[llvm] [X86] combineX86ShuffleChain - don't combine to VPERMI2W/VPERMI2B from just any single variable mask (PR #127914)

[Simon Pilgrim via llvm-commits]

================
@@ -40064,23 +40064,29 @@ static SDValue combineX86ShuffleChain(ArrayRef<SDValue> Inputs, SDValue Root,
   if (Depth < 1)
     return SDValue();
 
-  bool HasVariableMask = llvm::any_of(SrcNodes, [](const SDNode *N) {
+  int NumVariableMasks = llvm::count_if(SrcNodes, [](const SDNode *N) {
     return isTargetShuffleVariableMask(N->getOpcode());
   });
+  bool HasSlowVariableMask = llvm::any_of(SrcNodes, [](const SDNode *N) {
+    return (N->getOpcode() == X86ISD::VPERMV3 ||
+            N->getOpcode() == X86ISD::VPERMV);
+  });
 
   // Depth threshold above which we can efficiently use variable mask shuffles.
   int VariableCrossLaneShuffleDepth =
       Subtarget.hasFastVariableCrossLaneShuffle() ? 1 : 2;
   int VariablePerLaneShuffleDepth =
       Subtarget.hasFastVariablePerLaneShuffle() ? 1 : 2;
   AllowVariableCrossLaneMask &=
-      (Depth >= VariableCrossLaneShuffleDepth) || HasVariableMask;
+      (Depth >= VariableCrossLaneShuffleDepth) || NumVariableMasks;
   AllowVariablePerLaneMask &=
-      (Depth >= VariablePerLaneShuffleDepth) || HasVariableMask;
+      (Depth >= VariablePerLaneShuffleDepth) || NumVariableMasks;
   // VPERMI2W/VPERMI2B are 3 uops on Skylake and Icelake so we require a
   // higher depth before combining them.
+  int BWIVPERMV3ShuffleDepth =
+      VariableCrossLaneShuffleDepth + 2 - NumVariableMasks;
----------------
RKSimon wrote:

Done

https://github.com/llvm/llvm-project/pull/127914