Oriel — AI & technology worth noticing, every day.

NVIDIA cuDSS Now Generally Available to Accelerate Engineering and Scientific Simulations

Web page · https://blogs.nvidia.com/blog/cudss-generally-available-engineering-scientific-simulation

NVIDIA cuDSS, launched today in general availability, is an NVIDIA CUDA-X library that shifts a critical part of engineering and scientific simulations onto GPUs. Complex engineering feats — from advanced chips to aircraft to industrial systems —– depend on simulation to predict how designs will perform before they’re built. As designs become more complex, simulations […]

First seen by Oriel on .

AI summary

NVIDIA cuDSS is generally available as a CUDA-X library that uses GPUs to accelerate sparse-system solves in engineering and scientific simulations.

  • cuDSS targets large sparse systems, a repeated computational step that can limit simulation throughput and the number of designs teams can test.
  • Reported results include up to 10x speedup in Applied Materials’ Ginestra and 8-10x in Dassault Systèmes’ Abaqus electromagnetic solvers.
  • ZEISS SMT measured a 4x speedup in an EUV lithography plasma simulation using COMSOL Multiphysics with cuDSS.
  • The library scales from workstations to computing clusters and offers C, C++, Python, and Fortran interfaces for integration into existing software.
  • Cadence, Siemens, and Synopsys also use cuDSS in simulation tools for chip design, fluid-structure interaction, and device modeling.

#cuda #gpu computing #scientific computing #simulation

Generated by gpt-5.6-sol. Check the original for details.

Aliases

SourceExternal IDURL
NVIDIA Bloghttps://blogs.nvidia.com/?p=99204https://blogs.nvidia.com/blog/cudss-generally-available-engineering-scientific-simulation/ Read discussion