cuPDLP.jl: A GPU Implementation of Restarted Primal-Dual Hybrid Gradient for Linear Programming in Julia
arxiv(2023)
摘要
In this paper, we provide an affirmative answer to the long-standing
question: Are GPUs useful in solving linear programming? We present cuPDLP.jl,
a GPU implementation of restarted primal-dual hybrid gradient (PDHG) for
solving linear programming (LP). We show that this prototype implementation in
Julia has comparable numerical performance on standard LP benchmark sets as
Gurobi, a highly optimized implementation of the simplex and interior-point
methods. Furthermore, we present the superior performance of cuPDLP.jl with its
CPU counterpart. This demonstrates the power of using GPUs in the optimization
solvers.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要