Files
clang-p2996/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
Matt Arsenault c80282d333 AMDGPU: Directly select minimumnum/maximumnum with ieee_mode=0 (#141903)
The hardware min/max follow the IR rules with IEEE mode disabled,
so we can avoid the canonicalizes of the input. We lose the quieting
of a signaling nan if both inputs are nans, but we only require that
with strictfp.
2025-06-18 00:27:41 +09:00

274 KiB