MemMAP: Compact and Generalizable Meta-LSTM Models for Memory Access Prediction
MemMAP: Compact and Generalizable Meta-LSTM Models for Memory Access Prediction
复制标题
DOI：
10.1007/978-3-030-47436-2_5
复制
发表时间：
2020-04-17
期刊：
影响因子：
--
通讯作者：
Prasanna VK
中科院分区：
文献类型：
--
作者：
Srivastava A;Wang TY;Zhang P;De Rose CA;Kannan R;Prasanna VK
随着大数据的兴起，通过GPU，TPU和异质体系结构提高计算功率的努力已大大努力。结果，许多应用程序是内存绑定的，即，它们被数据从主内存到计算单元的移动所瓶颈。解决此问题的一种方法是通过数据预取，依赖于对内存访问的准确预测。尽管最近的深度学习模型在序列预测问题上表现良好，但在模型大小和推理潜伏期方面，它们对数据预取的实用性太大。在这里，我们提出了非常紧凑的LSTM模型，可以高精度预测下一个内存访问。先前基于LSTM的访问预测工作使用了更多参数的顺序，并为每个应用程序开发了一个模型（Trace）。尽管每个应用程序的一个（专业）模型可以更准确，但这不是可扩展的方法。相比之下，我们的模型可以通过以运行时的几个重新培训步骤来交换专业化，以预测一类应用程序，以获得更概括的紧凑型元模型。我们在13个基准应用上进行的实验表明，三种紧凑的元模型可以使用大多数应用中的几批再培训获得接近专业模型的准确性。
With the rise of Big Data, there has been a significant effort in increasing compute power through GPUs, TPUs, and heterogeneous architectures. As a result, many applications are memory bound, i.e., they are bottlenecked by the movement of data from main memory to compute units. One way to address this issue is through data prefetching, which relies on accurate prediction of memory accesses. While recent deep learning models have performed well on sequence prediction problems, they are far too heavy in terms of model size and inference latency to be practical for data prefetching. Here, we propose extremely compact LSTM models that can predict the next memory access with high accuracy. Prior LSTM based work on access prediction has used orders of magnitude more parameters and developed one model for each application (trace). While one (specialized) model per application can result in more accuracy, it is not a scalable approach. In contrast, our models can predict for a class of applications by trading off specialization at the cost of few retraining steps at runtime, for a more generalizable compact meta-model. Our experiments on 13 benchmark applications demonstrate that three compact meta-models can obtain accuracy close to specialized models using few batches of retraining for majority of the applications.
影响因子：
--
作者：
Luk, CK;Cohn, R;Hazelwood, K
通讯作者：
Hazelwood, K
影响因子：
2.9
作者：
Gers, FA;Schmidhuber, J;Cummins, F
通讯作者：
Cummins, F