diff --git a/llvm/lib/Target/AArch64/AArch64FrameLowering.h b/llvm/lib/Target/AArch64/AArch64FrameLowering.h
--- a/llvm/lib/Target/AArch64/AArch64FrameLowering.h
+++ b/llvm/lib/Target/AArch64/AArch64FrameLowering.h
@@ -35,6 +35,8 @@
   void emitPrologue(MachineFunction &MF, MachineBasicBlock &MBB) const override;
   void emitEpilogue(MachineFunction &MF, MachineBasicBlock &MBB) const override;
 
+  bool enableCFIFixup(MachineFunction &MF) const override;
+
   bool canUseAsPrologue(const MachineBasicBlock &MBB) const override;
 
   StackOffset getFrameIndexReference(const MachineFunction &MF, int FI,
diff --git a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
--- a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -1364,6 +1364,27 @@
   }
 }
 
+// Define the current CFA rule to use the provided FP.
+static void emitDefineCFAWithFP(MachineFunction &MF, MachineBasicBlock &MBB,
+                                MachineBasicBlock::iterator MBBI,
+                                const DebugLoc &DL, unsigned FixedObject) {
+  const AArch64Subtarget &STI = MF.getSubtarget<AArch64Subtarget>();
+  const AArch64RegisterInfo *TRI = STI.getRegisterInfo();
+  const TargetInstrInfo *TII = STI.getInstrInfo();
+  AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
+
+  const int OffsetToFirstCalleeSaveFromFP =
+      AFI->getCalleeSaveBaseToFrameRecordOffset() -
+      AFI->getCalleeSavedStackSize();
+  Register FramePtr = TRI->getFrameRegister(MF);
+  unsigned Reg = TRI->getDwarfRegNum(FramePtr, true);
+  unsigned CFIIndex = MF.addFrameInst(MCCFIInstruction::cfiDefCfa(
+      nullptr, Reg, FixedObject - OffsetToFirstCalleeSaveFromFP));
+  BuildMI(MBB, MBBI, DL, TII->get(TargetOpcode::CFI_INSTRUCTION))
+      .addCFIIndex(CFIIndex)
+      .setMIFlags(MachineInstr::FrameSetup);
+}
+
 void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
                                         MachineBasicBlock &MBB) const {
   MachineBasicBlock::iterator MBBI = MBB.begin();
@@ -1375,6 +1396,7 @@
   MachineModuleInfo &MMI = MF.getMMI();
   AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
   bool EmitCFI = AFI->needsDwarfUnwindInfo(MF);
+  bool EmitAsyncCFI = AFI->needsAsyncDwarfUnwindInfo(MF);
   bool HasFP = hasFP(MF);
   bool NeedsWinCFI = needsWinCFI(MF);
   bool HasWinCFI = false;
@@ -1535,7 +1557,7 @@
     emitFrameOffset(MBB, MBBI, DL, AArch64::SP, AArch64::SP,
                     StackOffset::getFixed(-NumBytes), TII,
                     MachineInstr::FrameSetup, false, NeedsWinCFI, &HasWinCFI,
-                    EmitCFI);
+                    EmitAsyncCFI);
     NumBytes = 0;
   } else if (HomPrologEpilog) {
     // Stack has been already adjusted.
@@ -1543,7 +1565,7 @@
   } else if (PrologueSaveSize != 0) {
     MBBI = convertCalleeSaveRestoreToSPPrePostIncDec(
         MBB, MBBI, DL, TII, -PrologueSaveSize, NeedsWinCFI, &HasWinCFI,
-        EmitCFI);
+        EmitAsyncCFI);
     NumBytes -= PrologueSaveSize;
   }
   assert(NumBytes >= 0 && "Negative stack allocation size!?");
@@ -1604,25 +1626,14 @@
         NeedsWinCFI = false;
       }
     }
-    if (EmitCFI) {
-      // Define the current CFA rule to use the provided FP.
-      const int OffsetToFirstCalleeSaveFromFP =
-          AFI->getCalleeSaveBaseToFrameRecordOffset() -
-          AFI->getCalleeSavedStackSize();
-      Register FramePtr = RegInfo->getFrameRegister(MF);
-      unsigned Reg = RegInfo->getDwarfRegNum(FramePtr, true);
-      unsigned CFIIndex = MF.addFrameInst(MCCFIInstruction::cfiDefCfa(
-          nullptr, Reg, FixedObject - OffsetToFirstCalleeSaveFromFP));
-      BuildMI(MBB, MBBI, DL, TII->get(TargetOpcode::CFI_INSTRUCTION))
-          .addCFIIndex(CFIIndex)
-          .setMIFlags(MachineInstr::FrameSetup);
-    }
+    if (EmitAsyncCFI)
+      emitDefineCFAWithFP(MF, MBB, MBBI, DL, FixedObject);
   }
 
   // Now emit the moves for whatever callee saved regs we have (including FP,
   // LR if those are saved). Frame instructions for SVE register are emitted
   // later, after the instruction which actually save SVE regs.
-  if (EmitCFI)
+  if (EmitAsyncCFI)
     emitCalleeSavedGPRLocations(MBB, MBBI);
 
   // Alignment is required for the parent frame, not the funclet
@@ -1766,16 +1777,16 @@
   emitFrameOffset(
       MBB, CalleeSavesBegin, DL, AArch64::SP, AArch64::SP, -AllocateBefore, TII,
       MachineInstr::FrameSetup, false, false, nullptr,
-      EmitCFI && !HasFP && AllocateBefore,
+      EmitAsyncCFI && !HasFP && AllocateBefore,
       StackOffset::getFixed((int64_t)MFI.getStackSize() - NumBytes));
 
-  if (EmitCFI)
+  if (EmitAsyncCFI)
     emitCalleeSavedSVELocations(MBB, CalleeSavesEnd);
 
   // Finally allocate remaining SVE stack space.
   emitFrameOffset(MBB, CalleeSavesEnd, DL, AArch64::SP, AArch64::SP,
                   -AllocateAfter, TII, MachineInstr::FrameSetup, false, false,
-                  nullptr, EmitCFI && !HasFP && AllocateAfter,
+                  nullptr, EmitAsyncCFI && !HasFP && AllocateAfter,
                   AllocateBefore + StackOffset::getFixed(
                                        (int64_t)MFI.getStackSize() - NumBytes));
 
@@ -1796,7 +1807,7 @@
       emitFrameOffset(
           MBB, MBBI, DL, scratchSPReg, AArch64::SP,
           StackOffset::getFixed(-NumBytes), TII, MachineInstr::FrameSetup,
-          false, NeedsWinCFI, &HasWinCFI, EmitCFI && !HasFP,
+          false, NeedsWinCFI, &HasWinCFI, EmitAsyncCFI && !HasFP,
           SVEStackSize +
               StackOffset::getFixed((int64_t)MFI.getStackSize() - NumBytes));
     }
@@ -1858,6 +1869,23 @@
       MBB.addLiveIn(AArch64::X1);
     }
   }
+
+  if (EmitCFI && !EmitAsyncCFI) {
+    if (HasFP) {
+      emitDefineCFAWithFP(MF, MBB, MBBI, DL, FixedObject);
+    } else {
+      StackOffset TotalSize =
+          SVEStackSize + StackOffset::getFixed((int64_t)MFI.getStackSize());
+      unsigned CFIIndex = MF.addFrameInst(createDefCFA(
+          *RegInfo, /*FrameReg=*/AArch64::SP, /*Reg=*/AArch64::SP, TotalSize,
+          /*LastAdjustmentWasScalable=*/false));
+      BuildMI(MBB, MBBI, DL, TII->get(TargetOpcode::CFI_INSTRUCTION))
+          .addCFIIndex(CFIIndex)
+          .setMIFlags(MachineInstr::FrameSetup);
+    }
+    emitCalleeSavedGPRLocations(MBB, MBBI);
+    emitCalleeSavedSVELocations(MBB, MBBI);
+  }
 }
 
 static void InsertReturnAddressAuth(MachineFunction &MF, MachineBasicBlock &MBB,
@@ -2229,6 +2257,11 @@
   }
 }
 
+bool AArch64FrameLowering::enableCFIFixup(MachineFunction &MF) const {
+  return TargetFrameLowering::enableCFIFixup(MF) &&
+         MF.getInfo<AArch64FunctionInfo>()->needsAsyncDwarfUnwindInfo(MF);
+}
+
 /// getFrameIndexReference - Provide a base+offset reference to an FI slot for
 /// debug info.  It's the same as what we use for resolving the code-gen
 /// references for now.  FIXME: This can go wrong when references are
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-variadic-musttail.ll b/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-variadic-musttail.ll
--- a/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-variadic-musttail.ll
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/call-translator-variadic-musttail.ll
@@ -31,13 +31,13 @@
 ; CHECK-LABEL: test_musttail_variadic_spill:
 ; CHECK:       ; %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #224
-; CHECK-NEXT:    .cfi_def_cfa_offset 224
 ; CHECK-NEXT:    stp x28, x27, [sp, #128] ; 16-byte Folded Spill
 ; CHECK-NEXT:    stp x26, x25, [sp, #144] ; 16-byte Folded Spill
 ; CHECK-NEXT:    stp x24, x23, [sp, #160] ; 16-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #176] ; 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #192] ; 16-byte Folded Spill
 ; CHECK-NEXT:    stp x29, x30, [sp, #208] ; 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 224
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    .cfi_offset w19, -24
@@ -103,13 +103,13 @@
 ; CHECK-LABEL: f_thunk:
 ; CHECK:       ; %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #256
-; CHECK-NEXT:    .cfi_def_cfa_offset 256
 ; CHECK-NEXT:    stp x28, x27, [sp, #160] ; 16-byte Folded Spill
 ; CHECK-NEXT:    stp x26, x25, [sp, #176] ; 16-byte Folded Spill
 ; CHECK-NEXT:    stp x24, x23, [sp, #192] ; 16-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #208] ; 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #224] ; 16-byte Folded Spill
 ; CHECK-NEXT:    stp x29, x30, [sp, #240] ; 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 256
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    .cfi_offset w19, -24
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/merge-stores-truncating.ll b/llvm/test/CodeGen/AArch64/GlobalISel/merge-stores-truncating.ll
--- a/llvm/test/CodeGen/AArch64/GlobalISel/merge-stores-truncating.ll
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/merge-stores-truncating.ll
@@ -348,8 +348,8 @@
 ; CHECK-LABEL: trunc_from_larger_src_val:
 ; CHECK:       ; %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    str w0, [sp, #12]
diff --git a/llvm/test/CodeGen/AArch64/aarch64-dynamic-stack-layout.ll b/llvm/test/CodeGen/AArch64/aarch64-dynamic-stack-layout.ll
--- a/llvm/test/CodeGen/AArch64/aarch64-dynamic-stack-layout.ll
+++ b/llvm/test/CodeGen/AArch64/aarch64-dynamic-stack-layout.ll
@@ -99,9 +99,9 @@
 ; CHECK: .cfi_startproc
 ;   Check that used callee-saved registers are saved
 ; CHECK: sub	sp, sp, #32
-; CHECK: .cfi_def_cfa_offset 32
 ; CHECK: stp	x30, x19, [sp, #16]
 ;   Check correctness of cfi pseudo-instructions
+; CHECK: .cfi_def_cfa_offset 32
 ; CHECK: .cfi_offset w19, -8
 ; CHECK: .cfi_offset w30, -16
 ;   Check correct access to arguments passed on the stack, through stack pointer
@@ -118,7 +118,6 @@
 ; CHECK-MACHO: .cfi_startproc
 ;   Check that used callee-saved registers are saved
 ; CHECK-MACHO: sub	sp, sp, #48
-; CHECK-MACHO:.cfi_def_cfa_offset 48
 ; CHECK-MACHO: stp	x20, x19, [sp, #16]
 ;   Check that the frame pointer is created:
 ; CHECK-MACHO: stp	x29, x30, [sp, #32]
@@ -182,18 +181,17 @@
 ; CHECK: .cfi_startproc
 ;   Check that used callee-saved registers are saved
 ; CHECK: stp	x29, x30, [sp, #-32]!
-; CHECK: .cfi_def_cfa_offset 32
 ;   Check that the frame pointer is created:
 ; CHECK: str	x19, [sp, #16]
 ; CHECK: mov	x29, sp
+;   Check the dynamic realignment of the stack pointer to a 128-byte boundary
+; CHECK: sub	x9, sp, #96
+; CHECK: and	sp, x9, #0xffffffffffffff80
 ;   Check correctness of cfi pseudo-instructions
 ; CHECK: .cfi_def_cfa w29, 32
 ; CHECK: .cfi_offset w19, -16
 ; CHECK: .cfi_offset w30, -24
 ; CHECK: .cfi_offset w29, -32
-;   Check the dynamic realignment of the stack pointer to a 128-byte boundary
-; CHECK: sub	x9, sp, #96
-; CHECK: and	sp, x9, #0xffffffffffffff80
 ;   Check correct access to arguments passed on the stack, through frame pointer
 ; CHECK: ldr	d[[DARG:[0-9]+]], [x29, #56]
 ; CHECK: ldr	w[[IARG:[0-9]+]], [x29, #40]
@@ -211,19 +209,18 @@
 ; CHECK-MACHO: .cfi_startproc
 ;   Check that used callee-saved registers are saved
 ; CHECK-MACHO: stp	x20, x19, [sp, #-32]!
-; CHECK-MACHO: .cfi_def_cfa_offset 32
 ;   Check that the frame pointer is created:
 ; CHECK-MACHO: stp	x29, x30, [sp, #16]
 ; CHECK-MACHO: add	x29, sp, #16
+;   Check the dynamic realignment of the stack pointer to a 128-byte boundary
+; CHECK-MACHO: sub	x9, sp, #96
+; CHECK-MACHO: and	sp, x9, #0xffffffffffffff80
 ;   Check correctness of cfi pseudo-instructions
 ; CHECK-MACHO: .cfi_def_cfa w29, 16
 ; CHECK-MACHO: .cfi_offset w30, -8
 ; CHECK-MACHO: .cfi_offset w29, -16
 ; CHECK-MACHO: .cfi_offset w19, -24
 ; CHECK-MACHO: .cfi_offset w20, -32
-;   Check the dynamic realignment of the stack pointer to a 128-byte boundary
-; CHECK-MACHO: sub	x9, sp, #96
-; CHECK-MACHO: and	sp, x9, #0xffffffffffffff80
 ;   Check correct access to arguments passed on the stack, through frame pointer
 ; CHECK-MACHO: ldr	d[[DARG:[0-9]+]], [x29, #32]
 ; CHECK-MACHO: ldr	w[[IARG:[0-9]+]], [x29, #20]
@@ -288,19 +285,18 @@
 ; CHECK: .cfi_startproc
 ;   Check that used callee-saved registers are saved
 ; CHECK: stp	x29, x30, [sp, #-32]!
-; CHECK: .cfi_def_cfa_offset 32
 ;   Check that the frame pointer is created:
 ; CHECK: stp	x20, x19, [sp, #16]
 ; CHECK: mov	x29, sp
+;   Check that space is reserved on the stack for the local variable,
+;   rounded up to a multiple of 16 to keep the stack pointer 16-byte aligned.
+; CHECK: sub	sp, sp, #16
 ;   Check correctness of cfi pseudo-instructions
 ; CHECK: .cfi_def_cfa w29, 32
 ; CHECK: .cfi_offset w19, -8
 ; CHECK: .cfi_offset w20, -16
 ; CHECK: .cfi_offset w30, -24
 ; CHECK: .cfi_offset w29, -32
-;   Check that space is reserved on the stack for the local variable,
-;   rounded up to a multiple of 16 to keep the stack pointer 16-byte aligned.
-; CHECK: sub	sp, sp, #16
 ;   Check correct access to arguments passed on the stack, through frame pointer
 ; CHECK: ldr	w[[IARG:[0-9]+]], [x29, #40]
 ;   Check correct reservation of 16-byte aligned VLA (size in w0) on stack
@@ -388,18 +384,10 @@
 ; CHECK: .cfi_startproc
 ;   Check that used callee-saved registers are saved
 ; CHECK: stp	x29, x30, [sp, #-48]!
-; CHECK: .cfi_def_cfa_offset 48
 ; CHECK: str	x21, [sp, #16]
 ; CHECK: stp	x20, x19, [sp, #32]
 ;   Check that the frame pointer is created:
 ; CHECK: mov	x29, sp
-;   Check correctness of cfi pseudo-instructions
-; CHECK: .cfi_def_cfa w29, 48
-; CHECK: .cfi_offset w19, -8
-; CHECK: .cfi_offset w20, -16
-; CHECK: .cfi_offset w21, -32
-; CHECK: .cfi_offset w30, -40
-; CHECK: .cfi_offset w29, -48
 ;   Check that the stack pointer gets re-aligned to 128
 ;   bytes & the base pointer (x19) gets initialized to
 ;   this 128-byte aligned area for local variables &
@@ -407,6 +395,13 @@
 ; CHECK: sub	x9, sp, #80
 ; CHECK: and	sp, x9, #0xffffffffffffff80
 ; CHECK: mov    x19, sp
+;   Check correctness of cfi pseudo-instructions
+; CHECK: .cfi_def_cfa w29, 48
+; CHECK: .cfi_offset w19, -8
+; CHECK: .cfi_offset w20, -16
+; CHECK: .cfi_offset w21, -32
+; CHECK: .cfi_offset w30, -40
+; CHECK: .cfi_offset w29, -48
 ;   Check correct access to arguments passed on the stack, through frame pointer
 ; CHECK: ldr	w[[IARG:[0-9]+]], [x29, #56]
 ;   Check correct reservation of 16-byte aligned VLA (size in w0) on stack
@@ -434,11 +429,17 @@
 ; CHECK-MACHO: .cfi_startproc
 ;   Check that used callee-saved registers are saved
 ; CHECK-MACHO: stp	x22, x21, [sp, #-48]!
-; CHECK-MACHO: .cfi_def_cfa_offset 48
 ; CHECK-MACHO: stp	x20, x19, [sp, #16]
 ;   Check that the frame pointer is created:
 ; CHECK-MACHO: stp	x29, x30, [sp, #32]
 ; CHECK-MACHO: add	x29, sp, #32
+;   Check that the stack pointer gets re-aligned to 128
+;   bytes & the base pointer (x19) gets initialized to
+;   this 128-byte aligned area for local variables &
+;   spill slots
+; CHECK-MACHO: sub	x9, sp, #80
+; CHECK-MACHO: and	sp, x9, #0xffffffffffffff80
+; CHECK-MACHO: mov    x19, sp
 ;   Check correctness of cfi pseudo-instructions
 ; CHECK-MACHO: .cfi_def_cfa w29, 16
 ; CHECK-MACHO: .cfi_offset w30, -8
@@ -447,13 +448,6 @@
 ; CHECK-MACHO: .cfi_offset w20, -32
 ; CHECK-MACHO: .cfi_offset w21, -40
 ; CHECK-MACHO: .cfi_offset w22, -48
-;   Check that the stack pointer gets re-aligned to 128
-;   bytes & the base pointer (x19) gets initialized to
-;   this 128-byte aligned area for local variables &
-;   spill slots
-; CHECK-MACHO: sub	x9, sp, #80
-; CHECK-MACHO: and	sp, x9, #0xffffffffffffff80
-; CHECK-MACHO: mov    x19, sp
 ;   Check correct access to arguments passed on the stack, through frame pointer
 ; CHECK-MACHO: ldr	w[[IARG:[0-9]+]], [x29, #20]
 ;   Check correct reservation of 16-byte aligned VLA (size in w0) on stack
diff --git a/llvm/test/CodeGen/AArch64/aarch64-fastcc-stackup.ll b/llvm/test/CodeGen/AArch64/aarch64-fastcc-stackup.ll
--- a/llvm/test/CodeGen/AArch64/aarch64-fastcc-stackup.ll
+++ b/llvm/test/CodeGen/AArch64/aarch64-fastcc-stackup.ll
@@ -21,8 +21,8 @@
 ; CHECK-LABEL: baz:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    mov x8, sp
 ; CHECK-NEXT:    mov x7, xzr
diff --git a/llvm/test/CodeGen/AArch64/aarch64-mops-consecutive.ll b/llvm/test/CodeGen/AArch64/aarch64-mops-consecutive.ll
--- a/llvm/test/CodeGen/AArch64/aarch64-mops-consecutive.ll
+++ b/llvm/test/CodeGen/AArch64/aarch64-mops-consecutive.ll
@@ -10,11 +10,10 @@
 ; CHECK-MOPS-LABEL: consecutive:
 ; CHECK-MOPS:       // %bb.0: // %entry
 ; CHECK-MOPS-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
-; CHECK-MOPS-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-MOPS-NEXT:    .cfi_offset w30, -8
-; CHECK-MOPS-NEXT:    .cfi_offset w29, -16
 ; CHECK-MOPS-NEXT:    sub sp, sp, #2016
 ; CHECK-MOPS-NEXT:    .cfi_def_cfa_offset 2032
+; CHECK-MOPS-NEXT:    .cfi_offset w30, -8
+; CHECK-MOPS-NEXT:    .cfi_offset w29, -16
 ; CHECK-MOPS-NEXT:    mov w8, #1000
 ; CHECK-MOPS-NEXT:    add x9, sp, #8
 ; CHECK-MOPS-NEXT:    adrp x10, .LCPI0_0
diff --git a/llvm/test/CodeGen/AArch64/aarch64-mops.ll b/llvm/test/CodeGen/AArch64/aarch64-mops.ll
--- a/llvm/test/CodeGen/AArch64/aarch64-mops.ll
+++ b/llvm/test/CodeGen/AArch64/aarch64-mops.ll
@@ -690,8 +690,8 @@
 ; GISel-WITHOUT-MOPS-O0-LABEL: memset_size:
 ; GISel-WITHOUT-MOPS-O0:       // %bb.0: // %entry
 ; GISel-WITHOUT-MOPS-O0-NEXT:    sub sp, sp, #32
-; GISel-WITHOUT-MOPS-O0-NEXT:    .cfi_def_cfa_offset 32
 ; GISel-WITHOUT-MOPS-O0-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; GISel-WITHOUT-MOPS-O0-NEXT:    .cfi_def_cfa_offset 32
 ; GISel-WITHOUT-MOPS-O0-NEXT:    .cfi_offset w30, -16
 ; GISel-WITHOUT-MOPS-O0-NEXT:    str x1, [sp, #8] // 8-byte Folded Spill
 ; GISel-WITHOUT-MOPS-O0-NEXT:    mov w1, w2
@@ -759,8 +759,8 @@
 ; GISel-WITHOUT-MOPS-O0-LABEL: memset_size_volatile:
 ; GISel-WITHOUT-MOPS-O0:       // %bb.0: // %entry
 ; GISel-WITHOUT-MOPS-O0-NEXT:    sub sp, sp, #32
-; GISel-WITHOUT-MOPS-O0-NEXT:    .cfi_def_cfa_offset 32
 ; GISel-WITHOUT-MOPS-O0-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; GISel-WITHOUT-MOPS-O0-NEXT:    .cfi_def_cfa_offset 32
 ; GISel-WITHOUT-MOPS-O0-NEXT:    .cfi_offset w30, -16
 ; GISel-WITHOUT-MOPS-O0-NEXT:    str x1, [sp, #8] // 8-byte Folded Spill
 ; GISel-WITHOUT-MOPS-O0-NEXT:    mov w1, w2
diff --git a/llvm/test/CodeGen/AArch64/active_lane_mask.ll b/llvm/test/CodeGen/AArch64/active_lane_mask.ll
--- a/llvm/test/CodeGen/AArch64/active_lane_mask.ll
+++ b/llvm/test/CodeGen/AArch64/active_lane_mask.ll
@@ -152,10 +152,11 @@
 ; CHECK-LABEL: lane_mask_nxv32i1_i32:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p5, [sp, #6, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    index z0.s, #0, #1
 ; CHECK-NEXT:    mov z3.s, w0
 ; CHECK-NEXT:    mov z1.d, z0.d
@@ -175,7 +176,6 @@
 ; CHECK-NEXT:    cmphi p3.s, p0/z, z4.s, z5.s
 ; CHECK-NEXT:    uqadd z5.s, z6.s, z3.s
 ; CHECK-NEXT:    incw z1.s, all, mul #4
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    cmphi p4.s, p0/z, z4.s, z5.s
 ; CHECK-NEXT:    uqadd z0.s, z0.s, z3.s
 ; CHECK-NEXT:    uqadd z1.s, z1.s, z3.s
@@ -187,7 +187,6 @@
 ; CHECK-NEXT:    cmphi p4.s, p0/z, z4.s, z1.s
 ; CHECK-NEXT:    uqadd z0.s, z2.s, z3.s
 ; CHECK-NEXT:    uqadd z1.s, z6.s, z3.s
-; CHECK-NEXT:    str p5, [sp, #6, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    cmphi p5.s, p0/z, z4.s, z0.s
 ; CHECK-NEXT:    cmphi p0.s, p0/z, z4.s, z1.s
 ; CHECK-NEXT:    uzp1 p3.h, p3.h, p4.h
@@ -207,10 +206,13 @@
 ; CHECK-LABEL: lane_mask_nxv32i1_i64:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p7, [sp, #4, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    str p6, [sp, #5, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    str p5, [sp, #6, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    index z0.d, #0, #1
 ; CHECK-NEXT:    mov z3.d, x0
 ; CHECK-NEXT:    mov z1.d, z0.d
@@ -236,16 +238,13 @@
 ; CHECK-NEXT:    uqadd z6.d, z7.d, z3.d
 ; CHECK-NEXT:    mov z25.d, z2.d
 ; CHECK-NEXT:    incd z24.d, all, mul #4
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    mov z26.d, z5.d
 ; CHECK-NEXT:    cmphi p4.d, p0/z, z4.d, z6.d
 ; CHECK-NEXT:    uqadd z6.d, z24.d, z3.d
 ; CHECK-NEXT:    incd z25.d, all, mul #4
-; CHECK-NEXT:    str p5, [sp, #6, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    cmphi p5.d, p0/z, z4.d, z6.d
 ; CHECK-NEXT:    uqadd z6.d, z25.d, z3.d
 ; CHECK-NEXT:    incd z26.d, all, mul #4
-; CHECK-NEXT:    str p6, [sp, #5, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    cmphi p6.d, p0/z, z4.d, z6.d
 ; CHECK-NEXT:    uqadd z6.d, z26.d, z3.d
 ; CHECK-NEXT:    uzp1 p2.s, p2.s, p3.s
@@ -278,7 +277,6 @@
 ; CHECK-NEXT:    cmphi p6.d, p0/z, z4.d, z1.d
 ; CHECK-NEXT:    uqadd z0.d, z25.d, z3.d
 ; CHECK-NEXT:    uqadd z1.d, z26.d, z3.d
-; CHECK-NEXT:    str p7, [sp, #4, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    cmphi p7.d, p0/z, z4.d, z0.d
 ; CHECK-NEXT:    cmphi p0.d, p0/z, z4.d, z1.d
 ; CHECK-NEXT:    uzp1 p5.s, p5.s, p6.s
diff --git a/llvm/test/CodeGen/AArch64/addsub-constant-folding.ll b/llvm/test/CodeGen/AArch64/addsub-constant-folding.ll
--- a/llvm/test/CodeGen/AArch64/addsub-constant-folding.ll
+++ b/llvm/test/CodeGen/AArch64/addsub-constant-folding.ll
@@ -50,8 +50,8 @@
 ; CHECK-LABEL: vec_add_const_add_const_extrause:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v1.4s, #8
 ; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
@@ -127,8 +127,8 @@
 ; CHECK-LABEL: vec_add_const_sub_const_extrause:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v1.4s, #8
 ; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
@@ -206,8 +206,8 @@
 ; CHECK-LABEL: vec_add_const_const_sub_extrause:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v1.4s, #8
 ; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
@@ -283,8 +283,8 @@
 ; CHECK-LABEL: vec_sub_const_add_const_extrause:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v1.4s, #8
 ; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
@@ -360,8 +360,8 @@
 ; CHECK-LABEL: vec_sub_const_sub_const_extrause:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v1.4s, #8
 ; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
@@ -439,8 +439,8 @@
 ; CHECK-LABEL: vec_sub_const_const_sub_extrause:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v1.4s, #8
 ; CHECK-NEXT:    sub v0.4s, v0.4s, v1.4s
@@ -519,8 +519,8 @@
 ; CHECK-LABEL: vec_const_sub_add_const_extrause:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v1.4s, #8
 ; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
@@ -599,8 +599,8 @@
 ; CHECK-LABEL: vec_const_sub_sub_const_extrause:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v1.4s, #8
 ; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
@@ -678,8 +678,8 @@
 ; CHECK-LABEL: vec_const_sub_const_sub_extrause:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v1.4s, #8
 ; CHECK-NEXT:    sub v0.4s, v1.4s, v0.4s
diff --git a/llvm/test/CodeGen/AArch64/addsub.ll b/llvm/test/CodeGen/AArch64/addsub.ll
--- a/llvm/test/CodeGen/AArch64/addsub.ll
+++ b/llvm/test/CodeGen/AArch64/addsub.ll
@@ -674,8 +674,6 @@
 ; CHECK-NEXT:    bl crng_reseed
 ; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:  .LBB36_3: // %if.end
-; CHECK-NEXT:    .cfi_def_cfa wsp, 0
-; CHECK-NEXT:    .cfi_same_value w30
 ; CHECK-NEXT:    ret
 entry:
   br i1 icmp slt (ptr @_extract_crng_crng, ptr null), label %if.then, label %lor.lhs.false
diff --git a/llvm/test/CodeGen/AArch64/argument-blocks-array-of-struct.ll b/llvm/test/CodeGen/AArch64/argument-blocks-array-of-struct.ll
--- a/llvm/test/CodeGen/AArch64/argument-blocks-array-of-struct.ll
+++ b/llvm/test/CodeGen/AArch64/argument-blocks-array-of-struct.ll
@@ -452,8 +452,8 @@
 ; CHECK-LABEL: caller_in_memory:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #96
-; CHECK-NEXT:    .cfi_def_cfa_offset 96
 ; CHECK-NEXT:    str x30, [sp, #80] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 96
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    add x8, sp, #8
 ; CHECK-NEXT:    bl return_in_memory
@@ -496,8 +496,8 @@
 ; CHECK-LABEL: argument_in_memory:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #96
-; CHECK-NEXT:    .cfi_def_cfa_offset 96
 ; CHECK-NEXT:    str x30, [sp, #80] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 96
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    adrp x8, in_memory_store
 ; CHECK-NEXT:    add x8, x8, :lo12:in_memory_store
diff --git a/llvm/test/CodeGen/AArch64/arm64-custom-call-saved-reg.ll b/llvm/test/CodeGen/AArch64/arm64-custom-call-saved-reg.ll
--- a/llvm/test/CodeGen/AArch64/arm64-custom-call-saved-reg.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-custom-call-saved-reg.ll
@@ -72,7 +72,6 @@
 ; CHECK-SAVED-X18: str x18, [sp
 
