Some examples to illustrate polyhederal schedule representations.
5 min read
Representing Fudan University, my teammates and I took part in the National Student Computer System Capability Challenge (NSCSCC) a.k.a. "Loongson Cup". It is a national contest where teams from top universities like Tsinghua University, University of Science and Technology of China compete to build a best CPU. After over a month of work, our "Vanilla" CPU won Second Prize for great performance and compatibility. It was the first time for a team from Fudan to take part in the contest.
2 min read
Keystone is an open framework for building customizable trusted execution environments (TEEs) based on RISC-V. We tried to implement it on a customizable RISC-V SoC seeking potentials for acceleration and enhanced security.
1 min read
Deep learning compilers rely heavily on manual written templates to schedule computations of deep learning kernels. Leveraging polyhedral models, the scheduling can be done automatically. The polyhedral model is a powerful abstraction for compiler optimization, turning scheduling problems into integer linear programs (ILPs). However, these ILPs may not be solvable due to scalability issues.
4 min read
"Network Planning with Deep Reinforcement Learning" vs "Solving Mixed Integer Programs Using Neural Networks"
2 min read