Announcement

Collapse
No announcement yet.

The Open-Source NVIDIA PhysX 4.0 Code Is Now Available

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • The Open-Source NVIDIA PhysX 4.0 Code Is Now Available

    Phoronix: The Open-Source NVIDIA PhysX 4.0 Code Is Now Available

    Earlier this month NVIDIA announced their latest plans for an open-source PhysX and at the time put out the PhysX 3.4 SDK under a three-clause BSD license. Now the PhysX 4.0 release is available...

    Phoronix, Linux Hardware Reviews, Linux hardware benchmarks, Linux server benchmarks, Linux benchmarking, Desktop Linux, Linux performance, Open Source graphics, Linux How To, Ubuntu benchmarks, Ubuntu hardware, Phoronix Test Suite

  • #2
    Code drops is not the way to properly run a successful open source project.
    The work should be done out in the work so the community can provide feedback during development and open pull requests.

    Comment


    • #3
      I'll just leave this here: https://patents.google.com/patent/US...q=nvidia+physx

      Comment


      • #4
        Originally posted by uid313 View Post
        Code drops is not the way to properly run a successful open source project.
        The work should be done out in the work so the community can provide feedback during development and open pull requests.
        How the project leader wants to handle it's projects are for users/observers not to care. What this open source project gives us is transparency though, good enough if you ask me.

        Comment


        • #5
          Originally posted by Sethox View Post

          How the project leader wants to handle it's projects are for users/observers not to care. What this open source project gives us is transparency though, good enough if you ask me.
          These code drops are targeted to the Deep and Reinforcement Learning communities as way to help/easy them generate physical simulations on Nvidia GPU's. For many RL tasks the use of CPU to perform these and others simulations hinders the GPU use due to the constant data movement between CPU and GPU.

          For instance in the recent announcement of the MLperf benchmark the only category that Nvidia does not have submitted a entry was for the RL task due to great use of CPU

          Comment


          • #6
            I wonder how this compares to Bullet.

            Comment


            • #7
              Originally posted by Sethox View Post

              How the project leader wants to handle it's projects are for users/observers not to care. What this open source project gives us is transparency though, good enough if you ask me.
              Sure. It gives us transparency, that is great and we do much appreciate it.
              However there is more to open source than just code drops. By doing this, they are missing out.
              To really reap the benefits of open source you should interact with the community, and an issue tracker and a Gitter and freenode IRC channel, pull requests, CI/CD pipeline, nightly builds, maybe a wiki. So the community can get involved and report issues, send in patches, etc.

              Comment


              • #8
                Is this a sign for RTX in the future. Closed source when coming up will be GPU's from Intel, AMD and Nvidia. The first two are open source friendly.

                Comment

                Working...
                X