Sign Up

Sign Up to our social questions and Answers Engine to ask questions, answer people’s questions, and connect with other people.

Have an account? Sign In

Have an account? Sign In Now

Sign In

Login to our social questions & Answers Engine to ask questions answer people’s questions & connect with other people.

Sign Up Here

Forgot Password?

Don't have account, Sign Up Here

Forgot Password

Lost your password? Please enter your email address. You will receive a link and will create a new password via email.

Have an account? Sign In Now

You must login to ask a question.

Forgot Password?

Need An Account, Sign Up Here

Please briefly explain why you feel this question should be reported.

Please briefly explain why you feel this answer should be reported.

Please briefly explain why you feel this user should be reported.

Sign InSign Up

The Archive Base

The Archive Base Logo The Archive Base Logo

The Archive Base Navigation

  • SEARCH
  • Home
  • About Us
  • Blog
  • Contact Us
Search
Ask A Question

Mobile menu

Close
Ask a Question
  • Home
  • Add group
  • Groups page
  • Feed
  • User Profile
  • Communities
  • Questions
    • New Questions
    • Trending Questions
    • Must read Questions
    • Hot Questions
  • Polls
  • Tags
  • Badges
  • Buy Points
  • Users
  • Help
  • Buy Theme
  • SEARCH
Home/ Questions/Q 6143919
In Process

The Archive Base Latest Questions

Editorial Team
  • 0
Editorial Team
Asked: May 23, 20262026-05-23T18:34:58+00:00 2026-05-23T18:34:58+00:00

I am doing Finite Difference computation (Stencil Computation) on GPU (Fermi) using CUDA. When

  • 0

I am doing Finite Difference computation (Stencil Computation) on GPU (Fermi) using CUDA. When I tested my code using CUDA profiler, I found the occupany was 0.333. After I ordered my computation and increased the occupany to 0.677, the execution time of the kernel didn’t decrease but increased. In other words, there was a decrease in performance when the occupany got increased by 1/3.

My question is:

Does the performance of the kernel depend on the computation irrespective of the occupancy?

  • 1 1 Answer
  • 0 Views
  • 0 Followers
  • 0
Share
  • Facebook
  • Report

Leave an answer
Cancel reply

You must login to add an answer.

Forgot Password?

Need An Account, Sign Up Here

1 Answer

  • Voted
  • Oldest
  • Recent
  • Random
  1. Editorial Team
    Editorial Team
    2026-05-23T18:34:58+00:00Added an answer on May 23, 2026 at 6:34 pm

    The answer is “it depends”, both on the characteristics of your workload and on how you define performance. Generally speaking, if your bottleneck is math throughput you’re often fine with a lower occupancy (12.5%-33%), but if your bottleneck is memory then you usually want a higher occupancy (66% or higher). This is just a rule of thumb, not an absolute rule. Most kernels fall somewhere in the middle but there are exceptions at both extremes.

    Occupancy is the maximum number of threads of your kernel that can be active at once (limited by register count per thread or other resources) divided by the maximum number of threads the GPU can have active when not limited by other resources. Active means the thread has hardware resources assigned and is available for scheduling, not that it has any instructions executing on a given clock cycle.

    After issuing instruction i for a thread, the instruction i+1 for that thread might not be able to run immediately, if it depends on the result of instruction i. If that instruction is a math instruction, the result will be available in a few clock cycles. If it’s a memory load instruction, it might be 100s of cycles. Rather than waiting, the GPU will issue instructions from some other thread who’s dependencies are satisfied.

    So if you’re mostly doing math, you only need a few (few in GPU terms; on a CPU it would be considered many) threads to hide the few cycles of latency from math instructions, so you can get away with low occupancy. But if you’ve got a lot of memory traffic, you need more threads to ensure that some of them are ready to execute on every cycle, since each one spends a lot of time “sleeping” waiting for memory operations to complete.

    If the algorithmic changes you made to increase occupancy also increased the amount of work done on each thread, and if you already had enough threads to keep the GPU busy, then the change will just slow you down. Increasing occupancy only improves performance up to the point where you have enough threads to keep the GPU busy.

    • 0
    • Reply
    • Share
      Share
      • Share on Facebook
      • Share on Twitter
      • Share on LinkedIn
      • Share on WhatsApp
      • Report

Sidebar

Related Questions

Doing an ajax get request works as expected using the following code: $.ajax({ type:
Doing some refactoring in some legacy code I've found in a project. This is
Doing a search using django-sphinx gives me results._sphinx that says there were 68 results,
I'm working on a finite deterministic automaton based on this . From this code:
Doing some code reading and stumbled upon this snippet that I haven't seen before:
Doing some code reviews lately I came across a number of classes that have
Doing this: s = hello s[0] outputs the character code value 104 . What
Doing a search around I've found this kind of question being asked in the
Doing cross platform development with 64bit. Using gcc/linux and msvc9/server 2008. Just recently deployed
Doing DJango 1.3 local development using manage.py runserver Created a directory called static in

Explore

  • Home
  • Add group
  • Groups page
  • Communities
  • Questions
    • New Questions
    • Trending Questions
    • Must read Questions
    • Hot Questions
  • Polls
  • Tags
  • Badges
  • Users
  • Help
  • SEARCH

Footer

© 2021 The Archive Base. All Rights Reserved
With Love by The Archive Base

Insert/edit link

Enter the destination URL

Or link to existing content

    No search term specified. Showing recent items. Search or use up and down arrow keys to select an item.