GPU and FPGA Applications in Computational Finance

# Reference request: Survey article on GPU in Finance


# Reference request: Survey article on GPU in Finance












I would like to get and idea of how people use GPUs in finance.

I can find some specific papers or books on the subject. GPUs in binomial model, finite difference, monte carlo,...

But I couldn't find any recent survey papers.

Do you know some recent survey paper? Or any kind of reference which try to gives a birdview on GPUs in finance?

Added Reference I found: Pagès, Wilbertz, 2011, GPGPUs in computational finance: Massive parallel computing for American style options

Labart, Lelong,2011,A Parallel Algorithm for solving BSDEs - Application to the pricing and hedging of American options

Bradley, 2012, State of GPU computing in computational finance The paper digs deep in current GPU method in QF, but the general survey is very short.

## Answer by lehalle (score 8, accepted)

https://quant.stackexchange.com/a/3905

The Pagès-Wilbertz paper is a very good one. To answer more directly to you underlying question that is: "in which quant finance area to use hardware acceleration?"; the points to take into account are:

- GPU is very good for parallel computations (already underlined in remarks)

- but bad for memory sharing between the master software and the GPU-hosted library

- FPGA is good for parallel computations too (but harder to use compared to GPU)

- FPGA works well for working on data flows

Consequently:

- if you need to solve numerically a PDE with few parameters (coefficients of the derivative terms): GPU is nice;

- if you need to compute on the flight analytics for high frequency trading: FPGA is nice.

## Answer by Quartz (score 2)

https://quant.stackexchange.com/a/4357

There are few surveys atm as people are still relatively secretive about it because of the various challenges a production system poses. Actually a major bank even backstepped after some initial efforts. So there is now quite some activity in the field but not so much as the initial hype suggested. You can also try asking in the dedicated Linkedin group.

Edit: I could give you various additional references on specific applications if you want to get an idea of the field anyway.

## Answer by James Dilworth (score 2)

https://quant.stackexchange.com/a/34192

It's been a few years since the OP, and GPU usage is much more common. While still experimental, most institutions we talk to are running GPUs in the data center in some capacity. GPUs are good at large aggregations and chewing through large and streaming datasets which translates to things like:

- x-Valuation Adjustments (xVA) in relation to derivative instruments... counterparty credit risk, FVA, KVA, etc.

- Value at Risk (VaR) calculations

- Order management, keeping track of positions

- Fraud Detection

One of the challenges of GPU compute has traditionally been the moving of data and niche programming languages required. GPU-accelerated databases such as Kinetica are now mature enough to allow things like custom risk analysis (Monte Carlo, etc) to operate in-database.

I recently wrote a blog post about it here: https://www.kinetica.com/blog/machine-learning-finance-observations/

## Answer by Mark Joshi (score 1)

https://quant.stackexchange.com/a/34193

they aren't really surveys but I have a couple of papers.

https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2388415

which discusses Monte Carlo pricing with an emphasis on Bermudan options using the kooderive open source project.

https://papers.ssrn.com/sol3/papers.cfm?abstract_id=1473563

which discusses asian option pricing.