Files
clang-p2996/llvm/test/CodeGen/AMDGPU/strict_fma.f16.ll
Jay Foad 54fc9eb9b3 [AMDGPU] Use v_fma_f16 on GFX10
Teach convertToThreeAddress to use the V_FMA_F16_gfx9 pseudo (i.e. the
standard instruction in GFX9 onwards) instead of V_FMA_F16 (the legacy
pseudo for GFX8 compatibility, which is no longer supported in GFX10).
This follows the example of macToMad in SIFoldOperands.

Differential Revision: https://reviews.llvm.org/D115731
2021-12-15 13:14:48 +00:00

11 KiB