Nested data-parallelism on the gpu
Nested data-parallelism on the gpu
复制标题
GPU 上的嵌套数据并行性
DOI：
10.1145/2364527.2364563
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
John H. Reppy
中科院分区：
文献类型：
--
作者：
Lars Bergstrom;John H. Reppy
图形处理单元（GPU）提供的内存带宽和算术性能远远大于CPU上可用的性能，但是由于其单一指令 - 元素 - data（SIMD）体系结构，它们很难编程。到目前为止，大多数已移植到GPU的程序都使用传统的数据级并行性，仅执行均匀操作的操作。 NESL是一种一阶功能语言，旨在允许程序员为宽矢量并行计算机编写不规则平行程序（例如平行分隔和串联算法）。本文介绍了我们的NESL实施港口以在GPU上运行的港口，并提供了嵌套数据并行性（NDP）的经验证据，在GPU上嵌套了大大优于基于CPU的实现和匹配或匹配或击败仅支持平行平行性的较新的GPU语言。尽管我们的性能与手工调整的CUDA程序的性能不符，但我们认为NESL的符号简洁性值得损失。这项工作提供了直接支持GPU上NDP的第一语言实现。
Graphics processing units (GPUs) provide both memory bandwidth and arithmetic performance far greater than that available on CPUs but, because of their Single-Instruction-Multiple-Data (SIMD) architecture, they are hard to program. Most of the programs ported to GPUs thus far use traditional data-level parallelism, performing only operations that operate uniformly over vectors. NESL is a first-order functional language that was designed to allow programmers to write irregular-parallel programs - such as parallel divide-and-conquer algorithms - for wide-vector parallel computers. This paper presents our port of the NESL implementation to work on GPUs and provides empirical evidence that nested data-parallelism (NDP) on GPUs significantly outperforms CPU-based implementations and matches or beats newer GPU languages that support only flat parallelism. While our performance does not match that of hand-tuned CUDA programs, we argue that the notational conciseness of NESL is worth the loss in performance. This work provides the first language implementation that directly supports NDP on a GPU.