Files
clang-p2996/llvm/test/CodeGen/AMDGPU/twoaddr-mad.mir
Jay Foad 8bed52c9eb [AMDGPU] Make more use of madmk/fmamk instructions
In convertToThreeAddress handle VOP2 mac/fmac instructions with a
literal src0 operand, since these are prime candidates for
converting to madmk/fmamk.

Previously this would only happen if src0 (or src1) was a register
defined by a move-immediate instruction, but in many cases these
operands have already been folded because SIFoldOperands runs
before TwoAddressInstructionPass.

Differential Revision: https://reviews.llvm.org/D120736
2022-03-02 10:22:10 +00:00

6.9 KiB