Update locking names backprop's sequential constraint: a layer cannot update until the full forward and backward passes complete

The synthetic-gradients paper formalizes three locks backpropagation imposes: forward locking (a module can't process until its inputs arrive), update locking (a module can't update until the full forward pass AND the backward pass that depends on it have run), and backward locking (it can't update until the backward pass reaches it). Update locking is the tightest: every weight waits on the entire round trip.

This is the computational cost of the backward pass, where claim-training-inference-compute-asymmetry-mechanism gave the arithmetic cost — the same backward pass that makes training ~3x inference is also what serializes it. Synthetic gradients break the lock by having each layer predict its own incoming gradient, decoupling updates. It sits alongside feedback alignment and Forward-Forward as attacks on backprop's structure, but from the systems/parallelism angle rather than the biological one — the lock is why the backward pass is hard to distribute, which connects the origins cluster to the inference-economics cluster's hardware concerns. See moc-backpropagation-origins, claim-hinton-biological-implausibility-four-objections.