diff --git a/llvm/include/llvm/CodeGen/LiveIntervals.h b/llvm/include/llvm/CodeGen/LiveIntervals.h
--- a/llvm/include/llvm/CodeGen/LiveIntervals.h
+++ b/llvm/include/llvm/CodeGen/LiveIntervals.h
@@ -378,6 +378,12 @@
     bool checkRegMaskInterference(LiveInterval &LI,
                                   BitVector &UsableRegs);
 
+    /// Get the interferenced slot index and its regmask for an live interval.
+    /// Return false if ther is no interference.
+    bool getInterferenceRegMasks(LiveInterval &LI,
+                                 SmallVector<SlotIndex, 8> &RegSlots,
+                                 SmallVector<const uint32_t *, 8> &RegMaskBits);
+
     // Register unit functions.
     //
     // Fixed interference occurs when MachineInstrs use physregs directly
diff --git a/llvm/lib/CodeGen/LiveIntervals.cpp b/llvm/lib/CodeGen/LiveIntervals.cpp
--- a/llvm/lib/CodeGen/LiveIntervals.cpp
+++ b/llvm/lib/CodeGen/LiveIntervals.cpp
@@ -952,6 +952,56 @@
   }
 }
 
+bool LiveIntervals::getInterferenceRegMasks(
+    LiveInterval &LI, SmallVector<SlotIndex, 8> &RegSlots,
+    SmallVector<const uint32_t *, 8> &RegBits) {
+  if (LI.empty())
+    return false;
+  LiveInterval::iterator LiveI = LI.begin(), LiveE = LI.end();
+
+  // Use a smaller arrays for local live ranges.
+  ArrayRef<SlotIndex> Slots;
+  ArrayRef<const uint32_t *> Bits;
+  if (MachineBasicBlock *MBB = intervalIsInOneMBB(LI)) {
+    Slots = getRegMaskSlotsInBlock(MBB->getNumber());
+    Bits = getRegMaskBitsInBlock(MBB->getNumber());
+  } else {
+    Slots = getRegMaskSlots();
+    Bits = getRegMaskBits();
+  }
+
+  // We are going to enumerate all the register mask slots contained in LI.
+  // Start with a binary search of RegMaskSlots to find a starting point.
+  ArrayRef<SlotIndex>::iterator SlotI = llvm::lower_bound(Slots, LiveI->start);
+  ArrayRef<SlotIndex>::iterator SlotE = Slots.end();
+
+  // No slots in range, LI begins after the last call.
+  if (SlotI == SlotE)
+    return false;
+
+  bool Found = false;
+  while (true) {
+    assert(*SlotI >= LiveI->start);
+    // Loop over all slots overlapping this segment.
+    while (*SlotI < LiveI->end) {
+      // *SlotI overlaps LI. Collect mask bits.
+      Found = true;
+      RegSlots.push_back(*SlotI);