 ; CHECK-SAVED-ALL: str x18, [sp
-; CHECK-SAVED-ALL-NEXT: .cfi_def_cfa_offset
 ; CHECK-SAVED-ALL-NEXT: stp x15, x14, [sp
 ; CHECK-SAVED-ALL-NEXT: stp x13, x12, [sp
 ; CHECK-SAVED-ALL-NEXT: stp x11, x10, [sp
diff --git a/llvm/test/CodeGen/AArch64/arm64-fp128.ll b/llvm/test/CodeGen/AArch64/arm64-fp128.ll
--- a/llvm/test/CodeGen/AArch64/arm64-fp128.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-fp128.ll
@@ -75,8 +75,8 @@
 ; CHECK-LABEL: test_fptosi:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    adrp x8, lhs
 ; CHECK-NEXT:    ldr q0, [x8, :lo12:lhs]
@@ -106,8 +106,8 @@
 ; CHECK-LABEL: test_fptoui:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    adrp x8, lhs
 ; CHECK-NEXT:    ldr q0, [x8, :lo12:lhs]
@@ -247,8 +247,8 @@
 ; CHECK-LABEL: test_setcc3:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    stp x30, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    adrp x8, lhs
@@ -342,8 +342,8 @@
 ; CHECK-LABEL: test_round:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    adrp x8, lhs
 ; CHECK-NEXT:    ldr q0, [x8, :lo12:lhs]
diff --git a/llvm/test/CodeGen/AArch64/arm64-large-frame.ll b/llvm/test/CodeGen/AArch64/arm64-large-frame.ll
--- a/llvm/test/CodeGen/AArch64/arm64-large-frame.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-large-frame.ll
@@ -12,11 +12,8 @@
   %var3 = alloca i8, i32 20000000
 
 ; CHECK:      sub sp, sp, #4095, lsl #12          // =16773120
-; CHECK-NEXT: .cfi_def_cfa_offset 16773136
 ; CHECK-NEXT: sub sp, sp, #4095, lsl #12          // =16773120
-; CHECK-NEXT: .cfi_def_cfa_offset 33546256
 ; CHECK-NEXT: sub sp, sp, #1575, lsl #12          // =6451200
-; CHECK-NEXT: .cfi_def_cfa_offset 39997456
 ; CHECK-NEXT: sub sp, sp, #2576
 ; CHECK-NEXT: .cfi_def_cfa_offset 40000032
 
@@ -56,7 +53,6 @@
   %var3 = alloca i8, i32 1000000
 
 ; CHECK:      sub sp, sp, #488, lsl #12           // =1998848
-; CHECK-NEXT: .cfi_def_cfa_offset 1998864
 ; CHECK-NEXT: sub sp, sp, #1168
 ; CHECK-NEXT: .cfi_def_cfa_offset 2000032
 
