Sat-based mapping of data-flow graphs onto coarse-grained reconfigurable arrays
Y Miyasaka, M Fujita, A Mishchenko… - VLSI-SoC: Design Trends …, 2021 - Springer
Recently, it has been common to use parallel processing for machine learning. CGRAs are
drawing attention in terms of reconfigurability and high performance. We propose a method
to map data-flow graphs onto CGRAs by SAT solving. The proposed method can perform the
automatic transformation which changes the order of operations in data-flow graphs to
obtain more efficient schedules. It also accommodates mapping of multi-node operations
like MAC operation. We have solved mapping problems of matrix-vector multiplication. In our …
drawing attention in terms of reconfigurability and high performance. We propose a method
to map data-flow graphs onto CGRAs by SAT solving. The proposed method can perform the
automatic transformation which changes the order of operations in data-flow graphs to
obtain more efficient schedules. It also accommodates mapping of multi-node operations
like MAC operation. We have solved mapping problems of matrix-vector multiplication. In our …
SAT-Based Mapping of Data-Flow Graphs onto Coarse-Grained Reconfigurable Arrays
J Wawrzynek - VLSI-SoC: Design Trends: 28th IFIP WG 10.5 …, 2021 - books.google.com
Recently, it has been common to use parallel processing for machine learning. CGRAs are
drawing attention in terms of reconfigurability and high performance. We propose a method
to map data-flow graphs onto CGRAs by SAT solving. The proposed method can perform the
automatic transformation which changes the order of operations in data-flow graphs to
obtain more efficient schedules. It also accommodates mapping of multi-node operations
like MAC operation. We have solved mapping problems of matrix-vector multiplication. In our …
drawing attention in terms of reconfigurability and high performance. We propose a method
to map data-flow graphs onto CGRAs by SAT solving. The proposed method can perform the
automatic transformation which changes the order of operations in data-flow graphs to
obtain more efficient schedules. It also accommodates mapping of multi-node operations
like MAC operation. We have solved mapping problems of matrix-vector multiplication. In our …
Showing the best results for this search. See all results