Benchmarking
Calculating Value Adjustments and Total xVA
Valuation adjustments (xVAs) are essential for derivative pricing, allowing investment banks to account for credit risk. As part of Basel III compliance, these are typically computed by solving stochastic differential equations using geometric Brownian motion and Monte Carlo methods, creating a challenge for banks aiming to balance regulatory rigor with operational efficiency.
Figure 1. Monte Carlo UQ implementation
Running xVA computations on Signaloid’s Cloud Compute Engine (SCCE) transforms this challenge into an opportunity for real-time computation of risk. Instead of evaluating millions of individual Brownian motion paths, the UxHw-enhanced code running on SCCE performs direct computation on representations of probability distributions. The result is the same output distribution that traditional Monte Carlo methods struggle to approximate, delivered in a single-shot computation.
Figure 2. Signaloid UQ implementation
A Total xVA kernel, running on a single-threaded Signaloid C0Pro-L+ core, achieves runtimes 700× faster than an optimized C-language Monte-Carlo-based implementation (i.e., the industry standard and status quo) running on an Amazon EC2 R7iz instance. With 95% confidence, a 4.8M-iteration Monte Carlo implementation matches the accuracy of the Signaloid UxHw-based version. This speedup enables risk teams to move from retrospective daily reporting to continuous, real-time risk visibility.
Key Performance Indicator
Signaloid Platform Solution
Competing Solution
Signaloid Benefit
Speed for the same uncertainty quantification accuracy.
Run existing non-Monte-Carlo code and use either the Signaloid Compute Engine's automated ingestion of distribution information, or use the Signaloid UxHw API to set program variables as probability distributions.
Run existing Monte Carlo code, or, starting from non-Monte-Carlo code, modify code to implement Monte Carlo sampling, iteration, and aggregation of the results from the Monte Carlo iterations of the computation.
700x faster execution time than 4.78M-iteration Monte Carlo, while achieving same fidelity of full distribution result.
Plot of output distribution when running on a Signaloid C0Pro-L+ core that provides the 700× speedup.
Plot of the output of an 4.78M-iteration Monte Carlo for this use case. Signaloid C0Pro-L+ core is 700× faster than this Monte Carlo, while achieving the same or better Wasserstein distance to the ground-truth (20M-iteration) Monte Carlo.
Plot of ground truth (20M-iteration) Monte Carlo.
Benchmarking Methodology
Monte Carlo simulations work by statistical sampling and therefore each multi-iteration Monte Carlo run will result in a slightly different output distribution. By contrast, Signaloid's platform is deterministic and each run produces the same distribution for a given Signaloid C0 core type.
The performance improvements are calculated by comparing Signaloid's platform with a Monte Carlo simulation of a similar quality of distribution. First, we run a large Monte Carlo simulation (about 50M iterations) on an AWS r7iz high-performance AWS instance: We use this distribution result as a baseline or ground truth reference of distribution quality. Then we calculate the performance of Signaloid's technology, and compare it with the performance of a Monte Carlo iteration count where the output distribution's Wasserstein distance (to the output distribution of the ground truth reference) is as accurate as the Signaloid-core-executed algorithm's output distribution, with 95% confidence level.
Performance data based on Fall 2025 release of Signaloid's technology.