Benchmarking Vanilla Option Pricing and Portfolio Scenario Workloads

Summary

The document asks for benchmarks to compare the performance of code that prices vanilla options across a portfolio and runs scenarios. It mentions a PDE pricing component in a large benchmark distribution, but the author has not reviewed it. The answer points to a paper comparing methods for pricing a single option and notes that it does not specifically benchmark portfolios.

The response argues that portfolio and scenario calculations can be parallelized, so portfolio throughput depends largely on distributing work effectively once an efficient single-option pricer is available. It also mentions a paper on FPGA pricing schemes, while expressing doubt about their practical relevance for option pricing compared with market-making on a delta grid. No benchmark measurements or direct portfolio comparison are given, so the discussion offers performance considerations and pointers rather than a ready-made benchmark suite.

Key ideas

• The question concerns performance benchmarks for pricing vanilla option portfolios and running scenarios.
• A cited comparison studies individual option pricers rather than portfolio workloads.
• Portfolio and scenario calculations are described as readily parallelizable.
• The response mentions FPGA pricing schemes but questions their practical relevance for this use case.
• No benchmark results or portfolio-level comparison are provided.

Tags

# Are there any good benchmarks for performance of vanilla option pricing code?


# Are there any good benchmarks for performance of vanilla option pricing code?












I've seen parsec (http://parsec.cs.princeton.edu/index.htm), which has a PDE pricing component, but the distribution is enormous and I haven't bothered to try to download it for review. I'm interested in finding benchmarks for pricing a portfolio of vanilla options and running some scenarios; has anybody seen anything like this?

## Answer by Brian B (score 3, accepted)

https://quant.stackexchange.com/a/8062

On a single-option basis, there is this paper comparing methods by Mark Joshi. It doesn't specifically examine portfolios, but there's a reason for that. Portfolio and scenario computations are embarrassingly parallel, so once you have achieved your most efficient available option pricer, the rest is simply about wise distribution of your computational load.

There is also this somewhat minimalist paper for FPGA schemes, though to be honest I doubt many people are bothering with FPGA for option pricing, since you can be faster market-making on a delta grid.

Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.