[X86] Mark vector STRICT_FADD/STRICT_FSUB as Legal and add mutation to X86ISelDAGToDAG
authorCraig Topper <craig.topper@intel.com>
Thu, 21 Nov 2019 22:24:32 +0000 (14:24 -0800)
committerCraig Topper <craig.topper@intel.com>
Fri, 22 Nov 2019 00:19:18 +0000 (16:19 -0800)
commit95f44cf44a68f2e7a3fced2b8d920340013f0349
tree363f10d3ce1ad2c2254407be4c8cb2d8fe1c59b2
parent0cc12b8a83100027b16e1dc5cec079ba437ca3e0
[X86] Mark vector STRICT_FADD/STRICT_FSUB as Legal and add mutation to X86ISelDAGToDAG

The prevents LegalizeVectorOps from scalarizing them. We'll need
to remove the X86 mutation code when we add isel patterns.
llvm/lib/Target/X86/X86ISelDAGToDAG.cpp
llvm/lib/Target/X86/X86ISelLowering.cpp
llvm/test/CodeGen/X86/vec-strict-128.ll
llvm/test/CodeGen/X86/vec-strict-256.ll
llvm/test/CodeGen/X86/vec-strict-512.ll
llvm/test/CodeGen/X86/vector-constrained-fp-intrinsics.ll