diff --git a/llvm/test/CodeGen/AArch64/arm64-memset-inline.ll b/llvm/test/CodeGen/AArch64/arm64-memset-inline.ll
--- a/llvm/test/CodeGen/AArch64/arm64-memset-inline.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-memset-inline.ll
@@ -96,8 +96,8 @@
 ; CHECK-LABEL: bzero_12_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    mov x0, sp
 ; CHECK-NEXT:    str wzr, [sp, #8]
@@ -116,8 +116,8 @@
 ; CHECK-LABEL: bzero_16_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp xzr, x30, [sp, #8] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    mov x0, sp
 ; CHECK-NEXT:    str xzr, [sp]
@@ -135,8 +135,8 @@
 ; CHECK-LABEL: bzero_20_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #32] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    add x0, sp, #8
 ; CHECK-NEXT:    stp xzr, xzr, [sp, #8]
@@ -155,8 +155,8 @@
 ; CHECK-LABEL: bzero_26_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #32] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    mov x0, sp
 ; CHECK-NEXT:    stp xzr, xzr, [sp]
@@ -176,8 +176,8 @@
 ; CHECK-LABEL: bzero_32_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #32] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v0.2d, #0000000000000000
 ; CHECK-NEXT:    mov x0, sp
@@ -196,8 +196,8 @@
 ; CHECK-LABEL: bzero_40_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #64
-; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    str x30, [sp, #48] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v0.2d, #0000000000000000
 ; CHECK-NEXT:    mov x0, sp
@@ -217,8 +217,8 @@
 ; CHECK-LABEL: bzero_64_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #80
-; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    str x30, [sp, #64] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v0.2d, #0000000000000000
 ; CHECK-NEXT:    mov x0, sp
@@ -238,8 +238,8 @@
 ; CHECK-LABEL: bzero_72_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #96
-; CHECK-NEXT:    .cfi_def_cfa_offset 96
 ; CHECK-NEXT:    str x30, [sp, #80] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 96
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v0.2d, #0000000000000000
 ; CHECK-NEXT:    mov x0, sp
@@ -260,8 +260,8 @@
 ; CHECK-LABEL: bzero_128_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #144
-; CHECK-NEXT:    .cfi_def_cfa_offset 144
 ; CHECK-NEXT:    str x30, [sp, #128] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 144
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v0.2d, #0000000000000000
 ; CHECK-NEXT:    mov x0, sp
@@ -283,8 +283,8 @@
 ; CHECK-LABEL: bzero_256_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #272
-; CHECK-NEXT:    .cfi_def_cfa_offset 272
 ; CHECK-NEXT:    stp x29, x30, [sp, #256] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 272
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    movi v0.2d, #0000000000000000
@@ -346,8 +346,8 @@
 ; CHECK-LABEL: memset_12_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    mov x8, #-6148914691236517206
 ; CHECK-NEXT:    mov x0, sp
@@ -387,8 +387,8 @@
 ; CHECK-LABEL: memset_20_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #32] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    mov x8, #-6148914691236517206
 ; CHECK-NEXT:    add x0, sp, #8
@@ -408,8 +408,8 @@
 ; CHECK-LABEL: memset_26_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #32] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    mov x8, #-6148914691236517206
 ; CHECK-NEXT:    mov x0, sp
@@ -430,8 +430,8 @@
 ; CHECK-LABEL: memset_32_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #32] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v0.16b, #170
 ; CHECK-NEXT:    mov x0, sp
@@ -450,8 +450,8 @@
 ; CHECK-LABEL: memset_40_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #64
-; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    str x30, [sp, #48] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v0.16b, #170
 ; CHECK-NEXT:    mov x8, #-6148914691236517206
@@ -472,8 +472,8 @@
 ; CHECK-LABEL: memset_64_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #80
-; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    str x30, [sp, #64] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v0.16b, #170
 ; CHECK-NEXT:    mov x0, sp
@@ -493,8 +493,8 @@
 ; CHECK-LABEL: memset_72_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #96
-; CHECK-NEXT:    .cfi_def_cfa_offset 96
 ; CHECK-NEXT:    str x30, [sp, #80] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 96
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v0.16b, #170
 ; CHECK-NEXT:    mov x8, #-6148914691236517206
@@ -516,8 +516,8 @@
 ; CHECK-LABEL: memset_128_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #144
-; CHECK-NEXT:    .cfi_def_cfa_offset 144
 ; CHECK-NEXT:    str x30, [sp, #128] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 144
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v0.16b, #170
 ; CHECK-NEXT:    mov x0, sp
@@ -539,8 +539,8 @@
 ; CHECK-LABEL: memset_256_stack:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #272
-; CHECK-NEXT:    .cfi_def_cfa_offset 272
 ; CHECK-NEXT:    stp x29, x30, [sp, #256] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 272
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    movi v0.16b, #170
diff --git a/llvm/test/CodeGen/AArch64/arm64-neon-mul-div.ll b/llvm/test/CodeGen/AArch64/arm64-neon-mul-div.ll
--- a/llvm/test/CodeGen/AArch64/arm64-neon-mul-div.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-neon-mul-div.ll
@@ -807,10 +807,10 @@
 ; CHECK-LABEL: srem16x8:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    stp x26, x25, [sp, #-64]! // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    stp x24, x23, [sp, #16] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #32] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #48] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -1171,10 +1171,10 @@
 ; CHECK-LABEL: urem16x8:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    stp x26, x25, [sp, #-64]! // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    stp x24, x23, [sp, #16] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #32] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #48] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -1469,8 +1469,8 @@
 ; CHECK-LABEL: frem2f32:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #64
-; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    str x30, [sp, #48] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
 ; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
@@ -1498,8 +1498,8 @@
 ; CHECK-LABEL: frem4f32:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #64
-; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    str x30, [sp, #48] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    stp q0, q1, [sp, #16] // 32-byte Folded Spill
 ; CHECK-NEXT:    mov s0, v0.s[1]
@@ -1554,8 +1554,8 @@
 ; CHECK-LABEL: frem2d64:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #64
-; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    str x30, [sp, #48] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    stp q0, q1, [sp] // 32-byte Folded Spill
 ; CHECK-NEXT:    mov d0, v0.d[1]
@@ -1712,4 +1712,3 @@
         %val = call <2 x double> @llvm.aarch64.neon.fmulx.v2f64(<2 x double> %lhs, <2 x double> %rhs)
         ret <2 x double> %val
 }
-
diff --git a/llvm/test/CodeGen/AArch64/arm64-neon-vector-list-spill.ll b/llvm/test/CodeGen/AArch64/arm64-neon-vector-list-spill.ll
--- a/llvm/test/CodeGen/AArch64/arm64-neon-vector-list-spill.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-neon-vector-list-spill.ll
@@ -15,8 +15,8 @@
 ; CHECK-NEXT:    ret
 ; CHECK-NEXT:  .LBB0_2: // %if.then
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    stp x29, x30, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov x8, sp
@@ -53,8 +53,8 @@
 ; CHECK-NEXT:    ret
 ; CHECK-NEXT:  .LBB1_2: // %if.then
 ; CHECK-NEXT:    sub sp, sp, #64
-; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    stp x29, x30, [sp, #48] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov x8, sp
@@ -91,8 +91,8 @@
 ; CHECK-NEXT:    ret
 ; CHECK-NEXT:  .LBB2_2: // %if.then
 ; CHECK-NEXT:    sub sp, sp, #80
-; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    stp x29, x30, [sp, #64] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov x8, sp
@@ -129,8 +129,8 @@
 ; CHECK-NEXT:    ret
 ; CHECK-NEXT:  .LBB3_2: // %if.then
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    stp x29, x30, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov x8, sp
@@ -167,8 +167,8 @@
 ; CHECK-NEXT:    ret
 ; CHECK-NEXT:  .LBB4_2: // %if.then
 ; CHECK-NEXT:    sub sp, sp, #64
-; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    stp x29, x30, [sp, #48] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov x8, sp
@@ -205,8 +205,8 @@
 ; CHECK-NEXT:    ret
 ; CHECK-NEXT:  .LBB5_2: // %if.then
 ; CHECK-NEXT:    sub sp, sp, #80
-; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    stp x29, x30, [sp, #64] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov x8, sp
diff --git a/llvm/test/CodeGen/AArch64/arm64-patchpoint.ll b/llvm/test/CodeGen/AArch64/arm64-patchpoint.ll
--- a/llvm/test/CodeGen/AArch64/arm64-patchpoint.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-patchpoint.ll
@@ -27,7 +27,6 @@
 ;
 ; CHECK-LABEL: caller_meta_leaf
 ; CHECK:       sub sp, sp, #48
-; CHECK-NEXT: .cfi_def_cfa_offset 48
 ; CHECK-NEXT:  stp x29, x30, [sp, #32]
 ; CHECK-NEXT:  add x29, sp, #32
 ; CHECK:       Ltmp
@@ -83,4 +82,3 @@
 declare void @llvm.experimental.stackmap(i64, i32, ...)
 declare void @llvm.experimental.patchpoint.void(i64, i32, ptr, i32, ...)
 declare i64 @llvm.experimental.patchpoint.i64(i64, i32, ptr, i32, ...)
-
diff --git a/llvm/test/CodeGen/AArch64/arm64-shrink-wrapping.ll b/llvm/test/CodeGen/AArch64/arm64-shrink-wrapping.ll
--- a/llvm/test/CodeGen/AArch64/arm64-shrink-wrapping.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-shrink-wrapping.ll
@@ -13,7 +13,6 @@
 ; ENABLE-NEXT:    b.ge LBB0_2
 ; ENABLE-NEXT:  ; %bb.1: ; %true
 ; ENABLE-NEXT:    sub sp, sp, #32
-; ENABLE-NEXT:    .cfi_def_cfa_offset 32
 ; ENABLE-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; ENABLE-NEXT:    add x29, sp, #16
 ; ENABLE-NEXT:    .cfi_def_cfa w29, 16
@@ -26,15 +25,11 @@
 ; ENABLE-NEXT:    ldp x29, x30, [sp, #16] ; 16-byte Folded Reload
 ; ENABLE-NEXT:    add sp, sp, #32
 ; ENABLE-NEXT:  LBB0_2: ; %false
-; ENABLE-NEXT:    .cfi_def_cfa wsp, 0
-; ENABLE-NEXT:    .cfi_same_value w30
-; ENABLE-NEXT:    .cfi_same_value w29
 ; ENABLE-NEXT:    ret
 ;
 ; DISABLE-LABEL: foo:
 ; DISABLE:       ; %bb.0:
 ; DISABLE-NEXT:    sub sp, sp, #32
-; DISABLE-NEXT:    .cfi_def_cfa_offset 32
 ; DISABLE-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; DISABLE-NEXT:    add x29, sp, #16
 ; DISABLE-NEXT:    .cfi_def_cfa w29, 16
@@ -77,7 +72,6 @@
 ; ENABLE-NEXT:    cbz w0, LBB1_4
 ; ENABLE-NEXT:  ; %bb.1: ; %for.body.preheader
 ; ENABLE-NEXT:    stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
-; ENABLE-NEXT:    .cfi_def_cfa_offset 32
 ; ENABLE-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; ENABLE-NEXT:    add x29, sp, #16
 ; ENABLE-NEXT:    .cfi_def_cfa w29, 16
@@ -99,18 +93,12 @@
 ; ENABLE-NEXT:    ldp x20, x19, [sp], #32 ; 16-byte Folded Reload
 ; ENABLE-NEXT:    ret
 ; ENABLE-NEXT:  LBB1_4: ; %if.else
-; ENABLE-NEXT:    .cfi_def_cfa wsp, 0
-; ENABLE-NEXT:    .cfi_same_value w30
-; ENABLE-NEXT:    .cfi_same_value w29
-; ENABLE-NEXT:    .cfi_same_value w19
-; ENABLE-NEXT:    .cfi_same_value w20
 ; ENABLE-NEXT:    lsl w0, w1, #1
 ; ENABLE-NEXT:    ret
 ;
 ; DISABLE-LABEL: freqSaveAndRestoreOutsideLoop:
 ; DISABLE:       ; %bb.0: ; %entry
 ; DISABLE-NEXT:    stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
-; DISABLE-NEXT:    .cfi_def_cfa_offset 32
 ; DISABLE-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; DISABLE-NEXT:    add x29, sp, #16
 ; DISABLE-NEXT:    .cfi_def_cfa w29, 16
@@ -171,7 +159,6 @@
 ; ENABLE-LABEL: freqSaveAndRestoreOutsideLoop2:
 ; ENABLE:       ; %bb.0: ; %entry
 ; ENABLE-NEXT:    stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
-; ENABLE-NEXT:    .cfi_def_cfa_offset 32
 ; ENABLE-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; ENABLE-NEXT:    add x29, sp, #16
 ; ENABLE-NEXT:    .cfi_def_cfa w29, 16
@@ -196,7 +183,6 @@
 ; DISABLE-LABEL: freqSaveAndRestoreOutsideLoop2:
 ; DISABLE:       ; %bb.0: ; %entry
 ; DISABLE-NEXT:    stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
-; DISABLE-NEXT:    .cfi_def_cfa_offset 32
 ; DISABLE-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; DISABLE-NEXT:    add x29, sp, #16
 ; DISABLE-NEXT:    .cfi_def_cfa w29, 16
@@ -241,7 +227,6 @@
 ; ENABLE-NEXT:    cbz w0, LBB3_4
 ; ENABLE-NEXT:  ; %bb.1: ; %for.body.preheader
 ; ENABLE-NEXT:    stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
-; ENABLE-NEXT:    .cfi_def_cfa_offset 32
 ; ENABLE-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; ENABLE-NEXT:    add x29, sp, #16
 ; ENABLE-NEXT:    .cfi_def_cfa w29, 16
@@ -264,18 +249,12 @@
 ; ENABLE-NEXT:    ldp x20, x19, [sp], #32 ; 16-byte Folded Reload
 ; ENABLE-NEXT:    ret
 ; ENABLE-NEXT:  LBB3_4: ; %if.else
-; ENABLE-NEXT:    .cfi_def_cfa wsp, 0
-; ENABLE-NEXT:    .cfi_same_value w30
-; ENABLE-NEXT:    .cfi_same_value w29
-; ENABLE-NEXT:    .cfi_same_value w19
-; ENABLE-NEXT:    .cfi_same_value w20
 ; ENABLE-NEXT:    lsl w0, w1, #1
 ; ENABLE-NEXT:    ret
 ;
 ; DISABLE-LABEL: loopInfoSaveOutsideLoop:
 ; DISABLE:       ; %bb.0: ; %entry
 ; DISABLE-NEXT:    stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
-; DISABLE-NEXT:    .cfi_def_cfa_offset 32
 ; DISABLE-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; DISABLE-NEXT:    add x29, sp, #16
 ; DISABLE-NEXT:    .cfi_def_cfa w29, 16
@@ -571,9 +550,6 @@
 ; ENABLE-NEXT:    ldp x20, x19, [sp], #16 ; 16-byte Folded Reload
 ; ENABLE-NEXT:    ret
 ; ENABLE-NEXT:  LBB7_4: ; %if.else
-; ENABLE-NEXT:    .cfi_def_cfa wsp, 0
-; ENABLE-NEXT:    .cfi_same_value w19
-; ENABLE-NEXT:    .cfi_same_value w20
 ; ENABLE-NEXT:    lsl w0, w1, #1
 ; ENABLE-NEXT:    ret
 ;
@@ -629,7 +605,6 @@
 ; ENABLE-NEXT:    cbz w0, LBB8_2
 ; ENABLE-NEXT:  ; %bb.1: ; %if.then
 ; ENABLE-NEXT:    sub sp, sp, #64
-; ENABLE-NEXT:    .cfi_def_cfa_offset 64
 ; ENABLE-NEXT:    stp x29, x30, [sp, #48] ; 16-byte Folded Spill
 ; ENABLE-NEXT:    add x29, sp, #48
 ; ENABLE-NEXT:    .cfi_def_cfa w29, 16
@@ -645,16 +620,12 @@
 ; ENABLE-NEXT:    add sp, sp, #64
 ; ENABLE-NEXT:    ret
 ; ENABLE-NEXT:  LBB8_2: ; %if.else
-; ENABLE-NEXT:    .cfi_def_cfa wsp, 0
-; ENABLE-NEXT:    .cfi_same_value w30
-; ENABLE-NEXT:    .cfi_same_value w29
 ; ENABLE-NEXT:    lsl w0, w1, #1
 ; ENABLE-NEXT:    ret
 ;
 ; DISABLE-LABEL: callVariadicFunc:
 ; DISABLE:       ; %bb.0: ; %entry
 ; DISABLE-NEXT:    sub sp, sp, #64
-; DISABLE-NEXT:    .cfi_def_cfa_offset 64
 ; DISABLE-NEXT:    stp x29, x30, [sp, #48] ; 16-byte Folded Spill
 ; DISABLE-NEXT:    add x29, sp, #48
 ; DISABLE-NEXT:    .cfi_def_cfa w29, 16
@@ -709,7 +680,6 @@
 ; ENABLE-NEXT:    ret
 ; ENABLE-NEXT:  LBB9_2: ; %if.abort
 ; ENABLE-NEXT:    stp x29, x30, [sp, #-16]! ; 16-byte Folded Spill
-; ENABLE-NEXT:    .cfi_def_cfa_offset 16
 ; ENABLE-NEXT:    mov x29, sp
 ; ENABLE-NEXT:    .cfi_def_cfa w29, 16
 ; ENABLE-NEXT:    .cfi_offset w30, -8
@@ -719,7 +689,6 @@
 ; DISABLE-LABEL: noreturn:
 ; DISABLE:       ; %bb.0: ; %entry
 ; DISABLE-NEXT:    stp x29, x30, [sp, #-16]! ; 16-byte Folded Spill
-; DISABLE-NEXT:    .cfi_def_cfa_offset 16
 ; DISABLE-NEXT:    mov x29, sp
 ; DISABLE-NEXT:    .cfi_def_cfa w29, 16
 ; DISABLE-NEXT:    .cfi_offset w30, -8
@@ -759,7 +728,6 @@
 ; ENABLE-LABEL: infiniteloop:
 ; ENABLE:       ; %bb.0: ; %entry
 ; ENABLE-NEXT:    stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
-; ENABLE-NEXT:    .cfi_def_cfa_offset 32
 ; ENABLE-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; ENABLE-NEXT:    add x29, sp, #16
 ; ENABLE-NEXT:    .cfi_def_cfa w29, 16
@@ -787,7 +755,6 @@
 ; DISABLE-LABEL: infiniteloop:
 ; DISABLE:       ; %bb.0: ; %entry
 ; DISABLE-NEXT:    stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
-; DISABLE-NEXT:    .cfi_def_cfa_offset 32
 ; DISABLE-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; DISABLE-NEXT:    add x29, sp, #16
 ; DISABLE-NEXT:    .cfi_def_cfa w29, 16
@@ -834,7 +801,6 @@
 ; ENABLE-LABEL: infiniteloop2:
 ; ENABLE:       ; %bb.0: ; %entry
 ; ENABLE-NEXT:    stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
-; ENABLE-NEXT:    .cfi_def_cfa_offset 32
 ; ENABLE-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; ENABLE-NEXT:    add x29, sp, #16
 ; ENABLE-NEXT:    .cfi_def_cfa w29, 16
@@ -868,7 +834,6 @@
 ; DISABLE-LABEL: infiniteloop2:
 ; DISABLE:       ; %bb.0: ; %entry
 ; DISABLE-NEXT:    stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
-; DISABLE-NEXT:    .cfi_def_cfa_offset 32
 ; DISABLE-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; DISABLE-NEXT:    add x29, sp, #16
 ; DISABLE-NEXT:    .cfi_def_cfa w29, 16
@@ -1010,20 +975,16 @@
 ; ENABLE-NEXT:    b.ge LBB13_2
 ; ENABLE-NEXT:  ; %bb.1: ; %true
 ; ENABLE-NEXT:    stp x29, x30, [sp, #-16]! ; 16-byte Folded Spill
-; ENABLE-NEXT:    .cfi_def_cfa_offset 16
 ; ENABLE-NEXT:    mov x29, sp
+; ENABLE-NEXT:    sub x1, sp, #16
+; ENABLE-NEXT:    and sp, x1, #0xffffffffffffffe0
 ; ENABLE-NEXT:    .cfi_def_cfa w29, 16
 ; ENABLE-NEXT:    .cfi_offset w30, -8
 ; ENABLE-NEXT:    .cfi_offset w29, -16
-; ENABLE-NEXT:    sub x1, sp, #16
-; ENABLE-NEXT:    and sp, x1, #0xffffffffffffffe0
 ; ENABLE-NEXT:    str w0, [sp]
 ; ENABLE-NEXT:    mov sp, x29
 ; ENABLE-NEXT:    ldp x29, x30, [sp], #16 ; 16-byte Folded Reload
 ; ENABLE-NEXT:  LBB13_2: ; %false
-; ENABLE-NEXT:    .cfi_def_cfa wsp, 0
-; ENABLE-NEXT:    .cfi_same_value w30
-; ENABLE-NEXT:    .cfi_same_value w29
 ; ENABLE-NEXT:    str w8, [x2]
 ; ENABLE-NEXT:    str w9, [x3]
 ; ENABLE-NEXT:    ret
@@ -1031,13 +992,12 @@
 ; DISABLE-LABEL: stack_realign:
 ; DISABLE:       ; %bb.0:
 ; DISABLE-NEXT:    stp x29, x30, [sp, #-16]! ; 16-byte Folded Spill
-; DISABLE-NEXT:    .cfi_def_cfa_offset 16
 ; DISABLE-NEXT:    mov x29, sp
+; DISABLE-NEXT:    sub x9, sp, #16
+; DISABLE-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; DISABLE-NEXT:    .cfi_def_cfa w29, 16
 ; DISABLE-NEXT:    .cfi_offset w30, -8
 ; DISABLE-NEXT:    .cfi_offset w29, -16
-; DISABLE-NEXT:    sub x9, sp, #16
-; DISABLE-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; DISABLE-NEXT:    lsl w8, w0, w1
 ; DISABLE-NEXT:    lsl w9, w1, w0
 ; DISABLE-NEXT:    cmp w0, w1
@@ -1077,13 +1037,14 @@
 ; ENABLE-LABEL: stack_realign2:
 ; ENABLE:       ; %bb.0:
 ; ENABLE-NEXT:    stp x28, x27, [sp, #-96]! ; 16-byte Folded Spill
-; ENABLE-NEXT:    .cfi_def_cfa_offset 96
 ; ENABLE-NEXT:    stp x26, x25, [sp, #16] ; 16-byte Folded Spill
 ; ENABLE-NEXT:    stp x24, x23, [sp, #32] ; 16-byte Folded Spill
 ; ENABLE-NEXT:    stp x22, x21, [sp, #48] ; 16-byte Folded Spill
 ; ENABLE-NEXT:    stp x20, x19, [sp, #64] ; 16-byte Folded Spill
 ; ENABLE-NEXT:    stp x29, x30, [sp, #80] ; 16-byte Folded Spill
 ; ENABLE-NEXT:    add x29, sp, #80
+; ENABLE-NEXT:    sub x9, sp, #32
+; ENABLE-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; ENABLE-NEXT:    .cfi_def_cfa w29, 16
 ; ENABLE-NEXT:    .cfi_offset w30, -8
 ; ENABLE-NEXT:    .cfi_offset w29, -16
@@ -1097,8 +1058,6 @@
 ; ENABLE-NEXT:    .cfi_offset w26, -80
 ; ENABLE-NEXT:    .cfi_offset w27, -88
 ; ENABLE-NEXT:    .cfi_offset w28, -96
-; ENABLE-NEXT:    sub x9, sp, #32
-; ENABLE-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; ENABLE-NEXT:    add w8, w1, w0
 ; ENABLE-NEXT:    lsl w9, w0, w1
 ; ENABLE-NEXT:    lsl w10, w1, w0
@@ -1137,13 +1096,14 @@
 ; DISABLE-LABEL: stack_realign2:
 ; DISABLE:       ; %bb.0:
