Accelerating BLAS on Custom Architecture through Algorithm-Architecture Co-design.
Farhad MerchantTarun VatwaniAnupam ChattopadhyaySoumyendu RahaS. K. NandyRanjani NarayanPublished in: CoRR (2016)
Keyphrases
- detection algorithm
- learning algorithm
- hardware implementation
- preprocessing
- computational complexity
- vlsi architecture
- management system
- significant improvement
- dynamic programming
- experimental evaluation
- times faster
- domain specific
- classification algorithm
- optimization algorithm
- hardware architecture
- associative memory
- convex hull
- software architecture
- clustering method
- pipeline architecture
- computationally efficient
- expectation maximization
- computational cost
- optimal solution
- objective function
- segmentation algorithm
- general purpose
- probabilistic model
- improved algorithm
- np hard
- vlsi implementation
- neural network