Sunil Puranik, Mahesh Barve, Dhaval Shah, Sharad Sinha, R. Patrikar, Swapnil Rodi
{"title":"基于高级合成流的键值存储在证券交易系统中的应用","authors":"Sunil Puranik, Mahesh Barve, Dhaval Shah, Sharad Sinha, R. Patrikar, Swapnil Rodi","doi":"10.1109/iCCECE49321.2020.9231158","DOIUrl":null,"url":null,"abstract":"Key-value Store (KVS) is one of the most important components in trading system for performing search operations. High Level Synthesis (HLS) provides a new flow for design of Field Programmable Gate Array (FPGA) systems. We describe a novel low latency, high throughput, memory efficient KVS block designed using conventional Verilog flow as well as High Level Synthesis flow and targeted to FPGA technology. We compare these two flows for designing KVS. Substantial advantage in gained in terms of productivity using HLS. The time for implementing in HLS is just 18% as compared to Verilog flow though the resource utilization in case of hand coded Verilog is better. The design shows promising performance numbers indicating that more complex FPGA systems could be designed using HLS.","PeriodicalId":413847,"journal":{"name":"2020 International Conference on Computing, Electronics & Communications Engineering (iCCECE)","volume":"3 4","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Key-Value Store using High Level Synthesis Flow for Securities Trading System\",\"authors\":\"Sunil Puranik, Mahesh Barve, Dhaval Shah, Sharad Sinha, R. Patrikar, Swapnil Rodi\",\"doi\":\"10.1109/iCCECE49321.2020.9231158\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Key-value Store (KVS) is one of the most important components in trading system for performing search operations. High Level Synthesis (HLS) provides a new flow for design of Field Programmable Gate Array (FPGA) systems. We describe a novel low latency, high throughput, memory efficient KVS block designed using conventional Verilog flow as well as High Level Synthesis flow and targeted to FPGA technology. We compare these two flows for designing KVS. Substantial advantage in gained in terms of productivity using HLS. The time for implementing in HLS is just 18% as compared to Verilog flow though the resource utilization in case of hand coded Verilog is better. The design shows promising performance numbers indicating that more complex FPGA systems could be designed using HLS.\",\"PeriodicalId\":413847,\"journal\":{\"name\":\"2020 International Conference on Computing, Electronics & Communications Engineering (iCCECE)\",\"volume\":\"3 4\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-08-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 International Conference on Computing, Electronics & Communications Engineering (iCCECE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/iCCECE49321.2020.9231158\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 International Conference on Computing, Electronics & Communications Engineering (iCCECE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/iCCECE49321.2020.9231158","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Key-Value Store using High Level Synthesis Flow for Securities Trading System
Key-value Store (KVS) is one of the most important components in trading system for performing search operations. High Level Synthesis (HLS) provides a new flow for design of Field Programmable Gate Array (FPGA) systems. We describe a novel low latency, high throughput, memory efficient KVS block designed using conventional Verilog flow as well as High Level Synthesis flow and targeted to FPGA technology. We compare these two flows for designing KVS. Substantial advantage in gained in terms of productivity using HLS. The time for implementing in HLS is just 18% as compared to Verilog flow though the resource utilization in case of hand coded Verilog is better. The design shows promising performance numbers indicating that more complex FPGA systems could be designed using HLS.