[X86] Disable DomainReassignment pass when AVX512BW is disabled to avoid injecting VK32/VK64 references into the MachineIR

Summary:
This pass replaces GR8/GR16/GR32/GR64 with their equivalent sized mask register classes. But VK32/VK64 aren't legal without AVX512BW. Apparently this mostly appears to work if the register coalescer is able to remove the VK32/VK64 register class reference. Or if we don't ever spill it. But there's no guarantee of that.

Another Intel employee managed to trigger a crash due to this with ISPC. Unfortunately, I've lost the test case he sent me at the time. I'm trying to get him to reproduce it for me. I'd like to get this in before 8.0 branches since its a little scary.

The regressions here are unfortunate, but I think we can make some improvements to DAG combine, load folding, etc. to fix them. Just not sure if we can get that done for 8.0.

Fixes PR39741

Reviewers: RKSimon, spatel

Reviewed By: RKSimon

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D56460

llvm-svn: 350800

1 files changed, 4 insertions, 1 deletions

diff --git a/llvm/lib/Target/X86/X86DomainReassignment.cpp b/llvm/lib/Target/X86/X86DomainReassignment.cpp
index 7e1f1e7876c..d9ebbb506ca 100644
--- a/llvm/lib/Target/X86/X86DomainReassignment.cpp
+++ b/llvm/lib/Target/X86/X86DomainReassignment.cpp
@@ -732,7 +732,10 @@ bool X86DomainReassignment::runOnMachineFunction(MachineFunction &MF) {
   STI = &MF.getSubtarget<X86Subtarget>();
   // GPR->K is the only transformation currently supported, bail out early if no
   // AVX512.
-  if (!STI->hasAVX512())
+  // TODO: We're also bailing of AVX512BW isn't supported since we use VK32 and
+  // VK64 for GR32/GR64, but those aren't legal classes on KNL. If the register
+  // coalescer doesn't clean it up and we generate a spill we will crash.
+  if (!STI->hasAVX512() || !STI->hasBWI())
     return false;
 
   MRI = &MF.getRegInfo();