solprop.backends.numba_cpu.batch

Execute CPU member stages with one compiled batch update and segmented norms.

Classes

NumbaCpuBatchBackend(members)

Run fixed CPU batches with contiguous member update buffers.

class solprop.backends.numba_cpu.batch.NumbaCpuBatchBackend(members)

Bases: LockstepRunner

Run fixed CPU batches with contiguous member update buffers.

Each member uses its own compiled response, FFT and BLAS policies. Stage evaluation is interleaved; the accepted update traverses every member’s columns in one existing Numba kernel. Error partials are segmented before the unchanged singleton reduction, preserving operation order and member error histories.

Parameters:

memberssequence of solprop.backends.numba_cpu.NumbaCpuBackend

Loaded fibre workspaces with the same field layout, frequency mask and tableau. Material parameters and initial fields may differ.

Raises:

BackendError

If a member is not a compatible Numba CPU fibre problem.

close()

Release member owners and all packed CPU workspace arrays.

helpers = Helpers(name='numba')

memory_ledger()

Count member slices once and include the two additional packing buffers.

Returns:

dict of str to int

Workspace bytes. Member update and partial views partition their backing arrays, so summing their ledgers already counts those allocations once.

metadata()

Record compiled update fusion while retaining each member’s policies.

Returns:

dict

Batch strategy and the specific compiled operation shared across members.