+      RegBits.push_back(Bits[SlotI - Slots.begin()]);
+      if (++SlotI == SlotE)
+        return Found;
+    }
+    // *SlotI is beyond the current LI segment.
+    LiveI = LI.advanceTo(LiveI, *SlotI);
+    if (LiveI == LiveE)
+      return Found;
+    // Advance SlotI until it overlaps.
+    while (*SlotI < LiveI->start)
+      if (++SlotI == SlotE)
+        return Found;
+  }
+}
+
 //===----------------------------------------------------------------------===//
 //                         IntervalUpdate class.
 //===----------------------------------------------------------------------===//
diff --git a/llvm/lib/Target/X86/X86ExpandPseudo.cpp b/llvm/lib/Target/X86/X86ExpandPseudo.cpp
--- a/llvm/lib/Target/X86/X86ExpandPseudo.cpp
+++ b/llvm/lib/Target/X86/X86ExpandPseudo.cpp
@@ -461,25 +461,13 @@
   case TargetOpcode::ICALL_BRANCH_FUNNEL:
     ExpandICallBranchFunnel(&MBB, MBBI);
     return true;
-  case X86::PLDTILECFG: {
-    MI.RemoveOperand(0);
-    MI.setDesc(TII->get(X86::LDTILECFG));
-    return true;
-  }
-  case X86::PSTTILECFG: {
-    MI.RemoveOperand(MI.getNumOperands() - 1); // Remove $tmmcfg
-    MI.setDesc(TII->get(X86::STTILECFG));
-    return true;
-  }
   case X86::PTILELOADDV: {
-    MI.RemoveOperand(8); // Remove $tmmcfg
     for (unsigned i = 2; i > 0; --i)
       MI.RemoveOperand(i);
     MI.setDesc(TII->get(X86::TILELOADD));
     return true;
   }
   case X86::PTDPBSSDV: {
-    MI.RemoveOperand(7); // Remove $tmmcfg
     MI.untieRegOperand(4);
     for (unsigned i = 3; i > 0; --i)
       MI.RemoveOperand(i);
@@ -488,14 +476,13 @@
     return true;
   }
   case X86::PTILESTOREDV: {
-    MI.RemoveOperand(8); // Remove $tmmcfg
     for (int i = 1; i >= 0; --i)
       MI.RemoveOperand(i);
     MI.setDesc(TII->get(X86::TILESTORED));
     return true;
   }
   case X86::PTILEZEROV: {
-    for (int i = 3; i > 0; --i) // Remove row, col, $tmmcfg
+    for (int i = 2; i > 0; --i) // Remove row, col
       MI.RemoveOperand(i);
     MI.setDesc(TII->get(X86::TILEZERO));
     return true;
diff --git a/llvm/lib/Target/X86/X86FrameLowering.cpp b/llvm/lib/Target/X86/X86FrameLowering.cpp
--- a/llvm/lib/Target/X86/X86FrameLowering.cpp
+++ b/llvm/lib/Target/X86/X86FrameLowering.cpp
@@ -2094,8 +2094,12 @@
 
