Giter VIP home page Giter VIP logo

Comments (4)

m4rs-mt avatar m4rs-mt commented on May 19, 2024

@Costigan Thank you for submitting this bug report. It seems to be an internal ILGPU compiler issue that should not occur and is not related to an error in your program. I have already investigated the described problem and I guess that it has been caused by a synchronization issue in the ABI class (fixed in d149410). After fixing this issue I can load the kernel using the CudaAccelerator and CLAccelerator classes without any problems.

Can you test whether the latest commits solve this problem? Furthermore, rolling back to version 0.6 should circumvent this problem as well.

from ilgpu.

m4rs-mt avatar m4rs-mt commented on May 19, 2024

Some additional remarks: It looks like you are not using any Group synchronization instructions after loading data into shared memory. Is this intended?

Note that using shared memory in combination with implicitly grouped kernels can lead to undefined and unintended behavior. We should add an error message to ILGPU that simply forbids such kernels. Please use an explicitly grouped kernel to have fine-grained control regarding the number of threads per group.

from ilgpu.

m4rs-mt avatar m4rs-mt commented on May 19, 2024

I'll close this issue for now, since the above-mentioned commit solves this problem on all test machines. Should you encounter further problems, we can always take up this topic again.

from ilgpu.

Costigan avatar Costigan commented on May 19, 2024

@m4rs-mt I'm sorry for not responding quickly. I ended up going with a multi-core solution, and performance was good enough. However, getting this implementation going will help me in the future. I'll get it running and add another comment confirming that. Wrt the synchronization instructions, you're right. I should have included one after loading shared memory. Thank you.

from ilgpu.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.