[PATCH] D60546: [X86] Use MOVQ for i64 non-seq_cst atomic_stores when SSE2 is enabled

[Craig Topper via Phabricator via llvm-commits]

craig.topper created this revision.
craig.topper added reviewers: spatel, RKSimon, reames, jfb, efriedma.
Herald added subscribers: dexonsmith, hiraditya.
Herald added a project: LLVM.

If we have SSE2 we can use a MOVQ to store 64-bits and avoid falling back to a cmpxchg8b loop. Unless the store is seq_cst.


https://reviews.llvm.org/D60546

Files:
  llvm/lib/Target/X86/X86ISelLowering.cpp
  llvm/lib/Target/X86/X86ISelLowering.h
  llvm/lib/Target/X86/X86InstrAVX512.td
  llvm/lib/Target/X86/X86InstrFragmentsSIMD.td
  llvm/lib/Target/X86/X86InstrSSE.td
  llvm/test/CodeGen/X86/atomic-fp.ll
  llvm/test/CodeGen/X86/atomic6432.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D60546.194602.patch
Type: text/x-patch
Size: 21518 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190410/2106222e/attachment.bin>