   // Emit tilerelease for AMX kernel.
   const MachineRegisterInfo &MRI = MF.getRegInfo();
-  if (!MRI.reg_nodbg_empty(X86::TMMCFG))
-    BuildMI(MBB, Terminator, DL, TII.get(X86::TILERELEASE));
+  for (unsigned I = 0; I < 8; I++) {
+    if (!MRI.reg_nodbg_empty(X86::TMM0 + I)) {
+      BuildMI(MBB, Terminator, DL, TII.get(X86::TILERELEASE));
+      break;
+    }
+  }
 }
 
 StackOffset X86FrameLowering::getFrameIndexReference(const MachineFunction &MF,
diff --git a/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp b/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp
--- a/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp
+++ b/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp
@@ -4606,7 +4606,6 @@
       SDValue Index = Node->getOperand(5);
       SDValue Disp = CurDAG->getTargetConstant(0, dl, MVT::i32);
       SDValue Segment = CurDAG->getRegister(0, MVT::i16);
-      SDValue CFG = CurDAG->getRegister(0, MVT::Untyped);
       SDValue Chain = Node->getOperand(0);
       MachineSDNode *CNode;
       SDValue Ops[] = {Node->getOperand(2),
@@ -4616,7 +4615,6 @@
                        Index,
                        Disp,
                        Segment,
-                       CFG,
                        Chain};
       CNode = CurDAG->getMachineNode(Opc, dl, {MVT::x86amx, MVT::Other}, Ops);
       ReplaceNode(Node, CNode);
@@ -4627,14 +4625,12 @@
         break;
       SDValue Chain = Node->getOperand(0);
       unsigned Opc = X86::PTDPBSSDV;
-      SDValue CFG = CurDAG->getRegister(0, MVT::Untyped);
       SDValue Ops[] = {Node->getOperand(2),
                        Node->getOperand(3),
                        Node->getOperand(4),
                        Node->getOperand(5),
                        Node->getOperand(6),
                        Node->getOperand(7),
-                       CFG,
                        Chain};
       MachineSDNode *CNode =
           CurDAG->getMachineNode(Opc, dl, {MVT::x86amx, MVT::Other}, Ops);
@@ -4646,8 +4642,7 @@
         break;
       unsigned Opc = X86::PTILEZEROV;
       SDValue Chain = Node->getOperand(0);
-      SDValue CFG = CurDAG->getRegister(0, MVT::Untyped);
-      SDValue Ops[] = {Node->getOperand(2), Node->getOperand(3), CFG, Chain};
+      SDValue Ops[] = {Node->getOperand(2), Node->getOperand(3), Chain};
       MachineSDNode *CNode =
           CurDAG->getMachineNode(Opc, dl, {MVT::x86amx, MVT::Other}, Ops);
       ReplaceNode(Node, CNode);
@@ -4718,7 +4713,6 @@
       SDValue Index = Node->getOperand(5);
       SDValue Disp = CurDAG->getTargetConstant(0, dl, MVT::i32);
       SDValue Segment = CurDAG->getRegister(0, MVT::i16);
-      SDValue CFG = CurDAG->getRegister(0, MVT::Untyped);
       SDValue Chain = Node->getOperand(0);
       MachineSDNode *CNode;
       SDValue Ops[] = {Node->getOperand(2),
@@ -4729,7 +4723,6 @@
                        Disp,
                        Segment,
                        Node->getOperand(6),
-                       CFG,
                        Chain};
       CNode = CurDAG->getMachineNode(Opc, dl, MVT::Other, Ops);
       ReplaceNode(Node, CNode);
diff --git a/llvm/lib/Target/X86/X86InstrAMX.td b/llvm/lib/Target/X86/X86InstrAMX.td
--- a/llvm/lib/Target/X86/X86InstrAMX.td
+++ b/llvm/lib/Target/X86/X86InstrAMX.td
@@ -48,23 +48,14 @@
                      VEX, T8XD;
 
     // Pseduo instruction for RA.
-    let hasSideEffects = 1, mayLoad = 1,
-        Defs = [TMM0,TMM1,TMM2,TMM3,TMM4,TMM5,TMM6,TMM7] in
-    def PLDTILECFG : PseudoI <(outs TILECFG:$cfg), (ins opaquemem:$src), []>;
-
-    let hasSideEffects = 1, mayStore = 1 in
-    def PSTTILECFG : PseudoI<(outs), (ins opaquemem:$dst, TILECFG:$cfg), []>;
-
     def PTILELOADDV : PseudoI<(outs TILE: $dst), (ins GR16:$src1,
                                                       GR16:$src2,
-                                                      opaquemem:$src3,
-                                                      TILECFG:$cfg), []>;
+                                                      opaquemem:$src3), []>;
     def PTILESTOREDV : PseudoI<(outs), (ins GR16:$src1,
                                             GR16:$src2, opaquemem:$src3,
-                                            TILE:$src4, TILECFG:$cfg), []>;
+                                            TILE:$src4), []>;
     def PTILEZEROV : PseudoI<(outs TILE: $dst), (ins GR16:$src1,
-                                                     GR16:$src2,
-                                                     TILECFG:$cfg), []>;
+                                                     GR16:$src2), []>;
 
     let usesCustomInserter = 1 in {
       // Pseudo instructions, using immediates instead of tile registers.
@@ -104,7 +95,7 @@
     let Constraints = "$src4 = $dst" in
     def PTDPBSSDV : PseudoI<(outs TILE: $dst), (ins GR16:$src1,
                             GR16:$src2, GR16:$src3, TILE:$src4,
-                            TILE:$src5, TILE:$src6, TILECFG:$cfg), []>;
+                            TILE:$src5, TILE:$src6), []>;
 