 ; DISABLE-NEXT:    stp x28, x27, [sp, #-96]! ; 16-byte Folded Spill
-; DISABLE-NEXT:    .cfi_def_cfa_offset 96
 ; DISABLE-NEXT:    stp x26, x25, [sp, #16] ; 16-byte Folded Spill
 ; DISABLE-NEXT:    stp x24, x23, [sp, #32] ; 16-byte Folded Spill
 ; DISABLE-NEXT:    stp x22, x21, [sp, #48] ; 16-byte Folded Spill
 ; DISABLE-NEXT:    stp x20, x19, [sp, #64] ; 16-byte Folded Spill
 ; DISABLE-NEXT:    stp x29, x30, [sp, #80] ; 16-byte Folded Spill
 ; DISABLE-NEXT:    add x29, sp, #80
+; DISABLE-NEXT:    sub x9, sp, #32
+; DISABLE-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; DISABLE-NEXT:    .cfi_def_cfa w29, 16
 ; DISABLE-NEXT:    .cfi_offset w30, -8
 ; DISABLE-NEXT:    .cfi_offset w29, -16
@@ -1157,8 +1117,6 @@
 ; DISABLE-NEXT:    .cfi_offset w26, -80
 ; DISABLE-NEXT:    .cfi_offset w27, -88
 ; DISABLE-NEXT:    .cfi_offset w28, -96
-; DISABLE-NEXT:    sub x9, sp, #32
-; DISABLE-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; DISABLE-NEXT:    add w8, w1, w0
 ; DISABLE-NEXT:    lsl w9, w0, w1
 ; DISABLE-NEXT:    lsl w10, w1, w0
diff --git a/llvm/test/CodeGen/AArch64/arm64-virtual_base.ll b/llvm/test/CodeGen/AArch64/arm64-virtual_base.ll
--- a/llvm/test/CodeGen/AArch64/arm64-virtual_base.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-virtual_base.ll
@@ -36,8 +36,8 @@
 ; CHECK-LABEL: Precompute_Patch_Values:
 ; CHECK:       ; %bb.0: ; %entry
 ; CHECK-NEXT:    sub sp, sp, #400
-; CHECK-NEXT:    .cfi_def_cfa_offset 400
 ; CHECK-NEXT:    stp x28, x27, [sp, #384] ; 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 400
 ; CHECK-NEXT:    .cfi_offset w27, -8
 ; CHECK-NEXT:    .cfi_offset w28, -16
 ; CHECK-NEXT:    ldr q0, [x0, #272]
diff --git a/llvm/test/CodeGen/AArch64/cfi-sync-async.ll b/llvm/test/CodeGen/AArch64/cfi-sync-async.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/cfi-sync-async.ll
@@ -0,0 +1,240 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=aarch64 %s -o - | FileCheck %s
+
+declare i32 @g0(i32)
+declare i32 @g1(ptr)
+
+define i32 @foo_nounwind(i1 %cmp) nounwind {
+; CHECK-LABEL: foo_nounwind:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
+; CHECK-NEXT:    sub sp, sp, #97, lsl #12 // =397312
+; CHECK-NEXT:    sub sp, sp, #2688
+; CHECK-NEXT:    tbz w0, #0, .LBB0_2
+; CHECK-NEXT:  // %bb.1: // %br1
+; CHECK-NEXT:    mov w0, wzr
+; CHECK-NEXT:    bl g0
+; CHECK-NEXT:    add w0, w0, #1
+; CHECK-NEXT:    add sp, sp, #97, lsl #12 // =397312
+; CHECK-NEXT:    add sp, sp, #2688
+; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; CHECK-NEXT:    ret
+; CHECK-NEXT:  .LBB0_2: // %br2
+; CHECK-NEXT:    mov w8, #42 // =0x2a
+; CHECK-NEXT:    mov x0, sp
+; CHECK-NEXT:    str w8, [sp]
+; CHECK-NEXT:    bl g1
+; CHECK-NEXT:    add sp, sp, #97, lsl #12 // =397312
+; CHECK-NEXT:    add sp, sp, #2688
+; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; CHECK-NEXT:    b g0
+  %ptr = alloca i32, i32 100000, align 4
+  br i1 %cmp, label %br1, label %br2
+
+br1:
+  %call1 = call i32 @g0(i32 0)
+  %rv1 = add i32 %call1, 1
+  ret i32 %rv1
+
+br2:
+  store i32 42, ptr %ptr, align 4
+  %call2 = call i32 @g1(ptr %ptr)
+  %rv2 = tail call i32 @g0(i32 %call2)
+  ret i32 %rv2
+}
+
+define i32 @foo_default(i1 %cmp) {
+; CHECK-LABEL: foo_default:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
+; CHECK-NEXT:    sub sp, sp, #97, lsl #12 // =397312
+; CHECK-NEXT:    sub sp, sp, #2688
+; CHECK-NEXT:    .cfi_def_cfa_offset 400016
+; CHECK-NEXT:    .cfi_offset w30, -8
+; CHECK-NEXT:    .cfi_offset w29, -16
+; CHECK-NEXT:    tbz w0, #0, .LBB1_2
+; CHECK-NEXT:  // %bb.1: // %br1
+; CHECK-NEXT:    mov w0, wzr
+; CHECK-NEXT:    bl g0
+; CHECK-NEXT:    add w0, w0, #1
+; CHECK-NEXT:    add sp, sp, #97, lsl #12 // =397312
+; CHECK-NEXT:    add sp, sp, #2688
+; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; CHECK-NEXT:    ret
+; CHECK-NEXT:  .LBB1_2: // %br2
+; CHECK-NEXT:    mov w8, #42 // =0x2a
+; CHECK-NEXT:    mov x0, sp
+; CHECK-NEXT:    str w8, [sp]
+; CHECK-NEXT:    bl g1
+; CHECK-NEXT:    add sp, sp, #97, lsl #12 // =397312
+; CHECK-NEXT:    add sp, sp, #2688
+; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; CHECK-NEXT:    b g0
+  %ptr = alloca i32, i32 100000, align 4
+  br i1 %cmp, label %br1, label %br2
+
+br1:
+  %call1 = call i32 @g0(i32 0)
+  %rv1 = add i32 %call1, 1
+  ret i32 %rv1
+
+br2:
+  store i32 42, ptr %ptr, align 4
+  %call2 = call i32 @g1(ptr %ptr)
+  %rv2 = tail call i32 @g0(i32 %call2)
+  ret i32 %rv2
+}
+
+define i32 @foo_uwtable(i1 %cmp) uwtable {
+; CHECK-LABEL: foo_uwtable:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset w30, -8
+; CHECK-NEXT:    .cfi_offset w29, -16
+; CHECK-NEXT:    sub sp, sp, #97, lsl #12 // =397312
+; CHECK-NEXT:    .cfi_def_cfa_offset 397328
+; CHECK-NEXT:    sub sp, sp, #2688
+; CHECK-NEXT:    .cfi_def_cfa_offset 400016
+; CHECK-NEXT:    .cfi_remember_state
+; CHECK-NEXT:    tbz w0, #0, .LBB2_2
+; CHECK-NEXT:  // %bb.1: // %br1
+; CHECK-NEXT:    mov w0, wzr
+; CHECK-NEXT:    bl g0
+; CHECK-NEXT:    add w0, w0, #1
+; CHECK-NEXT:    add sp, sp, #97, lsl #12 // =397312
+; CHECK-NEXT:    .cfi_def_cfa_offset 2704
+; CHECK-NEXT:    add sp, sp, #2688
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; CHECK-NEXT:    .cfi_def_cfa_offset 0
+; CHECK-NEXT:    .cfi_restore w30
+; CHECK-NEXT:    .cfi_restore w29
+; CHECK-NEXT:    ret
+; CHECK-NEXT:  .LBB2_2: // %br2
+; CHECK-NEXT:    .cfi_restore_state
+; CHECK-NEXT:    mov w8, #42 // =0x2a
+; CHECK-NEXT:    mov x0, sp
+; CHECK-NEXT:    str w8, [sp]
+; CHECK-NEXT:    bl g1
+; CHECK-NEXT:    add sp, sp, #97, lsl #12 // =397312
+; CHECK-NEXT:    .cfi_def_cfa_offset 2704
+; CHECK-NEXT:    add sp, sp, #2688
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; CHECK-NEXT:    .cfi_def_cfa_offset 0
+; CHECK-NEXT:    .cfi_restore w30
+; CHECK-NEXT:    .cfi_restore w29
+; CHECK-NEXT:    b g0
+  %ptr = alloca i32, i32 100000, align 4
+  br i1 %cmp, label %br1, label %br2
+
+br1:
+  %call1 = call i32 @g0(i32 0)
+  %rv1 = add i32 %call1, 1
+  ret i32 %rv1
+
+br2:
+  store i32 42, ptr %ptr, align 4
+  %call2 = call i32 @g1(ptr %ptr)
+  %rv2 = tail call i32 @g0(i32 %call2)
+  ret i32 %rv2
+}
+
+define i32 @foo_uwtable_sync(i1 %cmp) uwtable(sync) {
+; CHECK-LABEL: foo_uwtable_sync:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
+; CHECK-NEXT:    sub sp, sp, #97, lsl #12 // =397312
+; CHECK-NEXT:    sub sp, sp, #2688
+; CHECK-NEXT:    .cfi_def_cfa_offset 400016
+; CHECK-NEXT:    .cfi_offset w30, -8
+; CHECK-NEXT:    .cfi_offset w29, -16
+; CHECK-NEXT:    tbz w0, #0, .LBB3_2
+; CHECK-NEXT:  // %bb.1: // %br1
+; CHECK-NEXT:    mov w0, wzr
+; CHECK-NEXT:    bl g0
+; CHECK-NEXT:    add w0, w0, #1
+; CHECK-NEXT:    add sp, sp, #97, lsl #12 // =397312
+; CHECK-NEXT:    add sp, sp, #2688
+; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; CHECK-NEXT:    ret
+; CHECK-NEXT:  .LBB3_2: // %br2
+; CHECK-NEXT:    mov w8, #42 // =0x2a
+; CHECK-NEXT:    mov x0, sp
+; CHECK-NEXT:    str w8, [sp]
+; CHECK-NEXT:    bl g1
+; CHECK-NEXT:    add sp, sp, #97, lsl #12 // =397312
+; CHECK-NEXT:    add sp, sp, #2688
+; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; CHECK-NEXT:    b g0
+  %ptr = alloca i32, i32 100000, align 4
+  br i1 %cmp, label %br1, label %br2
+
+br1:
+  %call1 = call i32 @g0(i32 0)
+  %rv1 = add i32 %call1, 1
+  ret i32 %rv1
+
+br2:
+  store i32 42, ptr %ptr, align 4
+  %call2 = call i32 @g1(ptr %ptr)
+  %rv2 = tail call i32 @g0(i32 %call2)
+  ret i32 %rv2
+}
+
+define i32 @foo_uwtable_async(i1 %cmp) uwtable(async) {
+; CHECK-LABEL: foo_uwtable_async:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset w30, -8
+; CHECK-NEXT:    .cfi_offset w29, -16
+; CHECK-NEXT:    sub sp, sp, #97, lsl #12 // =397312
+; CHECK-NEXT:    .cfi_def_cfa_offset 397328
+; CHECK-NEXT:    sub sp, sp, #2688
+; CHECK-NEXT:    .cfi_def_cfa_offset 400016
+; CHECK-NEXT:    .cfi_remember_state
+; CHECK-NEXT:    tbz w0, #0, .LBB4_2
+; CHECK-NEXT:  // %bb.1: // %br1
+; CHECK-NEXT:    mov w0, wzr
+; CHECK-NEXT:    bl g0
+; CHECK-NEXT:    add w0, w0, #1
+; CHECK-NEXT:    add sp, sp, #97, lsl #12 // =397312
+; CHECK-NEXT:    .cfi_def_cfa_offset 2704
+; CHECK-NEXT:    add sp, sp, #2688
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; CHECK-NEXT:    .cfi_def_cfa_offset 0
+; CHECK-NEXT:    .cfi_restore w30
+; CHECK-NEXT:    .cfi_restore w29
+; CHECK-NEXT:    ret
+; CHECK-NEXT:  .LBB4_2: // %br2
+; CHECK-NEXT:    .cfi_restore_state
+; CHECK-NEXT:    mov w8, #42 // =0x2a
+; CHECK-NEXT:    mov x0, sp
+; CHECK-NEXT:    str w8, [sp]
+; CHECK-NEXT:    bl g1
+; CHECK-NEXT:    add sp, sp, #97, lsl #12 // =397312
+; CHECK-NEXT:    .cfi_def_cfa_offset 2704
+; CHECK-NEXT:    add sp, sp, #2688
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
+; CHECK-NEXT:    .cfi_def_cfa_offset 0
+; CHECK-NEXT:    .cfi_restore w30
+; CHECK-NEXT:    .cfi_restore w29
+; CHECK-NEXT:    b g0
+  %ptr = alloca i32, i32 100000, align 4
+  br i1 %cmp, label %br1, label %br2
+
+br1:
+  %call1 = call i32 @g0(i32 0)
+  %rv1 = add i32 %call1, 1
+  ret i32 %rv1
+
+br2:
+  store i32 42, ptr %ptr, align 4
+  %call2 = call i32 @g1(ptr %ptr)
+  %rv2 = tail call i32 @g0(i32 %call2)
+  ret i32 %rv2
+}
diff --git a/llvm/test/CodeGen/AArch64/cmp-select-sign.ll b/llvm/test/CodeGen/AArch64/cmp-select-sign.ll
--- a/llvm/test/CodeGen/AArch64/cmp-select-sign.ll
+++ b/llvm/test/CodeGen/AArch64/cmp-select-sign.ll
@@ -173,8 +173,8 @@
 ; CHECK-LABEL: sign_4xi32_multi_use:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    movi v1.2d, #0xffffffffffffffff
 ; CHECK-NEXT:    cmlt v2.4s, v0.4s, #0
diff --git a/llvm/test/CodeGen/AArch64/cmpxchg-idioms.ll b/llvm/test/CodeGen/AArch64/cmpxchg-idioms.ll
--- a/llvm/test/CodeGen/AArch64/cmpxchg-idioms.ll
+++ b/llvm/test/CodeGen/AArch64/cmpxchg-idioms.ll
@@ -25,8 +25,8 @@
 ; OUTLINE-ATOMICS-LABEL: test_return:
 ; OUTLINE-ATOMICS:       ; %bb.0:
 ; OUTLINE-ATOMICS-NEXT:    stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
-; OUTLINE-ATOMICS-NEXT:    .cfi_def_cfa_offset 32
 ; OUTLINE-ATOMICS-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
+; OUTLINE-ATOMICS-NEXT:    .cfi_def_cfa_offset 32
 ; OUTLINE-ATOMICS-NEXT:    .cfi_offset w30, -8
 ; OUTLINE-ATOMICS-NEXT:    .cfi_offset w29, -16
 ; OUTLINE-ATOMICS-NEXT:    .cfi_offset w19, -24
@@ -75,8 +75,8 @@
 ; OUTLINE-ATOMICS-LABEL: test_return_bool:
 ; OUTLINE-ATOMICS:       ; %bb.0:
 ; OUTLINE-ATOMICS-NEXT:    stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
-; OUTLINE-ATOMICS-NEXT:    .cfi_def_cfa_offset 32
 ; OUTLINE-ATOMICS-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
+; OUTLINE-ATOMICS-NEXT:    .cfi_def_cfa_offset 32
 ; OUTLINE-ATOMICS-NEXT:    .cfi_offset w30, -8
 ; OUTLINE-ATOMICS-NEXT:    .cfi_offset w29, -16
 ; OUTLINE-ATOMICS-NEXT:    .cfi_offset w19, -24
@@ -120,8 +120,8 @@
 ; OUTLINE-ATOMICS-LABEL: test_conditional:
 ; OUTLINE-ATOMICS:       ; %bb.0:
 ; OUTLINE-ATOMICS-NEXT:    stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
-; OUTLINE-ATOMICS-NEXT:    .cfi_def_cfa_offset 32
 ; OUTLINE-ATOMICS-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
+; OUTLINE-ATOMICS-NEXT:    .cfi_def_cfa_offset 32
 ; OUTLINE-ATOMICS-NEXT:    .cfi_offset w30, -8
 ; OUTLINE-ATOMICS-NEXT:    .cfi_offset w29, -16
 ; OUTLINE-ATOMICS-NEXT:    .cfi_offset w19, -24
@@ -166,9 +166,9 @@
 ; CHECK-LABEL: test_conditional2:
 ; CHECK:       ; %bb.0: ; %entry
 ; CHECK-NEXT:    stp x22, x21, [sp, #-48]! ; 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    stp x20, x19, [sp, #16] ; 16-byte Folded Spill
 ; CHECK-NEXT:    stp x29, x30, [sp, #32] ; 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    .cfi_offset w19, -24
@@ -222,9 +222,9 @@
 ; OUTLINE-ATOMICS-LABEL: test_conditional2:
 ; OUTLINE-ATOMICS:       ; %bb.0: ; %entry
 ; OUTLINE-ATOMICS-NEXT:    stp x22, x21, [sp, #-48]! ; 16-byte Folded Spill
-; OUTLINE-ATOMICS-NEXT:    .cfi_def_cfa_offset 48
 ; OUTLINE-ATOMICS-NEXT:    stp x20, x19, [sp, #16] ; 16-byte Folded Spill
 ; OUTLINE-ATOMICS-NEXT:    stp x29, x30, [sp, #32] ; 16-byte Folded Spill
+; OUTLINE-ATOMICS-NEXT:    .cfi_def_cfa_offset 48
 ; OUTLINE-ATOMICS-NEXT:    .cfi_offset w30, -8
 ; OUTLINE-ATOMICS-NEXT:    .cfi_offset w29, -16
 ; OUTLINE-ATOMICS-NEXT:    .cfi_offset w19, -24
diff --git a/llvm/test/CodeGen/AArch64/fast-isel-branch-cond-split.ll b/llvm/test/CodeGen/AArch64/fast-isel-branch-cond-split.ll
--- a/llvm/test/CodeGen/AArch64/fast-isel-branch-cond-split.ll
+++ b/llvm/test/CodeGen/AArch64/fast-isel-branch-cond-split.ll
@@ -153,9 +153,6 @@
 ; CHECK-NEXT:    bl _bar
 ; CHECK-NEXT:    ldp x29, x30, [sp], #16 ; 16-byte Folded Reload
 ; CHECK-NEXT:  LBB4_2: ; %common.ret
-; CHECK-NEXT:    .cfi_def_cfa wsp, 0
-; CHECK-NEXT:    .cfi_same_value w30
-; CHECK-NEXT:    .cfi_same_value w29
 ; CHECK-NEXT:    ret
 bb1:
   %0 = icmp eq i32 %a, 0
@@ -189,9 +186,6 @@
 ; CHECK-NEXT:    bl _bar
 ; CHECK-NEXT:    ldp x29, x30, [sp], #16 ; 16-byte Folded Reload
 ; CHECK-NEXT:  LBB5_2: ; %common.ret
-; CHECK-NEXT:    .cfi_def_cfa wsp, 0
-; CHECK-NEXT:    .cfi_same_value w30
-; CHECK-NEXT:    .cfi_same_value w29
 ; CHECK-NEXT:    ret
 bb1:
   %0 = icmp ne i32 %a, 0
@@ -212,4 +206,3 @@
 !0 = !{!"branch_weights", i32 5128, i32 32}
 !1 = !{!"branch_weights", i32 1024, i32 4136}
 !2 = !{}
-
diff --git a/llvm/test/CodeGen/AArch64/fpclamptosat_vec.ll b/llvm/test/CodeGen/AArch64/fpclamptosat_vec.ll
--- a/llvm/test/CodeGen/AArch64/fpclamptosat_vec.ll
+++ b/llvm/test/CodeGen/AArch64/fpclamptosat_vec.ll
@@ -353,9 +353,9 @@
 ; CHECK-LABEL: utest_f64i64:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
@@ -390,9 +390,9 @@
 ; CHECK-LABEL: ustest_f64i64:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
@@ -457,9 +457,9 @@
 ; CHECK-LABEL: utest_f32i64:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
@@ -495,9 +495,9 @@
 ; CHECK-LABEL: ustest_f32i64:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
@@ -575,9 +575,9 @@
 ; CHECK-LABEL: utesth_f16i64:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
@@ -613,9 +613,9 @@
 ; CHECK-LABEL: ustest_f16i64:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
@@ -978,9 +978,9 @@
 ; CHECK-LABEL: utest_f64i64_mm:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
@@ -1014,9 +1014,9 @@
 ; CHECK-LABEL: ustest_f64i64_mm:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
@@ -1075,9 +1075,9 @@
 ; CHECK-LABEL: utest_f32i64_mm:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
@@ -1112,9 +1112,9 @@
 ; CHECK-LABEL: ustest_f32i64_mm:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
@@ -1186,9 +1186,9 @@
 ; CHECK-LABEL: utesth_f16i64_mm:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
@@ -1223,9 +1223,9 @@
 ; CHECK-LABEL: ustest_f16i64_mm:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
diff --git a/llvm/test/CodeGen/AArch64/fptosi-sat-vector.ll b/llvm/test/CodeGen/AArch64/fptosi-sat-vector.ll
--- a/llvm/test/CodeGen/AArch64/fptosi-sat-vector.ll
+++ b/llvm/test/CodeGen/AArch64/fptosi-sat-vector.ll
@@ -248,8 +248,8 @@
 ; CHECK-LABEL: test_signed_v1f128_v1i32:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp x30, x19, [sp, #16] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    adrp x8, .LCPI14_0
@@ -286,10 +286,10 @@
 ; CHECK-LABEL: test_signed_v2f128_v2i32:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #112
-; CHECK-NEXT:    .cfi_def_cfa_offset 112
 ; CHECK-NEXT:    str x30, [sp, #64] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #96] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 112
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -355,10 +355,10 @@
 ; CHECK-LABEL: test_signed_v3f128_v3i32:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #128
-; CHECK-NEXT:    .cfi_def_cfa_offset 128
 ; CHECK-NEXT:    str x30, [sp, #80] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #96] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #112] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 128
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -445,10 +445,10 @@
 ; CHECK-LABEL: test_signed_v4f128_v4i32:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #144
-; CHECK-NEXT:    .cfi_def_cfa_offset 144
 ; CHECK-NEXT:    str x30, [sp, #96] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #112] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #128] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 144
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -808,12 +808,12 @@
 ; CHECK-LABEL: test_signed_v2f32_v2i100:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #80
-; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    str d10, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp d9, d8, [sp, #24] // 16-byte Folded Spill
 ; CHECK-NEXT:    str x30, [sp, #40] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #48] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #64] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -874,12 +874,12 @@
 ; CHECK-LABEL: test_signed_v2f32_v2i128:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #80
-; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    str d10, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp d9, d8, [sp, #24] // 16-byte Folded Spill
 ; CHECK-NEXT:    str x30, [sp, #40] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #48] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #64] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -1080,7 +1080,6 @@
 ; CHECK-LABEL: test_signed_v4f32_v4i100:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #128
-; CHECK-NEXT:    .cfi_def_cfa_offset 128
 ; CHECK-NEXT:    str d10, [sp, #32] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp d9, d8, [sp, #40] // 16-byte Folded Spill
 ; CHECK-NEXT:    str x30, [sp, #56] // 8-byte Folded Spill
@@ -1088,6 +1087,7 @@
 ; CHECK-NEXT:    stp x24, x23, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #96] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #112] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 128
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -1184,7 +1184,6 @@
 ; CHECK-LABEL: test_signed_v4f32_v4i128:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #128
-; CHECK-NEXT:    .cfi_def_cfa_offset 128
 ; CHECK-NEXT:    str d10, [sp, #32] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp d9, d8, [sp, #40] // 16-byte Folded Spill
 ; CHECK-NEXT:    str x30, [sp, #56] // 8-byte Folded Spill
@@ -1192,6 +1191,7 @@
 ; CHECK-NEXT:    stp x24, x23, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #96] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #112] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 128
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -1462,12 +1462,12 @@
 ; CHECK-LABEL: test_signed_v2f64_v2i100:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #80
-; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    str d10, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp d9, d8, [sp, #24] // 16-byte Folded Spill
 ; CHECK-NEXT:    str x30, [sp, #40] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #48] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #64] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -1528,12 +1528,12 @@
 ; CHECK-LABEL: test_signed_v2f64_v2i128:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #80
-; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    str d10, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp d9, d8, [sp, #24] // 16-byte Folded Spill
 ; CHECK-NEXT:    str x30, [sp, #40] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #48] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #64] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -1828,7 +1828,6 @@
 ; CHECK-LABEL: test_signed_v4f16_v4i100:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #112
-; CHECK-NEXT:    .cfi_def_cfa_offset 112
