Floating-Point Compiler: Increasing Performance With Fewer Resources

Showing new levels of high-performance, high-density, IEEE754-compliant floating-point applications in FPGAs is the focus of this white paper. A new tool is introduced that will allow 100 percent of the floating-point capability of the FPGA device to be used. Combined with the rich DSP resources and advanced routing fabrics of the most recent Altera FPGAs, unprecedented performance numbers are shown, including 40 Giga Floating-Point Operations Per second (GFLOP) double-precision and 90 GFLOP single-precision on 65-nm FPGAs. In addition, with higher system performance, the more optimal balancing of resources will leave sufficient logic and other resources to support full-featured applications based around these new floating-point datapaths.