Jarkko M. Vatjus-Anttila, T. Koskela, Seamus Hickey
{"title":"基于渲染复杂度的移动GPU功耗模型","authors":"Jarkko M. Vatjus-Anttila, T. Koskela, Seamus Hickey","doi":"10.1109/NGMAST.2013.45","DOIUrl":null,"url":null,"abstract":"This paper presents a mathematical model for predicting power consumption of a mobile device when it is rendering 3D graphics. The model is based on 3D primitives (triangles, render batches, texels), and hence is hardware agnostic. With the model, a complexity of any given 3D scene can be predicted already at a production phase without access to the actual target hardware. This paper describes how the power consumption model is derived. The model is verified with measurements of real-world content and hardware. With the given hardware, 3D data and given verification scenarios, the model is able to predict the total power consumption with an error ranging from 0.3% to 3.2%.","PeriodicalId":369374,"journal":{"name":"2013 Seventh International Conference on Next Generation Mobile Apps, Services and Technologies","volume":" 43","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"15","resultStr":"{\"title\":\"Power Consumption Model of a Mobile GPU Based on Rendering Complexity\",\"authors\":\"Jarkko M. Vatjus-Anttila, T. Koskela, Seamus Hickey\",\"doi\":\"10.1109/NGMAST.2013.45\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents a mathematical model for predicting power consumption of a mobile device when it is rendering 3D graphics. The model is based on 3D primitives (triangles, render batches, texels), and hence is hardware agnostic. With the model, a complexity of any given 3D scene can be predicted already at a production phase without access to the actual target hardware. This paper describes how the power consumption model is derived. The model is verified with measurements of real-world content and hardware. With the given hardware, 3D data and given verification scenarios, the model is able to predict the total power consumption with an error ranging from 0.3% to 3.2%.\",\"PeriodicalId\":369374,\"journal\":{\"name\":\"2013 Seventh International Conference on Next Generation Mobile Apps, Services and Technologies\",\"volume\":\" 43\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2013-09-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"15\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2013 Seventh International Conference on Next Generation Mobile Apps, Services and Technologies\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/NGMAST.2013.45\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 Seventh International Conference on Next Generation Mobile Apps, Services and Technologies","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NGMAST.2013.45","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Power Consumption Model of a Mobile GPU Based on Rendering Complexity
This paper presents a mathematical model for predicting power consumption of a mobile device when it is rendering 3D graphics. The model is based on 3D primitives (triangles, render batches, texels), and hence is hardware agnostic. With the model, a complexity of any given 3D scene can be predicted already at a production phase without access to the actual target hardware. This paper describes how the power consumption model is derived. The model is verified with measurements of real-world content and hardware. With the given hardware, 3D data and given verification scenarios, the model is able to predict the total power consumption with an error ranging from 0.3% to 3.2%.