diff --git a/llvm/lib/CodeGen/ShrinkWrap.cpp b/llvm/lib/CodeGen/ShrinkWrap.cpp
--- a/llvm/lib/CodeGen/ShrinkWrap.cpp
+++ b/llvm/lib/CodeGen/ShrinkWrap.cpp
@@ -53,6 +53,7 @@
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/Analysis/CFG.h"
+#include "llvm/Analysis/ValueTracking.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineDominators.h"
@@ -259,13 +260,30 @@
 
 bool ShrinkWrap::useOrDefCSROrFI(const MachineInstr &MI,
                                  RegScavenger *RS) const {
+  /// Check if \p Op is known to access an address not on the function's stack .
+  /// At the moment, accesses where the underlying object is a global or a
+  /// function argument are considered non-stack accesses. Note that the
+  /// caller's stack may get accessed when passing an argument via the stack,
+  /// but not the stack of the current function.
+  ///
+  auto IsKnownNonStackPtr = [](MachineMemOperand *Op) {
+    if (Op->getValue()) {
+      const Value *UO = getUnderlyingObject(Op->getValue());
+      if (!UO)
+        return false;
+      if (auto *Arg = dyn_cast<Argument>(UO))
+        return !Arg->hasPassPointeeByValueCopyAttr();
+      return isa<GlobalValue>(UO);
+    }
+    return false;
+  };
   // This prevents premature stack popping when occurs a indirect stack
-  // access. It is overly aggressive for the moment.
-  // TODO: - Obvious non-stack loads and store, such as global values,
-  //         are known to not access the stack.
+  // access.  It is overly aggressive for the moment.
+  // TODO:
   //       - Further, data dependency and alias analysis can validate
   //         that load and stores never derive from the stack pointer.
-  if (MI.mayLoadOrStore())
+  if (MI.mayLoadOrStore() && (MI.isCall() || MI.hasUnmodeledSideEffects() ||
+                              !all_of(MI.memoperands(), IsKnownNonStackPtr)))
     return true;
 
   if (MI.getOpcode() == FrameSetupOpcode ||
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
@@ -651,9 +651,6 @@
 define dso_local i32 @_extract_crng_crng() {
 ; CHECK-LABEL: _extract_crng_crng:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    adrp x8, _extract_crng_crng
 ; CHECK-NEXT:    add x8, x8, :lo12:_extract_crng_crng
 ; CHECK-NEXT:    tbnz x8, #63, .LBB36_2
@@ -665,6 +662,9 @@
 ; CHECK-NEXT:    cmn x8, #1272
 ; CHECK-NEXT:    b.pl .LBB36_3
 ; CHECK-NEXT:  .LBB36_2: // %if.then
+; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    adrp x8, primary_crng
 ; CHECK-NEXT:    adrp x9, input_pool
 ; CHECK-NEXT:    add x9, x9, :lo12:input_pool
@@ -672,8 +672,10 @@
 ; CHECK-NEXT:    cmp w8, #0
 ; CHECK-NEXT:    csel x0, xzr, x9, eq
 ; CHECK-NEXT:    bl crng_reseed
-; CHECK-NEXT:  .LBB36_3: // %if.end
 ; 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/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
@@ -1004,25 +1004,28 @@
 define i32 @stack_realign(i32 %a, i32 %b, ptr %ptr1, ptr %ptr2) {
 ; ENABLE-LABEL: stack_realign:
 ; ENABLE:       ; %bb.0:
+; ENABLE-NEXT:    lsl w8, w0, w1
+; ENABLE-NEXT:    lsl w9, w1, w0
+; ENABLE-NEXT:    cmp w0, w1
+; 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:    .cfi_def_cfa w29, 16
 ; ENABLE-NEXT:    .cfi_offset w30, -8
 ; ENABLE-NEXT:    .cfi_offset w29, -16
-; ENABLE-NEXT:    sub x9, sp, #16
-; ENABLE-NEXT:    and sp, x9, #0xffffffffffffffe0
-; ENABLE-NEXT:    lsl w8, w0, w1
-; ENABLE-NEXT:    lsl w9, w1, w0
-; ENABLE-NEXT:    cmp w0, w1
-; ENABLE-NEXT:    b.ge LBB13_2
-; ENABLE-NEXT:  ; %bb.1: ; %true
+; 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:    mov sp, x29
-; ENABLE-NEXT:    ldp x29, x30, [sp], #16 ; 16-byte Folded Reload
 ; ENABLE-NEXT:    ret
 ;
 ; DISABLE-LABEL: stack_realign:
diff --git a/llvm/test/CodeGen/AArch64/combine-comparisons-by-cse.ll b/llvm/test/CodeGen/AArch64/combine-comparisons-by-cse.ll
--- a/llvm/test/CodeGen/AArch64/combine-comparisons-by-cse.ll
+++ b/llvm/test/CodeGen/AArch64/combine-comparisons-by-cse.ll
@@ -658,28 +658,28 @@
 define i32 @fcmpri(i32 %argc, ptr nocapture readonly %argv) #0 {
 ; CHECK-LABEL: fcmpri:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    str d8, [sp, #-32]! // 8-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
-; CHECK-NEXT:    stp x30, x19, [sp, #16] // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_offset w19, -8
-; CHECK-NEXT:    .cfi_offset w30, -16
-; CHECK-NEXT:    .cfi_offset b8, -32
 ; CHECK-NEXT:    cmp w0, #2
 ; CHECK-NEXT:    b.lt .LBB9_3
 ; CHECK-NEXT:  // %bb.1: // %land.lhs.true
 ; CHECK-NEXT:    ldr x8, [x1, #8]
 ; CHECK-NEXT:    cbz x8, .LBB9_3
 ; CHECK-NEXT:  // %bb.2:
-; CHECK-NEXT:    mov w0, #3
-; CHECK-NEXT:    b .LBB9_4
+; CHECK-NEXT:    mov w0, #3 // =0x3
+; CHECK-NEXT:    ret
 ; CHECK-NEXT:  .LBB9_3: // %if.end
-; CHECK-NEXT:    mov w0, #1
+; CHECK-NEXT:    str d8, [sp, #-32]! // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
+; CHECK-NEXT:    stp x30, x19, [sp, #16] // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_offset w19, -8
+; CHECK-NEXT:    .cfi_offset w30, -16
+; CHECK-NEXT:    .cfi_offset b8, -32
+; CHECK-NEXT:    mov w0, #1 // =0x1
 ; CHECK-NEXT:    bl zoo
 ; CHECK-NEXT:    mov w19, w0
-; CHECK-NEXT:    mov w0, #-1
+; CHECK-NEXT:    mov w0, #-1 // =0xffffffff
 ; CHECK-NEXT:    bl yoo
 ; CHECK-NEXT:    cmp w19, #0
-; CHECK-NEXT:    mov w1, #2
+; CHECK-NEXT:    mov w1, #2 // =0x2
 ; CHECK-NEXT:    cinc w0, w19, gt
 ; CHECK-NEXT:    fmov d8, d0
 ; CHECK-NEXT:    bl xoo
@@ -689,9 +689,8 @@
 ; CHECK-NEXT:    fadd d0, d8, d0
 ; CHECK-NEXT:    fcsel d0, d8, d0, gt
 ; CHECK-NEXT:    bl woo
-; CHECK-NEXT:    mov w0, #4
-; CHECK-NEXT:  .LBB9_4: // %return
 ; CHECK-NEXT:    ldp x30, x19, [sp, #16] // 16-byte Folded Reload
+; CHECK-NEXT:    mov w0, #4 // =0x4
 ; CHECK-NEXT:    ldr d8, [sp], #32 // 8-byte Folded Reload
 ; CHECK-NEXT:    .cfi_def_cfa_offset 0
 ; CHECK-NEXT:    .cfi_restore w19
diff --git a/llvm/test/CodeGen/AArch64/csr-split.ll b/llvm/test/CodeGen/AArch64/csr-split.ll
--- a/llvm/test/CodeGen/AArch64/csr-split.ll
+++ b/llvm/test/CodeGen/AArch64/csr-split.ll
@@ -9,23 +9,17 @@
 define dso_local signext i32 @test1(ptr %b) local_unnamed_addr uwtable  {
 ; CHECK-LABEL: test1:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    stp x30, x19, [sp, #-16]! // 16-byte Folded Spill
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset w19, -8
-; CHECK-NEXT:    .cfi_offset w30, -16
-; CHECK-NEXT:    .cfi_remember_state
 ; CHECK-NEXT:    adrp x8, a
 ; CHECK-NEXT:    ldrsw x8, [x8, :lo12:a]
 ; CHECK-NEXT:    cmp x8, x0
 ; CHECK-NEXT:    b.eq .LBB0_2
 ; CHECK-NEXT:  // %bb.1: // %if.end
-; CHECK-NEXT:    ldp x30, x19, [sp], #16 // 16-byte Folded Reload
-; CHECK-NEXT:    .cfi_def_cfa_offset 0
-; CHECK-NEXT:    .cfi_restore w19
-; CHECK-NEXT:    .cfi_restore w30
 ; CHECK-NEXT:    ret
 ; CHECK-NEXT:  .LBB0_2: // %if.then
-; CHECK-NEXT:    .cfi_restore_state
