arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1211.3056cs.MScs.DCcs.NAmath.NA
收藏

GPU加速的正确舍入初等函数生成

GPU-accelerated generation of correctly-rounded elementary functions

UPMC Univ Paris 06(巴黎第六大学);CNRS UMR 7606, LIP6(法国国家科学研究中心第7606联合研究实验室,LIP6)

Pierre Fortin, Mourad Gouicem, Stef Graillat

AI总结:

针对IEEE 754-2008标准中初等函数正确舍入所需的Table Maker's Dilemma计算耗时问题,提出基于GPU的Lefèvre算法并行化方案,通过改进控制流和混合CPU-GPU部署,实现最高53.4倍单GPU加速和7.1倍多核CPU加速。

摘要:

IEEE 754-2008标准推荐对某些初等函数进行正确舍入。这需要解决Table Maker's Dilemma,该问题涉及大量的CPU计算时间。本文考虑在图形处理单元(GPU)上加速此类计算,即Lefèvre算法,GPU是一种具有部分SIMD执行(单指令多数据)的大规模并行架构。我们首先利用连分数的概念对Lefèvre难舍入参数搜索进行了分析。然后,我们提出了一种新的并行搜索算法,由于其更规则的控制流,在GPU上效率更高。我们还提出了一种高效的混合CPU-GPU部署方案,用于生成Lefèvre算法所需的多项式逼近。最终,我们在单个GPU上相对于顺序CPU执行实现了最高53.4倍的总体加速,相对于多核CPU实现了最高7.1倍的加速,从而能够更快地解决双精度格式下的Table Maker's Dilemma。

英文摘要:

The IEEE 754-2008 standard recommends the correct rounding of some elementary functions. This requires to solve the Table Maker's Dilemma which implies a huge amount of CPU computation time. We consider in this paper accelerating such computations, namely Lefe'vre algorithm on Graphics Processing Units (GPUs) which are massively parallel architectures with a partial SIMD execution (Single Instruction Multiple Data). We first propose an analysis of the Lefèvre hard-to-round argument search using the concept of continued fractions. We then propose a new parallel search algorithm much more efficient on GPU thanks to its more regular control flow. We also present an efficient hybrid CPU-GPU deployment of the generation of the polynomial approximations required in Lefèvre algorithm. In the end, we manage to obtain overall speedups up to 53.4x on one GPU over a sequential CPU execution, and up to 7.1x over a multi-core CPU, which enable a much faster solving of the Table Maker's Dilemma for the double precision format.

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。

↑