[PATCH] D68893: AMDGPU: Split flat offsets that don't fit in DAG
Nicolai Hähnle via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Mon Oct 14 09:38:42 PDT 2019
nhaehnle added a comment.
Mostly LGTM, but I wonder about the high level intention here. Is this intended to expose new load/store merging opportunities? If so, is there a test for this? Or is there some part of SIFoldOperands that can now be removed?
================
Comment at: lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp:1715
+#if 0
+ // TODO: Should this try to use a scalar add pseudo?
+ SDValue AddOffset
----------------
It does seem like an annoying duplication of concerns to implement the 64-bit addition here manually.
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D68893/new/
https://reviews.llvm.org/D68893
More information about the llvm-commits
mailing list