arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.01192cs.LGcs.AR
收藏

MOHAQ:循环神经网络的多目标硬件感知Quantization

MOHAQ: Multi-Objective Hardware-Aware Quantization of Recurrent Neural Networks

Halmstad University(哈尔姆斯塔德大学);Umeå University(于默奥大学);KTH University(瑞典皇家理工学院)

Nesma M. Rezk, Tomas Nordström, Dimitrios Stathis, Zain Ul-Abdin, Eren Erdal Aksoy, Ahmed Hemani

摘要:

深度学习模型的压缩对于将此类模型部署到边缘设备至关重要。压缩参数的选择可以使用优化算法自动化以满足硬件平台和应用的变化。本文介绍了一种多目标硬件量化方法(MOHAQ),它将硬件效率和推理误差作为混合精度量化的目标。所提出的方法可行地评估候选解决方案,在一个大的搜索空间,依靠两个步骤。首先,后训练量化应用于快速解决方案评估(仅推理搜索)。其次,我们提出了“基于信标的搜索”,重新训练选定的解决方案,并使用它们作为信标,知道再培训对其他解决方案的影响。我们使用一个基于简单递归单元(SRU)的语音识别模型,使用TIMIT数据集,并应用我们的方法在SiLago和Bitfusion平台上运行。我们提供的实验评估表明,SRU可以通过训练后量化压缩到8倍,而不会增加任何显着的误差。在SiLago上,我们发现解决方案实现了97%和86%的最大可能加速和节能,误差略有增加。在Bitfusion上,基于信标的搜索将仅推理搜索的错误增益降低了4.9个百分点。

英文摘要:

The compression of deep learning models is of fundamental importance in deploying such models to edge devices. The selection of compression parameters can be automated to meet changes in the hardware platform and application using optimization algorithms. This article introduces a Multi-Objective Hardware-Aware Quantization (MOHAQ) method, which considers hardware efficiency and inference error as objectives for mixed-precision quantization. The proposed method feasibly evaluates candidate solutions in a large search space by relying on two steps. First, post-training quantization is applied for fast solution evaluation (inference-only search). Second, we propose the "beacon-based search" to retrain selected solutions only and use them as beacons to know the effect of retraining on other solutions. We use a speech recognition model based on Simple Recurrent Unit (SRU) using the TIMIT dataset and apply our method to run on SiLago and Bitfusion platforms. We provide experimental evaluations showing that SRU can be compressed up to 8x by post-training quantization without any significant error increase. On SiLago, we found solutions that achieve 97\% and 86\% of the maximum possible speedup and energy saving, with a minor increase in error. On Bitfusion, beacon-based search reduced the error gain of inference-only search by up to 4.9 percentage points.

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。

↑