[PATCH] D135951: [X86] SUPPORT RAO-INT

pengfei added inline comments. Comment at: llvm/lib/Target/X86/X86.td:259 + "Support RAO-INT instructions", + [FeatureSSE2]>; def FeatureINVPCID : SubtargetFeature<"invpcid", "HasINVPCID", "true", --

[PATCH] D135951: [X86] SUPPORT RAO-INT

pengfei updated this revision to Diff 468049. pengfei marked an inline comment as done. pengfei added a comment. Split atomic operations lowering into D136032 . Repository: rG LLVM Github Monorepo CHANGES SINCE LAST ACTION https://reviews.llvm.org/D135951/

[PATCH] D135951: [X86] SUPPORT RAO-INT

craig.topper added inline comments. Comment at: llvm/lib/Target/X86/X86ISelLowering.cpp:31799 + // We can lower add/sub/or/xor/and into RAO-INT instructions when the result + // is unused. This should probably be in a separate patch. Repository: rG LLVM G

[PATCH] D135951: [X86] SUPPORT RAO-INT

craig.topper added inline comments. Comment at: llvm/lib/Target/X86/X86.td:259 + "Support RAO-INT instructions", + [FeatureSSE2]>; def FeatureINVPCID : SubtargetFeature<"invpcid", "HasINVPCID", "true", -

[PATCH] D135951: [X86] SUPPORT RAO-INT

RKSimon added inline comments. Comment at: llvm/lib/Target/X86/X86ISelLowering.h:801 +RXOR, +RAND, + very pedantic, but are these likely to get confused with ROR / RAND instructions? Would it be better to use a RAO_ prefix? Comment at: