diff options
| author | Justin Bogner <mail@justinbogner.com> | 2023-02-22 17:45:58 -0800 |
|---|---|---|
| committer | Justin Bogner <mail@justinbogner.com> | 2023-02-23 10:23:34 -0800 |
| commit | c083c8974400bcc665d7736cd0e2b653180026ff (patch) | |
| tree | c5dc6b99c3d9f04087eeefe1d00108b19bb05b10 /llvm/lib/CodeGen/MachineModuleInfo.cpp | |
| parent | a628ca4925f7249b4fbd3e932c9627b12e2770dd (diff) | |
| download | llvm-c083c8974400bcc665d7736cd0e2b653180026ff.zip llvm-c083c8974400bcc665d7736cd0e2b653180026ff.tar.gz llvm-c083c8974400bcc665d7736cd0e2b653180026ff.tar.bz2 | |
[AMDGPU] Move V_FMA_MIX pattern matching into tablegen. NFC
The matching for V_FMA_MIX was partially implemented with a C++
matcher (for fmas with 32 bit results and 16 bit inputs) and partially
in tablegen (for fmas with 16 bit results). Move the C++ matcher logic
into tablegen to make this more consistent and so we can remove the
duplication between SDAG and GISel.
Differential Revision: https://reviews.llvm.org/D144612
Diffstat (limited to 'llvm/lib/CodeGen/MachineModuleInfo.cpp')
0 files changed, 0 insertions, 0 deletions