Vector array functions in AOCL-LibM provide a flexible interface for processing variable-length arrays of floating-point numbers. Unlike fixed-size vector functions (AVX, AVX2, AVX512), array functions can handle arrays of arbitrary length, making them ideal for data processing scenarios where the data size is not known at compile time.
These functions are prefixed with amd_vrsa_ for single precision arrays and
amd_vrda_ for double precision arrays.
Note
Vector array functions are currently under development. This section will be expanded as more functions become available.