Keywords : floating-point arithmetic, software library, single precision, addition, multiplication, division, square root, VLIW processor.
FLIP: Floating-point Library for Integer Processors
FLIP is a C library for the software support of single precision floating-point arithmetic on processors without floating-point hardware units such as VLIW (Very Large Instruction Word) or DSP (Digital Signal Processor) processors for embedded applications. The current target architecture is the VLIW ST200 family from STMicroelectronics. This research project is funded by Région Rhône-Alpes.
The library provides the five basic operations: addition, subtraction, multiplication, division and square-root for the single-precision IEEE 754 FP format. It also provides some running modes with relaxed characteristics: no subnormal numbers nor restricted rounding modes for instance. The latest version (Flip-0.2) also includes the following optimized additional operators: square, FMA, reciprocal and square root reciprocal.
Status: Beta release (Flip-0.2) / Target: VLIW processors (ST200 family from STMicroelectronics)/ License: LGPL / OS: Linux, Windows / Programming Language: C / URL: http://lipforge.ens-lyon.fr/www/flip