NVIDIA introduced three new software tools at ISC Hamburg — cuPhoton, DAQIRI, and ALCHEMI — that accelerate AI for scien

At the ISC conference in Hamburg this week, NVIDIA is introducing new software that speeds AI for science, from chemistry and materials discovery to the search for dark matter. The NVIDIA DAQIRI library and new NVIDIA ALCHEMI NIM microservices, as well as the NVIDIA cuPhoton reference code coming soon, turn work that once took hours or days on CPUs into real-time GPU-accelerated pipelines. These are part of NVIDIA CUDA-X, a collection of tools and libraries delivering dramatically higher performance across application domains including AI and high-performance computing.

CuPhoton is a reference code for scientists extracting insights from multidimensional data collected from telescopes, X-rays and laser experiments. Running on NVIDIA GB200 NVL72 systems, cuPhoton accelerates loading, reading, processing and analysis of FITS data — the standard astronomical file format. In early access, cuPhoton accelerated loading and reading of FITS images from the Rubin Observatory's Legacy Survey of Space and Time by 14,900x, and enabled up to 8,400x faster signal processing and analysis using 32 NVIDIA Grace Blackwell superchips. Researchers at Princeton University and Harvard University collaborated with NVIDIA to develop cuPhoton and will use it for processing data from observatories and dark energy surveys.

DAQIRI, short for Data Acquisition for Integrated Real-time Instruments, is a high-performance networking library that streams data from fast detectors and sensors into NVIDIA software. A research project called A-GHOST, developed by scientists from CERN, the University of Chicago and University College London, uses DAQIRI to run AI in real time on collision data from the ATLAS Experiment at CERN, analyzing data that would normally be rejected due to storage constraints and catching potentially interesting signals.

ALCHEMI comprises domain-specific microservices and a toolkit for accelerating chemical and materials discovery across battery materials, catalysts, OLED displays and other applications. NVIDIA released in March two ALCHEMI NIM microservices for batched geometry relaxation and batched molecular dynamics, letting researchers simulate millions of molecules and materials at once. A forthcoming microservice for the Vienna Ab initio Simulation Package enables materials simulations with 3x speedup for geometry optimization. Lila Sciences, building a scientific superintelligence platform and autonomous lab, accelerated high-throughput materials screening by 50x using ALCHEMI BGR, and accelerated magnetic property calculations by 30% using the VASP microservice. ALCHEMI's specialized kernels gave Lila a 6x speedup in training and inference with 3x reduced memory usage.

The NVIDIA ALCHEMI Toolkit is available for download from Github and PyPI, while ALCHEMI NIM microservices are available from the NVIDIA NGC catalog. DAQIRI is now available on GitHub. CuPhoton and the VASP microservice are expected to be available later this summer.