dzheng

Aha, that makes sense, thanks!

I agree that the performance benefits of such stack allocation (over heap allocation) aren't quite clear in practice.

I feel the bigger win of delimited cont./closure-based AD approaches is that they can model the control flow of reverse-mode AD without AD-specific code transformations. Delimited cont. is especially great at making things modular: each differentiable function performs primal computation, calls the callback with primal result, then performs adjoint computation.

Could you please elaborate on what exactly enables stack allocation of intermediate values?

Is it a direct result of the semantics of delimited continuations? (perhaps because closures are passed as parameters and don't capture variables)

Or is it enabled via staging or optimizations?