The Notebook Review forums were hosted by TechTarget, who shut down them down on January 31, 2022. This static read-only archive was pulled by NBR forum users between January 20 and January 31, 2022, in an effort to make sure that the valuable technical information that had been posted on the forums is preserved. For current discussions, many NBR forum users moved over to NotebookTalk.net after the shutdown.
Problems? See this thread at archive.org.

    CUDA & AW Graphics Amplifier & Linux

    Discussion in '2015+ Alienware 13 / 15 / 17' started by londere, Jun 18, 2018.

  1. londere

    londere Notebook Enthusiast

    Reputations:
    0
    Messages:
    10
    Likes Received:
    1
    Trophy Points:
    6
    Hello everyone!!


    I'm currently working on deep learning, as you know some of the top performance algorithms works only with high-end desktops machines and obviously with the top of the line GPUs.

    The question, in fact, is anyone know if its possible to use cuda with a high-end graphics on the amplifier and Linux?

    The facing problem is: I don't have money to build an exotic high-end desktop either to buy a high end laptop.

    My device is an Alienware 15 R2, 8GB RAM, SSD Adata Sx900 series, Nvidia GTX970M 3GB, Ubuntu Mate 16.04, CUDA 9.1 and CUDNN 7.2.X.

    In advance thanks!!!

    Sent from my Moto Z2 Play using Tapatalk
     
    londere, Jun 18, 2018
    #1
  2. Vasudev

    Vasudev Notebook Nobel Laureate

    Reputations:
    12,050
    Messages:
    11,278
    Likes Received:
    8,815
    Trophy Points:
    931
    Tensor or CuDNN?
     
    Vasudev, Jun 19, 2018
    #2
  3. londere

    londere Notebook Enthusiast

    Reputations:
    0
    Messages:
    10
    Likes Received:
    1
    Trophy Points:
    6
    CUDNN, darknet, tensor and matlab

    Sent from my Moto Z2 Play using Tapatalk
     
    londere, Jun 19, 2018
    #3
    Vasudev likes this.
  4. Vasudev

    Vasudev Notebook Nobel Laureate

    Reputations:
    12,050
    Messages:
    11,278
    Likes Received:
    8,815
    Trophy Points:
    931
    I feel its better to get 1080 if it fits your budget.
    Then again, a notebook with GTX 1080 will perform a lot faster than a card in AGA.
     
    Vasudev, Jun 21, 2018
    #4