Get Started

#### Obtain Run-to-Run Reproducible Results

Learn how floating-point-intensive applications can provide both great performance and exactly the same results from run to run.

#### Sparse Linear Algebra Functions

An overview on the sparse linear algebra component (including BLAS functions, direct solvers, iterative solvers, and eigensolvers for sparse matrices) based on the FEAST algorithm.

#### Boost Performance for Tiny and Gigantic Computations

Improve operations on a single CPU core with minimal effort for small data sets. Efficiently solve large-scale sparse linear systems with tens of millions of equations on clusters.

## Cookbooks

Get routines to help you resolve various numerical problems, such as multiplying matrices, solving a system of equations, and computations involving fast Fourier transforms (FFT). While many problems do not have dedicated routines, you can solve them by assembling the building blocks in these recipes:

#### Numerics Recipes

**Noise Filtering in Financial Market Data Streams**

Use summary statistic routines that compute a correlation matrix for streaming data.

**Monte Carlo Method for Simulating European Options Pricing**

Compute a call and put with a basic random number generator.

**Black-Scholes Formula for European Options Pricing**

Speed up price computation by using vector math functions.

**Multiple Simple Random Sampling without Replacement**

Generate samples with a partial Fisher-Yates shuffle algorithm and random number generators.

**Histospline Technique for Scaling Images**

Use this technique to rescale color or grayscale images.

For more complete information about compiler optimizations, see our Optimization Notice.