GATE: GPU-Accelerated Traffic Engineering for the WAN

TL;DR

GATE is a GPU-accelerated traffic engineering solution that provides near-optimal routing solutions significantly faster than existing methods, scalable to large networks with guaranteed convergence.

Contribution

It introduces a GPU-compatible decomposition approach for traffic engineering that ensures fast, scalable, and provably convergent solutions for large networks.

Findings

GATE achieves 5-10x faster solutions than state-of-the-art methods.

It converges to the optimal solution with theoretical guarantees.

GATE scales efficiently with network size and supports various fairness objectives.

Abstract

Traffic engineering (TE) has become a crucial tool for enforcing routing policy and maintaining operational efficiency in large networks. Existing TE solutions pick an objective function to optimize, aiming to balance (i) allocating traffic optimally with (ii) reacting quickly to demand changes and disruption events. However, as the scale of networks grows, the runtime of the existing optimal solution becomes infeasibly large. The alternative - approximate solvers - result in costly inefficiencies. We present GPU-Accelerated Traffic Engineering (GATE), which achieves the best of both worlds: enabling fast TE runtimes through a highly-parallelizable GPU-compatible decomposition, while iteratively converging to the provably optimal solution. GATE unlocks a unique set of desirable properties: it becomes increasingly parallelizable with network size, supports a wide spectrum of fairness objectives, and offers theoretically guaranteed convergence to the optimal solution and near-optimal convergence within a bounded time. We evaluate GATE on production traces from two large cloud WANs, and show that GATE achieves near-optimal solutions 5-10x faster than state-of-the-art.