NVPL BLAS Developer Guide and Reference

NVPL BLAS (NVIDIA Performance Libraries BLAS) is part of NVIDIA Performance Libraries that provides standard Fortran 77 BLAS APIs as well as C (CBLAS).

The library supports various configurations, such as:

• Integer types: lp64, ilp64

• Threading interfaces: sequential, OpenMP-based threading

NVPL BLAS works on any 64-bit Arm based processors with Armv8.1-A or later architecture extension and is specifically optimized for:

• Arm Neoverse V2 based CPUs, such as NVIDIA Grace

• Arm Neoverse V1 based CPUs, such as Amazon (AWS) Graviton3

To learn more about the library, please check:

• Programming Model
• API Reference
• Packaging
• Acknowledgments
• Release Notes