+; CHECK-NEXT:    stp x30, x19, [sp, #-16]! // 16-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset w19, -8
+; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    mov x19, x0
 ; CHECK-NEXT:    bl callVoid
 ; CHECK-NEXT:    mov x0, x19
@@ -37,14 +31,6 @@
 ;
 ; CHECK-APPLE-LABEL: test1:
 ; 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:    .cfi_offset w30, -8
-; CHECK-APPLE-NEXT:    .cfi_offset w29, -16
-; CHECK-APPLE-NEXT:    .cfi_offset w19, -24
-; CHECK-APPLE-NEXT:    .cfi_offset w20, -32
-; CHECK-APPLE-NEXT:    .cfi_remember_state
 ; CHECK-APPLE-NEXT:  Lloh0:
 ; CHECK-APPLE-NEXT:    adrp x8, _a@PAGE
 ; CHECK-APPLE-NEXT:  Lloh1:
@@ -52,16 +38,15 @@
 ; CHECK-APPLE-NEXT:    cmp x8, x0
 ; CHECK-APPLE-NEXT:    b.eq LBB0_2
 ; CHECK-APPLE-NEXT:  ; %bb.1: ; %if.end
-; CHECK-APPLE-NEXT:    ldp x29, x30, [sp, #16] ; 16-byte Folded Reload
-; CHECK-APPLE-NEXT:    ldp x20, x19, [sp], #32 ; 16-byte Folded Reload
-; CHECK-APPLE-NEXT:    .cfi_def_cfa_offset 0
-; CHECK-APPLE-NEXT:    .cfi_restore w30
-; CHECK-APPLE-NEXT:    .cfi_restore w29
-; CHECK-APPLE-NEXT:    .cfi_restore w19
-; CHECK-APPLE-NEXT:    .cfi_restore w20
 ; CHECK-APPLE-NEXT:    ret
 ; CHECK-APPLE-NEXT:  LBB0_2: ; %if.then
-; CHECK-APPLE-NEXT:    .cfi_restore_state
+; 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:    .cfi_offset w30, -8
+; CHECK-APPLE-NEXT:    .cfi_offset w29, -16
+; CHECK-APPLE-NEXT:    .cfi_offset w19, -24
+; CHECK-APPLE-NEXT:    .cfi_offset w20, -32
 ; CHECK-APPLE-NEXT:    mov x19, x0
 ; CHECK-APPLE-NEXT:    bl _callVoid
 ; CHECK-APPLE-NEXT:    ldp x29, x30, [sp, #16] ; 16-byte Folded Reload
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
@@ -12,13 +12,6 @@
 define void @test_regular_pointers(ptr %a, ptr %b) {
 ; CHECK-LABEL: test_regular_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_offset w30, -8
-; CHECK-NEXT:    .cfi_offset w29, -16
-; CHECK-NEXT:    .cfi_offset w19, -24
-; CHECK-NEXT:    .cfi_offset w20, -32
 ; CHECK-NEXT:    ldr d0, [x0]
 ; CHECK-NEXT:    mov x8, #1 ; =0x1
 ; CHECK-NEXT:    ldr d1, [x1, #8]
@@ -30,12 +23,24 @@
 ; CHECK-NEXT:    b.mi LBB0_2
 ; 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_offset w30, -8
+; CHECK-NEXT:    .cfi_offset w29, -16
+; CHECK-NEXT:    .cfi_offset w19, -24
+; CHECK-NEXT:    .cfi_offset w20, -32
 ; CHECK-NEXT:    mov x19, x1
 ; CHECK-NEXT:    bl _fn
-; CHECK-NEXT:    str xzr, [x19]
-; CHECK-NEXT:  LBB0_2: ; %exit
 ; CHECK-NEXT:    ldp x29, x30, [sp, #16] ; 16-byte Folded Reload
+; 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
diff --git a/llvm/test/CodeGen/AArch64/taildup-cfi.ll b/llvm/test/CodeGen/AArch64/taildup-cfi.ll
--- a/llvm/test/CodeGen/AArch64/taildup-cfi.ll
+++ b/llvm/test/CodeGen/AArch64/taildup-cfi.ll
@@ -32,7 +32,7 @@
   store i32 0, ptr @f, align 4, !tbaa !2
   br label %if.end
 
-; DARWIN:           Merging into block
+; DARWIN-NOT:           Merging into block
 ; LINUX:    	      Merging into block
 
 if.end:                                           ; preds = %entry.if.end_crit_edge, %if.then
diff --git a/llvm/test/CodeGen/PowerPC/branch-on-store-cond.ll b/llvm/test/CodeGen/PowerPC/branch-on-store-cond.ll
--- a/llvm/test/CodeGen/PowerPC/branch-on-store-cond.ll
+++ b/llvm/test/CodeGen/PowerPC/branch-on-store-cond.ll
@@ -7,38 +7,38 @@
 define dso_local zeroext i8 @test1(ptr noundef %addr, i8 noundef zeroext %newval) local_unnamed_addr #0 {
 ; CHECK-LABEL: test1:
 ; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    stbcx. 4, 0, 3
+; CHECK-NEXT:    bne 0, .LBB0_2
+; CHECK-NEXT:  # %bb.1: # %if.then
 ; CHECK-NEXT:    mflr 0
 ; CHECK-NEXT:    stdu 1, -32(1)
 ; CHECK-NEXT:    std 0, 48(1)
 ; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset lr, 16
-; CHECK-NEXT:    stbcx. 4, 0, 3
-; CHECK-NEXT:    bne 0, .LBB0_2
-; CHECK-NEXT:  # %bb.1: # %if.then
 ; CHECK-NEXT:    bl dummy
 ; CHECK-NEXT:    nop
-; CHECK-NEXT:  .LBB0_2: # %if.end
-; CHECK-NEXT:    li 3, 55
 ; CHECK-NEXT:    addi 1, 1, 32
 ; CHECK-NEXT:    ld 0, 16(1)
 ; CHECK-NEXT:    mtlr 0
+; CHECK-NEXT:  .LBB0_2: # %if.end
+; CHECK-NEXT:    li 3, 55
 ; CHECK-NEXT:    blr
 ;
 ; CHECK-AIX-LABEL: test1:
 ; CHECK-AIX:       # %bb.0: # %entry
-; CHECK-AIX-NEXT:    mflr 0
-; CHECK-AIX-NEXT:    stdu 1, -112(1)
-; CHECK-AIX-NEXT:    std 0, 128(1)
 ; CHECK-AIX-NEXT:    stbcx. 4, 0, 3
 ; CHECK-AIX-NEXT:    bne 0, L..BB0_2
 ; CHECK-AIX-NEXT:  # %bb.1: # %if.then
+; CHECK-AIX-NEXT:    mflr 0
+; CHECK-AIX-NEXT:    stdu 1, -112(1)
+; CHECK-AIX-NEXT:    std 0, 128(1)
 ; CHECK-AIX-NEXT:    bl .dummy[PR]
 ; CHECK-AIX-NEXT:    nop
-; CHECK-AIX-NEXT:  L..BB0_2: # %if.end
-; CHECK-AIX-NEXT:    li 3, 55
 ; CHECK-AIX-NEXT:    addi 1, 1, 112
 ; CHECK-AIX-NEXT:    ld 0, 16(1)
 ; CHECK-AIX-NEXT:    mtlr 0
+; CHECK-AIX-NEXT:  L..BB0_2: # %if.end
+; CHECK-AIX-NEXT:    li 3, 55
 ; CHECK-AIX-NEXT:    blr
 entry:
   %conv = zext i8 %newval to i32
@@ -57,38 +57,38 @@
 define dso_local signext i16 @test2(ptr noundef %addr, i16 noundef signext %newval) local_unnamed_addr #0 {
 ; CHECK-LABEL: test2:
 ; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    sthcx. 4, 0, 3
+; CHECK-NEXT:    bne 0, .LBB1_2
+; CHECK-NEXT:  # %bb.1: # %if.then
 ; CHECK-NEXT:    mflr 0
 ; CHECK-NEXT:    stdu 1, -32(1)
 ; CHECK-NEXT:    std 0, 48(1)
 ; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset lr, 16
-; CHECK-NEXT:    sthcx. 4, 0, 3
-; CHECK-NEXT:    bne 0, .LBB1_2
-; CHECK-NEXT:  # %bb.1: # %if.then
 ; CHECK-NEXT:    bl dummy
 ; CHECK-NEXT:    nop
-; CHECK-NEXT:  .LBB1_2: # %if.end
-; CHECK-NEXT:    li 3, 55
 ; CHECK-NEXT:    addi 1, 1, 32
 ; CHECK-NEXT:    ld 0, 16(1)
 ; CHECK-NEXT:    mtlr 0
+; CHECK-NEXT:  .LBB1_2: # %if.end
+; CHECK-NEXT:    li 3, 55
 ; CHECK-NEXT:    blr
 ;
 ; CHECK-AIX-LABEL: test2:
 ; CHECK-AIX:       # %bb.0: # %entry
-; CHECK-AIX-NEXT:    mflr 0
-; CHECK-AIX-NEXT:    stdu 1, -112(1)
-; CHECK-AIX-NEXT:    std 0, 128(1)
 ; CHECK-AIX-NEXT:    sthcx. 4, 0, 3
 ; CHECK-AIX-NEXT:    bne 0, L..BB1_2
 ; CHECK-AIX-NEXT:  # %bb.1: # %if.then
+; CHECK-AIX-NEXT:    mflr 0
+; CHECK-AIX-NEXT:    stdu 1, -112(1)
+; CHECK-AIX-NEXT:    std 0, 128(1)
 ; CHECK-AIX-NEXT:    bl .dummy[PR]
 ; CHECK-AIX-NEXT:    nop
-; CHECK-AIX-NEXT:  L..BB1_2: # %if.end
-; CHECK-AIX-NEXT:    li 3, 55
 ; CHECK-AIX-NEXT:    addi 1, 1, 112
 ; CHECK-AIX-NEXT:    ld 0, 16(1)
 ; CHECK-AIX-NEXT:    mtlr 0
+; CHECK-AIX-NEXT:  L..BB1_2: # %if.end
+; CHECK-AIX-NEXT:    li 3, 55
 ; CHECK-AIX-NEXT:    blr
 entry:
   %0 = sext i16 %newval to i32
@@ -107,38 +107,38 @@
 define dso_local signext i32 @test3(ptr noundef %addr, i32 noundef signext %newval) local_unnamed_addr #0 {
 ; CHECK-LABEL: test3:
 ; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    stwcx. 4, 0, 3
+; CHECK-NEXT:    bne 0, .LBB2_2
+; CHECK-NEXT:  # %bb.1: # %if.then
 ; CHECK-NEXT:    mflr 0
