Third-party validated (TestFort QA Lab, Dec 2025)

Deterministic vector math at GPU scale

Bit-exact evaluation of dense numeric expressions (y = f(x)) via a stateless API. SHA-256 verification supported.

Memory-safe Rust core | SIMD + GPU acceleration | Edge to enterprise

286.94B
ops/sec
444.4T
ops (1-hr test)
0%
error rate
2.35B
ops/joule

Validated by

TestFort
QA Lab
PFLB
Load Testing

Dec 2025

Defense & Autonomous Systems

Deterministic vector math for safety-critical edge compute

DO-178C certification-ready architecture with SHA-256 verified calculations for targeting systems, sensor fusion, and autonomous navigation.

  • DO-178C certification-ready architecture
  • Sub-5MB container, Jetson-ready
  • 2.35B ops/joule for battery-powered systems
  • SHA-256 verified targeting calculations
  • Deterministic sensor fusion and path planning
  • Bit-exact reproducibility for certification

Quantitative Finance

FINRA-compliant reproducible calculations

Reproducible calculations for trading, risk modeling, and Monte Carlo simulations with complete regulatory audit trail support.

  • FINRA Rule 3110 compliant reproducibility
  • Bit-exact Monte Carlo simulations
  • Reproducible backtesting and VAR models
  • Audit-ready SHA-256 verification
  • Same input = same output, always
  • Regulatory audit trail support

Every Watt Counts

Faster compute means less time at full power

LuxiEdge completes calculations faster, so your hardware spends less time at full power.

  • Edge & Battery Systems: Drones, robots, satellites run longer between charges
  • Data Center Savings: Faster compute = less heat = reduced cooling costs
  • 2.35B ops/joule: Validated efficiency on NVIDIA H100
  • Scale savings: Facilities running LuxiEdge save enough electricity annually to power hundreds of homes
TestFort Validated

Validated Performance Metrics

Independently verified by TestFort QA Lab during a 1-hour GPU endurance test on NVIDIA H100 SXM, December 2025.

Reliability & Compliance

Metric Value Why It Matters
Determinism SHA-256 verified Bit-exact results for audits & certification
Error Rate 0.00% Zero failures over 444.4T operations
Hash Consistency 10/10 runs identical GPU and CPU produce same output

Performance

Metric Value Why It Matters
Aggregate Throughput 286.94B ops/sec Process massive vectors in milliseconds
Peak Throughput (sqrt) 331.13B ops/sec Function-dependent ceiling
P95 API Latency 1.47ms Real-time capable under load

Efficiency

Metric Value Why It Matters
Energy Efficiency 2.35B ops/joule Edge-deployable, battery-friendly
Average GPU Power 117.2W Below H100 TDP

Test Conditions

Parameter Value
Hardware NVIDIA H100 SXM, 80GB HBM3
Duration 1 hour continuous
Concurrent Users 200
Total Operations 444.4 trillion
Validator TestFort QA Lab, Dec 2025

Verified Output Hash (10 consecutive runs)

98bd97026a738671ec7c3d302efa6aa8ff078a5fb9183f7fdf51a1c4ff938321

Identical hash confirms bit-exact determinism across GPU and CPU execution modes.

Core Capabilities

Deterministic Execution

Same input + same environment = identical output with SHA-256 verification.

Dual Execution Modes

GPU mode (CUDA/Vulkan FP16/FP32) and CPU mode (Rust f32 with SIMD).

High Throughput

Demonstrated 286.94B ops/sec aggregate on NVIDIA H100 SXM.

Energy Efficient

2.35B ops/joule efficiency enables edge and power-constrained deployments.

REST API

Stateless HTTP interface for deterministic expression evaluation.

POST /evaluate

Vectorized expression evaluation with deterministic results.

Request:

POST /evaluate
{
  "expr": "2*x + cos(x)",
  "x": [1.0, 2.0, 3.0]
}

Response:

{
  "y": [2.5403, 4.5839, 6.0100]
}

expr = mathematical expression | x = scalar or vector input | Deterministic: same request = same response

For Researchers & Academics

Transparent methodology, reproducible benchmarks, and citation formats for academic evaluation.

For Researchers

  • 01 SHA-256 verification for bit-exact reproducibility
  • 02 Documented methodology with hardware specifications
  • 03 Third-party validation by independent QA lab
  • 04 Citation formats available for academic papers

Methodology

  • Same input + same execution mode = identical output bytes
  • GPU mode uses IEEE 754 FP16/FP32 with defined rounding
  • CPU mode uses Rust native f32 with SIMD (AVX-512/AVX2/ARM Neon)
  • Throughput = total floating-point operations per second

BibTeX

@software{luxiedge2025,
  author       = {Waller, Eric},
  title        = {{LuxiEdge}: Deterministic JSON 
                  Math Engine},
  year         = {2025},
  version      = {1.0},
  url          = {https://luxiedge.com},
  note         = {Accessed: 2025-12-18}
}

APA Style

Waller, E. (2025). LuxiEdge: Deterministic JSON Math Engine (Version 1.0) [Computer software]. https://luxiedge.com

Note: LuxiEdge is commercial software. This citation references the software directly.

Start 30-Day Pilot

Enterprise licensing available. 30-day pilot at no upfront cost.

Or email directly: e@ewaller.com