Pricing structured equity products on GPUs

Bernemann, A.; Schreyer, R.; Spanderen, K.

doi:10.1109/whpcf.2010.5671821

Cited by 8 publications

(7 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even though in a few cases (1,5) it performs better than the latter one, in several situations (3,4,6,12) hardly any convergence can be seen.…”

Section: Parameter Interactionsmentioning

confidence: 92%

“…Bernemann et al have highlighted the enormous speedup potential for Monte Carlo based Heston pricing on GPUs, also for multi-underlying simulations on the WHPCF 2010 [1]. For one underlying, they have achieved a speedup factor of 50 in their hybrid CPU/GPU setup, compared to CPU only simulations.…”

Section: Related Workmentioning

confidence: 99%

“…Bernemann et al have enhanced their WHPCF paper [1] with more measurement data in February 2011 [2]. They also included a comparison of two different random number generation approaches: Using pseudo random numbers in the Monte Carlo simulations, they achieve a speedup of up to 50 compared to CPU only simulations.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Algorithmic complexity in the heston model

Marxen

Kostiuk

Korn

et al. 2011

Proceedings of the Fourth Workshop on High Performance Computational Finance

View full text Add to dashboard Cite

In this paper, we present an in-depth investigation of the algorithmic parameter influence for barrier option pricing with the Heston model. For that purpose we focus on singleand multi-level Monte Carlo simulation methods. We investigate the impact of algorithmic variations on simulation time and energy consumption, giving detailed measurement results for a state-of-the-art 8-core CPU server and a Nvidia Tesla C2050 GPU. We particularly show that a naive algorithm on a powerful GPU can even increase the energy consumption and computation time, compared to a better algorithm running on a standard CPU. Furthermore we give preliminary results of a dedicated FPGA implementation and comment on the speedup and energy saving potential of this architecture.

show abstract

“…Even though in a few cases (1,5) it performs better than the latter one, in several situations (3,4,6,12) hardly any convergence can be seen.…”

Section: Parameter Interactionsmentioning

confidence: 92%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Algorithmic complexity in the heston model

Marxen

Kostiuk

Korn

et al. 2011

Proceedings of the Fourth Workshop on High Performance Computational Finance

View full text Add to dashboard Cite

show abstract

“…It was originally devised to accelerate the graphics processing because of its parallel processing capabilities and the parallelism schemas in the graphics applications [7]. Applications of GPUs have been embarking in multiple domains and represented higher-level performances, such as stock predictions and pricing equity products [8,9]. A 50 speedup by implementing GPUs has been achieved in some prior research, compared with the CPU counterparts [8,9].…”

Section: Data Transfer Minimization For Financial Derivative Pricing mentioning

confidence: 99%

Data transfer minimization for financial derivative pricing using Monte Carlo simulation with GPU in 5G

Qiu

Cao

et al. 2015

Int J Communication

103

View full text Add to dashboard Cite

Mobile devices with an enhanced capability are desired to achieve more efficient and energy-aware wireless communications in the future 5G networks. However, the performance of the expected hardware and networks will face a great challenge in efficiently calculating large data transmissions during the heavy wireless communications with a great number of random data. This paper proposes a novel paradigm for preventing future mobile technology implementations from the restrictions of hardware by using graphics processing units (GPUs). Our proposed mechanism is the first attempt in using GPUs to strengthen the wireless communication capability, which is proved by the experimental research and contributes to mobile technologies in 5G. We apply the Monte Carlo simulation method that is for evaluating the results of algorithms whose output depends on random variables. The experimental results show that Monte Carlo simulation based on GPU can achieve up to 25.9 speed compared with CPU-based implementation.

show abstract

“…Zhang and Oosterlee [29], Podlozhnyuk [24], Abbas-Turki and Lapeyre [5], Egloff [9], Joshi [12], and Dang et al [7] look at Black-Scholes pricing on the GPU, while Podlozhnyuk and Harris [25], Tian et al [28], Rees and Walkenhorst [26], Dixon et al [8], Pages and Wil-bertz [23], Bernemann et al [6], and Murakowski et al [15] look at GPU acceleration of Monte-Carlo for financial computation. Additional related work by Thomas [27] describes acceleration of Monte-Carlo using FPGAs.…”

Section: Related Workmentioning

confidence: 99%

Accelerating financial applications on the GPU

Grauer-Gray

Killian

Schleicher

et al. 2013

Proceedings of the 6th Workshop on General Purpose Processor Using Graphics Processing Units

View full text Add to dashboard Cite

The QuantLib library is a popular library used for many areas of computational finance. In this work, the parallel processing power of the GPU is used to accelerate QuantLib financial applications. Black-Scholes, Monte-Carlo, Bonds, and Repo code paths in QuantLib are accelerated using hand-written CUDA and OpenCL codes specifically targeted for the GPU. Additionally, HMPP and OpenACC versions of the applications were created to drive the automatic generation of GPU code from sequential code. The results demonstrate a significant speedup for each code using each parallelization method. We were also able to increase the speedup of HMPP-generated code with auto-tuning.

show abstract

Pricing structured equity products on GPUs

Cited by 8 publications

References 4 publications

Algorithmic complexity in the heston model

Algorithmic complexity in the heston model

Data transfer minimization for financial derivative pricing using Monte Carlo simulation with GPU in 5G

Accelerating financial applications on the GPU

Contact Info

Product

Resources

About