首页> 外文会议>IEEE symposium on FPGAs for custom computing machines >Field programmable gate array based reconfigurable preprocessor
【24h】

Field programmable gate array based reconfigurable preprocessor

机译:基于现场可编程门阵列的可重新配置预处理器

获取原文

摘要

Custom hardware implementations of preprocessors are seldom reusable, flexible enough to allow algorithm exploration or quickly realized. The Configurable Hardware Algorithm Mappable Preprocessor (CHAMP) technology is a solution to these problems. Recent developments in FPGA hardware and software have made a reconfigurable preprocessor with custom hardware performance but generic hardware flexibility possible. The key advancements are larger, faster RAM and electrically erasable devices, routers with deadline timers, and synthesis tools which can work with user-definable macros. Ongoing work in the areas of partitioning, synthesis, placement, packaging and compilation will make reconfigurable preprocessors more powerful. The present CHAMP implementation is based on Xilinx FPGAs. Its architecture consists of multiple reconfigurable processing elements connected through both a ring network and a global crossbar network. It is packaged as a VME 6U/spl times/160 slave board with two high-speed reconfigurable parallel interfaces. In order to allow development at the algorithm level while retaining preprocessor performance, off-the-shelf development tools have been integrated with a custom library of macros as part of the CHAMP design process. As a verification of the CHAMP technology, an advanced IR missile warning application was mapped onto the CHAMP architecture achieving greater than 1 billion operations/sec of real-time throughput while utilizing 75% of the CHAMP board's processing resources.
机译:预处理器的自定义硬件实现很少可重用,足够灵活,以允许算法探索或快速实现。可配置的硬件算法可映射预处理器(CHAMP)技术是解决这些问题的解决方案。 FPGA硬件和软件的最新进程使具有自定义硬件性能的可重新配置的预处理器,但通用硬件灵活性可能。关键进步更大,RAM和电动可擦除设备,具有截止日期定时器的路由器,以及可以使用用户可定义宏的合成工具。正在进行的划分,合成,放置,包装和编译领域的工作将使可重构的预处理器更强大。目前的冠军实施基于Xilinx FPGA。其架构包括通过环网络和全局横杆网络连接的多个可重新配置的处理元件。它被包装为VME 6U / SPL时间/ 160从电路板,具有两个高速可重新配置的并行接口。为了允许在算法级别的开发,同时保留预处理器性能,从头开发的开发工具已与宏自定义库集成,作为宏观设计过程的一部分。作为校正冠军技术的核实,先进的IR导弹警告申请旨在映射到冠军架构,在利用75%的校准委员会的加工资源的同时实现大于10亿运营/秒的冠军架构。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号