[anonymoushn]

For branch instructions but not for conditional move instructions, the processor will happily execute the next instruction before the values are actually ready, then invalidate the work it has done later if it turns out retrospectively to have been wrong. This is called branch prediction.

[vlovich123]

Technically my understanding of terminology is that the branch predictor is responsible for determining which branch to take when speculative execution encounters a branch. Speculative execution is the thing that will invalidate work if the branch predictor was wrong.

Also my understanding based on reading this thread is that a conditional move is harder to speculate across because of the data dependency carried across iteration loops, preventing speculation. With a conditional branch, speculation can keep executing the next loop and most of the time the branch predictor will guess correctly how to execute the next iteration for this problem.

[Dylan16807]

I wouldn't say it's harder to speculate the result of a conditional move, more that processors don't do it. Or even stronger, that a conditional move instruction is intentionally opting out of prediction for one reason or another.