RDNA GPU, codename navi14, including Radeon RX 5500XT/5500/5500M/5500XTB/5300/5300M, Radeon Pro 5500XT/5500M/5300/5300M, Radeon Pro W5500X/W5500/W5500M/W5300M
Name Category Description
hipBLAS sci-libs ROCm BLAS marshalling library
hipCUB sci-libs Wrapper of rocPRIM or CUB for GPU parallel primitives
hipFFT sci-libs CU / ROCM agnostic hip FFT implementation
hipRAND sci-libs CU / ROCM agnostic hip RAND implementation
hipSPARSE sci-libs ROCm SPARSE marshalling library
miopen sci-libs AMD's Machine Intelligence Library
rccl dev-libs ROCm Communication Collectives Library (RCCL)
rocBLAS sci-libs AMD's library for BLAS on ROCm
rocFFT sci-libs Next generation FFT implementation for ROCm
rocPRIM sci-libs HIP parallel primitives for developing performant GPU-accelerated code on ROCm
rocRAND sci-libs Generate pseudo-random and quasi-random numbers
rocSOLVER sci-libs Implementation of a subset of LAPACK functionality on the ROCm platform
rocSPARSE sci-libs Basic Linear Algebra Subroutines for sparse computation
rocThrust sci-libs HIP back-end for the parallel algorithm library Thrust
roctracer dev-util Callback/Activity Library for Performance tracing AMD GPU's
Tensile dev-util Stretching GPU performance for GEMMs and tensor contractions

Thank you!