Frontier supercomputer's simulation offers groundbreaking insights into cosmic evolution and dark matter.
Exascale computing revolutionises cosmic, AI, and climate research
Photo Credit: Phys.org
A groundbreaking cosmic simulation has been conducted using one of the world's most powerful supercomputers, offering an unprecedented level of detail in modeling the observable universe. The project utilised advanced computational techniques to incorporate dark matter, gas, and plasma movements rather than relying solely on gravitational forces. The scale and complexity of this simulation mark a significant step forward in understanding cosmic evolution and large-scale structures.
According to the study conducted under the U.S. Department of Energy's (DOE) Exascale Computing Project, the Frontier supercomputer at Oak Ridge National Laboratory (ORNL) executed the simulation using the Hardware/Hybrid Accelerated Cosmology Code (HACC). The Exascale Computing Project, a $1.8 billion initiative, requires scientific applications to achieve speeds up to 50 times faster than earlier benchmarks. Frontier, surpassing these expectations, processed data nearly 300 times faster than previous cosmological simulations.
As reported by Live Science, Hydrodynamic cosmology, which factors in dark matter and energy alongside conventional gravitational interactions, was central to this project. The increased computational demands were met by leveraging 9,000 computing nodes, each equipped with AMD Instinct MI250X graphics processors, enabling detailed simulations at an unprecedented resolution.
Frontier ranks as the second most powerful supercomputer globally, reaching a peak performance of 1.4 exaFLOPS. Systems classified as ‘exascale' perform beyond 999 petaFLOPS, making them capable of handling massive datasets and complex calculations with unparalleled speed. The only machine surpassing Frontier is El Capitan, which is expected to reach 1.7 exaFLOPS.
Beyond cosmological research, exascale computing has been instrumental in advancing climate science, material engineering, and artificial intelligence. In 2023, the Simple Cloud-Resolving E3SM Atmosphere Model (SCREAM) was developed using Frontier, providing high-resolution climate data crucial for atmospheric and environmental studies. Similar computational advancements have facilitated material science research, aiding in the design of stronger and more resilient substances for various industries.
Scientists anticipate that supercomputers like Frontier will play a crucial role in accelerating AI research, refining machine learning models, and enhancing predictive analytics in climate change studies. The ability to process vast datasets rapidly is expected to lead to significant advancements across multiple scientific domains
Catch the latest from the Consumer Electronics Show on Gadgets 360, at our CES 2026 hub.