arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1603.02526cs.DCcs.MSmath.OC
收藏

在因子图上测试ADMM的细粒度并行性

Testing fine-grained parallelism for the ADMM on a factor-graph

Ning Hao, AmirReza Oghbaee, Mohammad Rostami, Nate Derbinsky, José Bento

摘要:

目前正在努力开发应用分布式计算资源来解决大型问题或减少解决这些问题的时间的工具。在这种情况下,交替方向乘法(ADMM)出现作为一种方法,可以利用分布式资源,如双上升方法,并具有增广拉格朗日方法的鲁棒性和改进的收敛性。使用多核加速ADMM的传统方法是特定于问题的,并且通常需要多核编程。相比之下,我们提出了一个问题独立的计划,加速ADMM,不需要用户编写任何并行代码。我们表明,该计划,ADMM的解释作为一个消息传递算法的因子图,可以自动利用细粒度并行在GPU和共享内存的多核计算机,并实现显着的加速在不同的应用领域,如组合优化,机器学习,和最优控制。具体来说,我们在ADMM的串行优化C版本上使用GPU获得了10 - 18倍的加速,使用多个CPU核心获得了5 - 9倍的加速,这与现有GPU加速库报告的典型加速相似,包括cuFFT(19倍),cuBLAS(17倍)和cuRAND(8倍)。

英文摘要:

There is an ongoing effort to develop tools that apply distributed computational resources to tackle large problems or reduce the time to solve them. In this context, the Alternating Direction Method of Multipliers (ADMM) arises as a method that can exploit distributed resources like the dual ascent method and has the robustness and improved convergence of the augmented Lagrangian method. Traditional approaches to accelerate the ADMM using multiple cores are problem-specific and often require multi-core programming. By contrast, we propose a problem-independent scheme of accelerating the ADMM that does not require the user to write any parallel code. We show that this scheme, an interpretation of the ADMM as a message-passing algorithm on a factor-graph, can automatically exploit fine-grained parallelism both in GPUs and shared-memory multi-core computers and achieves significant speedup in such diverse application domains as combinatorial optimization, machine learning, and optimal control. Specifically, we obtain 10-18x speedup using a GPU, and 5-9x using multiple CPU cores, over a serial, optimized C-version of the ADMM, which is similar to the typical speedup reported for existing GPU-accelerated libraries, including cuFFT (19x), cuBLAS (17x), and cuRAND (8x).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