Implemented the Kalman Filter Algorithms on GPU using CUDA programming language. Analysed the run-time performance gain obtained by parallel computation of the various stages of the algorithm.Speed up of 1000x is observed for large input sets.
Implemented the Kalman Filter Algorithms on GPU using CUDA programming language. Analysed the run-time performance gain obtained by parallel computation of the various stages of the algorithm
The GPU and CUDA SDK are required to run the demo code.
The GPU-based matrix inverse can be found here
$make
$./kalman -ns 1000 -no 250-ns is the number of state and -no is the number of observation for Kalman filter
Implemented the Kalman Filter Algorithms on GPU using CUDA programming language. Analysed the run-time performance gain obtained by parallel computation of the various stages of the algorithm.Speed up of 1000x is observed for large input sets.