Red-Blue Pebbling with Multiple Processors: Time, Communication and Memory Trade-offs

TL;DR

This paper extends the red-blue pebble game to multiple processors with individual fast memories, analyzing the complex trade-offs between computation, communication, and memory constraints in parallel workloads.

Contribution

It introduces a multiprocessor pebbling model that captures workload balancing, communication, and memory trade-offs, providing new bounds and complexity results.

Findings

Established upper and lower bounds on pebbling costs.

Analyzed a greedy pebbling strategy.

Proved inapproximability of optimal I/O and total costs.

Abstract

The well-studied red-blue pebble game models the execution of an arbitrary computational DAG by a single processor over a two-level memory hierarchy. We present a natural generalization to a multiprocessor setting where each processor has its own limited fast memory, and all processors share unlimited slow memory. To our knowledge, this is the first thorough study that combines pebbling and DAG scheduling problems, capturing the computation of general workloads on multiple processors with memory constraints and communication costs. Our pebbling model enables us to analyze trade-offs between workload balancing, communication and memory limitations, and it captures real-world factors such as superlinear speedups due to parallelization. Our results include upper and lower bounds on the pebbling cost, an analysis of a greedy pebbling strategy, and an extension of NP-hardness results for specific DAG classes from simpler models. For our main technical contribution, we show two inapproximability results that already hold for the long-standing problem of standard red-blue pebbling: (i) the optimal I/O cost cannot be approximated to any finite factor, and (ii) the optimal total cost (I/O+computation) can only be approximated to a limited constant factor, i.e., it does not allow for a polynomial-time approximation scheme. These results also carry over naturally to our multiprocessor pebbling model.