Signaloid C0-microSD
Use Case Family:
Robotics and Sensors
Use Case
Uncertainty Quantification of Sensirion SDP36 ADC Conversion Routines
Sensors such as the Sensirion SDP37 are an important part of many industrial, manufacturing, and autonomous systems. This use case example quantifies the ease of implementation and the speed of execution, of automating the uncertainty quantification (UQ) of sensor data conversion firmware for the SDP37. The evaluation runs the software of the use case over an instance of the Signaloid Compute Engine. The output of the execution is both the usual calibrated pressure output as well as programmatically-accessible information on the uncertainty of the calibrated pressure outputs as a function of the measurement uncertainty in the raw sensor transducer voltage output. Such UQ can provide valuable design-time as well as real-time safety information. The implementation overhead and execution cost of the status quo method of Monte Carlo simulation however discourages many organizations from implementing UQ for sensor data conversion routines.
For the Sensirion SDP37 data conversion routine firmware, an implementation on the Signaloid C0 processor runs 12.8x faster than an already fast C-language Monte-Carlo-based implementation of the same model running on an AWS r7iz high-performance instance.
Plot (see Note 1 below for details) of output distribution when running on Signaloid C0Pro-M core that provides the 12.8x speedup.
Plot (see Note 1 below for details) of the output of an 182k-iteration Monte Carlo for this use case. This Monte Carlo iteration count provides the same or better Wasserstein distance to ground truth (large, converged) Monte Carlo as execution on a Signaloid C0Pro-M core (which is 12.8x faster).
Plot (see Note 1 below for details) of ground truth (large, converged) Monte Carlo.
Note 1:
The underlying distribution representations are not literal histograms: The distribution plots use an adaptive algorithm to render a mutually-consistent and human-interpretable depiction for both the Signaloid distribution representations and the Monte Carlo samples, to permit qualitative comparison.
Note 2:
Because Monte Carlo works by statistical sampling, each set of multi-iteration Monte Carlo runs (e.g., each time a 200k-iteration Monte Carlo is run) will result in a slightly different final distribution. By contrast, the results from Signaloid's platform are completely deterministic and yield the same distribution each time, for a given Signaloid C0 core type. The performance improvement over Monte Carlo results above show the performance speedup of running on Signaloid's platform, compared to running a Monte Carlo on an AWS r7iz high-performance AWS instance, for the same quality of distribution while accounting for the variations inherent in Monte Carlo. To compare the quality of distribution, we run a large Monte Carlo until convergence (e.g., 1M iterations) and use this as a baseline or ground truth reference for distribution quality (not for performance). We then compare performance of the Signaloid solution against a Monte Carlo iteration count for which the output distributions of 100 out of 100 repetitions are all at smaller Wasserstein distance (than the Signaloid-core-executed algorithm's output distribution) to the output distribution of the baseline reference. Intuitively, this analysis gives the Monte Carlo iteration count that results in an output distribution that is never worse than the Signaloid-core-executed computation's output distribution. The performance data is based on the Spring 2024 release of Signaloid's technology. 12.8x speedup achieved with Signaloid C0Pro-M core for linear mode. Performance data based on Spring 2024 release of Signaloid's technology.