The financial derivatives market is a high-stakes game, where even the slightest error in the valuation of a contract can lead to
big losses. Consequently, traders rely on complex mathematical models to arrive at the value and risk sensitivity of the contract.
The quick-paced nature of the financial markets makes it imperative that derivative valuations be fast and accurate.
One of the most widely used approaches, Monte Carlo models, can simulate millions of scenarios for underlying contract variables such as stock prices, commodity prices, interest rates, etc., but have computation times that are exceedingly long. The complexity of derivative contracts, and the need for both rapid model development and fast, accurate valuations, highlights some of the challenges faced by the derivatives market. Sophisticated software packages such as SciFinance® by SciComp, provide effective approaches for meeting these challenges.
SciFinance is a derivative model development environment that automatically generates serial C/C++ source code from
concise, high-level model specifications. Now, in order to dramatically speed up the execution time of the Monte Carlo
pricing and risk models, SciComp has added a feature that automatically generates NVIDIA® CUDA™-enabled
source code. This new code style allows critical sections of the pricing code to take advantage of the highly parallel
architecture of NVIDIA GPUs. To trigger the new code style, customers need simply add the keyword ‘CUDA’ to a model specification to produce
CUDA-enabled, compiler-ready parallel code. The result: speed increases from 30X to over 100X with one NVIDIA Tesla C1060 GPU. Further increases are nearly linear with the number of GPUs.
“The speed-ups our users can achieve with CUDA and GPUs are astonishing,” says Curt Randall, executive vice president of SciComp. “With parallel processing on GPUs, pricing a large portfolio of exotic contracts can be accomplished in minutes instead of hours. Because of the ease with which a financial institution can implement the NVIDIA solutions with our software, doing so is an easy choice for them.”