From f8804047af8c397db804e5775009981d96db8fb4 Mon Sep 17 00:00:00 2001 From: Craig Topper Date: Wed, 25 Sep 2019 23:25:15 +0000 Subject: [PATCH] [X86] Use VR512_0_15RegClass intead of VR512RegClass in X86VZeroUpper. This pass is only concerned with ZMM0-15 and YMM0-15. For YMM we use VR256 which only contains YMM0-15, but for ZMM we were using VR512 which contains ZMM0-31. Using VR512_0_15 is more correct. Given that the ABI and register allocator will use registers in order, its unlikely that register from 16-31 would be used without also using 0-15. So this probably doesn't functionally matter. llvm-svn: 372933 --- llvm/lib/Target/X86/X86VZeroUpper.cpp | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/llvm/lib/Target/X86/X86VZeroUpper.cpp b/llvm/lib/Target/X86/X86VZeroUpper.cpp index a07d2f20acab..9280d030b5d5 100644 --- a/llvm/lib/Target/X86/X86VZeroUpper.cpp +++ b/llvm/lib/Target/X86/X86VZeroUpper.cpp @@ -292,8 +292,7 @@ bool VZeroUpperInserter::runOnMachineFunction(MachineFunction &MF) { // need to insert any VZEROUPPER instructions. This is constant-time, so it // is cheap in the common case of no ymm/zmm use. bool YmmOrZmmUsed = FnHasLiveInYmmOrZmm; - const TargetRegisterClass *RCs[2] = {&X86::VR256RegClass, &X86::VR512RegClass}; - for (auto *RC : RCs) { + for (auto *RC : {&X86::VR256RegClass, &X86::VR512_0_15RegClass}) { if (!YmmOrZmmUsed) { for (TargetRegisterClass::iterator i = RC->begin(), e = RC->end(); i != e; i++) { @@ -304,9 +303,8 @@ bool VZeroUpperInserter::runOnMachineFunction(MachineFunction &MF) { } } } - if (!YmmOrZmmUsed) { + if (!YmmOrZmmUsed) return false; - } assert(BlockStates.empty() && DirtySuccessors.empty() && "X86VZeroUpper state should be clear");