Hardware components usage during processing - PIX4Dmapper

Follow

This article explains how PIX4Dmapper utilizes each hardware component at each processing step.

Information:

The software is highly parallelized and takes advantage of multi-core CPUs, as well as MMX/SIMD instructions and NVIDIA GPU Cuda processing. However, the different steps of the processing do not use the resources the same way, and not all parts can take advantage of multi-core or CUDA.

Step 1      
CPU RAM Hard Disk GPU
Most important component.

In some sub-processing steps all the available CPU resources will be used whereas in others not all the CPU is used*.

Low usage. Low usage. (optional) Medium/high usage.
Step 2      
CPU RAM Hard Disk GPU
Most important component.

Fully used. This step will use all the CPU resources available.

Most important component.

Fully used. This step will use all the RAM resources available.

Low usage. Low Usage 
Step 3      
CPU RAM Hard Disk GPU
Low usage. High usage. Most important component.

The speed of the Hard Disk defines the processing speed.

No usage.
rayCloud      
CPU RAM Hard Disk GPU
Low usage. Low usage. Low usage. Most important component.

 

*Some parts of the processing cannot be paralleled and some of them do not consume a lot of resources. However, they need to be completed in order to start the next processing process.

Was this article helpful?
56 out of 57 found this helpful

Article feedback (for troubleshooting, post here instead)

2 comments

  • Zaki Afshar

    Dear Sir/Madam,

    I want to subscribe for monthly Pix4DMapper to process images I took with my drones. I do not have a stronger computer, can I rent a processing cloud on or through Pix4D website? If so, could you please let me know the details and all costs?

     

    Thanks.

    Zaki

  • Avatar
    Blaž (Pix4D)

    Dear Zaki,

    it is possible to purchase a Pix4Dcloud license that will give access to processing online. For more information see Pix4D store and Pix4Dcloud documentation.

    Best

Article is closed for comments.