Achieve stunning acceleration for derivative pricing models

SciGPU is the parallel computing component of SciFinance®. Designed to take hand coding out of derivatives model development, SciFinance automatically generates C/C++/CUDA source code for any Monte Carlo-based pricing model.

SciGPU automatically generates NVIDIA GPU-enabled or OpenMP compliant source code for derivatives pricing models. No CUDA or parallel programming expertise is required.

SciComp Consulting, our highly-skilled and professional quantitative development team provides expert, cost-effective GPU programming and porting services for PDE (partial differential equation) pricing models.

Typical speedups:

• CUDA Monte Carlo pricing models:
  • 30X-50X faster than serial code (single GPU, double precision)
• OpenMP-compliant code executes in the multi-processor environment with nearly linear speed-up
  • 3.9X faster than serial code on a quad-core PC, 22X on a 24 CPU workstation

>Download the SciComp / NVIDIA Tech Brief to learn more How does SciFinance work? Select from hundreds of provided derivatives pricing model specifications Modify the model specification as needed Test the serial version of the pricing model Add the keyword "CUDA" to the specification and re-synthesize SciFinance does the rest by automatically generating fully documented GPU-enabled pricing model source code

Why use SciFinance for GPU computing?

• SciFinance automatically generates NVIDIA GPU-enabled or OpenMP-compliant source code for any Monte Carlo-based pricing model.
• No CUDA or parallel programming expertise required
• SciFinance automatically generates optimized CUDA code
• Optimized for double precision
• Mixed single/double precision code style option available
• Supports complex models with large parameter lists while respecting the CUDA kernel arguments limit
• Efficient CUDA local memory management
• Multi-GPU support

> Brief Overview Movie of GPU Computing with SciFinance

Case Studies

>Download the Reval/SciComp Case Study In order to quickly develop new structured products and vastly speed up Monte Carlo-based derivatives for its Software-as-a-Service (SaaS) customers, Reval uses SciFinance.