### Abstract

This paper presents a new scheduling approach for high-level synthesis based on a deterministic modified Hopfield model. Our model uses a four dimensional neural network architecture to schedule the operations of a data flow graph (DFG) and maps them to specific functional units. Neural Network-based Scheduling (NNS) is achieved by formulating the scheduling problem in terms of an energy function and by using the motion equation corresponding to the variation of energy. The algorithm searches the scheduling space in parallel and finds the optimal schedule. The main contribution of this work is an efficient parallel scheduling algorithm under time and resource constraints appropriate for implementing on a parallel machine. The algorithm is based on moves in the scheduling space, which correspond to moves towards the equilibrium point (lowest energy state) in the dynamic system space. Neurons' motion equation is the core of this guided movement mechanism and guarantees that the state of the system always converges to the lowest energy state.

Original language | English |
---|---|

Title of host publication | European Design Automation Conference |

Publisher | Publ by IEEE |

Pages | 341-346 |

Number of pages | 6 |

ISBN (Print) | 0818627808 |

Publication status | Published - 1992 |

Externally published | Yes |

Event | European Design Automation Conference -EURO-VHDL '92 - Hamburg, Ger Duration: 1992 Sep 7 → 1992 Sep 10 |

### Other

Other | European Design Automation Conference -EURO-VHDL '92 |
---|---|

City | Hamburg, Ger |

Period | 92/9/7 → 92/9/10 |

### Fingerprint

### ASJC Scopus subject areas

- Engineering(all)

### Cite this

*European Design Automation Conference*(pp. 341-346). Publ by IEEE.

**Neural network based algorithm for the scheduling problem in high-level synthesis.** / Nourani, Mehrdad; Papachristou, Christos; Takefuji, Yoshiyasu.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

*European Design Automation Conference.*Publ by IEEE, pp. 341-346, European Design Automation Conference -EURO-VHDL '92, Hamburg, Ger, 92/9/7.

}

TY - GEN

T1 - Neural network based algorithm for the scheduling problem in high-level synthesis

AU - Nourani, Mehrdad

AU - Papachristou, Christos

AU - Takefuji, Yoshiyasu

PY - 1992

Y1 - 1992

N2 - This paper presents a new scheduling approach for high-level synthesis based on a deterministic modified Hopfield model. Our model uses a four dimensional neural network architecture to schedule the operations of a data flow graph (DFG) and maps them to specific functional units. Neural Network-based Scheduling (NNS) is achieved by formulating the scheduling problem in terms of an energy function and by using the motion equation corresponding to the variation of energy. The algorithm searches the scheduling space in parallel and finds the optimal schedule. The main contribution of this work is an efficient parallel scheduling algorithm under time and resource constraints appropriate for implementing on a parallel machine. The algorithm is based on moves in the scheduling space, which correspond to moves towards the equilibrium point (lowest energy state) in the dynamic system space. Neurons' motion equation is the core of this guided movement mechanism and guarantees that the state of the system always converges to the lowest energy state.

AB - This paper presents a new scheduling approach for high-level synthesis based on a deterministic modified Hopfield model. Our model uses a four dimensional neural network architecture to schedule the operations of a data flow graph (DFG) and maps them to specific functional units. Neural Network-based Scheduling (NNS) is achieved by formulating the scheduling problem in terms of an energy function and by using the motion equation corresponding to the variation of energy. The algorithm searches the scheduling space in parallel and finds the optimal schedule. The main contribution of this work is an efficient parallel scheduling algorithm under time and resource constraints appropriate for implementing on a parallel machine. The algorithm is based on moves in the scheduling space, which correspond to moves towards the equilibrium point (lowest energy state) in the dynamic system space. Neurons' motion equation is the core of this guided movement mechanism and guarantees that the state of the system always converges to the lowest energy state.

UR - http://www.scopus.com/inward/record.url?scp=0027005103&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027005103&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0818627808

SP - 341

EP - 346

BT - European Design Automation Conference

PB - Publ by IEEE

ER -