 ; CHECK-NEXT:    str d10, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp d9, d8, [sp, #24] // 16-byte Folded Spill
 ; CHECK-NEXT:    str x30, [sp, #40] // 8-byte Folded Spill
@@ -1836,6 +1835,7 @@
 ; CHECK-NEXT:    stp x24, x23, [sp, #64] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #96] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 112
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -1935,7 +1935,6 @@
 ; CHECK-LABEL: test_signed_v4f16_v4i128:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #112
-; CHECK-NEXT:    .cfi_def_cfa_offset 112
 ; CHECK-NEXT:    str d10, [sp, #16] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp d9, d8, [sp, #24] // 16-byte Folded Spill
 ; CHECK-NEXT:    str x30, [sp, #40] // 8-byte Folded Spill
@@ -1943,6 +1942,7 @@
 ; CHECK-NEXT:    stp x24, x23, [sp, #64] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #96] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 112
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -2560,7 +2560,6 @@
 ; CHECK-LABEL: test_signed_v8f16_v8i100:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #192
-; CHECK-NEXT:    .cfi_def_cfa_offset 192
 ; CHECK-NEXT:    str d10, [sp, #64] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp d9, d8, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x29, x30, [sp, #96] // 16-byte Folded Spill
@@ -2569,6 +2568,7 @@
 ; CHECK-NEXT:    stp x24, x23, [sp, #144] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #160] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #176] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 192
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -2757,7 +2757,6 @@
 ; CHECK-LABEL: test_signed_v8f16_v8i128:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #192
-; CHECK-NEXT:    .cfi_def_cfa_offset 192
 ; CHECK-NEXT:    str d10, [sp, #64] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp d9, d8, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x29, x30, [sp, #96] // 16-byte Folded Spill
@@ -2766,6 +2765,7 @@
 ; CHECK-NEXT:    stp x24, x23, [sp, #144] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #160] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #176] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 192
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
diff --git a/llvm/test/CodeGen/AArch64/fptoui-sat-vector.ll b/llvm/test/CodeGen/AArch64/fptoui-sat-vector.ll
--- a/llvm/test/CodeGen/AArch64/fptoui-sat-vector.ll
+++ b/llvm/test/CodeGen/AArch64/fptoui-sat-vector.ll
@@ -248,8 +248,8 @@
 ; CHECK-LABEL: test_unsigned_v1f128_v1i32:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp x30, x19, [sp, #16] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    adrp x8, .LCPI14_0
@@ -279,9 +279,9 @@
 ; CHECK-LABEL: test_unsigned_v2f128_v2i32:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #96
-; CHECK-NEXT:    .cfi_def_cfa_offset 96
 ; CHECK-NEXT:    str x30, [sp, #64] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #80] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 96
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
@@ -332,9 +332,9 @@
 ; CHECK-LABEL: test_unsigned_v3f128_v3i32:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #112
-; CHECK-NEXT:    .cfi_def_cfa_offset 112
 ; CHECK-NEXT:    str x30, [sp, #80] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #96] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 112
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
@@ -400,9 +400,9 @@
 ; CHECK-LABEL: test_unsigned_v4f128_v4i32:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #128
-; CHECK-NEXT:    .cfi_def_cfa_offset 128
 ; CHECK-NEXT:    str x30, [sp, #96] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #112] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 128
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
@@ -722,10 +722,10 @@
 ; CHECK-LABEL: test_unsigned_v2f32_v2i100:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #64
-; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    stp d9, d8, [sp, #16] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x30, x21, [sp, #32] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #48] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -774,10 +774,10 @@
 ; CHECK-LABEL: test_unsigned_v2f32_v2i128:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #64
-; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    stp d9, d8, [sp, #16] // 16-byte Folded Spill
 ; CHECK-NEXT:    str x30, [sp, #32] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #48] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
@@ -947,12 +947,12 @@
 ; CHECK-LABEL: test_unsigned_v4f32_v4i100:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #112
-; CHECK-NEXT:    .cfi_def_cfa_offset 112
 ; CHECK-NEXT:    stp d9, d8, [sp, #32] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x30, x25, [sp, #48] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x24, x23, [sp, #64] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #96] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 112
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -1031,12 +1031,12 @@
 ; CHECK-LABEL: test_unsigned_v4f32_v4i128:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #112
-; CHECK-NEXT:    .cfi_def_cfa_offset 112
 ; CHECK-NEXT:    stp d9, d8, [sp, #32] // 16-byte Folded Spill
 ; CHECK-NEXT:    str x30, [sp, #48] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x24, x23, [sp, #64] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #96] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 112
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -1262,10 +1262,10 @@
 ; CHECK-LABEL: test_unsigned_v2f64_v2i100:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #64
-; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    stp d9, d8, [sp, #16] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x30, x21, [sp, #32] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #48] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -1313,10 +1313,10 @@
 ; CHECK-LABEL: test_unsigned_v2f64_v2i128:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #64
-; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    stp d9, d8, [sp, #16] // 16-byte Folded Spill
 ; CHECK-NEXT:    str x30, [sp, #32] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #48] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
@@ -1564,12 +1564,12 @@
 ; CHECK-LABEL: test_unsigned_v4f16_v4i100:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #96
-; CHECK-NEXT:    .cfi_def_cfa_offset 96
 ; CHECK-NEXT:    stp d9, d8, [sp, #16] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x30, x25, [sp, #32] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x24, x23, [sp, #48] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #64] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #80] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 96
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -1651,12 +1651,12 @@
 ; CHECK-LABEL: test_unsigned_v4f16_v4i128:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #96
-; CHECK-NEXT:    .cfi_def_cfa_offset 96
 ; CHECK-NEXT:    stp d9, d8, [sp, #16] // 16-byte Folded Spill
 ; CHECK-NEXT:    str x30, [sp, #32] // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x24, x23, [sp, #48] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #64] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #80] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 96
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -2162,7 +2162,6 @@
 ; CHECK-LABEL: test_unsigned_v8f16_v8i100:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #176
-; CHECK-NEXT:    .cfi_def_cfa_offset 176
 ; CHECK-NEXT:    stp d9, d8, [sp, #64] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x29, x30, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x28, x27, [sp, #96] // 16-byte Folded Spill
@@ -2170,6 +2169,7 @@
 ; CHECK-NEXT:    stp x24, x23, [sp, #128] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #144] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #160] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 176
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -2327,7 +2327,6 @@
 ; CHECK-LABEL: test_unsigned_v8f16_v8i128:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #176
-; CHECK-NEXT:    .cfi_def_cfa_offset 176
 ; CHECK-NEXT:    stp d9, d8, [sp, #64] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x29, x30, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x28, x27, [sp, #96] // 16-byte Folded Spill
@@ -2335,6 +2334,7 @@
 ; CHECK-NEXT:    stp x24, x23, [sp, #128] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #144] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #160] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 176
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
diff --git a/llvm/test/CodeGen/AArch64/i128-math.ll b/llvm/test/CodeGen/AArch64/i128-math.ll
--- a/llvm/test/CodeGen/AArch64/i128-math.ll
+++ b/llvm/test/CodeGen/AArch64/i128-math.ll
@@ -401,8 +401,8 @@
 ; CHECK-LABEL: i128_saturating_mul:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x30, [sp, #-32]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp x20, x19, [sp, #16] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
diff --git a/llvm/test/CodeGen/AArch64/isinf.ll b/llvm/test/CodeGen/AArch64/isinf.ll
--- a/llvm/test/CodeGen/AArch64/isinf.ll
+++ b/llvm/test/CodeGen/AArch64/isinf.ll
@@ -59,8 +59,8 @@
 ; CHECK-LABEL: replace_isinf_call_f128:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    str q0, [sp]
 ; CHECK-NEXT:    ldrb w8, [sp, #15]
diff --git a/llvm/test/CodeGen/AArch64/large-stack-cmp.ll b/llvm/test/CodeGen/AArch64/large-stack-cmp.ll
--- a/llvm/test/CodeGen/AArch64/large-stack-cmp.ll
+++ b/llvm/test/CodeGen/AArch64/large-stack-cmp.ll
@@ -5,16 +5,14 @@
 ; CHECK-LABEL: foo:
 ; CHECK:       ; %bb.0:
 ; CHECK-NEXT:    stp x28, x27, [sp, #-32]! ; 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
+; CHECK-NEXT:    sub sp, sp, #1, lsl #12 ; =4096
+; CHECK-NEXT:    sub sp, sp, #80
+; CHECK-NEXT:    .cfi_def_cfa_offset 4208
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    .cfi_offset w27, -24
 ; CHECK-NEXT:    .cfi_offset w28, -32
-; CHECK-NEXT:    sub sp, sp, #1, lsl #12 ; =4096
-; CHECK-NEXT:    .cfi_def_cfa_offset 4128
-; CHECK-NEXT:    sub sp, sp, #80
-; CHECK-NEXT:    .cfi_def_cfa_offset 4208
 ; CHECK-NEXT:    adds x8, sp, #1, lsl #12 ; =4096
 ; CHECK-NEXT:    cmn x8, #32
 ; CHECK-NEXT:    b.eq LBB0_2
diff --git a/llvm/test/CodeGen/AArch64/ldst-paired-aliasing.ll b/llvm/test/CodeGen/AArch64/ldst-paired-aliasing.ll
--- a/llvm/test/CodeGen/AArch64/ldst-paired-aliasing.ll
+++ b/llvm/test/CodeGen/AArch64/ldst-paired-aliasing.ll
@@ -13,8 +13,8 @@
 ; CHECK-LABEL: main:
 ; CHECK:       // %bb.0: // %for.body.lr.ph.i.i.i.i.i.i63
 ; CHECK-NEXT:    sub sp, sp, #112
-; CHECK-NEXT:    .cfi_def_cfa_offset 112
 ; CHECK-NEXT:    str x30, [sp, #96] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 112
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    bl _Z5setupv
 ; CHECK-NEXT:    movi v0.4s, #1
diff --git a/llvm/test/CodeGen/AArch64/machine-combiner.ll b/llvm/test/CodeGen/AArch64/machine-combiner.ll
--- a/llvm/test/CodeGen/AArch64/machine-combiner.ll
+++ b/llvm/test/CodeGen/AArch64/machine-combiner.ll
@@ -754,9 +754,9 @@
 ; CHECK-STD-LABEL: reassociate_adds_from_calls:
 ; CHECK-STD:       // %bb.0:
 ; CHECK-STD-NEXT:    str d10, [sp, #-32]! // 8-byte Folded Spill
-; CHECK-STD-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-STD-NEXT:    stp d9, d8, [sp, #8] // 16-byte Folded Spill
 ; CHECK-STD-NEXT:    str x30, [sp, #24] // 8-byte Folded Spill
+; CHECK-STD-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-STD-NEXT:    .cfi_offset w30, -8
 ; CHECK-STD-NEXT:    .cfi_offset b8, -16
 ; CHECK-STD-NEXT:    .cfi_offset b9, -24
@@ -779,9 +779,9 @@
 ; CHECK-UNSAFE-LABEL: reassociate_adds_from_calls:
 ; CHECK-UNSAFE:       // %bb.0:
 ; CHECK-UNSAFE-NEXT:    str d10, [sp, #-32]! // 8-byte Folded Spill
-; CHECK-UNSAFE-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-UNSAFE-NEXT:    stp d9, d8, [sp, #8] // 16-byte Folded Spill
 ; CHECK-UNSAFE-NEXT:    str x30, [sp, #24] // 8-byte Folded Spill
+; CHECK-UNSAFE-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-UNSAFE-NEXT:    .cfi_offset w30, -8
 ; CHECK-UNSAFE-NEXT:    .cfi_offset b8, -16
 ; CHECK-UNSAFE-NEXT:    .cfi_offset b9, -24
@@ -814,9 +814,9 @@
 ; CHECK-LABEL: already_reassociated:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str d10, [sp, #-32]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp d9, d8, [sp, #8] // 16-byte Folded Spill
 ; CHECK-NEXT:    str x30, [sp, #24] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset b8, -16
 ; CHECK-NEXT:    .cfi_offset b9, -24
@@ -844,4 +844,3 @@
   %t2 = fadd double %t0, %t1
   ret double %t2
 }
-
diff --git a/llvm/test/CodeGen/AArch64/machine-licm-sink-instr.ll b/llvm/test/CodeGen/AArch64/machine-licm-sink-instr.ll
--- a/llvm/test/CodeGen/AArch64/machine-licm-sink-instr.ll
+++ b/llvm/test/CodeGen/AArch64/machine-licm-sink-instr.ll
@@ -9,8 +9,8 @@
 ; CHECK-LABEL: sink_load_and_copy:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    stp x30, x21, [sp, #-32]! // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp x20, x19, [sp, #16] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -63,8 +63,8 @@
 ; CHECK-LABEL: cant_sink_successive_call:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    stp x30, x21, [sp, #-32]! // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp x20, x19, [sp, #16] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
@@ -120,8 +120,8 @@
 ; CHECK-LABEL: cant_sink_successive_store:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    stp x30, x21, [sp, #-32]! // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp x20, x19, [sp, #16] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
diff --git a/llvm/test/CodeGen/AArch64/machine-outliner-throw2.ll b/llvm/test/CodeGen/AArch64/machine-outliner-throw2.ll
--- a/llvm/test/CodeGen/AArch64/machine-outliner-throw2.ll
+++ b/llvm/test/CodeGen/AArch64/machine-outliner-throw2.ll
@@ -20,7 +20,6 @@
 ; NOOMIT-LABEL: _Z2f1v:
 ; NOOMIT:       // %bb.0: // %entry
 ; NOOMIT-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
-; NOOMIT-NEXT:    .cfi_def_cfa_offset 16
 ; NOOMIT-NEXT:    mov x29, sp
 ; NOOMIT-NEXT:    .cfi_def_cfa w29, 16
 ; NOOMIT-NEXT:    .cfi_offset w30, -8
@@ -47,7 +46,6 @@
 ; NOOMIT-LABEL: _Z2f2v:
 ; NOOMIT:       // %bb.0: // %entry
 ; NOOMIT-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
-; NOOMIT-NEXT:   .cfi_def_cfa_offset 16
 ; NOOMIT-NEXT:    mov x29, sp
 ; NOOMIT-NEXT:    .cfi_def_cfa w29, 16
 ; NOOMIT-NEXT:    .cfi_offset w30, -8
diff --git a/llvm/test/CodeGen/AArch64/neg-imm.ll b/llvm/test/CodeGen/AArch64/neg-imm.ll
--- a/llvm/test/CodeGen/AArch64/neg-imm.ll
+++ b/llvm/test/CodeGen/AArch64/neg-imm.ll
@@ -9,8 +9,8 @@
 ; CHECK-LABEL: test:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    str x30, [sp, #-32]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp x20, x19, [sp, #16] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
diff --git a/llvm/test/CodeGen/AArch64/peephole-and-tst.ll b/llvm/test/CodeGen/AArch64/peephole-and-tst.ll
--- a/llvm/test/CodeGen/AArch64/peephole-and-tst.ll
+++ b/llvm/test/CodeGen/AArch64/peephole-and-tst.ll
@@ -151,8 +151,8 @@
 ; CHECK-LABEL: test_and3:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x30, [sp, #-32]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp x20, x19, [sp, #16] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
diff --git a/llvm/test/CodeGen/AArch64/ragreedy-csr.ll b/llvm/test/CodeGen/AArch64/ragreedy-csr.ll
--- a/llvm/test/CodeGen/AArch64/ragreedy-csr.ll
+++ b/llvm/test/CodeGen/AArch64/ragreedy-csr.ll
@@ -27,8 +27,8 @@
 ; CHECK-NEXT:    b.ne LBB0_47
 ; CHECK-NEXT:  ; %bb.1: ; %if.end
 ; CHECK-NEXT:    sub sp, sp, #64
-; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    stp x29, x30, [sp, #48] ; 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:  Lloh0:
@@ -260,9 +260,6 @@
 ; CHECK-NEXT:    cbz w8, LBB0_43
 ; CHECK-NEXT:    b LBB0_12
 ; CHECK-NEXT:  LBB0_47:
-; CHECK-NEXT:    .cfi_def_cfa wsp, 0
-; CHECK-NEXT:    .cfi_same_value w30
-; CHECK-NEXT:    .cfi_same_value w29
 ; CHECK-NEXT:    mov w0, wzr
 ; CHECK-NEXT:    ret
 ; CHECK-NEXT:    .loh AdrpLdrGot Lloh0, Lloh1
diff --git a/llvm/test/CodeGen/AArch64/regress-tblgen-chains.ll b/llvm/test/CodeGen/AArch64/regress-tblgen-chains.ll
--- a/llvm/test/CodeGen/AArch64/regress-tblgen-chains.ll
+++ b/llvm/test/CodeGen/AArch64/regress-tblgen-chains.ll
@@ -16,7 +16,6 @@
 ; CHECK-LABEL: test_chains:
 ; CHECK:       ; %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; CHECK-NEXT:    add x29, sp, #16
 ; CHECK-NEXT:    .cfi_def_cfa w29, 16
diff --git a/llvm/test/CodeGen/AArch64/shrink-wrap-byval-inalloca-preallocated.ll b/llvm/test/CodeGen/AArch64/shrink-wrap-byval-inalloca-preallocated.ll
--- a/llvm/test/CodeGen/AArch64/shrink-wrap-byval-inalloca-preallocated.ll
+++ b/llvm/test/CodeGen/AArch64/shrink-wrap-byval-inalloca-preallocated.ll
@@ -24,8 +24,8 @@
 ; CHECK-NEXT:    b.gt LBB0_2
 ; CHECK-NEXT:  ; %bb.1: ; %then
 ; CHECK-NEXT:    stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    .cfi_offset w19, -24
@@ -36,11 +36,6 @@
 ; CHECK-NEXT:    str xzr, [x19]
 ; CHECK-NEXT:    ldp x20, x19, [sp], #32 ; 16-byte Folded Reload
 ; CHECK-NEXT:  LBB0_2: ; %exit
-; CHECK-NEXT:    .cfi_def_cfa wsp, 0
-; CHECK-NEXT:    .cfi_same_value w30
-; CHECK-NEXT:    .cfi_same_value w29
-; CHECK-NEXT:    .cfi_same_value w19
-; CHECK-NEXT:    .cfi_same_value w20
 ; CHECK-NEXT:    ret
 entry:
   %l.a = load double, ptr %a, align 8
@@ -65,8 +60,8 @@
 ; CHECK-LABEL: test_byval_pointers:
 ; CHECK:       ; %bb.0: ; %entry
 ; CHECK-NEXT:    stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    .cfi_offset w19, -24
@@ -113,8 +108,8 @@
 ; CHECK-LABEL: test_inalloca_pointers:
 ; CHECK:       ; %bb.0: ; %entry
 ; CHECK-NEXT:    stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    .cfi_offset w19, -24
@@ -161,8 +156,8 @@
 ; CHECK-LABEL: test_preallocated_pointers:
 ; CHECK:       ; %bb.0: ; %entry
 ; CHECK-NEXT:    stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    .cfi_offset w19, -24
@@ -203,4 +198,3 @@
 exit:
   ret void
 }
-
diff --git a/llvm/test/CodeGen/AArch64/sibling-call.ll b/llvm/test/CodeGen/AArch64/sibling-call.ll
--- a/llvm/test/CodeGen/AArch64/sibling-call.ll
+++ b/llvm/test/CodeGen/AArch64/sibling-call.ll
@@ -26,8 +26,8 @@
 ; CHECK-LABEL: caller_to8_from0:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    mov w8, #42
 ; CHECK-NEXT:    str x8, [sp]
@@ -58,8 +58,8 @@
 ; CHECK-LABEL: caller_to16_from8:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    bl callee_stack16
 ; CHECK-NEXT:    ldr x30, [sp, #16] // 8-byte Folded Reload
diff --git a/llvm/test/CodeGen/AArch64/stack-guard-remat-bitcast.ll b/llvm/test/CodeGen/AArch64/stack-guard-remat-bitcast.ll
--- a/llvm/test/CodeGen/AArch64/stack-guard-remat-bitcast.ll
+++ b/llvm/test/CodeGen/AArch64/stack-guard-remat-bitcast.ll
@@ -10,7 +10,6 @@
 ; CHECK-LABEL: test_stack_guard_remat2:
 ; CHECK:       ; %bb.0: ; %entry
 ; CHECK-NEXT:    sub sp, sp, #64
-; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    stp x29, x30, [sp, #48] ; 16-byte Folded Spill
 ; CHECK-NEXT:    add x29, sp, #48
 ; CHECK-NEXT:    .cfi_def_cfa w29, 16
diff --git a/llvm/test/CodeGen/AArch64/stack-protector-darwin-got.ll b/llvm/test/CodeGen/AArch64/stack-protector-darwin-got.ll
--- a/llvm/test/CodeGen/AArch64/stack-protector-darwin-got.ll
+++ b/llvm/test/CodeGen/AArch64/stack-protector-darwin-got.ll
@@ -9,9 +9,9 @@
 ; CHECK-LABEL: test:
