Nested loops revisited

Four variants of parallel index nested loop algorithms are compared with the parallel hybrid hash algorithm. The conclusions of experiments both with an analytic model and with an implementation in the Gamma parallel database system are that overall, parallel hybrid hash is the method of choice, but there are cases where nested loops with index wins big enough that systems could profit from implementing both algorithms. The experiments show further that among the nested loop algorithms, one of them, subset nested loops with sorting, clearly dominates.<
>