 ; CHECK-NEXT:    stdu 1, -32(1)
 ; CHECK-NEXT:    std 0, 48(1)
 ; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset lr, 16
-; CHECK-NEXT:    stwcx. 4, 0, 3
-; CHECK-NEXT:    bne 0, .LBB2_2
-; CHECK-NEXT:  # %bb.1: # %if.then
 ; CHECK-NEXT:    bl dummy
 ; CHECK-NEXT:    nop
-; CHECK-NEXT:  .LBB2_2: # %if.end
-; CHECK-NEXT:    li 3, 55
 ; CHECK-NEXT:    addi 1, 1, 32
 ; CHECK-NEXT:    ld 0, 16(1)
 ; CHECK-NEXT:    mtlr 0
+; CHECK-NEXT:  .LBB2_2: # %if.end
+; CHECK-NEXT:    li 3, 55
 ; CHECK-NEXT:    blr
 ;
 ; CHECK-AIX-LABEL: test3:
 ; CHECK-AIX:       # %bb.0: # %entry
-; CHECK-AIX-NEXT:    mflr 0
-; CHECK-AIX-NEXT:    stdu 1, -112(1)
-; CHECK-AIX-NEXT:    std 0, 128(1)
 ; CHECK-AIX-NEXT:    stwcx. 4, 0, 3
 ; CHECK-AIX-NEXT:    bne 0, L..BB2_2
 ; CHECK-AIX-NEXT:  # %bb.1: # %if.then
+; CHECK-AIX-NEXT:    mflr 0
+; CHECK-AIX-NEXT:    stdu 1, -112(1)
+; CHECK-AIX-NEXT:    std 0, 128(1)
 ; CHECK-AIX-NEXT:    bl .dummy[PR]
 ; CHECK-AIX-NEXT:    nop
-; CHECK-AIX-NEXT:  L..BB2_2: # %if.end
-; CHECK-AIX-NEXT:    li 3, 55
 ; CHECK-AIX-NEXT:    addi 1, 1, 112
 ; CHECK-AIX-NEXT:    ld 0, 16(1)
 ; CHECK-AIX-NEXT:    mtlr 0
+; CHECK-AIX-NEXT:  L..BB2_2: # %if.end
+; CHECK-AIX-NEXT:    li 3, 55
 ; CHECK-AIX-NEXT:    blr
 entry:
   %0 = tail call i32 @llvm.ppc.stwcx(ptr %addr, i32 %newval)
@@ -156,38 +156,38 @@
 define dso_local i64 @test4(ptr noundef %addr, i64 noundef %newval) local_unnamed_addr #0 {
 ; CHECK-LABEL: test4:
 ; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    stdcx. 4, 0, 3
+; CHECK-NEXT:    bne 0, .LBB3_2
+; CHECK-NEXT:  # %bb.1: # %if.then
 ; CHECK-NEXT:    mflr 0
 ; CHECK-NEXT:    stdu 1, -32(1)
 ; CHECK-NEXT:    std 0, 48(1)
 ; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset lr, 16
-; CHECK-NEXT:    stdcx. 4, 0, 3
-; CHECK-NEXT:    bne 0, .LBB3_2
-; CHECK-NEXT:  # %bb.1: # %if.then
 ; CHECK-NEXT:    bl dummy
 ; CHECK-NEXT:    nop
-; CHECK-NEXT:  .LBB3_2: # %if.end
-; CHECK-NEXT:    li 3, 55
 ; CHECK-NEXT:    addi 1, 1, 32
 ; CHECK-NEXT:    ld 0, 16(1)
 ; CHECK-NEXT:    mtlr 0
+; CHECK-NEXT:  .LBB3_2: # %if.end
+; CHECK-NEXT:    li 3, 55
 ; CHECK-NEXT:    blr
 ;
 ; CHECK-AIX-LABEL: test4:
 ; CHECK-AIX:       # %bb.0: # %entry
-; CHECK-AIX-NEXT:    mflr 0
-; CHECK-AIX-NEXT:    stdu 1, -112(1)
-; CHECK-AIX-NEXT:    std 0, 128(1)
 ; CHECK-AIX-NEXT:    stdcx. 4, 0, 3
 ; CHECK-AIX-NEXT:    bne 0, L..BB3_2
 ; CHECK-AIX-NEXT:  # %bb.1: # %if.then
+; CHECK-AIX-NEXT:    mflr 0
+; CHECK-AIX-NEXT:    stdu 1, -112(1)
+; CHECK-AIX-NEXT:    std 0, 128(1)
 ; CHECK-AIX-NEXT:    bl .dummy[PR]
 ; CHECK-AIX-NEXT:    nop
-; CHECK-AIX-NEXT:  L..BB3_2: # %if.end
-; CHECK-AIX-NEXT:    li 3, 55
 ; CHECK-AIX-NEXT:    addi 1, 1, 112
 ; CHECK-AIX-NEXT:    ld 0, 16(1)
 ; CHECK-AIX-NEXT:    mtlr 0
+; CHECK-AIX-NEXT:  L..BB3_2: # %if.end
+; CHECK-AIX-NEXT:    li 3, 55
 ; CHECK-AIX-NEXT:    blr
 entry:
   %0 = tail call i32 @llvm.ppc.stdcx(ptr %addr, i64 %newval)
diff --git a/llvm/test/CodeGen/PowerPC/more-dq-form-prepare.ll b/llvm/test/CodeGen/PowerPC/more-dq-form-prepare.ll
--- a/llvm/test/CodeGen/PowerPC/more-dq-form-prepare.ll
+++ b/llvm/test/CodeGen/PowerPC/more-dq-form-prepare.ll
@@ -10,6 +10,14 @@
 define void @foo(ptr %.m, ptr %.n, ptr %.a, ptr %.x, ptr %.l, ptr %.vy01, ptr %.vy02, ptr %.vy03, ptr %.vy04, ptr %.vy05, ptr %.vy06, ptr %.vy07, ptr %.vy08, ptr %.vy09, ptr %.vy0a, ptr %.vy0b, ptr %.vy0c, ptr %.vy21, ptr %.vy22, ptr %.vy23, ptr %.vy24, ptr %.vy25, ptr %.vy26, ptr %.vy27, ptr %.vy28, ptr %.vy29, ptr %.vy2a, ptr %.vy2b, ptr %.vy2c) {
 ; CHECK-LABEL: foo:
 ; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    lwz 4, 0(4)
+; CHECK-NEXT:    cmpwi 4, 1
+; CHECK-NEXT:    bltlr 0
+; CHECK-NEXT:  # %bb.1: # %_loop_1_do_.lr.ph
+; CHECK-NEXT:    lwz 3, 0(3)
+; CHECK-NEXT:    cmpwi 3, 1
+; CHECK-NEXT:    bltlr 0
+; CHECK-NEXT:  # %bb.2: # %_loop_1_do_.preheader
 ; CHECK-NEXT:    stdu 1, -592(1)
 ; CHECK-NEXT:    .cfi_def_cfa_offset 592
 ; CHECK-NEXT:    .cfi_offset r14, -192
@@ -48,34 +56,92 @@
 ; CHECK-NEXT:    .cfi_offset v29, -240
 ; CHECK-NEXT:    .cfi_offset v30, -224
 ; CHECK-NEXT:    .cfi_offset v31, -208
-; CHECK-NEXT:    lwz 4, 0(4)
-; CHECK-NEXT:    std 14, 400(1) # 8-byte Folded Spill
-; CHECK-NEXT:    std 15, 408(1) # 8-byte Folded Spill
-; CHECK-NEXT:    cmpwi 4, 1
-; CHECK-NEXT:    std 16, 416(1) # 8-byte Folded Spill
-; CHECK-NEXT:    std 17, 424(1) # 8-byte Folded Spill
+; CHECK-NEXT:    std 22, 464(1) # 8-byte Folded Spill
+; CHECK-NEXT:    std 23, 472(1) # 8-byte Folded Spill
+; CHECK-NEXT:    mr 22, 5
+; CHECK-NEXT:    ld 5, 848(1)
+; CHECK-NEXT:    mr 11, 7
+; CHECK-NEXT:    ld 23, 688(1)
+; CHECK-NEXT:    addi 3, 3, 1
+; CHECK-NEXT:    ld 2, 760(1)
+; CHECK-NEXT:    std 28, 512(1) # 8-byte Folded Spill
+; CHECK-NEXT:    std 29, 520(1) # 8-byte Folded Spill
+; CHECK-NEXT:    ld 28, 824(1)
+; CHECK-NEXT:    ld 7, 728(1)
 ; CHECK-NEXT:    std 18, 432(1) # 8-byte Folded Spill
 ; CHECK-NEXT:    std 19, 440(1) # 8-byte Folded Spill
+; CHECK-NEXT:    mr 18, 6
+; CHECK-NEXT:    ld 6, 712(1)
+; CHECK-NEXT:    cmpldi 3, 9
+; CHECK-NEXT:    ld 19, 768(1)
+; CHECK-NEXT:    std 10, 64(1) # 8-byte Folded Spill
+; CHECK-NEXT:    std 6, 72(1) # 8-byte Folded Spill
+; CHECK-NEXT:    std 5, 200(1) # 8-byte Folded Spill
+; CHECK-NEXT:    ld 5, 840(1)
+; CHECK-NEXT:    lxv 33, 0(6)
+; CHECK-NEXT:    std 14, 400(1) # 8-byte Folded Spill
+; CHECK-NEXT:    std 15, 408(1) # 8-byte Folded Spill
+; CHECK-NEXT:    std 30, 528(1) # 8-byte Folded Spill
+; CHECK-NEXT:    std 31, 536(1) # 8-byte Folded Spill
 ; CHECK-NEXT:    std 20, 448(1) # 8-byte Folded Spill
 ; CHECK-NEXT:    std 21, 456(1) # 8-byte Folded Spill
-; CHECK-NEXT:    std 22, 464(1) # 8-byte Folded Spill
-; CHECK-NEXT:    std 23, 472(1) # 8-byte Folded Spill
+; CHECK-NEXT:    ld 21, 784(1)
+; CHECK-NEXT:    ld 20, 776(1)
+; CHECK-NEXT:    lxv 10, 0(19)
+; CHECK-NEXT:    lxv 7, 0(21)
+; CHECK-NEXT:    ld 15, 736(1)
+; CHECK-NEXT:    ld 29, 704(1)
+; CHECK-NEXT:    ld 30, 720(1)
+; CHECK-NEXT:    std 2, 112(1) # 8-byte Folded Spill
+; CHECK-NEXT:    std 19, 120(1) # 8-byte Folded Spill
+; CHECK-NEXT:    lxv 42, 0(9)
+; CHECK-NEXT:    lxv 37, 0(7)
+; CHECK-NEXT:    std 20, 128(1) # 8-byte Folded Spill
+; CHECK-NEXT:    std 21, 136(1) # 8-byte Folded Spill
+; CHECK-NEXT:    lxv 43, 0(8)
+; CHECK-NEXT:    lxv 41, 0(10)
+; CHECK-NEXT:    std 16, 416(1) # 8-byte Folded Spill
+; CHECK-NEXT:    std 17, 424(1) # 8-byte Folded Spill
+; CHECK-NEXT:    ld 17, 752(1)
+; CHECK-NEXT:    ld 16, 744(1)
 ; CHECK-NEXT:    std 24, 480(1) # 8-byte Folded Spill
 ; CHECK-NEXT:    std 25, 488(1) # 8-byte Folded Spill
+; CHECK-NEXT:    ld 25, 800(1)
+; CHECK-NEXT:    ld 24, 792(1)
 ; CHECK-NEXT:    std 26, 496(1) # 8-byte Folded Spill
 ; CHECK-NEXT:    std 27, 504(1) # 8-byte Folded Spill
-; CHECK-NEXT:    std 28, 512(1) # 8-byte Folded Spill
