octave-bug-tracker
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Octave-bug-tracker] [bug #64971] parfor and parallel processing pools f


From: Liang Tang
Subject: [Octave-bug-tracker] [bug #64971] parfor and parallel processing pools for multi-core
Date: Sun, 3 Dec 2023 16:55:49 -0500 (EST)

URL:
  <https://savannah.gnu.org/bugs/?64971>

                 Summary: parfor and parallel processing pools for multi-core
                   Group: GNU Octave
               Submitter: lt1234
               Submitted: Sun 03 Dec 2023 09:55:47 PM UTC
                Category: Octave Function
                Severity: 3 - Normal
                Priority: 5 - Normal
              Item Group: Feature Request
                  Status: None
             Assigned to: None
         Originator Name: lt1234
        Originator Email: 
             Open/Closed: Open
                 Release: 8.2.0
         Discussion Lock: Any
        Operating System: Any
           Fixed Release: None
         Planned Release: None


    _______________________________________________________

Follow-up Comments:


-------------------------------------------------------
Date: Sun 03 Dec 2023 09:55:47 PM UTC By: Liang Tang <lt1234>
Pls consider to enable parfor in Octave for multi-core. 

The current status of parfor is found in command line help:  

*Warning:* parallel processing pools are currently unimplemented in Octave;

Why parfor?  parfor requires min or no change to the existing codes to test
the effectiveness of parallel computing. This minimizes users' investment to
identify the potential time/cost reduction opportunities.    

Why multi-core? HPC computing is limited to well-staffed business while high
power multi-core desktops or laptops are widely available at very moderate
cost.  The solution of many problems that must be conducted on mainframe or
clusters in the past now can be solved locally.   

Why to request now?  Lots of people will give their examples and needs.  About
8-10 years ago, to conduct a nonlinear solution or NLP in matlab vs. Octave,
for the problems I solved, it was roughly 50% difference in elapsed time. 
Since matlab parallel toolbox actually worked, starting from about 2016-2017
time frame, I had to hit the ctrl-C in Octave for those type of problems.  
Effectively NLP, in many different forms, is the main stream problem to solve
now days.  








    _______________________________________________________

Reply to this item at:

  <https://savannah.gnu.org/bugs/?64971>

_______________________________________________
Message sent via Savannah
https://savannah.gnu.org/




reply via email to

[Prev in Thread] Current Thread [Next in Thread]