Files
clang-p2996/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
Matt Arsenault 038d357dde AMDGPU: Use minimumnum/maximumnum for fmed3 with amdgpu-ieee=0
(#139546)

Try to respect the signaling nan behavior of the instruction,
so also start the special case fold for src2.
2025-05-12 20:31:52 +02:00

63 KiB