{"title":"RFT在GPU上的并行实现","authors":"Zhe-ran Shang, Xiansi Tan, Zhiguo Qu, Hong Wang","doi":"10.1109/RADAR.2016.8059450","DOIUrl":null,"url":null,"abstract":"Radon Fourier Transform (RFT) is a kind of generalized MTD, which can integrate along the track of targets. However, it is not easy for RFT to be engineered due to the calculating burden. Aiming at this problem, a kind of RFT parallelization strategy is put forward based on GPU and CUDA. Through experimental verification, the execution time of RFT on GPU platform proved a great speedup compared with that of RFT and fast RFT on CPU. In addition, it suggests in the results that the execution time can be as fast as MTD when RFT results are saved in global memory.","PeriodicalId":245387,"journal":{"name":"2016 CIE International Conference on Radar (RADAR)","volume":"161 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A parallel implementation of RFT on GPU\",\"authors\":\"Zhe-ran Shang, Xiansi Tan, Zhiguo Qu, Hong Wang\",\"doi\":\"10.1109/RADAR.2016.8059450\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Radon Fourier Transform (RFT) is a kind of generalized MTD, which can integrate along the track of targets. However, it is not easy for RFT to be engineered due to the calculating burden. Aiming at this problem, a kind of RFT parallelization strategy is put forward based on GPU and CUDA. Through experimental verification, the execution time of RFT on GPU platform proved a great speedup compared with that of RFT and fast RFT on CPU. In addition, it suggests in the results that the execution time can be as fast as MTD when RFT results are saved in global memory.\",\"PeriodicalId\":245387,\"journal\":{\"name\":\"2016 CIE International Conference on Radar (RADAR)\",\"volume\":\"161 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 CIE International Conference on Radar (RADAR)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/RADAR.2016.8059450\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 CIE International Conference on Radar (RADAR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/RADAR.2016.8059450","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Radon Fourier Transform (RFT) is a kind of generalized MTD, which can integrate along the track of targets. However, it is not easy for RFT to be engineered due to the calculating burden. Aiming at this problem, a kind of RFT parallelization strategy is put forward based on GPU and CUDA. Through experimental verification, the execution time of RFT on GPU platform proved a great speedup compared with that of RFT and fast RFT on CPU. In addition, it suggests in the results that the execution time can be as fast as MTD when RFT results are saved in global memory.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