     let usesCustomInserter = 1 in {
       // Pseudo instructions, using immediates instead of tile registers.
diff --git a/llvm/lib/Target/X86/X86InstrInfo.cpp b/llvm/lib/Target/X86/X86InstrInfo.cpp
--- a/llvm/lib/Target/X86/X86InstrInfo.cpp
+++ b/llvm/lib/Target/X86/X86InstrInfo.cpp
@@ -3808,10 +3808,6 @@
     MachineOperand &MO = NewMI->getOperand(2);
     MO.setReg(VirtReg);
     MO.setIsKill(true);
-  } else if (RC->getID() == X86::TILECFGRegClassID) {
-    unsigned Opc = X86::PSTTILECFG;
-    addFrameReference(BuildMI(MBB, MI, DebugLoc(), get(Opc)), FrameIdx)
-        .addReg(SrcReg, getKillRegState(isKill));
   } else {
     unsigned Alignment = std::max<uint32_t>(TRI->getSpillSize(*RC), 16);
     bool isAligned =
@@ -3840,10 +3836,6 @@
     MachineOperand &MO = NewMI->getOperand(3);
     MO.setReg(VirtReg);
     MO.setIsKill(true);
-  } else if (RC->getID() == X86::TILECFGRegClassID) {
-    unsigned Opc = X86::PLDTILECFG;
-    addFrameReference(BuildMI(MBB, MI, DebugLoc(), get(Opc), DestReg),
-                      FrameIdx);
   } else {
     const MachineFunction &MF = *MBB.getParent();
     unsigned Alignment = std::max<uint32_t>(TRI->getSpillSize(*RC), 16);
diff --git a/llvm/lib/Target/X86/X86PreTileConfig.cpp b/llvm/lib/Target/X86/X86PreTileConfig.cpp
--- a/llvm/lib/Target/X86/X86PreTileConfig.cpp
+++ b/llvm/lib/Target/X86/X86PreTileConfig.cpp
@@ -38,6 +38,7 @@
 #include "X86InstrBuilder.h"
 #include "X86RegisterInfo.h"
 #include "X86Subtarget.h"
+#include "llvm/CodeGen/LiveIntervals.h"
 #include "llvm/CodeGen/MachineDominators.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineInstr.h"
@@ -62,8 +63,11 @@
   const TargetInstrInfo *TII;
   MachineDominatorTree *DomTree = nullptr;
   MachineRegisterInfo *MRI = nullptr;
+  LiveIntervals *LIS = nullptr;
+  SmallVector<Register, 16> VTileRegs;
 
   MachineInstr *getTileConfigPoint();
+  void reloadTileConfig(int FI);
 
 public:
   X86PreTileConfig() : MachineFunctionPass(ID) {}
@@ -88,20 +92,22 @@
 
 INITIALIZE_PASS_BEGIN(X86PreTileConfig, "tilepreconfig",
                       "Tile Register Configure", false, false)
+INITIALIZE_PASS_DEPENDENCY(LiveIntervals)
 INITIALIZE_PASS_DEPENDENCY(MachineDominatorTree)
 INITIALIZE_PASS_END(X86PreTileConfig, "tilepreconfig",
                     "Tile Register Configure", false, false)
 
 void X86PreTileConfig::getAnalysisUsage(AnalysisUsage &AU) const {
   AU.setPreservesAll();
+  AU.addRequired<LiveIntervals>();
+  AU.addPreserved<LiveIntervals>();
   AU.addRequired<MachineDominatorTree>();
   MachineFunctionPass::getAnalysisUsage(AU);
 }
 
-static Register buildConfigMI(MachineBasicBlock::iterator MI, int FrameIdx,
-                              const TargetInstrInfo *TII,
-                              MachineRegisterInfo *MRI,
-                              const X86Subtarget *ST) {
+static void buildConfigMI(MachineBasicBlock::iterator MI, int FrameIdx,
+                          const TargetInstrInfo *TII, MachineRegisterInfo *MRI,
+                          const X86Subtarget *ST) {
   auto *MBB = MI->getParent();
 
