一种适用于GPU内存限制内核的通用软件系统执行模型
A Versatile Software Systolic Execution Model for GPU Memory-Bound Kernels
摘要：
本文提出了一种通用的高性能执行模型，灵感来自脉动阵列，内存受限的规则内核运行在CUDA使能的GPU。我们制定了一个脉动模型，转移部分和CUDA翘曲原语的计算。我们还采用寄存器文件作为缓存资源，以有效地操作整个模型。我们展示了所提出的模型的有效性和通用性，用于HPC中常见的各种模板内核，以及卷积内核（在深度学习工作负载中越来越重要）。我们的算法优于最先进的模板实现，包括复杂的时间和空间阻塞技术的实现，在两个最新的Nvidia架构：特斯拉V100和P100。对于一般滤波器大小和形状的2D卷积，我们的算法在V100和P100 GPU上的平均速度比Nvidia的NPP快2.5倍。
英文摘要：
This paper proposes a versatile high-performance execution model, inspired by systolic arrays, for memory-bound regular kernels running on CUDA-enabled GPUs. We formulate a systolic model that shifts partial sums by CUDA warp primitives for the computation. We also employ register files as a cache resource in order to operate the entire model efficiently. We demonstrate the effectiveness and versatility of the proposed model for a wide variety of stencil kernels that appear commonly in HPC, and also convolution kernels (increasingly important in deep learning workloads). Our algorithm outperforms the top reported state-of-the-art stencil implementations, including implementations with sophisticated temporal and spatial blocking techniques, on the two latest Nvidia architectures: Tesla V100 and P100. For 2D convolution of general filter sizes and shapes, our algorithm is on average 2.5x faster than Nvidia's NPP on V100 and P100 GPUs.
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。