-; CHECK-NEXT:    std 29, 520(1) # 8-byte Folded Spill
-; CHECK-NEXT:    std 30, 528(1) # 8-byte Folded Spill
-; CHECK-NEXT:    std 31, 536(1) # 8-byte Folded Spill
+; CHECK-NEXT:    ld 27, 816(1)
+; CHECK-NEXT:    ld 26, 808(1)
+; CHECK-NEXT:    std 8, 48(1) # 8-byte Folded Spill
+; CHECK-NEXT:    std 9, 56(1) # 8-byte Folded Spill
+; CHECK-NEXT:    lxv 40, 0(23)
+; CHECK-NEXT:    lxv 38, 0(29)
+; CHECK-NEXT:    std 7, 80(1) # 8-byte Folded Spill
+; CHECK-NEXT:    std 15, 88(1) # 8-byte Folded Spill
+; CHECK-NEXT:    lxv 32, 0(30)
+; CHECK-NEXT:    lxv 36, 0(15)
+; CHECK-NEXT:    mr 8, 29
+; CHECK-NEXT:    mr 10, 30
+; CHECK-NEXT:    std 26, 160(1) # 8-byte Folded Spill
+; CHECK-NEXT:    std 27, 168(1) # 8-byte Folded Spill
+; CHECK-NEXT:    lxv 13, 0(16)
+; CHECK-NEXT:    lxv 12, 0(17)
 ; CHECK-NEXT:    stfd 26, 544(1) # 8-byte Folded Spill
 ; CHECK-NEXT:    stfd 27, 552(1) # 8-byte Folded Spill
+; CHECK-NEXT:    lxv 11, 0(2)
+; CHECK-NEXT:    lxv 9, 0(20)
 ; CHECK-NEXT:    stfd 28, 560(1) # 8-byte Folded Spill
 ; CHECK-NEXT:    stfd 29, 568(1) # 8-byte Folded Spill
+; CHECK-NEXT:    lxv 5, 0(24)
+; CHECK-NEXT:    lxv 4, 0(25)
 ; CHECK-NEXT:    stfd 30, 576(1) # 8-byte Folded Spill
 ; CHECK-NEXT:    stfd 31, 584(1) # 8-byte Folded Spill
+; CHECK-NEXT:    lxv 2, 0(26)
+; CHECK-NEXT:    lxv 0, 0(27)
+; CHECK-NEXT:    li 27, 0
 ; CHECK-NEXT:    stxv 52, 208(1) # 16-byte Folded Spill
 ; CHECK-NEXT:    stxv 53, 224(1) # 16-byte Folded Spill
+; CHECK-NEXT:    lxv 1, 0(28)
 ; CHECK-NEXT:    stxv 54, 240(1) # 16-byte Folded Spill
 ; CHECK-NEXT:    stxv 55, 256(1) # 16-byte Folded Spill
 ; CHECK-NEXT:    stxv 56, 272(1) # 16-byte Folded Spill
@@ -86,58 +152,8 @@
 ; CHECK-NEXT:    stxv 61, 352(1) # 16-byte Folded Spill
 ; CHECK-NEXT:    stxv 62, 368(1) # 16-byte Folded Spill
 ; CHECK-NEXT:    stxv 63, 384(1) # 16-byte Folded Spill
-; CHECK-NEXT:    blt 0, .LBB0_7
-; CHECK-NEXT:  # %bb.1: # %_loop_1_do_.lr.ph
-; CHECK-NEXT:    lwz 3, 0(3)
-; CHECK-NEXT:    cmpwi 3, 1
-; CHECK-NEXT:    blt 0, .LBB0_7
-; CHECK-NEXT:  # %bb.2: # %_loop_1_do_.preheader
-; CHECK-NEXT:    mr 22, 5
-; CHECK-NEXT:    ld 5, 848(1)
-; CHECK-NEXT:    ld 28, 824(1)
-; CHECK-NEXT:    mr 11, 7
-; CHECK-NEXT:    mr 18, 6
-; CHECK-NEXT:    addi 3, 3, 1
-; CHECK-NEXT:    std 8, 48(1) # 8-byte Folded Spill
-; CHECK-NEXT:    std 9, 56(1) # 8-byte Folded Spill
-; CHECK-NEXT:    ld 6, 712(1)
-; CHECK-NEXT:    ld 23, 688(1)
-; CHECK-NEXT:    std 10, 64(1) # 8-byte Folded Spill
-; CHECK-NEXT:    std 6, 72(1) # 8-byte Folded Spill
-; CHECK-NEXT:    std 5, 200(1) # 8-byte Folded Spill
-; CHECK-NEXT:    ld 5, 840(1)
-; CHECK-NEXT:    cmpldi 3, 9
-; CHECK-NEXT:    ld 19, 768(1)
-; CHECK-NEXT:    ld 2, 760(1)
-; CHECK-NEXT:    lxv 33, 0(6)
-; CHECK-NEXT:    ld 21, 784(1)
-; CHECK-NEXT:    ld 20, 776(1)
-; CHECK-NEXT:    std 2, 112(1) # 8-byte Folded Spill
-; CHECK-NEXT:    std 19, 120(1) # 8-byte Folded Spill
-; CHECK-NEXT:    lxv 10, 0(19)
-; CHECK-NEXT:    ld 7, 728(1)
-; CHECK-NEXT:    std 20, 128(1) # 8-byte Folded Spill
-; CHECK-NEXT:    std 21, 136(1) # 8-byte Folded Spill
-; CHECK-NEXT:    lxv 7, 0(21)
-; CHECK-NEXT:    ld 27, 816(1)
-; CHECK-NEXT:    std 27, 168(1) # 8-byte Folded Spill
 ; CHECK-NEXT:    std 5, 192(1) # 8-byte Folded Spill
 ; CHECK-NEXT:    ld 5, 832(1)
-; CHECK-NEXT:    ld 26, 808(1)
-; CHECK-NEXT:    ld 25, 800(1)
-; CHECK-NEXT:    ld 24, 792(1)
-; CHECK-NEXT:    ld 17, 752(1)
-; CHECK-NEXT:    ld 16, 744(1)
-; CHECK-NEXT:    ld 15, 736(1)
-; CHECK-NEXT:    ld 29, 704(1)
-; CHECK-NEXT:    ld 30, 720(1)
-; CHECK-NEXT:    lxv 42, 0(9)
-; CHECK-NEXT:    std 7, 80(1) # 8-byte Folded Spill
-; CHECK-NEXT:    std 15, 88(1) # 8-byte Folded Spill
-; CHECK-NEXT:    lxv 37, 0(7)
-; CHECK-NEXT:    lxv 43, 0(8)
-; CHECK-NEXT:    mr 8, 29
-; CHECK-NEXT:    std 26, 160(1) # 8-byte Folded Spill
 ; CHECK-NEXT:    std 16, 96(1) # 8-byte Folded Spill
 ; CHECK-NEXT:    std 17, 104(1) # 8-byte Folded Spill
 ; CHECK-NEXT:    std 24, 144(1) # 8-byte Folded Spill
@@ -145,30 +161,14 @@
 ; CHECK-NEXT:    std 5, 184(1) # 8-byte Folded Spill
 ; CHECK-NEXT:    std 28, 176(1) # 8-byte Folded Spill
 ; CHECK-NEXT:    ld 5, 696(1)
-; CHECK-NEXT:    lxv 41, 0(10)
-; CHECK-NEXT:    lxv 40, 0(23)
-; CHECK-NEXT:    lxv 38, 0(29)
-; CHECK-NEXT:    lxv 32, 0(30)
-; CHECK-NEXT:    lxv 36, 0(15)
-; CHECK-NEXT:    lxv 13, 0(16)
-; CHECK-NEXT:    lxv 12, 0(17)
-; CHECK-NEXT:    lxv 11, 0(2)
-; CHECK-NEXT:    lxv 9, 0(20)
-; CHECK-NEXT:    lxv 5, 0(24)
-; CHECK-NEXT:    lxv 4, 0(25)
-; CHECK-NEXT:    mr 10, 30
+; CHECK-NEXT:    li 28, 1
+; CHECK-NEXT:    ld 7, 184(1) # 8-byte Folded Reload
+; CHECK-NEXT:    lxv 3, 0(7)
 ; CHECK-NEXT:    std 5, 32(1) # 8-byte Folded Spill
 ; CHECK-NEXT:    std 23, 40(1) # 8-byte Folded Spill
 ; CHECK-NEXT:    lwa 5, 0(11)
 ; CHECK-NEXT:    li 11, 9
-; CHECK-NEXT:    ld 7, 184(1) # 8-byte Folded Reload
-; CHECK-NEXT:    lxv 2, 0(26)
-; CHECK-NEXT:    lxv 0, 0(27)
-; CHECK-NEXT:    lxv 1, 0(28)
-; CHECK-NEXT:    li 28, 1
-; CHECK-NEXT:    li 27, 0
 ; CHECK-NEXT:    ld 9, 32(1) # 8-byte Folded Reload
-; CHECK-NEXT:    lxv 3, 0(7)
 ; CHECK-NEXT:    iselgt 3, 3, 11
 ; CHECK-NEXT:    addi 3, 3, -2
 ; CHECK-NEXT:    mulli 6, 5, 40
@@ -270,16 +270,52 @@
 ; CHECK-NEXT:    ble 0, .LBB0_3
 ; CHECK-NEXT:  # %bb.6: # %_loop_1_loopHeader_._return_bb_crit_edge.loopexit
 ; CHECK-NEXT:    ld 3, 48(1) # 8-byte Folded Reload
+; CHECK-NEXT:    lxv 63, 384(1) # 16-byte Folded Reload
 ; CHECK-NEXT:    stxv 43, 0(3)
 ; CHECK-NEXT:    ld 3, 56(1) # 8-byte Folded Reload
+; CHECK-NEXT:    lxv 62, 368(1) # 16-byte Folded Reload
+; CHECK-NEXT:    lxv 61, 352(1) # 16-byte Folded Reload
+; CHECK-NEXT:    lxv 60, 336(1) # 16-byte Folded Reload
+; CHECK-NEXT:    lxv 59, 320(1) # 16-byte Folded Reload
+; CHECK-NEXT:    lxv 58, 304(1) # 16-byte Folded Reload
+; CHECK-NEXT:    lxv 57, 288(1) # 16-byte Folded Reload
+; CHECK-NEXT:    lxv 56, 272(1) # 16-byte Folded Reload
+; CHECK-NEXT:    lxv 55, 256(1) # 16-byte Folded Reload
+; CHECK-NEXT:    lxv 54, 240(1) # 16-byte Folded Reload
+; CHECK-NEXT:    lxv 53, 224(1) # 16-byte Folded Reload
+; CHECK-NEXT:    lxv 52, 208(1) # 16-byte Folded Reload
 ; CHECK-NEXT:    stxv 42, 0(3)
 ; CHECK-NEXT:    ld 3, 64(1) # 8-byte Folded Reload
+; CHECK-NEXT:    lfd 31, 584(1) # 8-byte Folded Reload
+; CHECK-NEXT:    lfd 30, 576(1) # 8-byte Folded Reload
+; CHECK-NEXT:    lfd 29, 568(1) # 8-byte Folded Reload
+; CHECK-NEXT:    lfd 28, 560(1) # 8-byte Folded Reload
+; CHECK-NEXT:    lfd 27, 552(1) # 8-byte Folded Reload
+; CHECK-NEXT:    lfd 26, 544(1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld 31, 536(1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld 30, 528(1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld 29, 520(1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld 28, 512(1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld 27, 504(1) # 8-byte Folded Reload
