all together LogicNets on PINQ
1 Intro - Machine learning CUDA I
2 xNN - CNN, RNN, GNN, etc CUDA II
3 training - the use of CPUs Pytorch + CUDA
4 the use of GPUs Performance and power counters
5 GPU optimizations Pytorch CUDA II
6 Sparsity, pruning and compression Sparse data structures and algorithms
7 Inference Binarization and quantization Libraries for Binarization and quantization on CPU
8 Support for low power Libraries for Binarization and quantization on GPUs
9 Introduction to FPGA and ASIC Setting the FPGA environment PYNQ
10 Binarization and quantization on FPGA Topics for final work
11 Support for GNN - I Running Pytorch examples on FPGA
12 Support for GNN - II FIND on PINQ
13 Put it all together LogicNets on PINQ