More performance writing less code
Libra SDK is our flagship product, a highly sophisticated runtime including
API, sample programs and documentation for massively accelerating software computations.
Developing and designing high performance software for CPUs and GPUs using Libra SDK is robust and easy.
You start with a well-known and simple API following standard interfaces in common programming environments
resulting in less code and massive performance to your program. Hundreds of high performance functions and operators
focused on standard math, dense and sparse matrix/vector operations also including high performance random number generator, compares, conditional ops, fft, equation solvers and lots more.
Libra: C++ programming API for both the CPU and GPU.
Write hardware independent software using standard programming languages C, C++,
Java, C#, matlab, octave, fortran etc. Accelerate computations using the power of
CPUs and GPUs. Write code once and deploy on numerous hardware platforms - NVIDIA, AMD, Intel
and future devices.
Custom library development with Libra SDK
gVar add(gVar array1, gVar array2)
{
return array1 + array2;
}
A portable function to access the power of CUDA, OpenCL, OpenGL (GPU) and x86/x64 (CPU) devices.
Hello World
Libra on CUDA devices with less code than native CUDA
Libra on OpenCL devices with less code than native OpenCL
For more information regarding purchase and pricing, please contact us at
sales@gpusystems.com