Simvolt · Stage 03
Thousands of rollouts while you sleep
Simvolt is the compute engine. It runs your candidate policy across thousands of randomised environments at once on data-centre GPUs, so a full regression finishes in hours.
sweep #4812 · running
- Runs
- 12,480
- Completed
- 9,306
- GPUs
- 32
- Elapsed
- 1 h 12 m
- GPU-hours so far
- 38.4
Capabilities
What Simvolt does
Scale
Massively parallel
Thousands of environments per sweep with Isaac Sim and Isaac Lab.
Inference
Your policy, unchanged
Runs ONNX, TorchScript or TensorRT builds exactly as they ship.
Determinism
Seeded runs
Every run has a seed, so any failure replays exactly.
Scheduling
Priority queues
Release gates jump the queue; research sweeps fill idle capacity.
Elastic
Burst capacity
Scale out for big sweeps and back down when done.
Cost
GPU-hour metering
See the GPU-hours each sweep used, per suite and per team.
How it works
Inside Simvolt
Package
Load the policy build and the twin version.
Fan out
Spread scenarios and variations across GPUs.
Run
Step physics, sensors and policy together.
Collect
Stream outcomes and traces to Veridex.
Specification
Inputs, outputs and hardware
| Item | Detail |
|---|---|
| Simulator | NVIDIA Isaac Sim / Isaac Lab on Omniverse |
| Policy formats | ONNX, TorchScript, TensorRT engines, ROS 2 nodes in a container |
| Hardware | DGX / HGX (H100, B200 class) in Simprova Cloud or yours |
| Typical sweep | 10,000–50,000 runs in 1–4 hours |
| Outputs | Per-run outcomes, metrics, traces and replay files |
Part of the loop
Where Simvolt fits
Builds and keeps calibrating a digital twin of your real site.
02 · ScenariosScenovaFills the twin with rare and dangerous situations to test against.
03 · SweepSimvoltRuns the candidate policy across thousands of parallel rollouts.
04 · VerdictVeridexTurns the outcomes into a signed pass/fail certificate.
05 · RealitySentryxCaptures real telemetry at the edge and feeds it back.
Questions
About Simvolt
Can we bring our own GPUs?
Yes. On Hybrid and On-prem, Simvolt schedules onto your DGX or cloud GPU quota.
Does it support ROS 2 stacks?
Yes. Containerised ROS 2 nodes run in the loop with simulated sensors and clocks.
How do you estimate GPU-hours?
The pricing page has an estimator. Actual use depends on scene complexity and run length.
See Simvolt on your site
We'll run it on your own floor plan and one recent policy build.