[PATCH] D26897: AMDGPU: Refactor immediate folding logic

Matt Arsenault via llvm-commits llvm-commits at lists.llvm.org
Mon Nov 21 13:35:58 PST 2016


arsenm added a comment.

This will help for short term making 16-bit operands correct, but longer term it might be better to look at use instructions and finding the operand defs. Right now there seem to be some mis-optimizations when multiple operands might be able to be folded into the same instruction, and the wrong operand is selected


https://reviews.llvm.org/D26897





More information about the llvm-commits mailing list