SIMD

interFoam - the first multiphase solver we've ported to CUDA. Dam break, 4.9 M cells, 6 s simulated: • 28 min on one H100 • 5 h 37 min with OpenFOAM on 26 CPU cores 12× faster. brae.sh/solvers/interfoam

Your GPU, earning while you sleep. Brae turns your NVIDIA GPU into income. One command to join. Renters pay by the minute, you keep 80%. Paid to your bank or in USDC. Early access is open → app.brae.sh Settlement in SIMD comes after our smart contract audit.

InjectorPipe gasMixing ⛽️ 2.58M cells · 100 SIMPLE iterations Brae, 1 GH200: 21.5s Brae warm: 5.0s OpenFOAM, 64 Grace cores: 33.8s Matches OpenFOAM v2412 to 1.2e-11.

A transonic 180° U-bend Mach 0.999 on the inner radius, 960K. converged in 3.4 seconds. 112,000 cells. Brae: OpenFOAM’s rhoSimpleFoam, ported to CUDA. The run stopped on the tutorial’s own residualControl at iteration 154 - not a hand-picked iteration count.

Our previous SPUMA benchmark showed brae running 4.5× faster on a transient PimpleFoam case. This new rhoSimpleFoam port suite puts brae at more than 20× 🚀 faster than SPUMA by geometric mean across 6 cases, with up to 136× on the 1M-cell case. The lead is getting much bigger.

Brae now runs OpenFOAM’s rhoSimpleFoam fully on CUDA 🚀 Across cases from 15k to 24M cells on one GH200 outperforms all 64 Grace CPU cores. At 10M cells / 100 SIMPLE iterations: - GH200 GPU: 109s - 64 Grace CPU cores: 921s Matches OpenFOAM to 7e-08. A port, not a reimplementation.

93 million $SIMD tokens locked again until January 2027. We're here to build: GPU-native simulation infrastructure and real utility for the SIMD ecosystem - starting soon. Live Roadmap: simd.space/roadmap SIMD on top!

Brae is heading to the supercomputer 🚀 We’ve secured access to LuxProvide’s MeluXina platform, including NVIDIA A100s GPU infrastructure. We’ll use this pilot to accelerate BRAE’s development, benchmark it in an HPC environment, and advance our goal of building large, multiscale simulations. Thank you to @luxprovide for the support!

Please check out the new version of brae.sh 🤩

You only need GPU to run the simulation, not 1000 CPU core anymore. 2.78M cells · kOmega SST-IDDES · Re 1.6×10⁷ · 4,800 timesteps in less than 2 hours on one GH200.