   // FIXME: AMX should assume AVX512 enabled.
@@ -117,12 +123,10 @@
   }
 
   // build psuedo ldtilecfg
-  Register VReg = MRI->createVirtualRegister(&X86::TILECFGRegClass);
+  // Register VReg = MRI->createVirtualRegister(&X86::TILECFGRegClass);
 
-  addFrameReference(
-      BuildMI(*MBB, MI, DebugLoc(), TII->get(X86::PLDTILECFG), VReg), FrameIdx);
-
-  return VReg;
+  addFrameReference(BuildMI(*MBB, MI, DebugLoc(), TII->get(X86::LDTILECFG)),
+                    FrameIdx);
 }
 
 static ShapeT getShape(const MachineInstr &MI, MachineRegisterInfo *MRI) {
@@ -151,6 +155,7 @@
     const TargetRegisterClass &RC = *MRI->getRegClass(VirtReg);
     if (RC.getID() != X86::TILERegClassID)
       continue;
+    VTileRegs.push_back(VirtReg);
 
     // Find the common dominator for all MI that define tile register.
     for (const MachineOperand &MO : MRI->def_operands(VirtReg)) {
@@ -219,6 +224,7 @@
   return &*MII;
 }
 
+#if 0
 static void addTileCFGUse(MachineFunction &MF, Register CFG) {
   for (MachineBasicBlock &MBB : MF) {
 
@@ -240,6 +246,48 @@
     }
   }
 }
+#endif
+
+void X86PreTileConfig::reloadTileConfig(int FI) {
+  SmallSet<SlotIndex, 8> DoneSet;
+
+  for (Register VReg : VTileRegs) {
+    BitVector UsableRegs(TRI->getNumRegs());
+    for (unsigned I = 0; I < 8; I++)
+      UsableRegs.set(X86::TMM0 + I);
+    SmallVector<SlotIndex, 8> RegSlots;
+    SmallVector<const uint32_t *, 8> RegMasks;
+    LiveInterval &LI = LIS->getInterval(VReg);
+    if (!LIS->getInterferenceRegMasks(LI, RegSlots, RegMasks))
+      continue;
+    for (unsigned I = 0; I < RegSlots.size(); I++) {
+      SlotIndex &SI = RegSlots[I];
+      MachineInstr *MI = LIS->getInstructionFromIndex(SI);
+      // We have reload the tile config register before.
+      if (DoneSet.count(SI))
+        continue;
+      // For inline assembly, we don't reload tile config register.
+      // If there is any ldtilecfg instruction in inline assembly,
+      // it is user's reponsibility to restore everything.
+      if (!MI->isCall())
+        continue;
+      UsableRegs.clearBitsNotInMask(RegMasks[I]);
+      // There is no interference in callee. This is benifited from
+      // IPRA.
+      if (UsableRegs.empty())
+        continue;
+
+      // build psuedo ldtilecfg
+      auto *MBB = MI->getParent();
+      auto MII = MachineBasicBlock::iterator(MI);
+      MII++;
+      addFrameReference(
+          BuildMI(*MBB, *MII, DebugLoc(), TII->get(X86::LDTILECFG)), FI);
+
+      DoneSet.insert(SI);
+    }
+  }
+}
 
 bool X86PreTileConfig::runOnMachineFunction(MachineFunction &mf) {
   MF = &mf;
@@ -248,6 +296,7 @@
   TRI = ST->getRegisterInfo();
   TII = mf.getSubtarget().getInstrInfo();
   DomTree = &getAnalysis<MachineDominatorTree>();
+  LIS = &getAnalysis<LiveIntervals>();
 
