Geometric Performance Primitives (GPP)

Introduction

Computational geometry engines play a pivotal role in advanced Graphical Information Systems (GIS), integrated circuit design (EDA), computer vision, and motion planning solutions. Visualization and analysis of ever increasing amounts of data requires a computational foundation that can meet the challenge with flexible algorithms that are optimized for high performance GPU processing. Fixstars' Geometric Performance Primitives (GPP) library is perhaps the only computational geometry engine that's optimized for massive parallelization with accelerated NVIDIA GPU technology. This gives GPP incredible speed and the ability to process truly enormous datasets.

Key Features

High-Performance GPU Acceleration: GPP is specifically engineered to leverage the power of NVIDIA GPUs, enabling it to achieve remarkable parallelization.
Robust Algorithms: GPP incorporates cutting-edge, robust algorithms, ensuring accurate and reliable results even in complex geometric scenarios.
Superior Speed and Memory Efficiency: GPP delivers up to 25 times faster performance compared to reference CPUs while maintaining a minimal memory footprint.

Applications

GPP is ideal for a range of applications, including:

Advanced Geographical Information Systems (GIS)
Electronic Design Automation (EDA)
Computer Vision and Image Processing
Motion Planning and Robotics

How GPP Helps You

By harnessing the power of GPP, users can:

Process large datasets with unprecedented speed.
Achieve high levels of accuracy, especially in complex geometric scenarios.
Reduce memory consumption when compared with traditional CPU processing.
Gain a competitive advantage with enhanced efficiency and reduced computational time.

Download Documentation

To learn more about GPP's capabilities and technical specifications, you can download our detailed documentation:

GPP Overview and Specification:

This document provides an introduction to GPP, its functions, system requirements and performance metrics.

Download PDF

Robust and Efficient Polygon Overlay on Parallel Stream Processors:

This technical paper details the core algorithm of GPP's overlay capabilities, with performance and testing data.

Read the paper

About us

IR