 ; CHECK:       ; %bb.0: ; %entry
 ; CHECK-NEXT:    sub sp, sp, #80
-; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    stp x20, x19, [sp, #48] ; 16-byte Folded Spill
 ; CHECK-NEXT:    stp x29, x30, [sp, #64] ; 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    .cfi_offset w19, -24
diff --git a/llvm/test/CodeGen/AArch64/statepoint-call-lowering.ll b/llvm/test/CodeGen/AArch64/statepoint-call-lowering.ll
--- a/llvm/test/CodeGen/AArch64/statepoint-call-lowering.ll
+++ b/llvm/test/CodeGen/AArch64/statepoint-call-lowering.ll
@@ -161,8 +161,8 @@
 ; CHECK-LABEL: test_cross_bb:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    str x30, [sp, #-32]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp x20, x19, [sp, #16] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
@@ -205,8 +205,8 @@
 ; CHECK-LABEL: test_attributes:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    sub sp, sp, #48
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    str x30, [sp, #32] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    mov x18, xzr
 ; CHECK-NEXT:    ldr q0, [sp, #48]
diff --git a/llvm/test/CodeGen/AArch64/sve-alloca.ll b/llvm/test/CodeGen/AArch64/sve-alloca.ll
--- a/llvm/test/CodeGen/AArch64/sve-alloca.ll
+++ b/llvm/test/CodeGen/AArch64/sve-alloca.ll
@@ -9,14 +9,8 @@
 ; CHECK-NEXT:    tbz w0, #0, .LBB0_2
 ; CHECK-NEXT:  // %bb.1: // %if.then
 ; CHECK-NEXT:    stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    stp x28, x19, [sp, #16] // 16-byte Folded Spill
 ; CHECK-NEXT:    mov x29, sp
-; CHECK-NEXT:    .cfi_def_cfa w29, 32
-; CHECK-NEXT:    .cfi_offset w19, -8
-; CHECK-NEXT:    .cfi_offset w28, -16
-; CHECK-NEXT:    .cfi_offset w30, -24
-; CHECK-NEXT:    .cfi_offset w29, -32
 ; CHECK-NEXT:    addvl sp, sp, #-18
 ; CHECK-NEXT:    str p15, [sp, #4, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    str p14, [sp, #5, mul vl] // 2-byte Folded Spill
@@ -46,6 +40,12 @@
 ; CHECK-NEXT:    str z10, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CHECK-NEXT:    str z9, [sp, #16, mul vl] // 16-byte Folded Spill
 ; CHECK-NEXT:    str z8, [sp, #17, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    mov x19, sp
+; CHECK-NEXT:    .cfi_def_cfa w29, 32
+; CHECK-NEXT:    .cfi_offset w19, -8
+; CHECK-NEXT:    .cfi_offset w28, -16
+; CHECK-NEXT:    .cfi_offset w30, -24
+; CHECK-NEXT:    .cfi_offset w29, -32
 ; CHECK-NEXT:    .cfi_escape 0x10, 0x48, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 32 - 8 * VG
 ; CHECK-NEXT:    .cfi_escape 0x10, 0x49, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 32 - 16 * VG
 ; CHECK-NEXT:    .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 32 - 24 * VG
@@ -57,7 +57,6 @@
 ; CHECK-NEXT:    rdvl x9, #2
 ; CHECK-NEXT:    mov x8, sp
 ; CHECK-NEXT:    add x9, x9, #15
-; CHECK-NEXT:    mov x19, sp
 ; CHECK-NEXT:    and x9, x9, #0xfffffffffffffff0
 ; CHECK-NEXT:    sub x8, x8, x9
 ; CHECK-NEXT:    and x0, x8, #0xffffffffffffffe0
@@ -99,19 +98,6 @@
 ; CHECK-NEXT:    ldp x28, x19, [sp, #16] // 16-byte Folded Reload
 ; CHECK-NEXT:    ldp x29, x30, [sp], #32 // 16-byte Folded Reload
 ; CHECK-NEXT:  .LBB0_2: // %if.end
-; CHECK-NEXT:    .cfi_def_cfa wsp, 0
-; CHECK-NEXT:    .cfi_same_value b8
-; CHECK-NEXT:    .cfi_same_value b9
-; CHECK-NEXT:    .cfi_same_value b10
-; CHECK-NEXT:    .cfi_same_value b11
-; CHECK-NEXT:    .cfi_same_value b12
-; CHECK-NEXT:    .cfi_same_value b13
-; CHECK-NEXT:    .cfi_same_value b14
-; CHECK-NEXT:    .cfi_same_value b15
-; CHECK-NEXT:    .cfi_same_value w19
-; CHECK-NEXT:    .cfi_same_value w28
-; CHECK-NEXT:    .cfi_same_value w30
-; CHECK-NEXT:    .cfi_same_value w29
 ; CHECK-NEXT:    ret
 entry:
   br i1 %cond, label %if.then, label %if.end
diff --git a/llvm/test/CodeGen/AArch64/sve-calling-convention-mixed.ll b/llvm/test/CodeGen/AArch64/sve-calling-convention-mixed.ll
--- a/llvm/test/CodeGen/AArch64/sve-calling-convention-mixed.ll
+++ b/llvm/test/CodeGen/AArch64/sve-calling-convention-mixed.ll
@@ -450,11 +450,10 @@
 ; CHECK-LABEL: non_sve_caller_non_sve_callee_high_range:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w30, -8
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG
+; CHECK-NEXT:    .cfi_offset w30, -8
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    movi d0, #0000000000000000
 ; CHECK-NEXT:    fmov s1, #1.00000000
 ; CHECK-NEXT:    fmov s2, #2.00000000
@@ -477,11 +476,10 @@
 ; CHECK-LABEL: non_sve_caller_high_range_non_sve_callee_high_range:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w30, -8
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG
+; CHECK-NEXT:    .cfi_offset w30, -8
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    ptrue p0.s
 ; CHECK-NEXT:    movi d0, #0000000000000000
 ; CHECK-NEXT:    ld1w { z16.s }, p0/z, [x0]
@@ -509,11 +507,7 @@
 ; CHECK-LABEL: sve_caller_non_sve_callee_high_range:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w30, -8
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-18
-; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 144 * VG
 ; CHECK-NEXT:    str p15, [sp, #4, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    str p14, [sp, #5, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    str p13, [sp, #6, mul vl] // 2-byte Folded Spill
@@ -542,6 +536,10 @@
 ; CHECK-NEXT:    str z10, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CHECK-NEXT:    str z9, [sp, #16, mul vl] // 16-byte Folded Spill
 ; CHECK-NEXT:    str z8, [sp, #17, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    addvl sp, sp, #-3
+; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0xa8, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 168 * VG
+; CHECK-NEXT:    .cfi_offset w30, -8
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    .cfi_escape 0x10, 0x48, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 16 - 8 * VG
 ; CHECK-NEXT:    .cfi_escape 0x10, 0x49, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 16 - 16 * VG
 ; CHECK-NEXT:    .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 16 - 24 * VG
@@ -550,8 +548,6 @@
 ; CHECK-NEXT:    .cfi_escape 0x10, 0x4d, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x50, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d13 @ cfa - 16 - 48 * VG
 ; CHECK-NEXT:    .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 16 - 56 * VG
 ; CHECK-NEXT:    .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 16 - 64 * VG
-; CHECK-NEXT:    addvl sp, sp, #-3
-; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0xa8, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 168 * VG
 ; CHECK-NEXT:    mov z25.d, z0.d
 ; CHECK-NEXT:    str z0, [sp] // 16-byte Folded Spill
 ; CHECK-NEXT:    movi d0, #0000000000000000
@@ -610,11 +606,7 @@
 ; CHECK-LABEL: sve_ret_caller_non_sve_callee_high_range:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w30, -8
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-18
-; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x90, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 144 * VG
 ; CHECK-NEXT:    str p15, [sp, #4, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    str p14, [sp, #5, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    str p13, [sp, #6, mul vl] // 2-byte Folded Spill
@@ -643,6 +635,10 @@
 ; CHECK-NEXT:    str z10, [sp, #15, mul vl] // 16-byte Folded Spill
 ; CHECK-NEXT:    str z9, [sp, #16, mul vl] // 16-byte Folded Spill
 ; CHECK-NEXT:    str z8, [sp, #17, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    addvl sp, sp, #-2
+; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0xa0, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 160 * VG
+; CHECK-NEXT:    .cfi_offset w30, -8
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    .cfi_escape 0x10, 0x48, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 16 - 8 * VG
 ; CHECK-NEXT:    .cfi_escape 0x10, 0x49, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 16 - 16 * VG
 ; CHECK-NEXT:    .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 16 - 24 * VG
@@ -651,8 +647,6 @@
 ; CHECK-NEXT:    .cfi_escape 0x10, 0x4d, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x50, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d13 @ cfa - 16 - 48 * VG
 ; CHECK-NEXT:    .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 16 - 56 * VG
 ; CHECK-NEXT:    .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 16 - 64 * VG
-; CHECK-NEXT:    addvl sp, sp, #-2
-; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0xa0, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 160 * VG
 ; CHECK-NEXT:    movi d0, #0000000000000000
 ; CHECK-NEXT:    fmov s1, #1.00000000
 ; CHECK-NEXT:    fmov s2, #2.00000000
diff --git a/llvm/test/CodeGen/AArch64/sve-extract-fixed-from-scalable-vector.ll b/llvm/test/CodeGen/AArch64/sve-extract-fixed-from-scalable-vector.ll
--- a/llvm/test/CodeGen/AArch64/sve-extract-fixed-from-scalable-vector.ll
+++ b/llvm/test/CodeGen/AArch64/sve-extract-fixed-from-scalable-vector.ll
@@ -7,10 +7,9 @@
 ; CHECK-LABEL: extract_v4i32_nxv16i32_12:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-4
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 32 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    ptrue p0.s
 ; CHECK-NEXT:    st1w { z3.s }, p0, [sp, #3, mul vl]
 ; CHECK-NEXT:    st1w { z2.s }, p0, [sp, #2, mul vl]
@@ -28,10 +27,9 @@
 ; CHECK-LABEL: extract_v8i16_nxv32i16_8:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    ptrue p0.h
 ; CHECK-NEXT:    st1h { z1.h }, p0, [sp, #1, mul vl]
 ; CHECK-NEXT:    st1h { z0.h }, p0, [sp]
@@ -47,10 +45,9 @@
 ; CHECK-LABEL: extract_v4i16_nxv32i16_8:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-4
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 32 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    ptrue p0.h
 ; CHECK-NEXT:    st1h { z3.h }, p0, [sp, #3, mul vl]
 ; CHECK-NEXT:    st1h { z2.h }, p0, [sp, #2, mul vl]
@@ -70,10 +67,9 @@
 ; CHECK-LABEL: extract_v2i16_nxv32i16_8:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-8
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0xc0, 0x00, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 64 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov x8, sp
 ; CHECK-NEXT:    ptrue p0.h
 ; CHECK-NEXT:    add x8, x8, #32
@@ -101,10 +97,9 @@
 ; CHECK-LABEL: extract_v2i64_nxv8i64_8:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-4
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 32 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    cnth x8
 ; CHECK-NEXT:    mov w9, #8
 ; CHECK-NEXT:    sub x8, x8, #2
@@ -129,10 +124,9 @@
 ; CHECK-LABEL: extract_v4f32_nxv16f32_12:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-4
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 32 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    ptrue p0.s
 ; CHECK-NEXT:    st1w { z3.s }, p0, [sp, #3, mul vl]
 ; CHECK-NEXT:    st1w { z2.s }, p0, [sp, #2, mul vl]
@@ -150,10 +144,9 @@
 ; CHECK-LABEL: extract_v2f32_nxv16f32_2:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    ptrue p0.s
 ; CHECK-NEXT:    st1w { z0.s }, p0, [sp]
 ; CHECK-NEXT:    ldr d0, [sp, #8]
@@ -187,10 +180,9 @@
 ; CHECK-LABEL: extract_v4i1_nxv32i1_16:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-8
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0xc0, 0x00, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 64 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov x8, sp
 ; CHECK-NEXT:    ptrue p2.b
 ; CHECK-NEXT:    add x8, x8, #16
@@ -245,10 +237,9 @@
 ; CHECK-LABEL: extract_v4i3_nxv32i3_16:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-8
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0xc0, 0x00, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 64 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov x8, sp
 ; CHECK-NEXT:    ptrue p0.b
 ; CHECK-NEXT:    add x8, x8, #16
@@ -284,10 +275,9 @@
 ; CHECK-LABEL: extract_v2i32_nxv16i32_2:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    ptrue p0.s
 ; CHECK-NEXT:    st1w { z0.s }, p0, [sp]
 ; CHECK-NEXT:    ldr d0, [sp, #8]
@@ -302,10 +292,9 @@
 ; CHECK-LABEL: extract_v4i64_nxv8i64_0:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    st1d { z1.d }, p0, [sp, #1, mul vl]
 ; CHECK-NEXT:    st1d { z0.d }, p0, [sp]
diff --git a/llvm/test/CodeGen/AArch64/sve-fixed-length-frame-offests-crash.ll b/llvm/test/CodeGen/AArch64/sve-fixed-length-frame-offests-crash.ll
--- a/llvm/test/CodeGen/AArch64/sve-fixed-length-frame-offests-crash.ll
+++ b/llvm/test/CodeGen/AArch64/sve-fixed-length-frame-offests-crash.ll
@@ -12,10 +12,10 @@
 ; CHECK-LABEL: func1:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    stp x29, x25, [sp, #-64]! // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    stp x24, x23, [sp, #16] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x22, x21, [sp, #32] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #48] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w21, -24
diff --git a/llvm/test/CodeGen/AArch64/sve-fixed-length-permute-rev.ll b/llvm/test/CodeGen/AArch64/sve-fixed-length-permute-rev.ll
--- a/llvm/test/CodeGen/AArch64/sve-fixed-length-permute-rev.ll
+++ b/llvm/test/CodeGen/AArch64/sve-fixed-length-permute-rev.ll
@@ -195,13 +195,12 @@
 ; CHECK-LABEL: test_rev_elts_fail:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    sub x9, sp, #48
 ; CHECK-NEXT:    mov x29, sp
+; CHECK-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; CHECK-NEXT:    .cfi_def_cfa w29, 16
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
-; CHECK-NEXT:    sub x9, sp, #48
-; CHECK-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0]
 ; CHECK-NEXT:    mov z1.d, z0.d[2]
@@ -264,13 +263,12 @@
 ; CHECK-LABEL: test_revv8i32:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    sub x9, sp, #48
 ; CHECK-NEXT:    mov x29, sp
+; CHECK-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; CHECK-NEXT:    .cfi_def_cfa w29, 16
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
-; CHECK-NEXT:    sub x9, sp, #48
-; CHECK-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; CHECK-NEXT:    ptrue p0.s, vl8
 ; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x0]
 ; CHECK-NEXT:    mov w8, v0.s[1]
@@ -382,13 +380,12 @@
 ; CHECK-LABEL: test_rev_fail:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    sub x9, sp, #48
 ; CHECK-NEXT:    mov x29, sp
+; CHECK-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; CHECK-NEXT:    .cfi_def_cfa w29, 16
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
-; CHECK-NEXT:    sub x9, sp, #48
-; CHECK-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; CHECK-NEXT:    ptrue p0.h
 ; CHECK-NEXT:    ld1h { z0.h }, p0/z, [x0]
 ; CHECK-NEXT:    mov z1.h, z0.h[8]
@@ -448,13 +445,12 @@
 ; CHECK-LABEL: test_revv8i16v8i16:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    sub x9, sp, #48
 ; CHECK-NEXT:    mov x29, sp
+; CHECK-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; CHECK-NEXT:    .cfi_def_cfa w29, 16
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
-; CHECK-NEXT:    sub x9, sp, #48
-; CHECK-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; CHECK-NEXT:    mov x8, sp
 ; CHECK-NEXT:    ldr q0, [x1]
 ; CHECK-NEXT:    orr x9, x8, #0x1e
diff --git a/llvm/test/CodeGen/AArch64/sve-fixed-length-permute-zip-uzp-trn.ll b/llvm/test/CodeGen/AArch64/sve-fixed-length-permute-zip-uzp-trn.ll
--- a/llvm/test/CodeGen/AArch64/sve-fixed-length-permute-zip-uzp-trn.ll
+++ b/llvm/test/CodeGen/AArch64/sve-fixed-length-permute-zip-uzp-trn.ll
@@ -132,13 +132,12 @@
 ; VBITS_EQ_512-LABEL: zip_v4f64:
 ; VBITS_EQ_512:       // %bb.0:
 ; VBITS_EQ_512-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
-; VBITS_EQ_512-NEXT:    .cfi_def_cfa_offset 16
+; VBITS_EQ_512-NEXT:    sub x9, sp, #48
 ; VBITS_EQ_512-NEXT:    mov x29, sp
+; VBITS_EQ_512-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; VBITS_EQ_512-NEXT:    .cfi_def_cfa w29, 16
 ; VBITS_EQ_512-NEXT:    .cfi_offset w30, -8
 ; VBITS_EQ_512-NEXT:    .cfi_offset w29, -16
-; VBITS_EQ_512-NEXT:    sub x9, sp, #48
-; VBITS_EQ_512-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; VBITS_EQ_512-NEXT:    ptrue p0.d, vl4
 ; VBITS_EQ_512-NEXT:    mov x8, sp
 ; VBITS_EQ_512-NEXT:    ld1d { z0.d }, p0/z, [x0]
@@ -650,13 +649,12 @@
 ; CHECK-LABEL: zip_vscale2_4:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    sub x9, sp, #48
 ; CHECK-NEXT:    mov x29, sp
+; CHECK-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; CHECK-NEXT:    .cfi_def_cfa w29, 16
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
-; CHECK-NEXT:    sub x9, sp, #48
-; CHECK-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; CHECK-NEXT:    ptrue p0.d, vl4
 ; CHECK-NEXT:    mov x8, sp
 ; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0]
diff --git a/llvm/test/CodeGen/AArch64/sve-fixed-length-vector-shuffle.ll b/llvm/test/CodeGen/AArch64/sve-fixed-length-vector-shuffle.ll
--- a/llvm/test/CodeGen/AArch64/sve-fixed-length-vector-shuffle.ll
+++ b/llvm/test/CodeGen/AArch64/sve-fixed-length-vector-shuffle.ll
@@ -910,13 +910,12 @@
 ; CHECK-LABEL: shuffle_ext_invalid:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    sub x9, sp, #48
 ; CHECK-NEXT:    mov x29, sp
+; CHECK-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; CHECK-NEXT:    .cfi_def_cfa w29, 16
 ; CHECK-NEXT:    .cfi_offset w30, -8
 ; CHECK-NEXT:    .cfi_offset w29, -16
-; CHECK-NEXT:    sub x9, sp, #48
-; CHECK-NEXT:    and sp, x9, #0xffffffffffffffe0
 ; CHECK-NEXT:    ptrue p0.d, vl4
 ; CHECK-NEXT:    mov x8, sp
 ; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0]
diff --git a/llvm/test/CodeGen/AArch64/sve-fp-reduce.ll b/llvm/test/CodeGen/AArch64/sve-fp-reduce.ll
--- a/llvm/test/CodeGen/AArch64/sve-fp-reduce.ll
+++ b/llvm/test/CodeGen/AArch64/sve-fp-reduce.ll
@@ -43,10 +43,9 @@
 ; CHECK-LABEL: fadda_nxv6f16:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov w8, #32768 // =0x8000
 ; CHECK-NEXT:    ptrue p0.h
 ; CHECK-NEXT:    ptrue p1.d
@@ -68,10 +67,9 @@
 ; CHECK-LABEL: fadda_nxv10f16:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-3
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 24 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov w8, #32768 // =0x8000
 ; CHECK-NEXT:    ptrue p0.h
 ; CHECK-NEXT:    ptrue p1.d
diff --git a/llvm/test/CodeGen/AArch64/sve-insert-vector.ll b/llvm/test/CodeGen/AArch64/sve-insert-vector.ll
--- a/llvm/test/CodeGen/AArch64/sve-insert-vector.ll
+++ b/llvm/test/CodeGen/AArch64/sve-insert-vector.ll
@@ -914,18 +914,17 @@
 ; CHECK-LABEL: insert_nxv1i1_nxv16i1_0:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    punpklo p2.h, p0.b
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    punpkhi p0.h, p0.b
 ; CHECK-NEXT:    punpklo p3.h, p2.b
 ; CHECK-NEXT:    punpkhi p2.h, p2.b
 ; CHECK-NEXT:    punpklo p4.h, p3.b
 ; CHECK-NEXT:    punpkhi p3.h, p3.b
 ; CHECK-NEXT:    punpkhi p4.h, p4.b
-; CHECK-NEXT:    punpkhi p0.h, p0.b
 ; CHECK-NEXT:    uzp1 p1.d, p1.d, p4.d
 ; CHECK-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
 ; CHECK-NEXT:    uzp1 p1.s, p1.s, p3.s
@@ -942,18 +941,17 @@
 ; CHECK-LABEL: insert_nxv1i1_nxv16i1_1:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    punpklo p2.h, p0.b
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    punpkhi p0.h, p0.b
 ; CHECK-NEXT:    punpklo p3.h, p2.b
 ; CHECK-NEXT:    punpkhi p2.h, p2.b
 ; CHECK-NEXT:    punpklo p4.h, p3.b
 ; CHECK-NEXT:    punpkhi p3.h, p3.b
 ; CHECK-NEXT:    punpklo p4.h, p4.b
-; CHECK-NEXT:    punpkhi p0.h, p0.b
 ; CHECK-NEXT:    uzp1 p1.d, p4.d, p1.d
 ; CHECK-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
 ; CHECK-NEXT:    uzp1 p1.s, p1.s, p3.s
@@ -970,18 +968,17 @@
 ; CHECK-LABEL: insert_nxv1i1_nxv16i1_2:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    punpklo p2.h, p0.b
