brainevent.binary_fcnmm_p

brainevent.binary_fcnmm_p = <brainevent.XLACustomKernel object>

Low-level XLA custom-kernel primitive for binary_fcnmm.

This XLACustomKernel instance dispatches the binary (event-driven) fixed-connection matrix-matrix multiplication operation to registered backends (numba, pallas), using runtime shape/dtype metadata provided by the high-level wrapper.

Fixed-connection format stores connectivity where each neuron has a fixed number of incoming or outgoing connections. The event-driven formulation only processes active (spiking) entries, skipping zero entries for efficiency.

Beyond backend dispatch, the primitive stores JAX transformation bindings (JVP, transpose, batching, and call registration) so the operation integrates correctly with jit, vmap, and autodiff.

Available backends can be queried with binary_fcnmm_p.available_backends(platform), and the default backend can be configured with binary_fcnmm_p.set_default(platform, backend).

See also

binary_fcnmm

High-level user-facing function wrapper.