rocFFT precision support

This topic lists the data type support for the rocFFT library on AMD GPUs.

This page lists the data types supported by the library itself and does not indicate hardware support. A type listed here is only usable if the GPU architecture also supports it; otherwise it is unsupported. For data type support across the other ROCm libraries and by GPU architecture, see the Data types and precision support page.

Supported data types

rocFFT computes transforms on real and complex data in the precisions listed in the following table. The transform precision is selected through the rocfft_precision enumeration when creating a plan. For the complete API, see the API reference.

Icon	Definition
✅	Fully supported as both an input and output type.
⚠️	Partially supported as an input or output type.

Data types not listed in the table below are not supported.

Data type	Support
float16	✅
float32	✅
float64	✅
cfloat16	✅
cfloat32	✅
cfloat64	✅