NVIDIA announced the general availability of cuDSS on 2026-10-21, describing it as a CUDA-X library that shifts a critical part of engineering and scientific simulations onto GPUs (NVIDIA). The library targets the solving of large sparse systems, the math-heavy step that repeats throughout such simulations and often limits how many designs a team can test (NVIDIA). The company named Applied Materials, COMSOL, Cadence, Dassault Systèmes, Siemens and Synopsys as industry leaders already integrating it into their tools (NVIDIA).
Key Facts
| Item | Detail | Source |
|---|---|---|
| Product | NVIDIA cuDSS, a CUDA-X library | NVIDIA |
| Status | Generally available from 2026-10-21 | NVIDIA |
| Applied Materials result | Up to 10x faster sparse solves in Ginestra versus CPU-only approaches | NVIDIA |
| ZEISS SMT result | Measured 4x speedup in an EUV lithography plasma simulation benchmark | NVIDIA |
| Dassault Systèmes result | 8-10x speedup within Abaqus and electromagnetic solvers | NVIDIA |
| Interfaces | C, C++, Python and Fortran | NVIDIA |
Timeline
- 2026-10-21: NVIDIA announced that cuDSS launched in general availability (NVIDIA).
Details (as Reported)
NVIDIA said that engineering feats from advanced chips to aircraft to industrial systems depend on simulation to predict how designs will perform before they are built (NVIDIA). As designs become more complex, simulations take longer to run, which raises computing demands and limits the number of ideas teams can test (NVIDIA). By tapping into GPUs, cuDSS is meant to reduce time to results and increase simulation throughput, letting end users explore larger models, more accurate representations and a wider design space at a reduced cost (NVIDIA).
The company reported that Applied Materials accelerated sparse solves in Ginestra, its physics-based, defect-centric simulation platform, speeding exploration of semiconductor materials and device reliability (NVIDIA). Using COMSOL Multiphysics with cuDSS, ZEISS SMT completed the full EUV lithography plasma simulation benchmark in six days and 14 hours (NVIDIA). Cadence uses cuDSS in its Celsius software to simulate heat, structural stress and warpage in advanced chips and 3D chip designs, helping customers including Nokia analyze complex designs faster (NVIDIA).
Siemens uses cuDSS in Simcenter STAR-CCM+ to accelerate simulations of structures in fluid-structure interaction workflows (NVIDIA). Synopsys applies it in its Sentaurus Device simulator for advanced logic, memory and power chips, helping Infineon model increasingly complex devices faster (NVIDIA).
According to NVIDIA, cuDSS can scale out of the box from individual workstations to large computing clusters (NVIDIA). Developers can integrate it into existing engineering, scientific and optimization software, bringing GPU acceleration to tools already used by engineers and researchers (NVIDIA). NVIDIA invited attendees of GTC Berlin to learn more at its demo booth and the Dassault Systèmes booth (NVIDIA).
What Is Not Yet Confirmed
The sources do not list open questions.