NVIDIA cuDSS Now Generally Available to Accelerate Engineering and Scientific Simulations
nvidia ·
NVIDIA has announced the general availability of cuDSS, a CUDA-X library designed to accelerate engineering and scientific simulations by shifting critical computational tasks to GPUs. This technology specifically targets large sparse systems, which are math-intensive steps that often bottleneck simulation throughput in complex design processes. By leveraging GPU power, applications can significantly reduce time-to-results and explore larger, more realistic models at a lower cost. Industry leaders such as Applied Materials, COMSOL, Cadence, Dassault Systèmes, Siemens, and Synopsys have already integrated cuDSS into their platforms to achieve substantial speedups ranging from 4x to 10x. These integrations enable faster analysis of semiconductor materials, EUV lithography plasma, heat stress in chips, and fluid-structure interactions. The library supports scalability from individual workstations to large computing clusters and offers interfaces for C, C++, Python, and Fortran. This release allows developers to bring GPU acceleration to existing software tools used by engineers and researchers worldwide.
nvidia