Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Code compiling and tests passing with HEMELB_USE_SSE3=OFF #816

Merged
merged 3 commits into from
May 6, 2024
Merged

Conversation

mobernabeu
Copy link
Contributor

Trying to compile code on my Apple M2 to look into #815

@mobernabeu mobernabeu requested a review from rupertnash March 19, 2024 11:26
@rupertnash
Copy link
Member

Is this making the forcing collisions etc work without SSE? If so, great! I have just received a new MacBook with an M3 chip so can test this once I'm set up for development.

  • Tests are failing in CI
  • I've tried to move away from using raw pointers and switch to using std::span instead for the parameters
inline static void CalculateForceDistribution(const distribn_t &tau,
                                                      const LatticeVelocity& velocity,
                                                      const LatticeForceVector& force,
                                                      mut_span forceDist)
  • I'd prefer the "standard" interface into the velocity set related operations to use the Vector types. Then (at least for not horrible pseudo assembly that is the SSE version) you can write cleaner things like auto vScalarProductF = Dot(velocity, force); instead of your line 477

@mobernabeu
Copy link
Contributor Author

mobernabeu commented Mar 20, 2024

Thanks for the tip, @rupertnash. I'm bit behind on design choices. This is indeed passing without SSE3 on my M2, but I have buggered up the main build. I'll tidy things up as suggested.

Copy link
Member

@rupertnash rupertnash left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'm happy now

@rupertnash rupertnash merged commit b7dfb88 into main May 6, 2024
18 checks passed
@rupertnash rupertnash deleted the sse3_off branch May 6, 2024 10:03
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants