void MMALIB_LINALG_matrixTranspose_ixX_oxX_perfEst(const MMALIB_kernelHandle handle, const MMALIB_bufParams2D_t *bufParamsIn, const MMALIB_bufParams2D_t *bufParamsOut, const MMALIB_LINALG_matrixTranspose_ixX_oxX_InitArgs *pKerInitArgs, uint64_t *idealCycles, uint64_t *archCycles, uint64_t *estCycles)
This is a utility function that gives an estimate of the cycles consumed for the kernel execution.