Cogitan

Applied AI · Real engineering

Verify RSFQ circuits
at simulation speed.

Fluxus is a learned physics model for RSFQ circuits that predicts delay, current, and DRV violations — with calibrated confidence on every output — 200–500× faster than SPICE.

verify.py
import cogitan

# load your cell library and run verification
results = cogitan.verify(
    path = "./layouts/sfq5ee+",
    pdk = "mit-ll-sfq5ee+",
    batch = True,
)

for cell, r in results.items():
    print(
        f"{cell:<14} {r.delay:>5.1f}
        f" ± {r.sigma:.1f} ps  {r.status}"
    )
$ cogitan verify ./layouts/sfq5ee+

SPLIT_v1_a     17.2 ± 1.4 psSPLIT_v2_b     18.9 ± 1.1 psDFF_x3_c       22.1 ± 5.8 ps   → spice
AND2_v1_d      14.4 ± 1.6 ps...

─────────────────────────────────
1,000 cells  4.8s    (SPICE: ~85 min)
997 pass  ·  3 → spice fallback

Wall-clock time · chip-scale verification

1K cells~100× speedup
SPICE
5–10 min
Fluxus
5s
10K cells~120× speedup
SPICE
~90 min
Fluxus
45s
100K cells~140× speedup
SPICE
8–10 hrs
Fluxus
4–5 min

200–500×

faster than SPICE at chip scale

100%

functional classification on validated types

sub-3 ps

delay accuracy on SPLIT / DFF / AND2

99.2%

design rule violation detection

The problem

SPICE doesn't scale.

At RSFQ process nodes, a 1,000-cell verification block takes 5–10 minutes in SPICE. A full 100,000-cell chip is an entire engineering day — per iteration. There is no design-space exploration. There is no confidence scoring. There is no gradient-based optimization.

The constraint isn't compute. It's the simulation paradigm itself.

Speed
Sequential. Minutes per block, hours per chip.
Batch-parallel. Milliseconds per cell.
Confidence
One answer. No uncertainty. No ranking.
1σ bounds on every output. Low-confidence cells auto-flag.
Scale
Every candidate requires full simulation.
Screen 10,000 candidates. SPICE validates the shortlist.
Optimization
Not differentiable. Gradient-based optimization is impossible.
Fully differentiable. Backpropagate to any target metric.

Workflow

01

Provide your PDK

Cell library and SPICE simulation data for your process node. MIT-LL SFQ5ee+, IPHT, SeeQC, AIST, SkyWater, or proprietary.

02

We train the surrogate

A learned surrogate calibrated to your junction parameters, cell geometry, and design rules. Training runs on your data.

03

Explore at 200–500×

Run design-space exploration with per-cell confidence scoring. Low-sigma predictions pass. High-sigma cells are flagged.

04

SPICE on the shortlist only

SPICE validates final candidates. 5–10× wall-clock savings per design loop. Every shipped design is SPICE-verified.

Cogitan

RSFQ is the first application.

The same approach — learned physics surrogate, calibrated uncertainty, differentiable for optimization, trained on your data — applies to any domain where simulation is the bottleneck and ground truth is expensive to generate.

We are actively developing for additional domains. If you have a hard simulation problem, we'd like to understand it.

Get in touch

Product roadmap

Superconducting RSFQ
SFQ5ee+ completeActive
Photonic design
Exploring
RF / microwave EDA
Exploring
More in development

Have an RSFQ process?
We're onboarding now.

Bring your cell library and SPICE simulation data. We handle the rest. SFQ5ee+ is the proof of concept. Your process is next.

Request early access