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    punpkhi p0.h, p0.b
 ; CHECK-NEXT:    punpklo p3.h, p2.b
 ; CHECK-NEXT:    punpkhi p2.h, p2.b
 ; CHECK-NEXT:    punpkhi p4.h, p3.b
 ; CHECK-NEXT:    punpklo p3.h, p3.b
 ; CHECK-NEXT:    punpkhi p4.h, p4.b
-; CHECK-NEXT:    punpkhi p0.h, p0.b
 ; CHECK-NEXT:    uzp1 p1.d, p1.d, p4.d
 ; CHECK-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
 ; CHECK-NEXT:    uzp1 p1.s, p3.s, p1.s
@@ -998,18 +995,17 @@
 ; CHECK-LABEL: insert_nxv1i1_nxv16i1_3:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    punpklo p2.h, p0.b
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    punpkhi p0.h, p0.b
 ; CHECK-NEXT:    punpklo p3.h, p2.b
 ; CHECK-NEXT:    punpkhi p2.h, p2.b
 ; CHECK-NEXT:    punpkhi p4.h, p3.b
 ; CHECK-NEXT:    punpklo p3.h, p3.b
 ; CHECK-NEXT:    punpklo p4.h, p4.b
-; CHECK-NEXT:    punpkhi p0.h, p0.b
 ; CHECK-NEXT:    uzp1 p1.d, p4.d, p1.d
 ; CHECK-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
 ; CHECK-NEXT:    uzp1 p1.s, p3.s, p1.s
@@ -1026,18 +1022,17 @@
 ; CHECK-LABEL: insert_nxv1i1_nxv16i1_4:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    punpklo p2.h, p0.b
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    punpkhi p0.h, p0.b
 ; CHECK-NEXT:    punpkhi p3.h, p2.b
 ; CHECK-NEXT:    punpklo p2.h, p2.b
 ; CHECK-NEXT:    punpklo p4.h, p3.b
 ; CHECK-NEXT:    punpkhi p3.h, p3.b
 ; CHECK-NEXT:    punpkhi p4.h, p4.b
-; CHECK-NEXT:    punpkhi p0.h, p0.b
 ; CHECK-NEXT:    uzp1 p1.d, p1.d, p4.d
 ; CHECK-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
 ; CHECK-NEXT:    uzp1 p1.s, p1.s, p3.s
@@ -1054,18 +1049,17 @@
 ; CHECK-LABEL: insert_nxv1i1_nxv16i1_5:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    punpklo p2.h, p0.b
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    punpkhi p0.h, p0.b
 ; CHECK-NEXT:    punpkhi p3.h, p2.b
 ; CHECK-NEXT:    punpklo p2.h, p2.b
 ; CHECK-NEXT:    punpklo p4.h, p3.b
 ; CHECK-NEXT:    punpkhi p3.h, p3.b
 ; CHECK-NEXT:    punpklo p4.h, p4.b
-; CHECK-NEXT:    punpkhi p0.h, p0.b
 ; CHECK-NEXT:    uzp1 p1.d, p4.d, p1.d
 ; CHECK-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
 ; CHECK-NEXT:    uzp1 p1.s, p1.s, p3.s
@@ -1082,18 +1076,17 @@
 ; CHECK-LABEL: insert_nxv1i1_nxv16i1_6:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    punpklo p2.h, p0.b
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    punpkhi p0.h, p0.b
 ; CHECK-NEXT:    punpkhi p3.h, p2.b
 ; CHECK-NEXT:    punpklo p2.h, p2.b
 ; CHECK-NEXT:    punpkhi p4.h, p3.b
 ; CHECK-NEXT:    punpklo p3.h, p3.b
 ; CHECK-NEXT:    punpkhi p4.h, p4.b
-; CHECK-NEXT:    punpkhi p0.h, p0.b
 ; CHECK-NEXT:    uzp1 p1.d, p1.d, p4.d
 ; CHECK-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
 ; CHECK-NEXT:    uzp1 p1.s, p3.s, p1.s
@@ -1110,18 +1103,17 @@
 ; CHECK-LABEL: insert_nxv1i1_nxv16i1_7:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    punpklo p2.h, p0.b
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    punpkhi p0.h, p0.b
 ; CHECK-NEXT:    punpkhi p3.h, p2.b
 ; CHECK-NEXT:    punpklo p2.h, p2.b
 ; CHECK-NEXT:    punpkhi p4.h, p3.b
 ; CHECK-NEXT:    punpklo p3.h, p3.b
 ; CHECK-NEXT:    punpklo p4.h, p4.b
-; CHECK-NEXT:    punpkhi p0.h, p0.b
 ; CHECK-NEXT:    uzp1 p1.d, p4.d, p1.d
 ; CHECK-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
 ; CHECK-NEXT:    uzp1 p1.s, p3.s, p1.s
@@ -1138,18 +1130,17 @@
 ; CHECK-LABEL: insert_nxv1i1_nxv16i1_8:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    punpkhi p2.h, p0.b
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    punpklo p0.h, p0.b
 ; CHECK-NEXT:    punpklo p3.h, p2.b
 ; CHECK-NEXT:    punpkhi p2.h, p2.b
 ; CHECK-NEXT:    punpklo p4.h, p3.b
 ; CHECK-NEXT:    punpkhi p3.h, p3.b
 ; CHECK-NEXT:    punpkhi p4.h, p4.b
-; CHECK-NEXT:    punpklo p0.h, p0.b
 ; CHECK-NEXT:    uzp1 p1.d, p1.d, p4.d
 ; CHECK-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
 ; CHECK-NEXT:    uzp1 p1.s, p1.s, p3.s
@@ -1166,18 +1157,17 @@
 ; CHECK-LABEL: insert_nxv1i1_nxv16i1_9:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    punpkhi p2.h, p0.b
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    punpklo p0.h, p0.b
 ; CHECK-NEXT:    punpklo p3.h, p2.b
 ; CHECK-NEXT:    punpkhi p2.h, p2.b
 ; CHECK-NEXT:    punpklo p4.h, p3.b
 ; CHECK-NEXT:    punpkhi p3.h, p3.b
 ; CHECK-NEXT:    punpklo p4.h, p4.b
-; CHECK-NEXT:    punpklo p0.h, p0.b
 ; CHECK-NEXT:    uzp1 p1.d, p4.d, p1.d
 ; CHECK-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
 ; CHECK-NEXT:    uzp1 p1.s, p1.s, p3.s
@@ -1194,18 +1184,17 @@
 ; CHECK-LABEL: insert_nxv1i1_nxv16i1_10:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    punpkhi p2.h, p0.b
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    punpklo p0.h, p0.b
 ; CHECK-NEXT:    punpklo p3.h, p2.b
 ; CHECK-NEXT:    punpkhi p2.h, p2.b
 ; CHECK-NEXT:    punpkhi p4.h, p3.b
 ; CHECK-NEXT:    punpklo p3.h, p3.b
 ; CHECK-NEXT:    punpkhi p4.h, p4.b
-; CHECK-NEXT:    punpklo p0.h, p0.b
 ; CHECK-NEXT:    uzp1 p1.d, p1.d, p4.d
 ; CHECK-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
 ; CHECK-NEXT:    uzp1 p1.s, p3.s, p1.s
@@ -1222,18 +1211,17 @@
 ; CHECK-LABEL: insert_nxv1i1_nxv16i1_11:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    punpkhi p2.h, p0.b
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    punpklo p0.h, p0.b
 ; CHECK-NEXT:    punpklo p3.h, p2.b
 ; CHECK-NEXT:    punpkhi p2.h, p2.b
 ; CHECK-NEXT:    punpkhi p4.h, p3.b
 ; CHECK-NEXT:    punpklo p3.h, p3.b
 ; CHECK-NEXT:    punpklo p4.h, p4.b
-; CHECK-NEXT:    punpklo p0.h, p0.b
 ; CHECK-NEXT:    uzp1 p1.d, p4.d, p1.d
 ; CHECK-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
 ; CHECK-NEXT:    uzp1 p1.s, p3.s, p1.s
@@ -1250,18 +1238,17 @@
 ; CHECK-LABEL: insert_nxv1i1_nxv16i1_12:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    punpkhi p2.h, p0.b
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    punpklo p0.h, p0.b
 ; CHECK-NEXT:    punpkhi p3.h, p2.b
 ; CHECK-NEXT:    punpklo p2.h, p2.b
 ; CHECK-NEXT:    punpklo p4.h, p3.b
 ; CHECK-NEXT:    punpkhi p3.h, p3.b
 ; CHECK-NEXT:    punpkhi p4.h, p4.b
-; CHECK-NEXT:    punpklo p0.h, p0.b
 ; CHECK-NEXT:    uzp1 p1.d, p1.d, p4.d
 ; CHECK-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
 ; CHECK-NEXT:    uzp1 p1.s, p1.s, p3.s
@@ -1278,18 +1265,17 @@
 ; CHECK-LABEL: insert_nxv1i1_nxv16i1_13:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    punpkhi p2.h, p0.b
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    punpklo p0.h, p0.b
 ; CHECK-NEXT:    punpkhi p3.h, p2.b
 ; CHECK-NEXT:    punpklo p2.h, p2.b
 ; CHECK-NEXT:    punpklo p4.h, p3.b
 ; CHECK-NEXT:    punpkhi p3.h, p3.b
 ; CHECK-NEXT:    punpklo p4.h, p4.b
-; CHECK-NEXT:    punpklo p0.h, p0.b
 ; CHECK-NEXT:    uzp1 p1.d, p4.d, p1.d
 ; CHECK-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
 ; CHECK-NEXT:    uzp1 p1.s, p1.s, p3.s
@@ -1306,18 +1292,17 @@
 ; CHECK-LABEL: insert_nxv1i1_nxv16i1_14:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    punpkhi p2.h, p0.b
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    punpklo p0.h, p0.b
 ; CHECK-NEXT:    punpkhi p3.h, p2.b
 ; CHECK-NEXT:    punpklo p2.h, p2.b
 ; CHECK-NEXT:    punpkhi p4.h, p3.b
 ; CHECK-NEXT:    punpklo p3.h, p3.b
 ; CHECK-NEXT:    punpkhi p4.h, p4.b
-; CHECK-NEXT:    punpklo p0.h, p0.b
 ; CHECK-NEXT:    uzp1 p1.d, p1.d, p4.d
 ; CHECK-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
 ; CHECK-NEXT:    uzp1 p1.s, p3.s, p1.s
@@ -1334,18 +1319,17 @@
 ; CHECK-LABEL: insert_nxv1i1_nxv16i1_15:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    punpkhi p2.h, p0.b
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    punpklo p0.h, p0.b
 ; CHECK-NEXT:    punpkhi p3.h, p2.b
 ; CHECK-NEXT:    punpklo p2.h, p2.b
 ; CHECK-NEXT:    punpkhi p4.h, p3.b
 ; CHECK-NEXT:    punpklo p3.h, p3.b
 ; CHECK-NEXT:    punpklo p4.h, p4.b
-; CHECK-NEXT:    punpklo p0.h, p0.b
 ; CHECK-NEXT:    uzp1 p1.d, p4.d, p1.d
 ; CHECK-NEXT:    ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
 ; CHECK-NEXT:    uzp1 p1.s, p3.s, p1.s
diff --git a/llvm/test/CodeGen/AArch64/sve-split-extract-elt.ll b/llvm/test/CodeGen/AArch64/sve-split-extract-elt.ll
--- a/llvm/test/CodeGen/AArch64/sve-split-extract-elt.ll
+++ b/llvm/test/CodeGen/AArch64/sve-split-extract-elt.ll
@@ -19,10 +19,9 @@
 ; CHECK-LABEL: split_extract_32i8_idx:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov x8, #-1
 ; CHECK-NEXT:    mov w9, w0
 ; CHECK-NEXT:    ptrue p0.b
@@ -44,10 +43,9 @@
 ; CHECK-LABEL: split_extract_16i16_idx:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov x8, #-1
 ; CHECK-NEXT:    mov w9, w0
 ; CHECK-NEXT:    ptrue p0.h
@@ -69,10 +67,9 @@
 ; CHECK-LABEL: split_extract_8i32_idx:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    cnth x8
 ; CHECK-NEXT:    mov w9, w0
 ; CHECK-NEXT:    sub x8, x8, #1
@@ -94,10 +91,9 @@
 ; CHECK-LABEL: split_extract_8i64_idx:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-4
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 32 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    cnth x8
 ; CHECK-NEXT:    mov w9, w0
 ; CHECK-NEXT:    sub x8, x8, #1
@@ -141,10 +137,9 @@
 ; CHECK-LABEL: split_extract_16i16:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov x8, #-1
 ; CHECK-NEXT:    mov w9, #128
 ; CHECK-NEXT:    ptrue p0.h
@@ -166,10 +161,9 @@
 ; CHECK-LABEL: split_extract_16i32:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-4
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 32 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov x8, #-1
 ; CHECK-NEXT:    mov w9, #34464
 ; CHECK-NEXT:    movk w9, #1, lsl #16
@@ -194,10 +188,9 @@
 ; CHECK-LABEL: split_extract_4i64:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    cntw x8
 ; CHECK-NEXT:    mov w9, #10
 ; CHECK-NEXT:    sub x8, x8, #1
diff --git a/llvm/test/CodeGen/AArch64/sve-split-insert-elt.ll b/llvm/test/CodeGen/AArch64/sve-split-insert-elt.ll
--- a/llvm/test/CodeGen/AArch64/sve-split-insert-elt.ll
+++ b/llvm/test/CodeGen/AArch64/sve-split-insert-elt.ll
@@ -20,10 +20,9 @@
 ; CHECK-LABEL: split_insert_32i8_idx:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov x8, #-1
 ; CHECK-NEXT:    mov x9, sp
 ; CHECK-NEXT:    ptrue p0.b
@@ -46,10 +45,9 @@
 ; CHECK-LABEL: split_insert_8f32_idx:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    cnth x8
 ; CHECK-NEXT:    mov x9, sp
 ; CHECK-NEXT:    sub x8, x8, #1
@@ -72,10 +70,9 @@
 ; CHECK-LABEL: split_insert_8i64_idx:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-4
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 32 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    cnth x8
 ; CHECK-NEXT:    mov x9, sp
 ; CHECK-NEXT:    sub x8, x8, #1
@@ -135,10 +132,9 @@
 ; CHECK-LABEL: split_insert_32i16:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-4
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 32 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov x8, #-1
 ; CHECK-NEXT:    mov w9, #128
 ; CHECK-NEXT:    ptrue p0.h
@@ -166,10 +162,9 @@
 ; CHECK-LABEL: split_insert_8i32:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-2
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    cnth x8
 ; CHECK-NEXT:    mov w9, #16960
 ; CHECK-NEXT:    movk w9, #15, lsl #16
diff --git a/llvm/test/CodeGen/AArch64/sve-split-int-pred-reduce.ll b/llvm/test/CodeGen/AArch64/sve-split-int-pred-reduce.ll
--- a/llvm/test/CodeGen/AArch64/sve-split-int-pred-reduce.ll
+++ b/llvm/test/CodeGen/AArch64/sve-split-int-pred-reduce.ll
@@ -19,13 +19,12 @@
 ; CHECK-LABEL: andv_nxv64i1:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    and p1.b, p1/z, p1.b, p3.b
 ; CHECK-NEXT:    and p0.b, p0/z, p0.b, p2.b
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    ptrue p4.b
 ; CHECK-NEXT:    and p0.b, p0/z, p0.b, p1.b
 ; CHECK-NEXT:    nots p0.b, p4/z, p0.b
diff --git a/llvm/test/CodeGen/AArch64/sve-streaming-mode-fixed-length-permute-zip-uzp-trn.ll b/llvm/test/CodeGen/AArch64/sve-streaming-mode-fixed-length-permute-zip-uzp-trn.ll
--- a/llvm/test/CodeGen/AArch64/sve-streaming-mode-fixed-length-permute-zip-uzp-trn.ll
+++ b/llvm/test/CodeGen/AArch64/sve-streaming-mode-fixed-length-permute-zip-uzp-trn.ll
@@ -715,11 +715,11 @@
 ; CHECK-LABEL: uzp_v32i8:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    sub sp, sp, #128
-; CHECK-NEXT:    .cfi_def_cfa_offset 128
 ; CHECK-NEXT:    stp d15, d14, [sp, #64] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp d13, d12, [sp, #80] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp d11, d10, [sp, #96] // 16-byte Folded Spill
 ; CHECK-NEXT:    stp d9, d8, [sp, #112] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 128
 ; CHECK-NEXT:    .cfi_offset b8, -8
 ; CHECK-NEXT:    .cfi_offset b9, -16
 ; CHECK-NEXT:    .cfi_offset b10, -24
diff --git a/llvm/test/CodeGen/AArch64/sve-trunc.ll b/llvm/test/CodeGen/AArch64/sve-trunc.ll
--- a/llvm/test/CodeGen/AArch64/sve-trunc.ll
+++ b/llvm/test/CodeGen/AArch64/sve-trunc.ll
@@ -110,16 +110,16 @@
 ; CHECK-LABEL: trunc_i64toi1_split3:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    str p5, [sp, #6, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    and z7.d, z7.d, #0x1
 ; CHECK-NEXT:    ptrue p0.d
 ; CHECK-NEXT:    and z6.d, z6.d, #0x1
 ; CHECK-NEXT:    and z5.d, z5.d, #0x1
 ; CHECK-NEXT:    and z4.d, z4.d, #0x1
-; CHECK-NEXT:    str p4, [sp, #7, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    cmpne p1.d, p0/z, z7.d, #0
 ; CHECK-NEXT:    cmpne p2.d, p0/z, z6.d, #0
 ; CHECK-NEXT:    cmpne p3.d, p0/z, z5.d, #0
@@ -128,7 +128,6 @@
 ; CHECK-NEXT:    and z2.d, z2.d, #0x1
 ; CHECK-NEXT:    and z1.d, z1.d, #0x1
 ; CHECK-NEXT:    and z0.d, z0.d, #0x1
-; CHECK-NEXT:    str p5, [sp, #6, mul vl] // 2-byte Folded Spill
 ; CHECK-NEXT:    uzp1 p1.s, p2.s, p1.s
 ; CHECK-NEXT:    uzp1 p2.s, p4.s, p3.s
 ; CHECK-NEXT:    cmpne p3.d, p0/z, z3.d, #0
@@ -212,4 +211,3 @@
   store <vscale x 4 x i16> %1, <vscale x 4 x i16>* %ptr, align 2
   ret void
 }
-
diff --git a/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-loads.ll b/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-loads.ll
--- a/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-loads.ll
+++ b/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-loads.ll
@@ -137,11 +137,10 @@
 ; CHECK-LABEL: ld1_x2_i8_z0_taken:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
 ; CHECK-NEXT:    str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov p8.b, p0.b
 ; CHECK-NEXT:    ld1b { z2.b, z3.b }, pn8/z, [x0]
 ; CHECK-NEXT:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
@@ -288,11 +287,10 @@
 ; CHECK-LABEL: ld1_x4_i16_z0_taken:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
 ; CHECK-NEXT:    str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov p8.b, p0.b
 ; CHECK-NEXT:    ld1h { z4.h - z7.h }, pn8/z, [x0]
 ; CHECK-NEXT:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
@@ -442,11 +440,10 @@
 ; CHECK-LABEL: ldnt1_x2_i32_z0_taken:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
 ; CHECK-NEXT:    str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov p8.b, p0.b
 ; CHECK-NEXT:    ldnt1w { z2.s, z3.s }, pn8/z, [x0]
 ; CHECK-NEXT:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
@@ -593,11 +590,10 @@
 ; CHECK-LABEL: ldnt1_x4_i64_z0_taken:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    addvl sp, sp, #-1
-; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
 ; CHECK-NEXT:    str p8, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
 ; CHECK-NEXT:    mov p8.b, p0.b
 ; CHECK-NEXT:    ldnt1d { z4.d - z7.d }, pn8/z, [x0]
 ; CHECK-NEXT:    ldr p8, [sp, #7, mul vl] // 2-byte Folded Reload
diff --git a/llvm/test/CodeGen/AArch64/swifterror.ll b/llvm/test/CodeGen/AArch64/swifterror.ll
--- a/llvm/test/CodeGen/AArch64/swifterror.ll
+++ b/llvm/test/CodeGen/AArch64/swifterror.ll
@@ -14,7 +14,6 @@
 ; CHECK-APPLE-LABEL: foo:
 ; CHECK-APPLE:       ; %bb.0: ; %entry
 ; CHECK-APPLE-NEXT:    stp x29, x30, [sp, #-16]! ; 16-byte Folded Spill
-; CHECK-APPLE-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-APPLE-NEXT:    mov x29, sp
 ; CHECK-APPLE-NEXT:    .cfi_def_cfa w29, 16
 ; CHECK-APPLE-NEXT:    .cfi_offset w30, -8
@@ -31,7 +30,6 @@
 ; CHECK-O0-AARCH64-LABEL: foo:
 ; CHECK-O0-AARCH64:       ; %bb.0: ; %entry
 ; CHECK-O0-AARCH64-NEXT:    stp x29, x30, [sp, #-16]! ; 16-byte Folded Spill
-; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-O0-AARCH64-NEXT:    mov x29, sp
 ; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa w29, 16
 ; CHECK-O0-AARCH64-NEXT:    .cfi_offset w30, -8
@@ -74,7 +72,6 @@
 ; CHECK-APPLE-AARCH64-LABEL: caller:
 ; CHECK-APPLE-AARCH64:       ; %bb.0: ; %entry
 ; CHECK-APPLE-AARCH64-NEXT:    sub sp, sp, #64
-; CHECK-APPLE-AARCH64-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-APPLE-AARCH64-NEXT:    stp x22, x21, [sp, #16] ; 16-byte Folded Spill
 ; CHECK-APPLE-AARCH64-NEXT:    stp x20, x19, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-APPLE-AARCH64-NEXT:    stp x29, x30, [sp, #48] ; 16-byte Folded Spill
@@ -106,7 +103,6 @@
 ; CHECK-O0-AARCH64-LABEL: caller:
 ; CHECK-O0-AARCH64:       ; %bb.0: ; %entry
 ; CHECK-O0-AARCH64-NEXT:    sub sp, sp, #64
-; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-O0-AARCH64-NEXT:    stp x22, x21, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    stp x29, x30, [sp, #48] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    add x29, sp, #48
@@ -138,7 +134,6 @@
 ; CHECK-APPLE-ARM64_32-LABEL: caller:
 ; CHECK-APPLE-ARM64_32:       ; %bb.0: ; %entry
 ; CHECK-APPLE-ARM64_32-NEXT:    sub sp, sp, #64
-; CHECK-APPLE-ARM64_32-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-APPLE-ARM64_32-NEXT:    stp x22, x21, [sp, #16] ; 16-byte Folded Spill
 ; CHECK-APPLE-ARM64_32-NEXT:    stp x20, x19, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-APPLE-ARM64_32-NEXT:    stp x29, x30, [sp, #48] ; 16-byte Folded Spill
@@ -170,9 +165,9 @@
 ; CHECK-O0-ARM64_32-LABEL: caller:
 ; CHECK-O0-ARM64_32:       ; %bb.0: ; %entry
 ; CHECK-O0-ARM64_32-NEXT:    sub sp, sp, #64
-; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-O0-ARM64_32-NEXT:    stp x22, x21, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-O0-ARM64_32-NEXT:    stp x29, x30, [sp, #48] ; 16-byte Folded Spill
+; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w30, -8
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w29, -16
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w21, -24
@@ -222,7 +217,6 @@
 ; CHECK-APPLE-AARCH64-LABEL: caller2:
 ; CHECK-APPLE-AARCH64:       ; %bb.0: ; %entry
 ; CHECK-APPLE-AARCH64-NEXT:    sub sp, sp, #80
-; CHECK-APPLE-AARCH64-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-APPLE-AARCH64-NEXT:    stp d9, d8, [sp, #16] ; 16-byte Folded Spill
 ; CHECK-APPLE-AARCH64-NEXT:    stp x22, x21, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-APPLE-AARCH64-NEXT:    stp x20, x19, [sp, #48] ; 16-byte Folded Spill
@@ -265,7 +259,6 @@
 ; CHECK-O0-AARCH64-LABEL: caller2:
 ; CHECK-O0-AARCH64:       ; %bb.0: ; %entry
 ; CHECK-O0-AARCH64-NEXT:    sub sp, sp, #64
-; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-O0-AARCH64-NEXT:    stp x22, x21, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    stp x29, x30, [sp, #48] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    add x29, sp, #48
@@ -306,7 +299,6 @@
 ; CHECK-APPLE-ARM64_32-LABEL: caller2:
 ; CHECK-APPLE-ARM64_32:       ; %bb.0: ; %entry
 ; CHECK-APPLE-ARM64_32-NEXT:    sub sp, sp, #80
-; CHECK-APPLE-ARM64_32-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-APPLE-ARM64_32-NEXT:    stp d9, d8, [sp, #16] ; 16-byte Folded Spill
 ; CHECK-APPLE-ARM64_32-NEXT:    stp x22, x21, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-APPLE-ARM64_32-NEXT:    stp x20, x19, [sp, #48] ; 16-byte Folded Spill
