YunQiang Su 58b5df09dc Clang: Add elementwise minnum/maxnum builtin functions (#129207) ...

With https://github.com/llvm/llvm-project/pull/112852, we claimed that
llvm.minnum and llvm.maxnum should treat +0.0>-0.0, while libc doesn't
require fmin(3)/fmax(3) for it.

To make llvm.minnum/llvm.maxnum easy to use, we define the builtin
functions for them, include
    __builtin_elementwise_minnum
    __builtin_elementwise_maxnum

All of them support _Float16, __bf16, float, double, long double.

2025-04-14 13:49:32 +08:00

254 KiB

Raw Blame History

View Raw