SEGGER releases Floating-Point Library for RISC-V
SEGGER's stand-alone Floating-Point Library is now extended by an assembly-optimized variant for RISC-V.
The floating-point library contains the complete set of arithmetic functions, hand coded and fully optimized in assembly language for RISC-V. The complete set of high-level mathematical functions is written in C, and uses advanced algorithms to maximize performance.
All functionality is fully verified, for both single and double precision operations.
The RISC-V variant, like the variant for ARM, is optimized for both high speed and small code size. The balance between size and speed can be configured at library build time. The SEGGER Floating-Point Library for RISC-V is much smaller than equivalent open-source libraries while achieving up to 100 times the performance on some operations.
For details on what makes a thoughtfully designed runtime library different from a run-of-the-mill runtime library, refer to SEGGER Runtime Library webpage: https://www.segger.com/runtime-library
For more information on the SEGGER Floating-Point Library see https://www.segger.com/floating-point-library
For performance data see https://wiki.segger.com/SEGGER_Floating-Point_Library
To experience it, download Embedded Studio (Windows, Linux and macOS): https://www.segger.com/downloads/embedded-studio