GPU simulationPermeon
Reservoir simulation at GPU speed
Permeon is a blackoil numerical reservoir simulator built from first principles for GPU hardware. Run SPE-validated simulations via cloud API or deploy a direct license on your own GPUs — up to 100× faster than legacy CPU simulators. Reads Eclipse-compatible .DATA input, so existing models migrate with zero conversion effort.
Capabilities
Everything Permeon does
Native GPU Solver
An IMPES / fully-implicit solver written ground-up for CUDA. Every linear-algebra operation runs on the GPU with a CPR preconditioner — no CPU-fallback bottleneck.
Blackoil Physics
Full three-phase oil, gas, and water: dead/live oil, dissolved gas (Rs), wet gas (Rv), Stone I/II three-phase relperm, and WAG gas-trapping hysteresis — all validated against OPM Flow.
Eclipse-Compatible Input
Reads the standard .DATA file format used by Eclipse, tNavigator, and OPM. Existing models migrate with zero conversion effort; unsupported keywords are flagged, never silently ignored.
Naturally-Fractured & Aquifer Drive
Dual-porosity matrix–fracture transfer plus analytic Fetkovich / Carter-Tracy and numerical (AQUNUM) aquifers — all fully implicit and within ~1% of OPM Flow.
Advanced Well Models
Peaceman completions, multi-segment wells with segment-tree hydraulics, VFP/THP control, group controls, and WCONHIST history matching — validated to ~1% vs OPM.
Cloud API Access
Submit simulation jobs via REST from any language. Integrate directly into your Python workflows, web apps, or automation pipelines with a Python SDK and example notebooks.
Ensemble & History Matching
Run hundreds of realizations in parallel on the cloud — ideal for ensemble-based history matching and uncertainty quantification without managing your own HPC cluster.
Rich Output & Direct License
EGRID/UNRST output, summary vectors (WOPR, WBHP, FOPT…), and VTK export for ParaView. Available as a cloud API or a direct on-prem license on your own GPU hardware.
How it works
From input to answer
Prepare your model
Use your existing Eclipse-compatible .DATA file, or build one with any standard reservoir modeling tool. Permeon reads industry-standard input directly.
Upload via API or dashboard
Submit through the REST API or web dashboard, specifying GPU tier, simulation parameters, and output options in a single JSON payload.
GPU-accelerated solve
Permeon dispatches the job to dedicated GPU hardware and solves fully on-GPU — most field-scale models finish in minutes, not overnight.
Download results
Retrieve EGRID/UNRST files and summary vectors via the API and stream them straight into your post-processing or visualization pipeline.
Ready to build with Permeon?
Request API access or talk to our team about how Permeon fits into your upstream workflows.
