[PATCH] D41293: [DAG, X86] Improve Dependency analysis when doing multi-node Instruction Selection

[Nirav Dave via Phabricator via llvm-commits]

niravd updated this revision to Diff 129669.
niravd retitled this revision from "[DAG] Improve Dependency analysis when doing multi-node Instruction Selection" to "[DAG,X86] Improve Dependency analysis when doing multi-node Instruction Selection".
niravd edited the summary of this revision.
niravd added a comment.

In testing I discovered the follow on patch to X86's load-op-store pattern check needed to be folded in. Added discovered test as well.


https://reviews.llvm.org/D41293

Files:
  llvm/include/llvm/CodeGen/SelectionDAGNodes.h
  llvm/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp
  llvm/lib/Target/X86/X86ISelDAGToDAG.cpp
  llvm/test/CodeGen/X86/2012-01-16-mfence-nosse-flags.ll
  llvm/test/CodeGen/X86/avg.ll
  llvm/test/CodeGen/X86/avx-vbroadcastf128.ll
  llvm/test/CodeGen/X86/avx2-vbroadcast.ll
  llvm/test/CodeGen/X86/avx2-vbroadcasti128.ll
  llvm/test/CodeGen/X86/avx512-vbroadcasti128.ll
  llvm/test/CodeGen/X86/i256-add.ll
  llvm/test/CodeGen/X86/load-op-store-fusion.ll
  llvm/test/CodeGen/X86/masked_memop.ll
  llvm/test/CodeGen/X86/merge-consecutive-stores.ll
  llvm/test/CodeGen/X86/nontemporal.ll
  llvm/test/CodeGen/X86/store_op_load_fold2.ll
  llvm/test/CodeGen/X86/subvector-broadcast.ll
  llvm/test/CodeGen/X86/var-permute-256.ll
  llvm/test/CodeGen/X86/vector-shuffle-variable-256.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D41293.129669.patch
Type: text/x-patch
Size: 78299 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20180112/5b804d5e/attachment-0001.bin>