 ; CHECK-NEXT:    stxv 41, 0(3)
 ; CHECK-NEXT:    ld 3, 40(1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld 26, 496(1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld 25, 488(1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld 24, 480(1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld 23, 472(1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld 22, 464(1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld 21, 456(1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld 20, 448(1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld 19, 440(1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld 18, 432(1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld 17, 424(1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld 16, 416(1) # 8-byte Folded Reload
 ; CHECK-NEXT:    stxv 40, 0(3)
 ; CHECK-NEXT:    ld 3, 72(1) # 8-byte Folded Reload
 ; CHECK-NEXT:    stxv 39, 0(9)
 ; CHECK-NEXT:    stxv 38, 0(8)
+; CHECK-NEXT:    ld 15, 408(1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld 14, 400(1) # 8-byte Folded Reload
 ; CHECK-NEXT:    stxv 33, 0(3)
 ; CHECK-NEXT:    ld 3, 80(1) # 8-byte Folded Reload
 ; CHECK-NEXT:    stxv 32, 0(10)
@@ -314,43 +350,6 @@
 ; CHECK-NEXT:    stxv 8, 0(3)
 ; CHECK-NEXT:    ld 3, 200(1) # 8-byte Folded Reload
 ; CHECK-NEXT:    stxv 6, 0(3)
-; CHECK-NEXT:  .LBB0_7: # %_return_bb
-; CHECK-NEXT:    lxv 63, 384(1) # 16-byte Folded Reload
-; CHECK-NEXT:    lxv 62, 368(1) # 16-byte Folded Reload
-; CHECK-NEXT:    lxv 61, 352(1) # 16-byte Folded Reload
-; CHECK-NEXT:    lxv 60, 336(1) # 16-byte Folded Reload
-; CHECK-NEXT:    lxv 59, 320(1) # 16-byte Folded Reload
-; CHECK-NEXT:    lxv 58, 304(1) # 16-byte Folded Reload
-; CHECK-NEXT:    lxv 57, 288(1) # 16-byte Folded Reload
-; CHECK-NEXT:    lxv 56, 272(1) # 16-byte Folded Reload
-; CHECK-NEXT:    lxv 55, 256(1) # 16-byte Folded Reload
-; CHECK-NEXT:    lxv 54, 240(1) # 16-byte Folded Reload
-; CHECK-NEXT:    lxv 53, 224(1) # 16-byte Folded Reload
-; CHECK-NEXT:    lxv 52, 208(1) # 16-byte Folded Reload
-; CHECK-NEXT:    lfd 31, 584(1) # 8-byte Folded Reload
-; CHECK-NEXT:    lfd 30, 576(1) # 8-byte Folded Reload
-; CHECK-NEXT:    lfd 29, 568(1) # 8-byte Folded Reload
-; CHECK-NEXT:    lfd 28, 560(1) # 8-byte Folded Reload
-; CHECK-NEXT:    lfd 27, 552(1) # 8-byte Folded Reload
-; CHECK-NEXT:    lfd 26, 544(1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld 31, 536(1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld 30, 528(1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld 29, 520(1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld 28, 512(1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld 27, 504(1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld 26, 496(1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld 25, 488(1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld 24, 480(1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld 23, 472(1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld 22, 464(1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld 21, 456(1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld 20, 448(1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld 19, 440(1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld 18, 432(1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld 17, 424(1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld 16, 416(1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld 15, 408(1) # 8-byte Folded Reload
-; CHECK-NEXT:    ld 14, 400(1) # 8-byte Folded Reload
 ; CHECK-NEXT:    addi 1, 1, 592
 ; CHECK-NEXT:    blr
 entry:
diff --git a/llvm/test/CodeGen/PowerPC/ppc64-sibcall-shrinkwrap.ll b/llvm/test/CodeGen/PowerPC/ppc64-sibcall-shrinkwrap.ll
--- a/llvm/test/CodeGen/PowerPC/ppc64-sibcall-shrinkwrap.ll
+++ b/llvm/test/CodeGen/PowerPC/ppc64-sibcall-shrinkwrap.ll
@@ -1,10 +1,9 @@
 ; RUN: llc -relocation-model=static -verify-machineinstrs < %s -mtriple=powerpc64-unknown-linux-gnu -disable-ppc-sco=false --enable-shrink-wrap=false | FileCheck %s -check-prefix=CHECK-SCO-ONLY
-; RUN: llc -relocation-model=static -verify-machineinstrs < %s -mtriple=powerpc64-unknown-linux-gnu -disable-ppc-sco=false --enable-shrink-wrap=true | FileCheck %s -check-prefix=CHECK-SCO-ONLY
+; RUN: llc -relocation-model=static -verify-machineinstrs < %s -mtriple=powerpc64-unknown-linux-gnu -disable-ppc-sco=false --enable-shrink-wrap=true | FileCheck %s -check-prefix=CHECK-SCO-SR
 ; RUN: llc -relocation-model=static -verify-machineinstrs < %s -mtriple=powerpc64le-unknown-linux-gnu -disable-ppc-sco=false --enable-shrink-wrap=false | FileCheck %s -check-prefix=CHECK-SCO-ONLY
-; RUN: llc -relocation-model=static -verify-machineinstrs < %s -mtriple=powerpc64le-unknown-linux-gnu -disable-ppc-sco=false --enable-shrink-wrap=true | FileCheck %s -check-prefix=CHECK-SCO-ONLY
+; RUN: llc -relocation-model=static -verify-machineinstrs < %s -mtriple=powerpc64le-unknown-linux-gnu -disable-ppc-sco=false --enable-shrink-wrap=true | FileCheck %s -check-prefix=CHECK-SCO-SR
 ; RUN: not --crash llc -relocation-model=pic -verify-machineinstrs < %s -mtriple=powerpc64-ibm-aix-xcoff -tailcallopt -disable-ppc-sco=false --enable-shrink-wrap=true 2>&1 | FileCheck %s -check-prefix=CHECK-AIX
 ;; The above RUN command is expected to fail on AIX since tail calling is not implemented ATM
-;; Edit: D63152 prevents stack popping before loads and stores, so shrink-wrap does nothing here
 %"class.clang::NamedDecl" = type { i32 }
 declare void @__assert_fail();
 
@@ -31,6 +30,12 @@
 ; CHECK-SCO-ONLY: #TC_RETURNd8
 ; CHECK-SCO-ONLY: bl __assert_fail
 ;
+; CHECK-SCO-SR-LABEL: _ZNK5clang9NamedDecl23getLinkageAndVisibilityEv:
+; CHECK-SCO-SR: b LVComputationKind
+; CHECK-SCO-SR: #TC_RETURNd8
+; CHECK-SCO-SR: stdu 1, -{{[0-9]+}}(1)
+; CHECK-SCO-SR: bl __assert_fail
+
 ; CHECK-AIX: LLVM ERROR: Tail call support is unimplemented on AIX.
 }
 
diff --git a/llvm/test/CodeGen/RISCV/hoist-global-addr-base.ll b/llvm/test/CodeGen/RISCV/hoist-global-addr-base.ll
--- a/llvm/test/CodeGen/RISCV/hoist-global-addr-base.ll
+++ b/llvm/test/CodeGen/RISCV/hoist-global-addr-base.ll
@@ -139,34 +139,30 @@
 define dso_local i32 @load_half() nounwind {
 ; RV32-LABEL: load_half:
 ; RV32:       # %bb.0: # %entry
-; RV32-NEXT:    addi sp, sp, -16
-; RV32-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
 ; RV32-NEXT:    lui a0, %hi(foo+8)
 ; RV32-NEXT:    lhu a0, %lo(foo+8)(a0)
 ; RV32-NEXT:    li a1, 140
 ; RV32-NEXT:    bne a0, a1, .LBB8_2
 ; RV32-NEXT:  # %bb.1: # %if.end
 ; RV32-NEXT:    li a0, 0
-; RV32-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
-; RV32-NEXT:    addi sp, sp, 16
 ; RV32-NEXT:    ret
 ; RV32-NEXT:  .LBB8_2: # %if.then
+; RV32-NEXT:    addi sp, sp, -16
+; RV32-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
 ; RV32-NEXT:    call abort@plt
 ;
 ; RV64-LABEL: load_half:
 ; RV64:       # %bb.0: # %entry
-; RV64-NEXT:    addi sp, sp, -16
-; RV64-NEXT:    sd ra, 8(sp) # 8-byte Folded Spill
 ; RV64-NEXT:    lui a0, %hi(foo+8)
 ; RV64-NEXT:    lhu a0, %lo(foo+8)(a0)
 ; RV64-NEXT:    li a1, 140
 ; RV64-NEXT:    bne a0, a1, .LBB8_2
 ; RV64-NEXT:  # %bb.1: # %if.end
 ; RV64-NEXT:    li a0, 0
-; RV64-NEXT:    ld ra, 8(sp) # 8-byte Folded Reload
-; RV64-NEXT:    addi sp, sp, 16
 ; RV64-NEXT:    ret
 ; RV64-NEXT:  .LBB8_2: # %if.then
+; RV64-NEXT:    addi sp, sp, -16
+; RV64-NEXT:    sd ra, 8(sp) # 8-byte Folded Spill
 ; RV64-NEXT:    call abort@plt
 entry:
   %0 = load i16, ptr getelementptr inbounds ([6 x i16], ptr @foo, i32 0, i32 4), align 2
diff --git a/llvm/test/CodeGen/RISCV/pr51206.ll b/llvm/test/CodeGen/RISCV/pr51206.ll
--- a/llvm/test/CodeGen/RISCV/pr51206.ll
+++ b/llvm/test/CodeGen/RISCV/pr51206.ll
@@ -11,8 +11,6 @@
 define signext i32 @wobble() nounwind {
 ; CHECK-LABEL: wobble:
 ; CHECK:       # %bb.0: # %bb
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    sd ra, 8(sp) # 8-byte Folded Spill
 ; CHECK-NEXT:    lui a0, %hi(global)
 ; CHECK-NEXT:    lbu a0, %lo(global)(a0)
 ; CHECK-NEXT:    lui a1, %hi(global.2)
@@ -31,11 +29,13 @@
 ; CHECK-NEXT:    sw a1, %lo(global.3)(a2)
 ; CHECK-NEXT:    bltu a0, a3, .LBB0_2
 ; CHECK-NEXT:  # %bb.1: # %bb10
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    sd ra, 8(sp) # 8-byte Folded Spill
 ; CHECK-NEXT:    call quux@plt
-; CHECK-NEXT:  .LBB0_2: # %bb12
-; CHECK-NEXT:    li a0, 0
 ; CHECK-NEXT:    ld ra, 8(sp) # 8-byte Folded Reload
 ; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:  .LBB0_2: # %bb12
+; CHECK-NEXT:    li a0, 0
 ; CHECK-NEXT:    ret
 bb:
   %tmp = load i8, ptr @global, align 1
diff --git a/llvm/test/CodeGen/Thumb/thumb-shrink-wrapping.ll b/llvm/test/CodeGen/Thumb/thumb-shrink-wrapping.ll
--- a/llvm/test/CodeGen/Thumb/thumb-shrink-wrapping.ll
+++ b/llvm/test/CodeGen/Thumb/thumb-shrink-wrapping.ll
@@ -1445,47 +1445,53 @@
 define i1 @beq_to_bx(ptr %y, i32 %head) {
 ; ENABLE-V4T-LABEL: beq_to_bx:
 ; ENABLE-V4T:       @ %bb.0: @ %entry
-; ENABLE-V4T-NEXT:    push {r4, lr}
-; ENABLE-V4T-NEXT:    .cfi_def_cfa_offset 8
-; ENABLE-V4T-NEXT:    .cfi_offset lr, -4
-; ENABLE-V4T-NEXT:    .cfi_offset r4, -8
 ; ENABLE-V4T-NEXT:    movs r2, r0
 ; ENABLE-V4T-NEXT:    movs r0, #1
 ; ENABLE-V4T-NEXT:    cmp r2, #0
 ; ENABLE-V4T-NEXT:    beq LBB11_3
 ; ENABLE-V4T-NEXT:  @ %bb.1: @ %if.end
+; ENABLE-V4T-NEXT:    push {r4, lr}
+; ENABLE-V4T-NEXT:    .cfi_def_cfa_offset 8
+; ENABLE-V4T-NEXT:    .cfi_offset lr, -4
+; ENABLE-V4T-NEXT:    .cfi_offset r4, -8
 ; ENABLE-V4T-NEXT:    ldr r3, [r2]
 ; ENABLE-V4T-NEXT:    lsls r4, r3, #30
+; ENABLE-V4T-NEXT:    ldr r4, [sp, #4]
+; ENABLE-V4T-NEXT:    mov lr, r4
+; ENABLE-V4T-NEXT:    pop {r4}
+; ENABLE-V4T-NEXT:    add sp, #4
 ; ENABLE-V4T-NEXT:    bpl LBB11_3
 ; ENABLE-V4T-NEXT:  @ %bb.2: @ %if.end4
 ; ENABLE-V4T-NEXT:    str r1, [r2]
 ; ENABLE-V4T-NEXT:    str r3, [r2]
 ; ENABLE-V4T-NEXT:    movs r0, #0
 ; ENABLE-V4T-NEXT:  LBB11_3: @ %cleanup
-; ENABLE-V4T-NEXT:    pop {r4}
-; ENABLE-V4T-NEXT:    pop {r1}
-; ENABLE-V4T-NEXT:    bx r1
+; ENABLE-V4T-NEXT:    bx lr
 ;
 ; ENABLE-V5T-LABEL: beq_to_bx:
 ; ENABLE-V5T:       @ %bb.0: @ %entry
-; ENABLE-V5T-NEXT:    push {r4, lr}
-; ENABLE-V5T-NEXT:    .cfi_def_cfa_offset 8
-; ENABLE-V5T-NEXT:    .cfi_offset lr, -4
-; ENABLE-V5T-NEXT:    .cfi_offset r4, -8
 ; ENABLE-V5T-NEXT:    movs r2, r0
 ; ENABLE-V5T-NEXT:    movs r0, #1
 ; ENABLE-V5T-NEXT:    cmp r2, #0
 ; ENABLE-V5T-NEXT:    beq LBB11_3
 ; ENABLE-V5T-NEXT:  @ %bb.1: @ %if.end
+; ENABLE-V5T-NEXT:    push {r4, lr}
+; ENABLE-V5T-NEXT:    .cfi_def_cfa_offset 8
+; ENABLE-V5T-NEXT:    .cfi_offset lr, -4
+; ENABLE-V5T-NEXT:    .cfi_offset r4, -8
 ; ENABLE-V5T-NEXT:    ldr r3, [r2]
 ; ENABLE-V5T-NEXT:    lsls r4, r3, #30
+; ENABLE-V5T-NEXT:    ldr r4, [sp, #4]
+; ENABLE-V5T-NEXT:    mov lr, r4
+; ENABLE-V5T-NEXT:    pop {r4}
+; ENABLE-V5T-NEXT:    add sp, #4
 ; ENABLE-V5T-NEXT:    bpl LBB11_3
 ; ENABLE-V5T-NEXT:  @ %bb.2: @ %if.end4
 ; ENABLE-V5T-NEXT:    str r1, [r2]
 ; ENABLE-V5T-NEXT:    str r3, [r2]
 ; ENABLE-V5T-NEXT:    movs r0, #0
 ; ENABLE-V5T-NEXT:  LBB11_3: @ %cleanup
-; ENABLE-V5T-NEXT:    pop {r4, pc}
+; ENABLE-V5T-NEXT:    bx lr
 ;
 ; DISABLE-V4T-LABEL: beq_to_bx:
 ; DISABLE-V4T:       @ %bb.0: @ %entry
diff --git a/llvm/test/CodeGen/X86/2010-08-04-MaskedSignedCompare.ll b/llvm/test/CodeGen/X86/2010-08-04-MaskedSignedCompare.ll
--- a/llvm/test/CodeGen/X86/2010-08-04-MaskedSignedCompare.ll
+++ b/llvm/test/CodeGen/X86/2010-08-04-MaskedSignedCompare.ll
@@ -9,7 +9,6 @@
 define dso_local i32 @main() nounwind {
 ; CHECK-LABEL: main:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpq g_16(%rip), %rax
 ; CHECK-NEXT:    sbbl %eax, %eax
@@ -22,6 +21,7 @@
 ; CHECK-NEXT:  .LBB0_1: # %entry.if.end_crit_edge
 ; CHECK-NEXT:    movl g_38(%rip), %esi
 ; CHECK-NEXT:  .LBB0_3: # %if.end
+; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    movl $.L.str, %edi
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    callq printf@PLT
diff --git a/llvm/test/CodeGen/X86/cmov.ll b/llvm/test/CodeGen/X86/cmov.ll
--- a/llvm/test/CodeGen/X86/cmov.ll
+++ b/llvm/test/CodeGen/X86/cmov.ll
@@ -78,7 +78,6 @@
 define i1 @test4() nounwind {
 ; CHECK-LABEL: test4:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    pushq %rbx
 ; CHECK-NEXT:    movsbl g_3(%rip), %edx
 ; CHECK-NEXT:    movzbl %dl, %ecx
 ; CHECK-NEXT:    shrl $7, %ecx
@@ -91,6 +90,7 @@
 ; CHECK-NEXT:  # %bb.1: # %bb.i.i.i
 ; CHECK-NEXT:    movzbl g_100(%rip), %ecx
 ; CHECK-NEXT:  .LBB3_2: # %func_4.exit.i
+; CHECK-NEXT:    pushq %rbx
 ; CHECK-NEXT:    xorl %esi, %esi
 ; CHECK-NEXT:    testb %dl, %dl
 ; CHECK-NEXT:    setne %bl
diff --git a/llvm/test/CodeGen/X86/copy-eflags.ll b/llvm/test/CodeGen/X86/copy-eflags.ll
--- a/llvm/test/CodeGen/X86/copy-eflags.ll
+++ b/llvm/test/CodeGen/X86/copy-eflags.ll
@@ -43,7 +43,6 @@
 ;
 ; X64-LABEL: test1:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    movzbl b(%rip), %ecx
 ; X64-NEXT:    leal 1(%rcx), %eax
 ; X64-NEXT:    movb %al, b(%rip)
@@ -57,11 +56,12 @@
 ; X64-NEXT:    testb %dl, %dl
 ; X64-NEXT:    jne .LBB0_2
 ; X64-NEXT:  # %bb.1: # %if.then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    movsbl %al, %edi
 ; X64-NEXT:    callq external
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB0_2: # %if.end
 ; X64-NEXT:    xorl %eax, %eax
-; X64-NEXT:    popq %rcx
 ; X64-NEXT:    retq
 entry:
   %bval = load i8, ptr @b
diff --git a/llvm/test/CodeGen/X86/csr-split.ll b/llvm/test/CodeGen/X86/csr-split.ll
--- a/llvm/test/CodeGen/X86/csr-split.ll
+++ b/llvm/test/CodeGen/X86/csr-split.ll
@@ -9,18 +9,15 @@
