Scaling the semidefinite program solver SDPB

TL;DR

This paper improves the SDPB semidefinite program solver's performance and scalability using Elemental and MPI, enabling it to handle larger problems in conformal bootstrap research efficiently.

Contribution

The paper introduces a new version of SDPB with enhanced scalability and performance for large-scale semidefinite programming in conformal bootstrap applications.

Findings

SDPB now runs efficiently on multiple nodes with hundreds of cores.

Performance improvements enable larger conformal bootstrap problems to be solved.

Demonstrated on 3d Ising CFT and O(2) Model problems.

Abstract

We present enhancements to SDPB, an open source, parallelized, arbitrary precision semidefinite program solver designed for the conformal bootstrap. The main enhancement is significantly improved performance and scalability using the Elemental library and MPI. The result is a new version of SDPB that runs on multiple nodes with hundreds of cores with excellent scaling, making it practical to solve larger problems. We demonstrate performance on a moderate-size problem in the 3d Ising CFT and a much larger problem in the $O(2)$ Model.