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

vec_slqi() operation incorrectly nests defined (_ARCH_PWR10) code before if (__builtin_constant_p (shb) && ((shb % 8) == 0)) #186

Open
munroesj52 opened this issue Dec 20, 2023 · 1 comment

Comments

@munroesj52
Copy link
Contributor

The vec_slqi(0 operation is not generating vsldoi when (__builtin_constant_p (shb) && ((shb % 8) == 0)).
For the case: vec_slqi (vec, 64) and -mcpu-power10, PVECLIB will generate vslq but requires vector load of constant (__int128) 0.
This is more code and cycles then the simpler xxspltib/vsldoi sequence.

The correction moves the defined (_ARCH_PWR10) conditional code sequence to the if (__builtin_constant_p (shb) && ((shb % 8) == 0)) else block.

@munroesj52
Copy link
Contributor Author

This also impacts vec_srqi(), vec_sraqi(0, and vec_rlqi().

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

No branches or pull requests

1 participant