An Algorithm-Hardware Co-Optimized Framework for Accelerating N: M Sparse Transformers.
Chao FangAojun ZhouZhongfeng WangPublished in: IEEE Trans. Very Large Scale Integr. Syst. (2022)
Keyphrases
- learning algorithm
- improved algorithm
- experimental evaluation
- hardware implementation
- optimal solution
- times faster
- theoretical analysis
- detection algorithm
- worst case
- low cost
- optimization algorithm
- dynamic programming
- graph based algorithm
- theoretical guarantees
- image processing
- image segmentation
- significant improvement
- recognition algorithm
- preprocessing
- matching algorithm
- sparse matrix
- convergence rate
- search space
- k means
- particle swarm optimization
- linear programming
- real time
- np hard
- computational cost