[PATCH] D100026: [X86] Support AMX fast register allocation

Benjamin Kramer via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Thu Apr 29 09:57:49 PDT 2021


bkramer added inline comments.


================
Comment at: llvm/lib/Target/X86/X86LowerAMXType.cpp:68
+// as a new Row for other new created AMX intrinsics.
+static std::map<Value *, Value *> Col2Row;
+
----------------
xiangzhangllvm wrote:
> pengfei wrote:
> > Better move it to class `X86LowerAMXType`
> I thought it before, here I just won't to pass it into static function (getRowFromCol).
You can't simply have global state here, it doesn't work in a multithreaded environment. I reverted this change in df323ba445f7fc4d29def8950e80dec6ba487961 because it breaks us.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D100026/new/

https://reviews.llvm.org/D100026



More information about the llvm-commits mailing list