You are here: Welcome
Dew Math for .NET
ContentsIndex
PreviousUpNext
Welcome
 
Welcome to Dew Math for .NET 

 

Dew Math adds the following capabilities to your development environment:

  • Comprehensive set of mathematical and statistical functions.
  • Substantial performance improvements of floating point math by exploiting the SSE3, SSE4 and Intel AVX 1, AVX 2 and AVX 512 instruction sets.
  • Improved compactness and readability of code.
  • Significantly shorter development times by protecting the developer from a wide range of possible errors.
  • Optimizing the performance of .NET code can be a real challenge. MtxVec delivers patterns which allow fast executing floating point code to be also written fast.
  • The advantage of SSE instruction sets can be exploited only with unmanaged code.
  • Provides an interface to LAPACK 3.7 to be used from any .NET language.
  • Unmanaged code is encapsulated in to efficient and thin wrappers making the code "safe" for the end user, with little or no overhead associated with transitions from managed to unmanaged code. Many difficult to trace bugs and performance issues are avoided in this way.
  • Efficient memory usage and unmanaged code interop.
  • Especially for complex numbers, the performance gain against native .NET code can be very large.
  • Cougar OpenCL libary for easy access to fast Open CL kernels. Over 2000 kernels are included with the library.
  • Double and Single precision support for all functions of the core library via Dew.Math and Dew.Math.Single namespaces.

 

Typical performance improvements observed by most users are 3-5 times for vector functions, but speed ups up to 20 times are not rare especially on Core i7 CPUs. The matrix multiplication for example is faster up to 40 times.

Copyright (c) 1999-2022 by Dew Research. All rights reserved.
What do you think about this topic? Send feedback!