Compiling
Zilu Wang, Steve Lantz
Cornell Center for Advanced Computing
10/2026 (original)
Horizon is the flagship of the NSF Leadership-Class Computing Facility (LCCF), provided through The University of Texas at Austin's Texas Advanced Computing Center (TACC). It is intended to be the largest academic supercomputer that is available for open research in the United States. Horizon, like its precursor Vista, is targeted towards scientific computing projects that require highly capable resources for AI and other HPC applications. It accordingly features NVIDIA "superchips" that closely couple CPUs with GPUs.
This topic covers how to compile and link your code for execution on Horizon. It will focus initially on codes that are intended for Horizon's "Grace Blackwell" nodes. Since these nodes include GPUs, you should first peruse this topic, continue on to the GPU Integration topic.
Objectives
After you complete this topic, you should be able to:
- Explain how to build an executable file from source code
- Show how to build either a serial or parallel code from the command line
- Identify the major MPI implementations used on Horizon
- Explain how to determine MPI implementation and compiler compatibility
Prerequisites
Horizon is the centerpiece of the NSF Leadership-Class Computing Facility at TACC, so its prospective users are already likely to have a high degree of familiarity and experience with HPC and parallel computing. The pace of this roadmap is meant to be relatively brisk, for that reason.
With that being understood, there are no formal prerequisites for this Virtual Workshop roadmap. A working knowledge of Linux is recommended; if you need more preparation in Linux, try working through the Linux roadmap first.
CVW material development is supported by NSF OAC awards 1854828, 2321040, 2323116 (UT Austin) and 2005506 (Indiana University)