Accelerating the execution of the Partition Problem on PYNQ FPGA platform

Pratik Shrestha; Chirag Parikh; Christian Trefftz

doi:10.29007/nkcz

Download PDF Open PDF in browser

Accelerating the execution of the Partition Problem on PYNQ FPGA platform

10 pages•Published: January 24, 2024

Pratik Shrestha, Chirag Parikh and Christian Trefftz

Abstract

Exponential-time algorithms for solving intractable problems are inefficient compared to polynomial-time algorithms for solving tractable problems as execution time for former grows rapidly as problem size increases. A problem is NP-complete when a problem is non-deterministic polynomial (NP) and all other NP-problems are polynomial-time reducible to it. The partition problem is one of the simplest NP- complete problems. Many real-life applications can be modeled as NP-complete problems and it is important for software developers to understand the limitations of existing algorithms that can solve those problems. Solving the partition problem is a time consuming endeavor. Exact algorithms can find solutions, in a reasonable amount of time, only for small instances of these problems. Large instances of NP-hard problems will take so long to solve with exact algorithms, that for practical purposes those large instances should be considered intractable. The execution time required to find a solution to instances of the partition problem is greatly reduced using a Field Programmable Gate Array (FPGA). In this paper, we talk about the use of the PYNQ board in conjunction with an overlay to accelerate the execution of a function that evaluates if a partition is a solution to an instance of the partition problem. In order to assist with the evaluation, four different overlays are created and performance comparison among them using native python is then presented in the paper.

Keyphrases: FPGA, Overlay, Partition problem

In: Krishna Kambhampaty, Gongzhu Hu and Indranil Roy (editors). Proceedings of 36th International Conference on Computer Applications in Industry and Engineering, vol 97, pages 62--71

Links:	https://easychair.org/publications/paper/hkXVW
	https://doi.org/10.29007/nkcz

BibTeX entry

@inproceedings{CAINE2023:Accelerating_execution_of_Partition,
  author    = {Pratik Shrestha and Chirag Parikh and Christian Trefftz},
  title     = {Accelerating the execution of the Partition Problem on PYNQ FPGA platform},
  booktitle = {Proceedings of 36th International Conference on Computer Applications in Industry and Engineering},
  editor    = {Krishna Kambhampaty and Gongzhu Hu and Indranil Roy},
  series    = {EPiC Series in Computing},
  volume    = {97},
  pages     = {62--71},
  year      = {2024},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {https://easychair.org/publications/paper/hkXVW},
  doi       = {10.29007/nkcz}}

Download PDF Open PDF in browser