Markus Bantle, Pierre Bayerl, Stefan Funken, Michael N. Thoma
{"title":"集成图形处理器上的OpenCL雷达信号处理","authors":"Markus Bantle, Pierre Bayerl, Stefan Funken, Michael N. Thoma","doi":"10.23919/IRS.2018.8448262","DOIUrl":null,"url":null,"abstract":"In this work we investigate the use of OpenCL to implement radar signal processing algorithms on integrated graphic chips of Intel processors. Hereby a typical radar signal processing chain consisting of pulse compression, Doppler filtering, CFAR detection, and plot extraction is considered. The full processing chain is implemented and optimized with OpenCL and benchmarked extensively. Our results show that in general GPUs are well suited for radar signal processing. The usage of integrated graphics chips has the potential to add significant processing power of the magnitude of a typical CPU. With a middle class dedicated GPU we could achieve a significant speed-up of all signal processing algorithms as compared to CPUs or integrated graphics chips.","PeriodicalId":436201,"journal":{"name":"2018 19th International Radar Symposium (IRS)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Radar Signal Processing with OpenCL on Integrated Graphic Processors\",\"authors\":\"Markus Bantle, Pierre Bayerl, Stefan Funken, Michael N. Thoma\",\"doi\":\"10.23919/IRS.2018.8448262\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this work we investigate the use of OpenCL to implement radar signal processing algorithms on integrated graphic chips of Intel processors. Hereby a typical radar signal processing chain consisting of pulse compression, Doppler filtering, CFAR detection, and plot extraction is considered. The full processing chain is implemented and optimized with OpenCL and benchmarked extensively. Our results show that in general GPUs are well suited for radar signal processing. The usage of integrated graphics chips has the potential to add significant processing power of the magnitude of a typical CPU. With a middle class dedicated GPU we could achieve a significant speed-up of all signal processing algorithms as compared to CPUs or integrated graphics chips.\",\"PeriodicalId\":436201,\"journal\":{\"name\":\"2018 19th International Radar Symposium (IRS)\",\"volume\":\"79 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 19th International Radar Symposium (IRS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.23919/IRS.2018.8448262\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 19th International Radar Symposium (IRS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.23919/IRS.2018.8448262","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Radar Signal Processing with OpenCL on Integrated Graphic Processors
In this work we investigate the use of OpenCL to implement radar signal processing algorithms on integrated graphic chips of Intel processors. Hereby a typical radar signal processing chain consisting of pulse compression, Doppler filtering, CFAR detection, and plot extraction is considered. The full processing chain is implemented and optimized with OpenCL and benchmarked extensively. Our results show that in general GPUs are well suited for radar signal processing. The usage of integrated graphics chips has the potential to add significant processing power of the magnitude of a typical CPU. With a middle class dedicated GPU we could achieve a significant speed-up of all signal processing algorithms as compared to CPUs or integrated graphics chips.