Argonne National Laboratory

Computing, Environment and Life Sciences

HEP-CCE Activities

The HEP-CCE comprises the following four technical teams.

Noise-suppressed calorimeter clusters in a high-jet multiplicity collision event, as seen by the ATLAS detector. (Credit: the ATLAS collaboration.)

Portable Parallelization Strategies for High-Performance Computing Systems

High-energy physics (HEP) experiments have developed millions of lines of code over decades that are optimized to run on traditional x86 CPU systems. The CCE Portable Parallelization Strategies (PPS) team will help define strategies to prioritize codes to parallelize and determine how to parallelize these codes in a portable fashion so that the same code base can run on multiple architectures with few or no changes.

A neutrino-interaction event in the protoDUNE single-phase LArTPC, as reconstructed by Wirecell.

Fine-Grained I/O and Storage on HPC Platforms, including Data Models and Structures

HEP experiments rely on file-based input/output (I/O) and storage to process hundreds of petabytes of data every year. The CCE Fine-Grained I/O and Storage (IOS) team will help optimize I/O performance at scale on U.S. Department of Energy high-performance computing systems by proposing fine-grained parallel I/O and storage solutions. In collaboration with PPS, this team will design data models that map efficiently to memory constructs.

Projected data volumes at the HL-LHC under various scenarios. (credit: the ATLAS collaboration)

Event Generators on High-Performance Computing Systems

Monte Carlo simulation of particle collisions (event generation) will consume a significant fraction of computational resources at CERN’s High-Luminosity Large Hadron Collider. The CCE Event Generators (EG) team will develop, from scratch, a parallel matrix-element generator that runs on new and traditional architecture. This team will coordinate with the HEP Software Foundation EG group and efforts worldwide. In collaboration with PPS, it will explore multiple portable parallelization strategies for that.

A collision event as simulated by the SHERPA event generator (credit: Ben Nachman, LBNL)

Complex Workflows on High-Performance Computing Systems

High-performance computing (HPC) systems and their software stacks are not optimized for complex, dynamic workflows such as cosmology data pipelines and particle physics uncertainty quantification studies. Conversely HEP distributed workflow management systems are not optimized for execution on a single HPC system. The CCE Complex Workflows (CW) team will identify requirements for production and user-focused workflows, components, and execution environments. It will then develop HPC, container, and data scheduling models for improving performance in combination with node-level parallelization.