Why aren't out of order CPUs troublesome?

Question

i\'ve recently learned about out-of-order execution CPUs in this link https://en.wikipedia.org/wiki/Out-of-order_execution

There is something that i can\'t quite und

Answer 1

@paul-a-clayton already gave a great answer. I would like to mention one thing more.

Earlier out-of-order architectures were notoriously troublesome. The fundamental problem was that they couldn't guarantee precise interrupts. This changed in the late 80s/early 90s due to the solutions proposed in Smith & Pleszkun's seminal paper. They introduced the idea of a reorder buffer which allows instructions to issue out of order but commit in order.

Answer 2

In an out-of-order processor, the instructions are executed out-of-order but committed in order. This means that externally visible state becomes visible in order. Writes to memory (including I/O operations) are buffered locally so that they can be released to the external memory system in order, similarly register results are stored locally using register renaming. This allows the local processor to use the early speculative values without violating externally visible ordering. On incorrect speculation, a rollback mechanism is used to restore state back to a previous known-valid state.

Note that technically commitment of results to processor-core-external state does not have to be in order as long as the out-of-order result is non-speculative and does not violate ordering guarantees. With weak memory consistency models, this could (in theory) allow values to become externally visible out-of-order. (I/O is required to be in-order, so the print example would still be required to commit in order.) Furthermore, if other cores know that values are speculative in nature or order, the values could be made externally visible out-of-order (again, in theory) and consumers of the values would rollback on incorrect speculation. (This is extending "externally visible" from external to the single processor core to external to some larger system component which is aware of speculation and supports rollback.)

(In very impractical theory, extending speculative realization to the human computer interface would be possible if the definition of the interface allowed such glitches (i.e., the human corrects for wrongly speculated values and ordering). However, since humans are even slower than most I/O devices (speculations would be resolved on a shorter time scale than is significant) and such an extension of speculation would be extremely complex and generally undesirable, it is unlikely ever to be broadly used.)