 define dso_local signext i32 @test1(ptr %b) local_unnamed_addr  {
 ; CHECK-LABEL: test1:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    pushq %rbx
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    .cfi_offset %rbx, -16
 ; CHECK-NEXT:    movslq a(%rip), %rax
 ; CHECK-NEXT:    cmpq %rdi, %rax
 ; CHECK-NEXT:    je .LBB0_2
 ; CHECK-NEXT:  # %bb.1: # %if.end
-; CHECK-NEXT:    popq %rbx
-; CHECK-NEXT:    .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    retq
 ; CHECK-NEXT:  .LBB0_2: # %if.then
+; CHECK-NEXT:    pushq %rbx
 ; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset %rbx, -16
 ; CHECK-NEXT:    movq %rdi, %rbx
 ; CHECK-NEXT:    callq callVoid@PLT
 ; CHECK-NEXT:    movq %rbx, %rdi
diff --git a/llvm/test/CodeGen/X86/i686-win-shrink-wrapping.ll b/llvm/test/CodeGen/X86/i686-win-shrink-wrapping.ll
--- a/llvm/test/CodeGen/X86/i686-win-shrink-wrapping.ll
+++ b/llvm/test/CodeGen/X86/i686-win-shrink-wrapping.ll
@@ -11,10 +11,6 @@
 define x86_thiscallcc void @stackRealignment(ptr %this) {
 ; SHRINK-WRAP-LABEL: stackRealignment:
 ; SHRINK-WRAP:       # %bb.0: # %entry
-; SHRINK-WRAP-NEXT:    pushl %ebp
-; SHRINK-WRAP-NEXT:    movl %esp, %ebp
-; SHRINK-WRAP-NEXT:    andl $-8, %esp
-; SHRINK-WRAP-NEXT:    subl $16, %esp
 ; SHRINK-WRAP-NEXT:    movl (%ecx), %eax
 ; SHRINK-WRAP-NEXT:    cmpl $33, %eax
 ; SHRINK-WRAP-NEXT:    movl $42, %edx
@@ -22,6 +18,10 @@
 ; SHRINK-WRAP-NEXT:  # %bb.1: # %entry
 ; SHRINK-WRAP-NEXT:    movl $128, %edx
 ; SHRINK-WRAP-NEXT:  LBB0_2: # %entry
+; SHRINK-WRAP-NEXT:    pushl %ebp
+; SHRINK-WRAP-NEXT:    movl %esp, %ebp
+; SHRINK-WRAP-NEXT:    andl $-8, %esp
+; SHRINK-WRAP-NEXT:    subl $16, %esp
 ; SHRINK-WRAP-NEXT:    movl %edx, {{[0-9]+}}(%esp)
 ; SHRINK-WRAP-NEXT:    cmpl $32, %eax
 ; SHRINK-WRAP-NEXT:    jl LBB0_4
diff --git a/llvm/test/CodeGen/X86/inline-asm-flag-output.ll b/llvm/test/CodeGen/X86/inline-asm-flag-output.ll
--- a/llvm/test/CodeGen/X86/inline-asm-flag-output.ll
+++ b/llvm/test/CodeGen/X86/inline-asm-flag-output.ll
@@ -888,15 +888,15 @@
 ;
 ; X64-LABEL: test_cca_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jbe .LBB28_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB28_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@cca},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -928,15 +928,15 @@
 ;
 ; X64-LABEL: test_ccae_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jb .LBB29_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB29_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccae},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -968,15 +968,15 @@
 ;
 ; X64-LABEL: test_ccb_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jae .LBB30_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB30_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccb},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1008,15 +1008,15 @@
 ;
 ; X64-LABEL: test_ccbe_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    ja .LBB31_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB31_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccbe},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1048,15 +1048,15 @@
 ;
 ; X64-LABEL: test_ccc_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jae .LBB32_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB32_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccc},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1088,15 +1088,15 @@
 ;
 ; X64-LABEL: test_cce_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jne .LBB33_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB33_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@cce},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1128,15 +1128,15 @@
 ;
 ; X64-LABEL: test_ccz_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jne .LBB34_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB34_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccz},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1168,15 +1168,15 @@
 ;
 ; X64-LABEL: test_ccg_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jle .LBB35_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB35_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccg},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1208,15 +1208,15 @@
 ;
 ; X64-LABEL: test_ccge_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jl .LBB36_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB36_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccge},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1248,15 +1248,15 @@
 ;
 ; X64-LABEL: test_ccl_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jge .LBB37_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB37_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccl},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1288,15 +1288,15 @@
 ;
 ; X64-LABEL: test_ccle_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jg .LBB38_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB38_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccle},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1328,15 +1328,15 @@
 ;
 ; X64-LABEL: test_ccna_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    ja .LBB39_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB39_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccna},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1368,15 +1368,15 @@
 ;
 ; X64-LABEL: test_ccnae_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jae .LBB40_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB40_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccnae},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1408,15 +1408,15 @@
 ;
 ; X64-LABEL: test_ccnb_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jb .LBB41_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB41_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccnb},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1448,15 +1448,15 @@
 ;
 ; X64-LABEL: test_ccnbe_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jbe .LBB42_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB42_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccnbe},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1488,15 +1488,15 @@
 ;
 ; X64-LABEL: test_ccnc_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jb .LBB43_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB43_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccnc},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1528,15 +1528,15 @@
 ;
 ; X64-LABEL: test_ccne_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    je .LBB44_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB44_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccne},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1568,15 +1568,15 @@
 ;