@@ -349,9 +341,9 @@
 ; CHECK-O0-ARM64_32-LABEL: caller2:
 ; CHECK-O0-ARM64_32:       ; %bb.0: ; %entry
 ; CHECK-O0-ARM64_32-NEXT:    sub sp, sp, #64
-; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-O0-ARM64_32-NEXT:    stp x22, x21, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-O0-ARM64_32-NEXT:    stp x29, x30, [sp, #48] ; 16-byte Folded Spill
+; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 64
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w30, -8
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w29, -16
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w21, -24
@@ -416,7 +408,6 @@
 ; CHECK-APPLE-LABEL: foo_if:
 ; CHECK-APPLE:       ; %bb.0: ; %entry
 ; CHECK-APPLE-NEXT:    stp x29, x30, [sp, #-16]! ; 16-byte Folded Spill
-; CHECK-APPLE-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-APPLE-NEXT:    mov x29, sp
 ; CHECK-APPLE-NEXT:    .cfi_def_cfa w29, 16
 ; CHECK-APPLE-NEXT:    .cfi_offset w30, -8
@@ -439,7 +430,6 @@
 ; CHECK-O0-AARCH64-LABEL: foo_if:
 ; CHECK-O0-AARCH64:       ; %bb.0: ; %entry
 ; CHECK-O0-AARCH64-NEXT:    sub sp, sp, #32
-; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-O0-AARCH64-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    add x29, sp, #16
 ; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa w29, 16
@@ -468,8 +458,8 @@
 ; CHECK-O0-ARM64_32-LABEL: foo_if:
 ; CHECK-O0-ARM64_32:       ; %bb.0: ; %entry
 ; CHECK-O0-ARM64_32-NEXT:    sub sp, sp, #32
-; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-O0-ARM64_32-NEXT:    str x30, [sp, #16] ; 8-byte Folded Spill
+; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w30, -16
 ; CHECK-O0-ARM64_32-NEXT:    str x21, [sp, #8] ; 8-byte Folded Spill
 ; CHECK-O0-ARM64_32-NEXT:    cbz w0, LBB3_2
@@ -514,7 +504,6 @@
 ; CHECK-APPLE-LABEL: foo_loop:
 ; CHECK-APPLE:       ; %bb.0: ; %entry
 ; CHECK-APPLE-NEXT:    stp d9, d8, [sp, #-48]! ; 16-byte Folded Spill
-; CHECK-APPLE-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-APPLE-NEXT:    stp x20, x19, [sp, #16] ; 16-byte Folded Spill
 ; CHECK-APPLE-NEXT:    stp x29, x30, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-APPLE-NEXT:    add x29, sp, #32
@@ -555,7 +544,6 @@
 ; CHECK-O0-AARCH64-LABEL: foo_loop:
 ; CHECK-O0-AARCH64:       ; %bb.0: ; %entry
 ; CHECK-O0-AARCH64-NEXT:    sub sp, sp, #48
-; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-O0-AARCH64-NEXT:    stp x29, x30, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    add x29, sp, #32
 ; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa w29, 16
@@ -599,8 +587,8 @@
 ; CHECK-O0-ARM64_32-LABEL: foo_loop:
 ; CHECK-O0-ARM64_32:       ; %bb.0: ; %entry
 ; CHECK-O0-ARM64_32-NEXT:    sub sp, sp, #48
-; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-O0-ARM64_32-NEXT:    str x30, [sp, #32] ; 8-byte Folded Spill
+; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w30, -16
 ; CHECK-O0-ARM64_32-NEXT:    str s0, [sp, #16] ; 4-byte Folded Spill
 ; CHECK-O0-ARM64_32-NEXT:    str w0, [sp, #20] ; 4-byte Folded Spill
@@ -674,7 +662,6 @@
 ; CHECK-APPLE-LABEL: foo_sret:
 ; CHECK-APPLE:       ; %bb.0: ; %entry
 ; CHECK-APPLE-NEXT:    stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
-; CHECK-APPLE-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-APPLE-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; CHECK-APPLE-NEXT:    add x29, sp, #16
 ; CHECK-APPLE-NEXT:    .cfi_def_cfa w29, 16
@@ -697,7 +684,6 @@
 ; CHECK-O0-AARCH64-LABEL: foo_sret:
 ; CHECK-O0-AARCH64:       ; %bb.0: ; %entry
 ; CHECK-O0-AARCH64-NEXT:    sub sp, sp, #32
-; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-O0-AARCH64-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    add x29, sp, #16
 ; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa w29, 16
@@ -722,8 +708,8 @@
 ; CHECK-O0-ARM64_32-LABEL: foo_sret:
 ; CHECK-O0-ARM64_32:       ; %bb.0: ; %entry
 ; CHECK-O0-ARM64_32-NEXT:    sub sp, sp, #32
-; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-O0-ARM64_32-NEXT:    str x30, [sp, #16] ; 8-byte Folded Spill
+; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w30, -16
 ; CHECK-O0-ARM64_32-NEXT:    str w0, [sp, #12] ; 4-byte Folded Spill
 ; CHECK-O0-ARM64_32-NEXT:    str x8, [sp] ; 8-byte Folded Spill
@@ -758,7 +744,6 @@
 ; CHECK-APPLE-AARCH64-LABEL: caller3:
 ; CHECK-APPLE-AARCH64:       ; %bb.0: ; %entry
 ; CHECK-APPLE-AARCH64-NEXT:    sub sp, sp, #80
-; CHECK-APPLE-AARCH64-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-APPLE-AARCH64-NEXT:    stp x22, x21, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-APPLE-AARCH64-NEXT:    stp x20, x19, [sp, #48] ; 16-byte Folded Spill
 ; CHECK-APPLE-AARCH64-NEXT:    stp x29, x30, [sp, #64] ; 16-byte Folded Spill
@@ -792,7 +777,6 @@
 ; CHECK-O0-AARCH64-LABEL: caller3:
 ; CHECK-O0-AARCH64:       ; %bb.0: ; %entry
 ; CHECK-O0-AARCH64-NEXT:    sub sp, sp, #80
-; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-O0-AARCH64-NEXT:    stp x22, x21, [sp, #48] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    stp x29, x30, [sp, #64] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    add x29, sp, #64
@@ -826,7 +810,6 @@
 ; CHECK-APPLE-ARM64_32-LABEL: caller3:
 ; CHECK-APPLE-ARM64_32:       ; %bb.0: ; %entry
 ; CHECK-APPLE-ARM64_32-NEXT:    sub sp, sp, #80
-; CHECK-APPLE-ARM64_32-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-APPLE-ARM64_32-NEXT:    stp x22, x21, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-APPLE-ARM64_32-NEXT:    stp x20, x19, [sp, #48] ; 16-byte Folded Spill
 ; CHECK-APPLE-ARM64_32-NEXT:    stp x29, x30, [sp, #64] ; 16-byte Folded Spill
@@ -860,9 +843,9 @@
 ; CHECK-O0-ARM64_32-LABEL: caller3:
 ; CHECK-O0-ARM64_32:       ; %bb.0: ; %entry
 ; CHECK-O0-ARM64_32-NEXT:    sub sp, sp, #80
-; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-O0-ARM64_32-NEXT:    stp x22, x21, [sp, #48] ; 16-byte Folded Spill
 ; CHECK-O0-ARM64_32-NEXT:    stp x29, x30, [sp, #64] ; 16-byte Folded Spill
+; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w30, -8
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w29, -16
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w21, -24
@@ -920,7 +903,6 @@
 ; CHECK-APPLE-AARCH64-LABEL: foo_vararg:
 ; CHECK-APPLE-AARCH64:       ; %bb.0: ; %entry
 ; CHECK-APPLE-AARCH64-NEXT:    sub sp, sp, #48
-; CHECK-APPLE-AARCH64-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-APPLE-AARCH64-NEXT:    stp x29, x30, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-APPLE-AARCH64-NEXT:    add x29, sp, #32
 ; CHECK-APPLE-AARCH64-NEXT:    .cfi_def_cfa w29, 16
@@ -948,7 +930,6 @@
 ; CHECK-O0-AARCH64-LABEL: foo_vararg:
 ; CHECK-O0-AARCH64:       ; %bb.0: ; %entry
 ; CHECK-O0-AARCH64-NEXT:    sub sp, sp, #48
-; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-O0-AARCH64-NEXT:    stp x29, x30, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    add x29, sp, #32
 ; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa w29, 16
@@ -985,7 +966,6 @@
 ; CHECK-APPLE-ARM64_32-LABEL: foo_vararg:
 ; CHECK-APPLE-ARM64_32:       ; %bb.0: ; %entry
 ; CHECK-APPLE-ARM64_32-NEXT:    sub sp, sp, #48
-; CHECK-APPLE-ARM64_32-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-APPLE-ARM64_32-NEXT:    stp x29, x30, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-APPLE-ARM64_32-NEXT:    add x29, sp, #32
 ; CHECK-APPLE-ARM64_32-NEXT:    .cfi_def_cfa w29, 16
@@ -1017,8 +997,8 @@
 ; CHECK-O0-ARM64_32-LABEL: foo_vararg:
 ; CHECK-O0-ARM64_32:       ; %bb.0: ; %entry
 ; CHECK-O0-ARM64_32-NEXT:    sub sp, sp, #48
-; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-O0-ARM64_32-NEXT:    str x30, [sp, #32] ; 8-byte Folded Spill
+; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w30, -16
 ; CHECK-O0-ARM64_32-NEXT:    mov w8, #16
 ; CHECK-O0-ARM64_32-NEXT:    mov w0, w8
@@ -1087,7 +1067,6 @@
 ; CHECK-APPLE-AARCH64-LABEL: caller4:
 ; CHECK-APPLE-AARCH64:       ; %bb.0: ; %entry
 ; CHECK-APPLE-AARCH64-NEXT:    sub sp, sp, #96
-; CHECK-APPLE-AARCH64-NEXT:    .cfi_def_cfa_offset 96
 ; CHECK-APPLE-AARCH64-NEXT:    stp x22, x21, [sp, #48] ; 16-byte Folded Spill
 ; CHECK-APPLE-AARCH64-NEXT:    stp x20, x19, [sp, #64] ; 16-byte Folded Spill
 ; CHECK-APPLE-AARCH64-NEXT:    stp x29, x30, [sp, #80] ; 16-byte Folded Spill
@@ -1126,7 +1105,6 @@
 ; CHECK-O0-AARCH64-LABEL: caller4:
 ; CHECK-O0-AARCH64:       ; %bb.0: ; %entry
 ; CHECK-O0-AARCH64-NEXT:    sub sp, sp, #96
-; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa_offset 96
 ; CHECK-O0-AARCH64-NEXT:    stp x22, x21, [sp, #64] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    stp x29, x30, [sp, #80] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    add x29, sp, #80
@@ -1174,7 +1152,6 @@
 ; CHECK-APPLE-ARM64_32-LABEL: caller4:
 ; CHECK-APPLE-ARM64_32:       ; %bb.0: ; %entry
 ; CHECK-APPLE-ARM64_32-NEXT:    sub sp, sp, #80
-; CHECK-APPLE-ARM64_32-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-APPLE-ARM64_32-NEXT:    stp x22, x21, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-APPLE-ARM64_32-NEXT:    stp x20, x19, [sp, #48] ; 16-byte Folded Spill
 ; CHECK-APPLE-ARM64_32-NEXT:    stp x29, x30, [sp, #64] ; 16-byte Folded Spill
@@ -1215,9 +1192,9 @@
 ; CHECK-O0-ARM64_32-LABEL: caller4:
 ; CHECK-O0-ARM64_32:       ; %bb.0: ; %entry
 ; CHECK-O0-ARM64_32-NEXT:    sub sp, sp, #80
-; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-O0-ARM64_32-NEXT:    stp x22, x21, [sp, #48] ; 16-byte Folded Spill
 ; CHECK-O0-ARM64_32-NEXT:    stp x29, x30, [sp, #64] ; 16-byte Folded Spill
+; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w30, -8
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w29, -16
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w21, -24
@@ -1293,7 +1270,6 @@
 ; CHECK-APPLE-LABEL: tailcallswifterror:
 ; CHECK-APPLE:       ; %bb.0: ; %entry
 ; CHECK-APPLE-NEXT:    stp x29, x30, [sp, #-16]! ; 16-byte Folded Spill
-; CHECK-APPLE-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-APPLE-NEXT:    mov x29, sp
 ; CHECK-APPLE-NEXT:    .cfi_def_cfa w29, 16
 ; CHECK-APPLE-NEXT:    .cfi_offset w30, -8
@@ -1305,7 +1281,6 @@
 ; CHECK-O0-AARCH64-LABEL: tailcallswifterror:
 ; CHECK-O0-AARCH64:       ; %bb.0: ; %entry
 ; CHECK-O0-AARCH64-NEXT:    stp x29, x30, [sp, #-16]! ; 16-byte Folded Spill
-; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-O0-AARCH64-NEXT:    mov x29, sp
 ; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa w29, 16
 ; CHECK-O0-AARCH64-NEXT:    .cfi_offset w30, -8
@@ -1330,7 +1305,6 @@
 ; CHECK-APPLE-LABEL: tailcallswifterror_swiftcc:
 ; CHECK-APPLE:       ; %bb.0: ; %entry
 ; CHECK-APPLE-NEXT:    stp x29, x30, [sp, #-16]! ; 16-byte Folded Spill
-; CHECK-APPLE-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-APPLE-NEXT:    mov x29, sp
 ; CHECK-APPLE-NEXT:    .cfi_def_cfa w29, 16
 ; CHECK-APPLE-NEXT:    .cfi_offset w30, -8
@@ -1342,7 +1316,6 @@
 ; CHECK-O0-AARCH64-LABEL: tailcallswifterror_swiftcc:
 ; CHECK-O0-AARCH64:       ; %bb.0: ; %entry
 ; CHECK-O0-AARCH64-NEXT:    stp x29, x30, [sp, #-16]! ; 16-byte Folded Spill
-; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-O0-AARCH64-NEXT:    mov x29, sp
 ; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa w29, 16
 ; CHECK-O0-AARCH64-NEXT:    .cfi_offset w30, -8
@@ -1368,7 +1341,6 @@
 ; CHECK-APPLE-LABEL: swifterror_clobber:
 ; CHECK-APPLE:       ; %bb.0:
 ; CHECK-APPLE-NEXT:    stp x29, x30, [sp, #-16]! ; 16-byte Folded Spill
-; CHECK-APPLE-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-APPLE-NEXT:    mov x29, sp
 ; CHECK-APPLE-NEXT:    .cfi_def_cfa w29, 16
 ; CHECK-APPLE-NEXT:    .cfi_offset w30, -8
@@ -1384,7 +1356,6 @@
 ; CHECK-O0-AARCH64-LABEL: swifterror_clobber:
 ; CHECK-O0-AARCH64:       ; %bb.0:
 ; CHECK-O0-AARCH64-NEXT:    sub sp, sp, #32
-; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-O0-AARCH64-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    add x29, sp, #16
 ; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa w29, 16
@@ -1418,7 +1389,6 @@
 ; CHECK-APPLE-LABEL: swifterror_reg_clobber:
 ; CHECK-APPLE:       ; %bb.0:
 ; CHECK-APPLE-NEXT:    stp x22, x21, [sp, #-32]! ; 16-byte Folded Spill
-; CHECK-APPLE-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-APPLE-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; CHECK-APPLE-NEXT:    add x29, sp, #16
 ; CHECK-APPLE-NEXT:    .cfi_def_cfa w29, 16
@@ -1436,7 +1406,6 @@
 ; CHECK-O0-AARCH64-LABEL: swifterror_reg_clobber:
 ; CHECK-O0-AARCH64:       ; %bb.0:
 ; CHECK-O0-AARCH64-NEXT:    stp x22, x21, [sp, #-32]! ; 16-byte Folded Spill
-; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-O0-AARCH64-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    add x29, sp, #16
 ; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa w29, 16
@@ -1470,7 +1439,6 @@
 ; CHECK-APPLE-LABEL: params_in_reg:
 ; CHECK-APPLE:       ; %bb.0:
 ; CHECK-APPLE-NEXT:    sub sp, sp, #112
-; CHECK-APPLE-NEXT:    .cfi_def_cfa_offset 112
 ; CHECK-APPLE-NEXT:    stp x21, x28, [sp, #8] ; 16-byte Folded Spill
 ; CHECK-APPLE-NEXT:    stp x27, x26, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-APPLE-NEXT:    stp x25, x24, [sp, #48] ; 16-byte Folded Spill
@@ -1532,7 +1500,6 @@
 ; CHECK-O0-AARCH64-LABEL: params_in_reg:
 ; CHECK-O0-AARCH64:       ; %bb.0:
 ; CHECK-O0-AARCH64-NEXT:    sub sp, sp, #128
-; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa_offset 128
 ; CHECK-O0-AARCH64-NEXT:    str x20, [sp, #96] ; 8-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    stp x29, x30, [sp, #112] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    add x29, sp, #112
@@ -1590,8 +1557,8 @@
 ; CHECK-O0-ARM64_32-LABEL: params_in_reg:
 ; CHECK-O0-ARM64_32:       ; %bb.0:
 ; CHECK-O0-ARM64_32-NEXT:    sub sp, sp, #112
-; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 112
 ; CHECK-O0-ARM64_32-NEXT:    stp x20, x30, [sp, #96] ; 16-byte Folded Spill
+; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 112
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w30, -8
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w20, -16
 ; CHECK-O0-ARM64_32-NEXT:    str x21, [sp, #80] ; 8-byte Folded Spill
@@ -1651,7 +1618,6 @@
 ; CHECK-APPLE-LABEL: params_and_return_in_reg:
 ; CHECK-APPLE:       ; %bb.0:
 ; CHECK-APPLE-NEXT:    sub sp, sp, #128
-; CHECK-APPLE-NEXT:    .cfi_def_cfa_offset 128
 ; CHECK-APPLE-NEXT:    stp x20, x28, [sp, #24] ; 16-byte Folded Spill
 ; CHECK-APPLE-NEXT:    stp x27, x26, [sp, #48] ; 16-byte Folded Spill
 ; CHECK-APPLE-NEXT:    stp x25, x24, [sp, #64] ; 16-byte Folded Spill
@@ -1742,7 +1708,6 @@
 ; CHECK-O0-AARCH64-LABEL: params_and_return_in_reg:
 ; CHECK-O0-AARCH64:       ; %bb.0:
 ; CHECK-O0-AARCH64-NEXT:    sub sp, sp, #272
-; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa_offset 272
 ; CHECK-O0-AARCH64-NEXT:    stp x28, x20, [sp, #240] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    stp x29, x30, [sp, #256] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    add x29, sp, #256
@@ -1850,9 +1815,9 @@
 ; CHECK-O0-ARM64_32-LABEL: params_and_return_in_reg:
 ; CHECK-O0-ARM64_32:       ; %bb.0:
 ; CHECK-O0-ARM64_32-NEXT:    sub sp, sp, #272
-; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 272
 ; CHECK-O0-ARM64_32-NEXT:    str x28, [sp, #240] ; 8-byte Folded Spill
 ; CHECK-O0-ARM64_32-NEXT:    stp x20, x30, [sp, #256] ; 16-byte Folded Spill
+; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 272
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w30, -8
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w20, -16
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w28, -32
@@ -1969,7 +1934,6 @@
 ; CHECK-APPLE-LABEL: tailcall_from_swifterror:
 ; CHECK-APPLE:       ; %bb.0: ; %entry
 ; CHECK-APPLE-NEXT:    str x19, [sp, #-32]! ; 8-byte Folded Spill
-; CHECK-APPLE-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-APPLE-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; CHECK-APPLE-NEXT:    add x29, sp, #16
 ; CHECK-APPLE-NEXT:    .cfi_def_cfa w29, 16
@@ -1987,7 +1951,6 @@
 ; CHECK-O0-AARCH64-LABEL: tailcall_from_swifterror:
 ; CHECK-O0-AARCH64:       ; %bb.0: ; %entry
 ; CHECK-O0-AARCH64-NEXT:    sub sp, sp, #32
-; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-O0-AARCH64-NEXT:    stp x29, x30, [sp, #16] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    add x29, sp, #16
 ; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa w29, 16
@@ -2004,8 +1967,8 @@
 ; CHECK-O0-ARM64_32-LABEL: tailcall_from_swifterror:
 ; CHECK-O0-ARM64_32:       ; %bb.0: ; %entry
 ; CHECK-O0-ARM64_32-NEXT:    sub sp, sp, #32
-; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-O0-ARM64_32-NEXT:    str x30, [sp, #16] ; 8-byte Folded Spill
+; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w30, -16
 ; CHECK-O0-ARM64_32-NEXT:    str x21, [sp, #8] ; 8-byte Folded Spill
 ; CHECK-O0-ARM64_32-NEXT:    mov x0, xzr
@@ -2026,7 +1989,6 @@
 ; CHECK-APPLE-LABEL: testAssign:
 ; CHECK-APPLE:       ; %bb.0: ; %entry
 ; CHECK-APPLE-NEXT:    sub sp, sp, #48
-; CHECK-APPLE-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-APPLE-NEXT:    stp x22, x21, [sp, #16] ; 16-byte Folded Spill
 ; CHECK-APPLE-NEXT:    stp x29, x30, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-APPLE-NEXT:    add x29, sp, #32
@@ -2046,7 +2008,6 @@
 ; CHECK-O0-AARCH64-LABEL: testAssign:
 ; CHECK-O0-AARCH64:       ; %bb.0: ; %entry
 ; CHECK-O0-AARCH64-NEXT:    sub sp, sp, #48
-; CHECK-O0-AARCH64-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-O0-AARCH64-NEXT:    stp x22, x21, [sp, #16] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    stp x29, x30, [sp, #32] ; 16-byte Folded Spill
 ; CHECK-O0-AARCH64-NEXT:    add x29, sp, #32
@@ -2069,9 +2030,9 @@
 ; CHECK-O0-ARM64_32-LABEL: testAssign:
 ; CHECK-O0-ARM64_32:       ; %bb.0: ; %entry
 ; CHECK-O0-ARM64_32-NEXT:    sub sp, sp, #48
-; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-O0-ARM64_32-NEXT:    stp x22, x21, [sp, #16] ; 16-byte Folded Spill
 ; CHECK-O0-ARM64_32-NEXT:    stp x29, x30, [sp, #32] ; 16-byte Folded Spill
+; CHECK-O0-ARM64_32-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w30, -8
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w29, -16
 ; CHECK-O0-ARM64_32-NEXT:    .cfi_offset w21, -24
diff --git a/llvm/test/CodeGen/AArch64/unwind-preserved-from-mir.mir b/llvm/test/CodeGen/AArch64/unwind-preserved-from-mir.mir
--- a/llvm/test/CodeGen/AArch64/unwind-preserved-from-mir.mir
+++ b/llvm/test/CodeGen/AArch64/unwind-preserved-from-mir.mir
@@ -53,7 +53,6 @@
   ; CHECK:   successors: %bb.1, %bb.2
   ; CHECK:   liveins: $q0, $q22, $q23, $q20, $q21, $q18, $q19, $q16, $q17, $q14, $q15, $q12, $q13, $q10, $q11, $q8, $q9, $lr, $fp
   ; CHECK:   $sp = frame-setup SUBXri $sp, 304, 0
-  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 304
   ; CHECK:   frame-setup STPQi killed $q23, killed $q22, $sp, 2 :: (store (s128) into %stack.19), (store (s128) into %stack.18)
   ; CHECK:   frame-setup STPQi killed $q21, killed $q20, $sp, 4 :: (store (s128) into %stack.17), (store (s128) into %stack.16)
   ; CHECK:   frame-setup STPQi killed $q19, killed $q18, $sp, 6 :: (store (s128) into %stack.15), (store (s128) into %stack.14)
@@ -63,6 +62,7 @@
   ; CHECK:   frame-setup STPQi killed $q11, killed $q10, $sp, 14 :: (store (s128) into %stack.7), (store (s128) into %stack.6)
   ; CHECK:   frame-setup STPQi killed $q9, killed $q8, $sp, 16 :: (store (s128) into %stack.5), (store (s128) into %stack.4)
   ; CHECK:   frame-setup STPXi killed $fp, killed $lr, $sp, 36 :: (store (s64) into %stack.3), (store (s64) into %stack.2)
+  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 304
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $w30, -8
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $w29, -16
   ; CHECK:   frame-setup CFI_INSTRUCTION offset $b8, -32