[X86] Fix problem in D147541

llvm/lib/Target/X86/X86FixupInstTuning.cpp

auto ProcessVPERMILPSmi = [&](unsigned NewOpc) -> bool {
     // `vpshufd` saves a byte of code size.
     if (!ST->hasNoDomainDelayShuffle() &&
         !NewOpcPreferable(NewOpc, /*ReplaceInTie*/ false))
       return false;
     MI.setDesc(TII->get(NewOpc));
     return true;
   };
 
-  // `vunpcklpd/vmovlhps r, r` -> `vshufps r, r, 0x44`
-  // `vunpckhpd/vmovlhps r, r` -> `vshufps r, r, 0xee`
+  // `vunpcklpd/vmovlhps r, r` -> `vshufpd r, r, 0x00`
+  // `vunpckhpd/vmovlhps r, r` -> `vshufpd r, r, 0xff`
   // `vunpcklpd r, r, k` -> `vshufpd r, r, 0x00`
   // `vunpckhpd r, r, k` -> `vshufpd r, r, 0xff`
   // iff `vshufps` is faster than `vunpck{l|h}pd`. Otherwise stick with
   // `vunpck{l|h}pd` as it uses less code size.
   // TODO: Look into using `{VP}UNPCK{L|H}QDQ{...}` instead of `{V}SHUF{...}PS`
   // as the replacement. `{VP}UNPCK{L|H}QDQ{...}` has no codesize cost.
   auto ProcessUNPCKPD = [&](unsigned NewOpc, unsigned MaskImm) -> bool {
     if (!NewOpcPreferable(NewOpc, /*ReplaceInTie*/ false))
case X86::VPERMILPSZmik:
     // TODO: {V}UNPCK{L|H}PD{...} is probably safe to transform to
     // `{VP}UNPCK{L|H}QDQ{...}` which gets the same perf benefit as
     // `{V}SHUF{...}PS` but 1) without increasing code size and 2) can also
     // handle the `mr` case. ICL doesn't have a domain penalty for replacing
     // float unpck -> int unpck, but at this time, I haven't verified the set of
     // processors where its safe.
   case X86::MOVLHPSrr:
   case X86::UNPCKLPDrr:
-    return ProcessUNPCKLPDrr(X86::SHUFPSrri);
+    return ProcessUNPCKLPDrr(X86::SHUFPDrri);
   case X86::VMOVLHPSrr:
   case X86::VUNPCKLPDrr:
-    return ProcessUNPCKLPDrr(X86::VSHUFPSrri);
+    return ProcessUNPCKLPDrr(X86::VSHUFPDrri);
   case X86::VUNPCKLPDYrr:
-    return ProcessUNPCKLPDrr(X86::VSHUFPSYrri);
+    return ProcessUNPCKLPDrr(X86::VSHUFPDYrri);
     // VMOVLHPS is always 128 bits.
   case X86::VMOVLHPSZrr:
   case X86::VUNPCKLPDZ128rr:
     return ProcessUNPCKLPDrr(X86::VSHUFPDZ128rri);
   case X86::VUNPCKLPDZ256rr:
     return ProcessUNPCKLPDrr(X86::VSHUFPDZ256rri);
   case X86::VUNPCKLPDZrr:
     return ProcessUNPCKLPDrr(X86::VSHUFPDZrri);