CAMBRIDGE, Mass and TOKYO, April 14, 2026 (GLOBE NEWSWIRE) — Matlantis today announced the integration of the NVIDIA ALCHEMI Toolkit into its platform to deliver unprecedented computational throughput for industrial materials simulation.
This new milestone builds on a strong foundation of technical collaboration and synergy between the two companies. Matlantis has previously integrated NVIDIA Warp-optimized kernels into its simulation pipeline, including critical components such as neighbor list construction and DFT-D3 dispersion corrections. These integrations have significantly reduced computational overhead, achieving up to 10x speed improvement in key atomistic calculations.
LightPFP: Scaling Simulation to Industrial Demands (available in mid-April): LightPFP, Matlantis’ lightweight potential for large-scale simulations, integrates with the NVIDIA ALCHEMI Toolkit-Ops. To ensure more flexible resource allocation and highly stable operations, LightPFP has transitioned to a server-based architecture that can be seamlessly invoked from standard notebook environments. While communication overhead is a common bottleneck in such distributed configurations, Matlantis successfully mitigated this challenge by replacing the neighborhood list construction process during inference with the NVIDIA ALCHEMI Toolkit-Ops.
Future Roadmap: PFP Integration: Looking ahead, Matlantis is also planning the integration of its flagship Universal Machine-Learning Interatomic Potential (uMLIP), PFP, with the NVIDIA ALCHEMI Toolkit. This upcoming development aims to further power both small-scale research and large-scale industrial materials design, bridging the gap with unparalleled GPU efficiency.
“Our continued collaboration with NVIDIA represents our commitment to providing the most advanced tools for material developers,” said Masateru Kawaguchi, VP of Product Department, Matlantis. “With LightPFP, followed by our plans for the full PFP potential, we’re enabling customers to accelerate their R&D cycles while maintaining the highest level of accuracy and performance in the industry.”
For more information about the NVIDIA ALCHEMI Toolkit, visit https://developer.nvidia.com/blog/building-custom-atomistic-simulation-workflows-for-chemistry-and-materials-science-with-nvidia-alchemi-toolkit/.
About Matlantis
Jointly developed by PFN and ENEOS, Matlantis is a universal atomistic simulator that supports large-scale material discovery by reproducing new materials’ behavior at an atomic level on the computer. PFN and ENEOS have incorporated a deep learning model into a conventional physical simulator to increase the simulation speed by tens of thousands of times and to support a wide variety of materials. Matlantis was launched in July 2021 as a cloud-based software-as-a-service by Matlantis Corp. (formerly named Preferred Computational Chemistry), a company jointly invested by PFN, ENEOS and Mitsubishi Corporation. Matlantis is used by over 150 companies and organizations for discovering various materials including catalysts, batteries, semiconductors, alloys, lubricants, ceramics and chemicals. For more information, please visit: https://matlantis.com/en/.
Media Contact:
Emily Townsend
Scratch Marketing + Media for Matlantis
matlantis@scratchmm.com
