Opportunistic Computing in GPU Architectures
Opportunistic Computing in GPU Architectures
复制标题
DOI：
10.1145/3307650.3322212
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Ashutosh Pattnaik;Xulong Tang;Onur Kayiran;Adwait Jog;Asit K. Mishra;M. Kandemir;A. Sivasubramaniam;C. Das
中科院分区：
文献类型：
--
作者：
Ashutosh Pattnaik;Xulong Tang;Onur Kayiran;Adwait Jog;Asit K. Mishra;M. Kandemir;A. Sivasubramaniam;C. Das
计算核心和内存层次结构之间的数据传输开销一直是von Neumann架构的持续问题，并且随着许多核心系统的出现，问题才变得更具挑战性。一种减轻此开销的概念强大的方法是使计算更接近数据，称为近数据计算（NDC）。最近，NDC在不同口味的基于CPU的多周中进行了研究，而GPU域很少受到关注。在本文中，我们提出了一种用于GPU架构的新型NDC解决方案，目的是最大程度地减少计算核心和最后级高速缓存（LLC）之间的片上数据传输。为了实现这一目标，我们首先在GPU应用中确定经常发生的负载计算商店指令链。将这些连锁店卸载到更接近数据所在的位置的计算单元时，这些链会大大减少数据移动。我们开发了两种称为LLC计算和Omni-Compute的卸载技术。第一种技术，LLC计算，使用计算硬件来增强LLC，以处理向其卸载的计算。第二种技术（无所事事）采用简单的簿记硬件，使GPU内核能够计算其他GPU内核卸载的说明。我们对9个GPGPU工作负载的实验评估表明，LLC计算技术平均提供了19％的性能提高（IPC）（IPC），11％的表现/WATT改善，与芯片上数据移动相比，芯片数据移动降低了29％基线GPU设计。 Omni计算设计将这些好处分别提高到31％，16％和44％。
Data transfer overhead between computing cores and memory hierarchy has been a persistent issue for von Neumann architectures and the problem has only become more challenging with the emergence of manycore systems. A conceptually powerful approach to mitigate this overhead is to bring the computation closer to data, known as Near Data Computing (NDC). Recently, NDC has been investigated in different flavors for CPU-based multicores, while the GPU domain has received little attention. In this paper, we present a novel NDC solution for GPU architectures with the objective of minimizing on-chip data transfer between the computing cores and Last-Level Cache (LLC). To achieve this, we first identify frequently occurring Load-Compute- Store instruction chains in GPU applications. These chains, when offloaded to a compute unit closer to where the data resides, can significantly reduce data movement. We develop two offloading techniques, called LLC-Compute and Omni- Compute. The first technique, LLC-Compute, augments the LLCs with computational hardware for handling the computation offloaded to them. The second technique (Omni- Compute) employs simple bookkeeping hardware to enable GPU cores to compute instructions offloaded by other GPU cores. Our experimental evaluations on nine GPGPU workloads indicate that the LLC-Compute technique provides, on an average, 19% performance improvement (IPC), 11% per- formance/watt improvement, and 29% reduction in on-chip data movement compared to the baseline GPU design. The Omni-Compute design boosts these benefits to 31%, 16% and 44%, respectively.