Enable reproducible math functions across vector extensions with Arm Performance Libraries
Introduction
Understand numerical reproducibility in floating-point math
Explore where reproducibility is critical
Enable reproducibility in Libamath
Verify reproducible results across scalar, Neon, and SVE
Next Steps
Enable reproducible math functions across vector extensions with Arm Performance Libraries
Who is this for?
This is an introductory topic for developers who want to produce reproducible code across vector extensions using math functions in Libamath, a component of Arm Performance Libraries.
What will you learn?
After completing this Learning Path, you'll be able to perform the following tasks:
- Explain what numerical reproducibility means in numerical software
- Describe generic applications of numerical reproducibility in the industry
- Describe how reproducibility is defined and implemented in Libamath
- Enable and use reproducible Libamath functions in real applications
Prerequisites
Before starting, you'll need the following prerequisites:
- An Arm computer running Linux with Arm Performance Libraries version 26.01 or newer installed
- A C compiler such as GCC or Clang installed