BWhat changed
Decoupled slow regional data-placement planning from fast job scheduling, combining GPU/data colocation, resource-aware placement and local scheduling across Meta's geo-distributed datacenters.
Scientific scope
Decoupled slow regional data-placement planning from fast job scheduling, combining GPU/data colocation, resource-aware placement and local scheduling across Meta's geo-distributed datacenters. The home-region formulation uses historical usage estimates, soft GPU balancing and hard storage/CPU constraints; home and replica placement are not solved jointly. New jobs may wait for on-demand data movement. External resource assignments, quotas, preemption and freshness policies remain constraints; observed overload reduction is not a universal optimality theorem.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. The home-region formulation uses historical usage estimates, soft GPU balancing and hard storage/CPU constraints; home and replica placement are not solved jointly. New jobs may wait for on-demand data movement. External resource assignments, quotas, preemption and freshness policies remain constraints; observed overload reduction is not a universal optimality theorem.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction