Hitachi Vantara Pentaho Community Forums
Results 1 to 16 of 16

Thread: [Mondrian] Parallelization of MDX queries in mondrian using OpenCL

  1. #1
    Abhishek Sharma Guest

    Default [Mondrian] Parallelization of MDX queries in mondrian using OpenCL

    Hello all,

    With opencl in current picture of parallel computing, is it possible
    (even more, is it feasible in the first case) to optimize the
    performance of cube and roll operations in MySQL using opencl?? Kindly
    respond to this.

    Thank You.

    --
    Abhishek Sharma
    B-Tech Information Technology
    Indian Institute of Information Technology Allahabad
    _______________________________________________
    Mondrian mailing list
    Mondrian (AT) pentaho (DOT) org
    http://lists.pentaho.org/mailman/listinfo/mondrian

  2. #2
    Abhishek Sharma Guest

    Default [Mondrian] Re: Parallelization of MDX queries in mondrian usingOpenCL

    Hello all,

    With opencl in current picture of parallel computing, is it possible
    (even more, is it feasible in the first case) to optimize the
    performance of MDX queries on cubes using opencl?? Kindly
    respond to this.

    Thank You.


    --
    Abhishek Sharma
    B-Tech Information Technology
    Indian Institute of Information Technology Allahabad
    _______________________________________________
    Mondrian mailing list
    Mondrian (AT) pentaho (DOT) org
    http://lists.pentaho.org/mailman/listinfo/mondrian

  3. #3
    Julian Hyde Guest

    Default RE: [Mondrian] Parallelization of MDX queries in mondrian using OpenCL

    > Abhishek Sharma wrote:
    >
    > With opencl in current picture of parallel computing, is it possible
    > (even more, is it feasible in the first case) to optimize the
    > performance of cube and roll operations in MySQL using opencl?? Kindly
    > respond to this.


    Is your question about Mondrian or MySQL?

    Mondrian is implemented in Java, so opencl is not an option.

    Julian

    _______________________________________________
    Mondrian mailing list
    Mondrian (AT) pentaho (DOT) org
    http://lists.pentaho.org/mailman/listinfo/mondrian

  4. #4
    Abhishek Sharma Guest

    Default Re: [Mondrian] Parallelization of MDX queries in mondrian using OpenCL

    No its about Mondrian only, sorry for the previous error. Plus we do
    have opencl bindings for java available as well known as JOCL. So with
    this scene in front of us, I repost my question, is it possible to
    parallelize MDX queries in mondrian using OpenCL??

    Regards,

    Abhishek Sharma
    B-Tech Information Technology
    Indian Institute of Information Technology Allahabad
    _______________________________________________
    Mondrian mailing list
    Mondrian (AT) pentaho (DOT) org
    http://lists.pentaho.org/mailman/listinfo/mondrian

  5. #5
    Julian Hyde Guest

    Default RE: [Mondrian] Parallelization of MDX queries in mondrian using OpenCL

    > Abhishek Sharma wrote:
    >
    > No its about Mondrian only, sorry for the previous error. Plus we do
    > have opencl bindings for java available as well known as JOCL. So with
    > this scene in front of us, I repost my question, is it possible to
    > parallelize MDX queries in mondrian using OpenCL??


    Clearly it doesn't work at present. We have no OpenCL support whatsoever.

    If would be possible to implement certain MDX functions in OpenCL, and
    create Java wrappers for them using JOCL. That would be an interesting
    project. I would tend to focus on the MDX functions/operators that tend to
    be performance-intensive, such as Filter, Order, TopCount/BottomCount,
    Crossjoin.

    See http://jira.pentaho.com/browse/MONDRIAN-874 for a discussion of
    parallelism. Many of the issues raised in that bug would relate to an OpenCL
    implementation.

    Julian

    _______________________________________________
    Mondrian mailing list
    Mondrian (AT) pentaho (DOT) org
    http://lists.pentaho.org/mailman/listinfo/mondrian

  6. #6
    Abhishek Sharma Guest

    Default Re: [Mondrian] Parallelization of MDX queries in mondrian using OpenCL

    Thanks

    --
    Abhishek Sharma
    B-Tech Information Technology
    Indian Institute of Information Technology Allahabad
    _______________________________________________
    Mondrian mailing list
    Mondrian (AT) pentaho (DOT) org
    http://lists.pentaho.org/mailman/listinfo/mondrian

  7. #7
    Abhishek Sharma Guest

    Default Re: [Mondrian] Parallelization of MDX queries in mondrian using OpenCL

    One more thing I wanted to confirm from you Julian is that - In SSAS
    provided by Microsoft (which I currently use for BI) the cube is a
    separate storage of data which is created out of the RDBMS (i.e
    created about dimensions and facts of course). But I don't think its
    the same in Pentaho mondrian, right?? There we are directly using the
    data and agreegating it in runtime, right?? If not please correct me
    wherever i am wrong. Thanks



    --
    Abhishek Sharma
    B-Tech Information Technology
    Indian Institute of Information Technology Allahabad
    _______________________________________________
    Mondrian mailing list
    Mondrian (AT) pentaho (DOT) org
    http://lists.pentaho.org/mailman/listinfo/mondrian

  8. #8
    Luc Boudreau Guest

    Default Re: [Mondrian] Parallelization of MDX queries in mondrian using OpenCL

    You are right. Mondrian aggregates the data in memory and feeds itself from
    a RDBMS.

    Luc

    On Sat, Mar 5, 2011 at 11:44 AM, Abhishek Sharma <spyzer.abhishek0 (AT) gmail (DOT) com
    > wrote:


    > One more thing I wanted to confirm from you Julian is that - In SSAS
    > provided by Microsoft (which I currently use for BI) the cube is a
    > separate storage of data which is created out of the RDBMS (i.e
    > created about dimensions and facts of course). But I don't think its
    > the same in Pentaho mondrian, right?? There we are directly using the
    > data and agreegating it in runtime, right?? If not please correct me
    > wherever i am wrong. Thanks
    >
    >
    >
    > --
    > Abhishek Sharma
    > B-Tech Information Technology
    > Indian Institute of Information Technology Allahabad
    > _______________________________________________
    > Mondrian mailing list
    > Mondrian (AT) pentaho (DOT) org
    > http://lists.pentaho.org/mailman/listinfo/mondrian
    >


    _______________________________________________
    Mondrian mailing list
    Mondrian (AT) pentaho (DOT) org
    http://lists.pentaho.org/mailman/listinfo/mondrian

  9. #9
    Abhishek Sharma Guest

    Default Re: [Mondrian] Parallelization of MDX queries in mondrian using OpenCL

    Thanks for clarifying that. Please don't mind answering a pretty basic
    question as well. The BI platform of pentaho, does it contain all the
    features of reporting, ETL and analysis or only some part of it. I
    mean, if I wish to develop for Mondrian and test the performance
    through reports do I need to use only Mondrian source or do i need to
    go for BI Platform source. Please do answer this small and basic
    question.

    Thank You.

    --
    Abhishek Sharma
    B-Tech Information Technology
    Indian Institute of Information Technology Allahabad
    _______________________________________________
    Mondrian mailing list
    Mondrian (AT) pentaho (DOT) org
    http://lists.pentaho.org/mailman/listinfo/mondrian

  10. #10
    Luc Boudreau Guest

    Default Re: [Mondrian] Parallelization of MDX queries in mondrian using OpenCL

    No problem. We're here to answer your questions. Mondrian is a stand-alone
    project. Although it is integrated in the Pentaho platform, it does not
    depend on it. It can be run in a separate webapp container or directly
    embedded in your software.

    Luc

    On Sat, Mar 5, 2011 at 11:58 AM, Abhishek Sharma <spyzer.abhishek0 (AT) gmail (DOT) com
    > wrote:


    > Thanks for clarifying that. Please don't mind answering a pretty basic
    > question as well. The BI platform of pentaho, does it contain all the
    > features of reporting, ETL and analysis or only some part of it. I
    > mean, if I wish to develop for Mondrian and test the performance
    > through reports do I need to use only Mondrian source or do i need to
    > go for BI Platform source. Please do answer this small and basic
    > question.
    >
    > Thank You.
    >
    > --
    > Abhishek Sharma
    > B-Tech Information Technology
    > Indian Institute of Information Technology Allahabad
    >


    _______________________________________________
    Mondrian mailing list
    Mondrian (AT) pentaho (DOT) org
    http://lists.pentaho.org/mailman/listinfo/mondrian

  11. #11
    Abhishek Sharma Guest

    Default Re: [Mondrian] Parallelization of MDX queries in mondrian using OpenCL

    okay, so if i need to view reports or just data from OLAP what else
    apart from Mondrian will i need to use??

    --
    Abhishek Sharma
    B-Tech Information Technology
    Indian Institute of Information Technology Allahabad
    _______________________________________________
    Mondrian mailing list
    Mondrian (AT) pentaho (DOT) org
    http://lists.pentaho.org/mailman/listinfo/mondrian

  12. #12
    Abhishek Sharma Guest

    Default Re: [Mondrian] Parallelization of MDX queries in mondrian using OpenCL

    i mean if i change something in mondrian, and then i need to fire mdx
    and view the data and the releated performance what all do i need
    apart from mondrian, please tell.


    --
    Abhishek Sharma
    B-Tech Information Technology
    Indian Institute of Information Technology Allahabad
    _______________________________________________
    Mondrian mailing list
    Mondrian (AT) pentaho (DOT) org
    http://lists.pentaho.org/mailman/listinfo/mondrian

  13. #13
    Luc Boudreau Guest

    Default Re: [Mondrian] Parallelization of MDX queries in mondrian using OpenCL

    You can deploy Mondrian in a webapp container and then query it using
    Warehouse Explorer (Rex).

    It's available here: https://sourceforge.net/projects/whex/

    Mondrian is available here:
    http://sourceforge.net/projects/mond...n-3.2.1.13885/

    Luc


    On Sat, Mar 5, 2011 at 12:20 PM, Abhishek Sharma <spyzer.abhishek0 (AT) gmail (DOT) com
    > wrote:


    > i mean if i change something in mondrian, and then i need to fire mdx
    > and view the data and the releated performance what all do i need
    > apart from mondrian, please tell.
    >
    >
    > --
    > Abhishek Sharma
    > B-Tech Information Technology
    > Indian Institute of Information Technology Allahabad
    >


    _______________________________________________
    Mondrian mailing list
    Mondrian (AT) pentaho (DOT) org
    http://lists.pentaho.org/mailman/listinfo/mondrian

  14. #14
    Abhishek Sharma Guest

    Default Re: [Mondrian] Parallelization of MDX queries in mondrian using OpenCL

    Thanks
    --
    Abhishek Sharma
    B-Tech Information Technology
    Indian Institute of Information Technology Allahabad
    _______________________________________________
    Mondrian mailing list
    Mondrian (AT) pentaho (DOT) org
    http://lists.pentaho.org/mailman/listinfo/mondrian

  15. #15
    Abhishek Sharma Guest

    Default Re: [Mondrian] Parallelization of MDX queries in mondrian using OpenCL

    Hello everyone,

    Previously I was discussing about introducing parallelism into Mondrian code
    specifically GPGPU computing. Sorry but I lost touch to the community for a
    while coz of some personal work. I have a question. When I went through
    Mondrian's documentation I found out that most of the work of *backend* is
    carried out by database manager itself rather mondrian. And to be precise
    GPGPU computing can only scale up calculations. So is there calculation
    based code in Mondrian as well?? Also when I was going through the API
    documentation it was pretty hard to locate as in which class might be using
    which smaller or fundamental class for its functionalities. Because for
    parallelization we need to find out the "hotspots" of code where most of the
    processing takes place and then there is one more question that whether that
    hotspot has calculations in it. So those calculations can be carried out
    parallely (if possible, some codes just can't be parallelized without
    changing design!!!). So locating out hotspot can crucial areas can be made
    easier if we have a "class diagram", so is there any such class diagram
    which I may refer to.

    I would like to ask the senior developers of mondrian about the above
    mentioned state. If mondrian's code in itself involves no or less
    calculations then I might have to target underlying RDBMS to make things
    faster. Although I believe that since there is caching of data involved then
    there must be some calculations going on in mondrian as well. So please
    guide me about this.


    --
    Abhishek Sharma
    B-Tech Information Technology
    Indian Institute of Information Technology Allahabad

    On Sun, Mar 6, 2011 at 12:25 AM, Abhishek Sharma <spyzer.abhishek0 (AT) gmail (DOT) com
    > wrote:


    > Thanks
    > --
    > Abhishek Sharma
    > B-Tech Information Technology
    > Indian Institute of Information Technology Allahabad
    >


    _______________________________________________
    Mondrian mailing list
    Mondrian (AT) pentaho (DOT) org
    http://lists.pentaho.org/mailman/listinfo/mondrian

  16. #16
    Julian Hyde Guest

    Default RE: [Mondrian] Parallelization of MDX queries in mondrian using OpenCL

    There are class diagrams in the online javadoc:

    http://mondrian.pentaho.com/api/overview-summary.html

    While class diagrams undoubtedly help in understanding the code, they don't
    help much in finding hotspots. To find hotspots, do profiling using a
    realistic benchmark. Even easier, run the benchmark and issue 'kill -QUIT
    <pid>' signals to the process to cause Java to print a stack dump. Whever
    the code is, that's likely to be your hotspot.

    Mondrian is ROLAP. We intentionally do as much work as possible in the
    database. We reason that a good database is written in C or C++, well tuned,
    and parallelizable/scalable.

    If you are looking for a DBMS to work with, consider LucidDB, and open
    source database. We have worked closely with them in the past (in fact, I am
    a committer). Mondrian performs extremely well on LucidDB, but LucidDB could
    nevertheless benefit from novel evaluation strategies.

    Julian



    _____

    From: mondrian-bounces (AT) pentaho (DOT) org [mailto:mondrian-bounces (AT) pentaho (DOT) org] On
    Behalf Of Abhishek Sharma
    Sent: Friday, April 08, 2011 10:25 PM
    To: Luc Boudreau
    Cc: Mondrian developer mailing list
    Subject: Re: [Mondrian] Parallelization of MDX queries in mondrian using
    OpenCL


    Hello everyone,

    Previously I was discussing about introducing parallelism into Mondrian code
    specifically GPGPU computing. Sorry but I lost touch to the community for a
    while coz of some personal work. I have a question. When I went through
    Mondrian's documentation I found out that most of the work of *backend* is
    carried out by database manager itself rather mondrian. And to be precise
    GPGPU computing can only scale up calculations. So is there calculation
    based code in Mondrian as well?? Also when I was going through the API
    documentation it was pretty hard to locate as in which class might be using
    which smaller or fundamental class for its functionalities. Because for
    parallelization we need to find out the "hotspots" of code where most of the
    processing takes place and then there is one more question that whether that
    hotspot has calculations in it. So those calculations can be carried out
    parallely (if possible, some codes just can't be parallelized without
    changing design!!!). So locating out hotspot can crucial areas can be made
    easier if we have a "class diagram", so is there any such class diagram
    which I may refer to.

    I would like to ask the senior developers of mondrian about the above
    mentioned state. If mondrian's code in itself involves no or less
    calculations then I might have to target underlying RDBMS to make things
    faster. Although I believe that since there is caching of data involved then
    there must be some calculations going on in mondrian as well. So please
    guide me about this.



    --
    Abhishek Sharma
    B-Tech Information Technology
    Indian Institute of Information Technology Allahabad

    On Sun, Mar 6, 2011 at 12:25 AM, Abhishek Sharma
    <spyzer.abhishek0 (AT) gmail (DOT) com> wrote:


    Thanks
    --

    Abhishek Sharma
    B-Tech Information Technology
    Indian Institute of Information Technology Allahabad







    _______________________________________________
    Mondrian mailing list
    Mondrian (AT) pentaho (DOT) org
    http://lists.pentaho.org/mailman/listinfo/mondrian

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •  
Privacy Policy | Legal Notices | Safe Harbor Privacy Policy

Copyright © 2005 - 2019 Hitachi Vantara Corporation. All Rights Reserved.