Delegate PolyChebMulxKernel
One fused chebmulx call (see DirectILKernelGenerator's PolyAlgebra file header): NumPy's
prd for a series of n ≥ 2 terms of one dtype, computed in one forward pass.
public delegate void PolyChebMulxKernel(byte* c, long n, byte* prd)
Parameters
cbyte*c[0]; the
nterms are contiguous. It may beprd + itemsize— the series already converted into the result's slots 1 … n: every element is read before the pass writes its slot.nlongTerms (≥ 2; the one-term series is the calculus mulx kernel's).
prdbyte*prd[0]:
n+ 1 contiguous elements, every one written.