Results 1 to 4 of 4

Thread: Profiling of kernel code

  1. #1
    Junior Member
    Join Date
    Mar 2013

    Profiling of kernel code

    I have a kernel code which is taking 8 ms. Kernel code is large, i want to know which line or part of kernel is causing bottleneck?

    What is the best way to identify bottleneck inside kernel?

    Note: I am using AMD machine.

  2. #2

    Re: Profiling of kernel code

    I have yet to find a good OpenCL profiler to measure performance within a kernel. My usual approach is to break the kernel into smaller pieces and profile each of those. Not ideal, but it may work for you.

  3. #3
    Senior Member
    Join Date
    Oct 2012

    Re: Profiling of kernel code

    Same here.

    Havent found anything that can profile my kernels. Just a sharp look at the file can help you profiling. Think about registers, global Mem access, coalescing, branching and so on. Dismiss anything you dont need. Try to spread your kernel over more or less workitems.

  4. #4
    Junior Member
    Join Date
    Mar 2013
    Thanks kylelutz and clint3112.

Similar Threads

  1. use pointer in kernel code
    By zakketto in forum OpenCL
    Replies: 4
    Last Post: 12-06-2010, 10:45 AM
  2. Profiling Code
    By PaulS in forum OpenCL
    Replies: 15
    Last Post: 10-15-2009, 04:14 AM

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
Proudly hosted by Digital Ocean