使用2.5M模拟相变存储器器件在软件等效精度下推断长短期记忆网络

2019 Symposium on VLSI Technology Pub Date : 2019-06-09 DOI:10.23919/VLSIT.2019.8776519

H. Tsai, S. Ambrogio, C. Mackin, P. Narayanan, R. Shelby, K. Rocki, A. Chen, G. Burr

{"title":"使用2.5M模拟相变存储器器件在软件等效精度下推断长短期记忆网络","authors":"H. Tsai, S. Ambrogio, C. Mackin, P. Narayanan, R. Shelby, K. Rocki, A. Chen, G. Burr","doi":"10.23919/VLSIT.2019.8776519","DOIUrl":null,"url":null,"abstract":"We report accuracy for forward inference of long-short-term-memory (LSTM) networks using weights programmed into the conductances of $> 2.5\\text{M}$ phase-change memory (PCM) devices. We demonstrate strategies for software weight-mapping and programming of hardware analog conductances that provide accurate weight programming despite significant device variability. Inference accuracy very close to software-model baselines is achieved on several language modeling tasks.","PeriodicalId":6752,"journal":{"name":"2019 Symposium on VLSI Technology","volume":"47 31 1","pages":"T82-T83"},"PeriodicalIF":0.0000,"publicationDate":"2019-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"26","resultStr":"{\"title\":\"Inference of Long-Short Term Memory networks at software-equivalent accuracy using 2.5M analog Phase Change Memory devices\",\"authors\":\"H. Tsai, S. Ambrogio, C. Mackin, P. Narayanan, R. Shelby, K. Rocki, A. Chen, G. Burr\",\"doi\":\"10.23919/VLSIT.2019.8776519\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We report accuracy for forward inference of long-short-term-memory (LSTM) networks using weights programmed into the conductances of $> 2.5\\\\text{M}$ phase-change memory (PCM) devices. We demonstrate strategies for software weight-mapping and programming of hardware analog conductances that provide accurate weight programming despite significant device variability. Inference accuracy very close to software-model baselines is achieved on several language modeling tasks.\",\"PeriodicalId\":6752,\"journal\":{\"name\":\"2019 Symposium on VLSI Technology\",\"volume\":\"47 31 1\",\"pages\":\"T82-T83\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-06-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"26\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 Symposium on VLSI Technology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.23919/VLSIT.2019.8776519\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 Symposium on VLSI Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.23919/VLSIT.2019.8776519","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 26

摘要

我们报告了长短期记忆(LSTM)网络前向推理的准确性，使用将权重编程到$> 2.5\text{M}$相变记忆(PCM)器件的电导中。我们演示了硬件模拟电导的软件权重映射和编程策略，这些策略可以在显著的器件可变性下提供准确的权重编程。在几个语言建模任务上，实现了非常接近软件模型基线的推理精度。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Inference of Long-Short Term Memory networks at software-equivalent accuracy using 2.5M analog Phase Change Memory devices

We report accuracy for forward inference of long-short-term-memory (LSTM) networks using weights programmed into the conductances of $> 2.5\text{M}$ phase-change memory (PCM) devices. We demonstrate strategies for software weight-mapping and programming of hardware analog conductances that provide accurate weight programming despite significant device variability. Inference accuracy very close to software-model baselines is achieved on several language modeling tasks.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2019 Symposium on VLSI Technology

自引率

0.00%

发文量