A Systematic Approach for Acceleration of Matrix-Vector Operations in CGRA through Algorithm-Architecture Co-Design.
Farhad MerchantTarun VatwaniAnupam ChattopadhyaySoumyendu RahaS. K. NandyRanjani NarayanRainer LeupersPublished in: VLSI Design (2019)
Keyphrases
- times faster
- dynamic programming
- cost function
- learning algorithm
- experimental evaluation
- optimal solution
- objective function
- sparse matrix
- high accuracy
- real time
- theoretical analysis
- preprocessing
- k means
- significant improvement
- np hard
- hardware implementation
- clustering method
- tree structure
- linear programming
- matrix multiplication
- parallel implementation
- optimization algorithm
- segmentation algorithm
- data structure
- similarity measure
- computational complexity