A Tabu Search-Based Memetic Algorithm for Hardware/Software Partitioning

Algorithm 1

List schedule algorithm [16, 22].

(1) Initialization. Set two attributes for every node, start and finish, which are used for recording the node’s

  starting time and finishing time. Choose all nodes without data dependency from the node set and put them

  into a ready queue. Choose one software node from the queue to be executed by CPU, and all hardware nodes

  to be executed at the same time. Set 0 as the values of the start attributes for the running nodes. Set the sum

  of the executing time and the communication time as the values of the finish attributes. If there is a software

  node being executed by CPU, set CPU = BUSY.

(2) repeat

(3)   Select the node with the minimal 𝑓𝑖𝑛𝑖𝑠ℎ time from the ready queue, mark it as 𝑖.

(4)   Remove node 𝑖 from the queue. If 𝑖 is a software node, set 𝐶𝑃𝑈=𝐹𝑅𝐸𝐸.

(5)   If 𝐶𝑃𝑈=𝐹𝑅𝐸𝐸, choose one software node 𝑗 from the queue to execute and set 𝐶𝑃𝑈=𝐵𝑈𝑆𝑌.

  Set 𝑠𝑡𝑎𝑟𝑡[𝑗]=𝑓𝑖𝑛𝑖𝑠ℎ[𝑖], 𝑓𝑖𝑛𝑖𝑠ℎ[𝑗]=𝑠𝑡𝑎𝑟𝑡[𝑗]+𝑡𝑠_𝑗+𝑐𝑜𝑚𝑚[𝑗], where 𝑐𝑜𝑚𝑚[𝑗] denotes the communication

  time of node 𝑗 with other nodes.

(6) Choose all hardware nodes to execute concurrently. Set their 𝑠𝑡𝑎𝑟𝑡 and 𝑓𝑖𝑛𝑖𝑠ℎ attributes as in Line (5).

(7) until The ready queue is empty

(8) return Choose the maximal 𝑓𝑖𝑛𝑖𝑠ℎ time of all the nodes as the system executing time, denoted as 𝑇.