   MachineInstr *MI = getTileConfigPoint();
   if (!MI)
@@ -255,8 +304,10 @@
   unsigned Size = ST->getTileConfigSize();
   Align Alignment = ST->getTileConfigAlignment();
   int SS = mf.getFrameInfo().CreateStackObject(Size, Alignment, false);
-  Register CFG = buildConfigMI(MI, SS, TII, MRI, ST);
-  addTileCFGUse(mf, CFG);
+  buildConfigMI(MI, SS, TII, MRI, ST);
+  // addTileCFGUse(mf, CFG);
+  reloadTileConfig(SS);
+  VTileRegs.clear();
   return true;
 }
 
diff --git a/llvm/lib/Target/X86/X86RegisterInfo.td b/llvm/lib/Target/X86/X86RegisterInfo.td
--- a/llvm/lib/Target/X86/X86RegisterInfo.td
+++ b/llvm/lib/Target/X86/X86RegisterInfo.td
@@ -639,8 +639,3 @@
 let CopyCost = -1 in // Don't allow copying of tile registers
 def TILE : RegisterClass<"X86", [x86amx], 8192,
                          (sequence "TMM%u", 0, 7)> {let Size = 8192;}
-def TILECFG : RegisterClass<"X86", [untyped], 512, (add TMMCFG)> {
-  let CopyCost = -1;  // Don't allow copying of tile config registers.
-  let isAllocatable = 1;
-  let Size = 512;
-}
diff --git a/llvm/lib/Target/X86/X86TileConfig.cpp b/llvm/lib/Target/X86/X86TileConfig.cpp
--- a/llvm/lib/Target/X86/X86TileConfig.cpp
+++ b/llvm/lib/Target/X86/X86TileConfig.cpp
@@ -22,6 +22,7 @@
 #include "X86MachineFunctionInfo.h"
 #include "X86RegisterInfo.h"
 #include "X86Subtarget.h"
+#include "llvm/ADT/PostOrderIterator.h"
 #include "llvm/CodeGen/LiveIntervals.h"
 #include "llvm/CodeGen/MachineDominators.h"
 #include "llvm/CodeGen/MachineFrameInfo.h"
@@ -130,15 +131,28 @@
 }
 
 MachineInstr *X86TileConfig::getTileConfigPoint() {
+  MachineBasicBlock *Entry = &*MF->begin();
+  ReversePostOrderTraversal<MachineBasicBlock *> RPOT(Entry);
+  for (MachineBasicBlock *MBB : RPOT) {
+    for (MachineInstr &MI : *MBB)
+      // Refer X86PreTileConfig.cpp.
+      // We only support one tile config for now. The other ldtilecfg
+      // is for spill purpose and is dominated by the first ldtilecfg.
+      if (MI.getOpcode() == X86::LDTILECFG)
+        return &MI;
+  }
+
+#if 0
   for (MachineBasicBlock &MBB : *MF) {
 
     // Traverse the basic block.
     for (MachineInstr &MI : MBB)
       // Refer X86PreTileConfig.cpp.
       // We only support one tile config for now.
-      if (MI.getOpcode() == X86::PLDTILECFG)
+      if (MI.getOpcode() == X86::LDTILECFG)
         return &MI;
   }
+#endif
 
   return nullptr;
 }
@@ -148,7 +162,7 @@
   if (!MI)
     return;
   MachineBasicBlock *MBB = MI->getParent();
-  int SS = MI->getOperand(1).getIndex();
+  int SS = MI->getOperand(0).getIndex();
   BitVector PhysRegs(TRI->getNumRegs());
 
