Shapes and flattening

Shapes and flattening
复制标题

形状和扁平化

DOI:
10.1145/3412932.3412946
复制
发表时间:
2019
期刊:
IFL '19: Proceedings of the 31st Symposium on Implementation and Application of Functional Languages
影响因子:
--
通讯作者:
Wingerter, Joe
Wingerter, Joe
中科院分区:
--
文献类型:
--
作者:
Reppy, John;Wingerter, Joe

文献摘要

参考文献

相似文献

Nesl是一种一阶函数式语言,具有apply-to-each构造和其他并行原语,支持不规则嵌套数据并行(NDP)算法的表达。为了编译Nesl,Blelloch和其他人开发了一种全局扁平化转换,该转换将不规则的NDP代码映射为适合在SIMD或SIMT架构(例如GPU)上执行的规则的扁平数据并行(FDP)代码。虽然扁平化解决了将不规则并行映射为规则模型的问题,但它需要显著的额外优化来产生高性能代码。Nessie是Nesl的一个编译器,它生成CUDA代码,以便在Nvidia GPU上运行。Nessie编译器依赖于一个相当复杂的形状分析,该分析是对由扁平化转换产生的FDP代码执行的。形状分析在编译器中起着关键作用,因为它是融合优化,智能内核调度和其他优化的使能器。在本文中,我们提出了一种新的方法来解决Nesl的形状分析问题,该方法既易于实现,又能提供更好的形状信息。其核心思想是分析程序的NDP表示,然后通过平坦化变换来保持形状信息。
Nesl is a first-order functional language with an apply-to-each construct and other parallel primitives that enables the expression of irregular nested data-parallel (NDP) algorithms. To compile Nesl, Blelloch and others developed a global flattening transformation that maps irregular NDP code into regular flat data parallel (FDP) code suitable for executing on SIMD or SIMT architectures, such as GPUs.While flattening solves the problem of mapping irregular parallelism into a regular model, it requires significant additional optimizations to produce performant code. Nessie is a compiler for Nesl that generates CUDA code for running on Nvidia GPUs. The Nessie compiler relies on a fairly complicatedshape analysisthat is performed on the FDP code produced by the flattening transformation. Shape analysis plays a key rôle in the compiler as it is the enabler of fusion optimizations, smart kernel scheduling, and other optimizations.In this paper, we present a new approach to the shape analysis problem for Nesl that is both simpler to implement and provides better quality shape information. The key idea is to analyze the NDP representation of the program and then preserve shape information through the flattening transformation.
GPU 上的嵌套数据并行性
DOI: 10.1145/2364527.2364563
发表时间: 2012
期刊: Proceedings of the 17th ACM SIGPLAN international conference on Functional programming
影响因子: --
作者:
Lars Bergstrom;John H. Reppy
通讯作者: John H. Reppy
Haskell 中的规则、形状多态、并行数组
DOI: 10.1145/1863543.1863582
发表时间: 2010
期刊: Proceedings of the 18th ACM SIGPLAN international conference on Functional programming
影响因子: --
作者:
G. Keller;M. Chakravarty;Roman Leshchinskiy;S. Jones;B. Lippmeier
通讯作者: B. Lippmeier
DOI: 10.1145/2364506.2364512
发表时间: 2013
期刊: Statistical science : a review journal of the Institute of Mathematical Statistics
影响因子: --
作者:
G. Keller;M. Chakravarty;Roman Leshchinskiy;B. Lippmeier;S. Jones
通讯作者: S. Jones
DOI: 10.14279/depositonce-1367
发表时间: 2006
期刊: Proceedings of the 17th ACM SIGPLAN international conference on Functional programming
影响因子: --
作者:
Roman Leshchinskiy
通讯作者: Roman Leshchinskiy
将面向集合的语言编译到大规模并行计算机上
DOI: 10.1109/fmpc.1988.47500
发表时间: 1988
期刊: Proceedings., 2nd Symposium on the Frontiers of Massively Parallel Computation
影响因子: --
作者:
G. Blelloch;G. Sabot
通讯作者: G. Sabot