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

[Xiang Zhang via Phabricator via llvm-commits]

xiangzhangllvm marked 7 inline comments as done.
xiangzhangllvm added inline comments.


================
Comment at: llvm/lib/Target/X86/X86PreAMXConfig.cpp:193
+
+// Todo: We may need to handle "more than one store" case in the future.
+bool X86PreAMXConfig::checkVolatileModel(SmallSet<Value *, 4> &Loads,
----------------
pengfei wrote:
> Better add assert for this case.
Multi-TileStores of tile definition is not fit current Volatile Model, it will failed in assert.


================
Comment at: llvm/test/CodeGen/X86/AMX/amx-configO2toO0.ll:2
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -O0 -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx512f | FileCheck %s --check-prefix=AMX_O0
+
----------------
pengfei wrote:
> Better change one case to use avx or sse to check if stack cleared correctly.
I'll add it, thanks!


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

https://reviews.llvm.org/D100026