   // Fill in the palette first.
diff --git a/llvm/test/CodeGen/X86/AMX/amx-across-func.ll b/llvm/test/CodeGen/X86/AMX/amx-across-func.ll
--- a/llvm/test/CodeGen/X86/AMX/amx-across-func.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-across-func.ll
@@ -34,7 +34,6 @@
 ; CHECK-NEXT:    movb $8, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movw %bx, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    ldtilecfg {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    sttilecfg {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Folded Spill
 ; CHECK-NEXT:    movl $buf, %eax
 ; CHECK-NEXT:    movl $32, %r14d
 ; CHECK-NEXT:    movw $8, %r15w
@@ -48,8 +47,8 @@
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    vzeroupper
 ; CHECK-NEXT:    callq foo
+; CHECK-NEXT:    ldtilecfg {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movl $buf+2048, %eax
-; CHECK-NEXT:    ldtilecfg {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Folded Reload
 ; CHECK-NEXT:    tileloadd (%rax,%r14), %tmm0
 ; CHECK-NEXT:    movabsq $64, %rcx
 ; CHECK-NEXT:    tileloadd 2048(%rsp,%rcx), %tmm1 # 1024-byte Folded Reload
diff --git a/llvm/test/CodeGen/X86/AMX/amx-bf16-intrinsics.ll b/llvm/test/CodeGen/X86/AMX/amx-bf16-intrinsics.ll
--- a/llvm/test/CodeGen/X86/AMX/amx-bf16-intrinsics.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-bf16-intrinsics.ll
@@ -5,7 +5,6 @@
 ; CHECK-LABEL: test_amx:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    tdpbf16ps %tmm7, %tmm4, %tmm3
-; CHECK-NEXT:    retq
   call void @llvm.x86.tdpbf16ps(i8 3, i8 4, i8 7)
   ret void
 }
diff --git a/llvm/test/CodeGen/X86/AMX/amx-spill-merge.ll b/llvm/test/CodeGen/X86/AMX/amx-spill-merge.ll
--- a/llvm/test/CodeGen/X86/AMX/amx-spill-merge.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-spill-merge.ll
@@ -48,11 +48,10 @@
 ; CHECK-NEXT:    tileloadd (%r15,%r14), %tmm5
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    testb %al, %al
-; CHECK-NEXT:    sttilecfg {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Folded Spill
-; CHECK-NEXT:    movl $buf, %eax
-; CHECK-NEXT:    movw $8, %cx
 ; CHECK-NEXT:    jne .LBB0_2
 ; CHECK-NEXT:  # %bb.1: # %if.true
+; CHECK-NEXT:    movl $buf, %eax
+; CHECK-NEXT:    movw $8, %cx
 ; CHECK-NEXT:    tileloadd (%rax,%r14), %tmm0
 ; CHECK-NEXT:    movl $buf+1024, %eax
 ; CHECK-NEXT:    tileloadd (%rax,%r14), %tmm1
@@ -64,11 +63,13 @@
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    vzeroupper
 ; CHECK-NEXT:    callq foo
-; CHECK-NEXT:    ldtilecfg {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Folded Reload
+; CHECK-NEXT:    ldtilecfg {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movabsq $64, %rax
 ; CHECK-NEXT:    tileloadd 1024(%rsp,%rax), %tmm6 # 1024-byte Folded Reload
 ; CHECK-NEXT:    jmp .LBB0_3
 ; CHECK-NEXT:  .LBB0_2: # %if.false
+; CHECK-NEXT:    movl $buf, %eax
+; CHECK-NEXT:    movw $8, %cx
 ; CHECK-NEXT:    tileloadd (%rax,%r14), %tmm2
 ; CHECK-NEXT:    movl $buf+1024, %eax
 ; CHECK-NEXT:    tileloadd (%rax,%r14), %tmm3
@@ -80,7 +81,7 @@
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    vzeroupper
 ; CHECK-NEXT:    callq foo
-; CHECK-NEXT:    ldtilecfg {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Folded Reload
+; CHECK-NEXT:    ldtilecfg {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movabsq $64, %rax
 ; CHECK-NEXT:    tileloadd 1024(%rsp,%rax), %tmm6 # 1024-byte Folded Reload
 ; CHECK-NEXT:    tilestored %tmm6, (%r15,%r14)