[PATCH] D35014: [X86] PR32755 : Improvement in CodeGen instruction selection for LEAs.

[Jatin Bhateja via Phabricator via llvm-commits]

jbhateja updated this revision to Diff 111035.
jbhateja added a comment.

- Changes to avoid creating costly complex LEAs having scale less than equal to 2 in loops.
- Strength reduction for simple LEAs with unit scale for better throughput.
- Incorporating other review comments.


https://reviews.llvm.org/D35014

Files:
  include/llvm/CodeGen/MachineInstr.h
  include/llvm/CodeGen/SelectionDAG.h
  lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp
  lib/Target/X86/X86ISelDAGToDAG.cpp
  lib/Target/X86/X86OptimizeLEAs.cpp
  test/CodeGen/X86/GlobalISel/gep.ll
  test/CodeGen/X86/GlobalISel/memop-scalar.ll
  test/CodeGen/X86/lea-opt-cse1.ll
  test/CodeGen/X86/lea-opt-cse2.ll
  test/CodeGen/X86/lea-opt-cse3.ll
  test/CodeGen/X86/mul-constant-i16.ll
  test/CodeGen/X86/mul-constant-i32.ll
  test/CodeGen/X86/mul-constant-i64.ll
  test/CodeGen/X86/mul-constant-result.ll
  test/CodeGen/X86/umul-with-overflow.ll
  test/Transforms/LoopStrengthReduce/X86/ivchain-X86.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D35014.111035.patch
Type: text/x-patch
Size: 43667 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170814/0b3465dd/attachment.bin>