brainevent.jitsmv_p

brainevent.jitsmv_p = <brainevent.XLACustomKernel object>

Low-level XLA custom-kernel primitive for jitsmv.

This XLACustomKernel instance dispatches the JIT scalar connectivity matrix-vector multiplication with floating-point weights operation to registered backends (numba, pallas), using runtime shape/dtype metadata provided by the high-level wrapper.

In this operation, the connectivity matrix has all weights set to a single scalar value, and the input vector contains floating-point values. The operation computes a standard matrix-vector product without event-driven sparsity.

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 jitsmv_p.available_backends(platform), and the default backend can be configured with jitsmv_p.set_default(platform, backend).

See also

jitsmv

High-level user-facing function wrapper.