GAC R&D Center sets record-low vehicle drag coefficient using NVIDIA GPU-accelerated CFD simulation
Guangzhou Automobile Group Co., Ltd. (GAC Group)· ChinaNVIDIA V100 SXM2 Tensor Core GPUs · Altair ultraFluidX
GAC R&D Center (GAC Group) deployed NVIDIA V100 SXM2 Tensor Core GPUs on its hybrid cloud HPC platform, using Altair's ultraFluidX CFD software for GPU double-precision computing, to design a new concept car. In less than six months the team completed over 200 transient CFD simulations of vehicle outflow, achieving a simulation drag coefficient of 0.147 (wind tunnel test value 0.146 at Tongji University's Shanghai Automotive Wind Tunnel Center), a new record versus the previous 0.19. Compared to conventional CFD approaches, manual modeling effort was reduced by nearly 60% and total simulation time was shortened by about 70%.
Overview
GAC R&D Center (GAC Group) deployed NVIDIA V100 SXM2 Tensor Core GPUs on its hybrid cloud HPC platform, using Altair's ultraFluidX CFD software for GPU double-precision computing, to design a new concept car. In less than six months the team completed over 200 transient CFD simulations of vehicle outflow, achieving a simulation drag coefficient of 0.147 (wind tunnel test value 0.146 at Tongji University's Shanghai Automotive Wind Tunnel Center), a new record versus the previous 0.19. Compared to conventional CFD approaches, manual modeling effort was reduced by nearly 60% and total simulation time was shortened by about 70%.
This entry has 13 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
GAC R&D Center needed to decide which CFD simulation technology to use to design a new concept car with a record-low drag coefficient. Conventional CFD approaches using multi-core CPU HPC clusters demanded high CPU core counts, presented high energy consumption and maintenance costs, and required higher grid quality, complex pre-processing, and heavy manual investment. Larger-scale grids and transient simulation needed for high-precision results also sharply increased computing resource consumption.
The solution
GAC R&D Center deployed NVIDIA V100 SXM2 Tensor Core GPUs on its heterogeneous hybrid cloud HPC platform, adopting Altair's ultraFluidX CFD software built on GPU double-precision computing. In less than six months, the team completed over 200 transient CFD simulations of the vehicle outflow field.
Reported business value
The simulation achieved a drag coefficient of 0.147, matching a wind tunnel test value of 0.146 at Tongji University's Shanghai Automotive Wind Tunnel Center, setting a new record versus the previous 0.19. Compared to conventional CFD approaches, manual modeling effort was reduced by nearly 60% and total simulation time was shortened by about 70%.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other automotive entries in the register.
Volvo Trucks uses proprietary AI models to power adaptive maintenance in its Blue Service Contract
Volvo Trucks North America upgraded its Blue Service Contract to offer optimized service stops based on fuel consumption, idle time and oil samples, powered by the OEM's proprietary AI models, enabling fewer stops for 2023 model year and newer trucks and reducing operating costs for customers.
Volvo Trucks North America· United StatesBMW Group builds plant-scale digital twins with NVIDIA Omniverse, cutting vehicle aerodynamics simulation time 30x
BMW Group is building digital twins of its production facilities using NVIDIA Omniverse libraries, letting global production planning teams collaborate in real time, optimize the layout and design of complex manufacturing systems, and develop autonomous robot and vision AI applications prior to real-world deployment. Working with Siemens, BMW is also accelerating simulation of vehicle aerodynamics: tests on NVIDIA Grace Blackwell and CUDA-X-accelerated Simcenter Star-CCM+ software showed a 30x speedup for transient aerodynamics simulations of entire vehicle geometries, while reducing energy consumption and costs.
BMW GroupNVIDIA Omniverse · NVIDIA Grace Blackwell · NVIDIA CUDA-X +1European automotive marketer uses AI to target engaged customers and lifts open rates 50%
A regional automotive marketing organization covering more than 30 European countries used Oracle Unity and Oracle Marketing with AI to identify which email messages and digital touchpoints are likely to engage customers based on profile and behavior. The organization runs more than 120 always-on automated campaigns, seeing a 50% increase in email open rates, a 230% increase in lead submissions, and a 5% increase in order uptake.
Martur Fompak International Boosts Throughput and Efficiency with Intelligent Robotics Enabled by Joule and Embodied AI
Martur Fompak International, a global automotive seating and interior systems manufacturer, deployed an autonomous intralogistics model using SAP's Joule solution and embodied AI capabilities, partnering with UK-based robotics company Humanoid. Built on SAP S/4HANA and SAP Extended Warehouse Management, the system gives humanoid robots and autonomous mobile robots real-time knowledge of tasks, storage locations, sequencing and production priorities, letting them identify, transport and deliver materials to the production line while continuously confirming actions back into SAP systems. The company has 400 daily production line feeds with 100% SAP software-driven decision making. Early results show increased throughput and fewer errors, with a future target of up to five times greater work efficiency for mass production. Martur Fompak International was named sole winner in the AI Excellence category at the 2026 SAP Innovation Awards.
Was this helpful?
Your feedback helps us improve our use case database