Decision Optimization

 View Only
  • 1.  GPU accleration issue of CPLEX

    Posted Tue July 19, 2011 03:58 AM

    Originally posted by: duyuquan2006


    Hi R&D engineers of CPLEX,

    By default, CPLEX runs several threads in parallel on multi-cores/CPUs. Do you plan to add the computation functionality of GPU, which may complement the ability of CPUs to some extent, and accelerate the computation? If the answer is NO, could you tell me Why?

    Thanks a lot.

    Best,

    Yuquan
    #CPLEXOptimizers
    #DecisionOptimization


  • 2.  Re: GPU accleration issue of CPLEX

    Posted Tue July 19, 2011 04:18 AM

    Originally posted by: SystemAdmin


    First of all, we cannot discuss future code extensions in public as this has some subtle legal consequences.

    Using the GPU to speed-up MIP solvers is certainly an interesting idea, but it has a number of issues to get it into a product like CPLEX. As an academic you would only need to make sure that it runs on some combination of CPU, GPU, and operating system, and then you can write a paper that discusses the approach and presents computational experiments. For a commercial product like CPLEX, you need to make sure that it basically runs on any combination of CPU, GPU, and OS, which is much more challenging. So, it boils down (as always) to the trade-off between our investment in development time and other resources compared to the potential benefit that our users would have.
    Tobias
    #CPLEXOptimizers
    #DecisionOptimization


  • 3.  Re: GPU accleration issue of CPLEX

    Posted Thu January 30, 2014 04:55 AM

    Originally posted by: J.Haas


    Hello,

    is there any change/news regarding the implementation of Cplex on gpu's?

     

    Cheers!


    #CPLEXOptimizers
    #DecisionOptimization


  • 4.  Re: GPU accleration issue of CPLEX

    Community Leadership
    Posted Thu January 30, 2014 11:42 AM

    Dear Jannik,

    The situation for CPLEX with respect to GPUs has not changed since Tobias answered the original question. And, as was the case then, we don't discuss publicly about our plans. So there's not much I can help with, I suppose...

    Xavier


    #CPLEXOptimizers
    #DecisionOptimization


  • 5.  Re: GPU accleration issue of CPLEX

    Posted Tue January 26, 2016 04:35 AM

    Originally posted by: EiFx


    Hello again.

     

    Another two year has passed, and I was wondering if there is any change/news regarding the implementation of CPLEX on GPU's this time?

     

    Cheers!


    #CPLEXOptimizers
    #DecisionOptimization


  • 6.  Re: GPU accleration issue of CPLEX

    Community Leadership
    Posted Tue January 26, 2016 12:15 PM

    Hello,

    The situation has not changed: there is not a CPLEX release that uses GPUs, and we don't discuss about future plans.

    Thanks!

     

    Xavier


    #CPLEXOptimizers
    #DecisionOptimization


  • 7.  RE: Re: GPU accleration issue of CPLEX

    Posted Wed June 08, 2022 01:55 PM
    Edited by System Fri January 20, 2023 04:09 PM

    It is now year 2022. Would you please share any insight on GPU helping CPLEX computation? Also, I am considering using IBM Watson Cloud environment. Does Watson utilize GPU to speed up CP computation?




  • 8.  RE: Re: GPU accleration issue of CPLEX

    Community Leadership
    Posted Wed June 08, 2022 05:25 PM

    Dear Andy,

    The situation has not changed: there is not a CPLEX release that uses GPUs, and we don't discuss future plans for our products.
    Each CPLEX release comes with release notes. The last ones are available at https://www.ibm.com/docs/en/icos/22.1.0?topic=2210-release-notes-cplex.  Rest assured that a change such as adding the ability to use GPUs would have its place in the release notes for that version...

    It is possible to use GPUs in Watson Cloud: this may help on some workloads, but not on computations done by CPLEX.

    Best regards,



    ------------------------------
    Xavier
    ------------------------------