Achieving One TeraFLOPS with 28-nm FPGAs
ثبت نشده
چکیده
Due to recent technological developments, high-performance floating-point signal processing can, for the first time, be easily achieved using FPGAs. To date, virtually all FPGA-based signal processing has been implemented using fixed-point operations. This white paper describes how floating-point technology on FPGAs is not only practical now, but that processing rates of one trillion floating-point operations per second (teraFLOPS) are feasible—and on a single FPGA die.
منابع مشابه
Achieving SerDes Interoperability on Altera's 28 nm FPGAs Using Introspect ESP
Introspect Technology has implemented its award-winning Introspect ESP embedded signal integrity analyzer on Altera’s high-end 28 nm transceiver FPGAs. The result was a gamechanging ability to achieve link optimization and interoperability on complex system boards containing a multitude of SerDes links. This white paper describes the various Introspect and Altera® technologies involved and illu...
متن کاملLowering Power at 28 nm with Xilinx 7 Series FPGAs
www.xilinx.com 1 © Copyright 2011–2012 Xilinx, Inc. XILINX, the Xilinx logo, Virtex, Spartan, ISE, and other designated brands included herein are trademarks of Xilinx in the United States and other countries. PCI, PCIe and PCI Express are trademarks of PCI-SIG and used under license. All other trademarks are the property of their respective owners. This white paper describes several aspects of...
متن کاملReducing Total System Cost with Low-Power 28 nm FPGAs
When building systems for high-volume applications, it is very important to keep costs in check. There are several dimensions that affect total cost of ownership beyond the price per part. These include the power demands of the silicon, total bill of materials (BOM) cost, and the productivity of the engineers who design and test the system. It is important to choose an FPGA vendor that has cons...
متن کاملOptimizing Performance on Linux Clusters Using Advanced Communication Protocols: How 10+ Teraflops Was Achieved on a 8.6 Teraflops Linpack-Rated Linux Cluster
Advancements in high-performance networks (Quadrics, Infiniband or Myrinet) continue to improve the efficiency of modern clusters. However, the average application efficiency is as small fraction of the peak as the system’s efficiency. This paper describes techniques for optimizing application performance on Linux clusters using Remote Memory Access communication protocols. The effectiveness of...
متن کاملEnhancing Robust SEU Mitigation with 28-nm FPGAs
Systems designed with FPGAs benefit from significant improvements over ASICS, such as rapid-process technology scaling and design innovation, which permit the use of FPGAs in high-availability, high-reliability, and safety-critical systems. However, along with technology scaling come other effects such as increased susceptibility to soft errors that previously could be ignored. These soft error...
متن کامل