| Issue |
181846
|
| Summary |
[libc][math] Optimize C23 half precision pow function
|
| Labels |
libc
|
| Assignees |
|
| Reporter |
AnonMiraj
|
`powf16` implementation currently performs all computations in double precision. To improve performance it should use float whenever possible, finding an alternative way to compute for integer y would also be ideal
https://github.com/llvm/llvm-project/pull/159906#pullrequestreview-3814710951
![]()
_______________________________________________
llvm-bugs mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-bugs
