Performance Comparison

Old vs. New — A 26,000× Leap in AI Processing

Performance comparison infographic: Old system (0.001 TOPS, rule-based + SVM on CPU) vs New system (26 TOPS, Mythic M1076 Analog NPU) — a 26,000x improvement. Pixels analyzed: 0.01% vs 100%. CIS modes: 3 vs 5. Tape detection: 65% vs ~100%.

Hardware Performance

Specification Old (Zynq 7010/7020) New (Zynq 1EG + M1076) Improvement
CPU cores2× Cortex-A94× Cortex-A53 + 2× Cortex-R5F3× more cores + real-time unit
CPU clock667–866 MHzUp to 1.5 GHz~2× clock speed
CPU architecture32-bit ARMv764-bit ARMv82× data width
Est. CPU performance~1.5 GFLOPS~7 GFLOPS~5× faster
GPUNoneMali-400 MP2From zero to display-capable
AI computeNone (rule-based + SVM on CPU)Mythic M1076: 26 TOPS26 trillion ops/sec
MemoryDDR3 (1,066 MT/s)DDR4 (2,400 MT/s)~2.3× bandwidth
PCIeNoneGen2 x4 (20 Gbps)Enables NPU connection
Display outputNoneDisplayPort 1.2a (4K@30Hz)External monitor support
Total AI throughput~0.001 TOPS (rule-based + SVM)~26 TOPS (NPU) + ~7 GFLOPS (CPU)~26,000× for AI

The old system's entire compute budget — both CPU cores running rule-based logic and SVM — delivered roughly 0.001 TOPS. The new platform delivers 26 TOPS from the NPU alone, a roughly 26,000× increase in AI processing capability.

Software Performance

The hardware leap enables a corresponding revolution in what the software can do:

Capability Old (Rule-based + SVM) New (ResNet on NPU)
AlgorithmRule-based (counterfeit) + SVM (denomination & counterfeit)Deep neural network (ResNet)
Pixels analyzed per note~14,000 (0.01%)~11,250,000 (100%)
Classification methodRule-based thresholds + multiple SVMs (~224 hand-crafted features total)End-to-end learned features → multi-class neural network
Feature engineeringManual — engineers define what to measureAutomatic — network learns optimal features from data
Multi-task capabilitySequential: each task runs separatelyParallel: single forward pass classifies all attributes
Model parameters~hundreds (SVM hyperplane)~millions (ResNet weights in NPU flash)
AdaptabilityWeeks to months of manual re-engineeringHours to days — retrain → deploy via remote upgrade
Spectral utilization3 modes, sampled at sparse points5 modes, fully analyzed at every pixel
Tape detection accuracy64.58% (CBRF best)Target: near 100%
False positive handlingHard-coded thresholdsLearned decision boundary, optimized for both
Display & visualizationNoneReal-time visualization of detection results

Why the Software Gap Is Even Bigger Than the Hardware Gap

The hardware delivers a ~26,000× increase in raw AI compute. But the software improvement is non-linear — the new system is not just doing the same thing faster; it is doing something fundamentally different:

1. Rule-based → Learned features

The old system relied primarily on rule-based programming for counterfeit detection, with SVM used for denomination classification and supplementary counterfeit checks. If no engineer anticipated a particular counterfeit pattern, the machine would never detect it. ResNet discovers features on its own — including patterns no engineer would think to look for.

2. Sparse sampling → Full image

Analyzing 0.01% of pixels means 99.99% of the information is discarded. With 100% pixel analysis, nothing is missed — the difference between glancing at a banknote and examining it under a microscope.

3. Single-task sequential → Multi-task parallel

The old CPU ran denomination SVM, then rule-based counterfeit checks, then counterfeit SVMs, then fitness sorting — sequentially. The NPU performs all tasks in a single forward pass, taking the same time regardless of how many attributes are classified.

4. Static → Continuously improving

The old software was frozen at the level of engineering knowledge at the time of release. Whenever a new counterfeit appeared, engineers had to analyze it and write new rule-based detection logic — a process that took weeks or months. The new system can be retrained with new sample data and deployed remotely in hours to days — improving continuously without hardware changes.

AI Platform

Question? Let us know.