Customisable Architectures for the Set Covering Problem

Add to your list(s) Download to your calendar using vCal

• Liucheng Guo (Imperial College)
• Tuesday 11 June 2013, 11:00-12:00
• Level 9 Mahanakorn Lab., EE Dept..

If you have a question about this talk, please contact nobody.

This talk has been canceled/deleted

We have proposed novel customisable streaming architectures for the NP-hard set covering problem. Our approach covers both greedy and genetic algorithms, supporting coarse-grain parallelism and deep pipelines while allowing trade-offs between performance and resource usage. Experiments targeting Maxeler systems show that our FPGA -based designs are more effective than the corresponding multicore software versions. The speed up of the greedy algorithm exceeds 250 times, and that of the genetic algorithm exceeds 60 times. Meanwhile, our implementations are more flexible than other FPGA solutions, allowing users to customise parameters at run time without recompilation.

This talk is part of the CAS Talks series.

This talk is included in these lists:

This talk is not included in any other list

Note that ex-directory lists are not shown.