 ; X64-LABEL: test_ccnz_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    je .LBB45_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB45_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccnz},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1608,15 +1608,15 @@
 ;
 ; X64-LABEL: test_ccng_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jg .LBB46_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB46_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccng},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1648,15 +1648,15 @@
 ;
 ; X64-LABEL: test_ccnge_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jge .LBB47_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB47_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccnge},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1688,15 +1688,15 @@
 ;
 ; X64-LABEL: test_ccnl_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jl .LBB48_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB48_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccnl},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1728,15 +1728,15 @@
 ;
 ; X64-LABEL: test_ccnle_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jle .LBB49_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB49_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccnle},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1768,15 +1768,15 @@
 ;
 ; X64-LABEL: test_ccno_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jo .LBB50_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB50_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccno},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1808,15 +1808,15 @@
 ;
 ; X64-LABEL: test_ccnp_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jp .LBB51_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB51_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccnp},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1848,15 +1848,15 @@
 ;
 ; X64-LABEL: test_ccns_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    js .LBB52_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB52_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccns},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1888,15 +1888,15 @@
 ;
 ; X64-LABEL: test_cco_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jno .LBB53_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB53_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@cco},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1928,15 +1928,15 @@
 ;
 ; X64-LABEL: test_ccp_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jnp .LBB54_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB54_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccp},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
@@ -1968,15 +1968,15 @@
 ;
 ; X64-LABEL: test_ccs_branch:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    #APP
 ; X64-NEXT:    cmp %rdi,(%rsi)
 ; X64-NEXT:    #NO_APP
 ; X64-NEXT:    jns .LBB55_2
 ; X64-NEXT:  # %bb.1: # %then
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    callq bar@PLT
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB55_2: # %exit
-; X64-NEXT:    popq %rax
 ; X64-NEXT:    retq
 entry:
   %cc = tail call i8 asm "cmp $2,$1", "={@ccs},=*m,r,~{cc},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(i64) %addr, i64 %nr) nounwind
diff --git a/llvm/test/CodeGen/X86/peep-test-5.ll b/llvm/test/CodeGen/X86/peep-test-5.ll
--- a/llvm/test/CodeGen/X86/peep-test-5.ll
+++ b/llvm/test/CodeGen/X86/peep-test-5.ll
@@ -12,25 +12,22 @@
 define void @decref(ptr %p) {
 ; CHECK-LABEL: decref:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    pushq %rax
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    movl (%rdi), %eax
 ; CHECK-NEXT:    cmpl $1, %eax
 ; CHECK-NEXT:    jne .LBB0_2
 ; CHECK-NEXT:  # %bb.1: # %bb_free
+; CHECK-NEXT:    pushq %rax
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    callq free_object@PLT
-; CHECK-NEXT:  .LBB0_4: # %end
-; CHECK-NEXT:    popq %rax
+; CHECK-NEXT:    addq $8, %rsp
 ; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:  .LBB0_4: # %end
 ; CHECK-NEXT:    retq
 ; CHECK-NEXT:  .LBB0_2: # %bb2
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    jle .LBB0_4
 ; CHECK-NEXT:  # %bb.3: # %bb_dec
 ; CHECK-NEXT:    decl %eax
 ; CHECK-NEXT:    movl %eax, (%rdi)
-; CHECK-NEXT:    popq %rax
-; CHECK-NEXT:    .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    retq
   %count = load i32, ptr %p, align 4
   %cmp0 = icmp eq i32 %count, 1
diff --git a/llvm/test/CodeGen/X86/shrink-wrap-chkstk-x86_64.ll b/llvm/test/CodeGen/X86/shrink-wrap-chkstk-x86_64.ll
--- a/llvm/test/CodeGen/X86/shrink-wrap-chkstk-x86_64.ll
+++ b/llvm/test/CodeGen/X86/shrink-wrap-chkstk-x86_64.ll
@@ -9,10 +9,6 @@
 define void @fn1() nounwind uwtable {
 ; CHECK-LABEL: fn1:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    movl $4136, %eax # imm = 0x1028
-; CHECK-NEXT:    callq ___chkstk_ms
-; CHECK-NEXT:    subq %rax, %rsp
-; CHECK-NEXT:    .cfi_def_cfa_offset 4144
 ; CHECK-NEXT:    movl a(%rip), %eax
 ; CHECK-NEXT:    testl %eax, %eax
 ; CHECK-NEXT:    jne .LBB0_2
@@ -24,6 +20,12 @@
 ; CHECK-NEXT:    shrq $32, %rax
 ; CHECK-NEXT:    addl %ecx, %eax
 ; CHECK-NEXT:  .LBB0_2: # %select.end
+; CHECK-NEXT:    pushq %rax
+; CHECK-NEXT:    movl $4128, %eax # imm = 0x1020
+; CHECK-NEXT:    callq ___chkstk_ms
+; CHECK-NEXT:    subq %rax, %rsp
+; CHECK-NEXT:    movq {{[0-9]+}}(%rsp), %rax
+; CHECK-NEXT:    .cfi_def_cfa_offset 4144
 ; CHECK-NEXT:    movl %eax, b(%rip)
 ; CHECK-NEXT:    leaq {{[0-9]+}}(%rsp), %rcx
 ; CHECK-NEXT:    # kill: def $ecx killed $ecx killed $rcx
diff --git a/llvm/test/CodeGen/X86/statepoint-vector.ll b/llvm/test/CodeGen/X86/statepoint-vector.ll
--- a/llvm/test/CodeGen/X86/statepoint-vector.ll
+++ b/llvm/test/CodeGen/X86/statepoint-vector.ll
@@ -57,10 +57,10 @@
 define <2 x ptr addrspace(1)> @test3(i1 %cnd, ptr %ptr) gc "statepoint-example" {
 ; CHECK-LABEL: test3:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    subq $40, %rsp
-; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    testb $1, %dil
 ; CHECK-NEXT:    movaps (%rsi), %xmm0
+; CHECK-NEXT:    subq $40, %rsp
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    movaps %xmm0, (%rsp)
 ; CHECK-NEXT:    movaps %xmm0, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    callq do_safepoint@PLT
diff --git a/llvm/test/DebugInfo/X86/merge_inlined_loc.ll b/llvm/test/DebugInfo/X86/merge_inlined_loc.ll
--- a/llvm/test/DebugInfo/X86/merge_inlined_loc.ll
+++ b/llvm/test/DebugInfo/X86/merge_inlined_loc.ll
@@ -26,7 +26,9 @@
 
 ; CHECK: .loc 1 2 25 epilogue_begin
 ; CHECK-NEXT: popq %rax
+; CHECK-NEXT: .Ltmp{{.*}}:
 ; CHECK-NEXT: .cfi_def_cfa_offset 8
+; CHECK-NEXT: .loc 1 2 25 is_stmt 0
 ; CHECK-NEXT: jmp _Z6commonv
 ; CHECK-NEXT: [[LABEL:.*]]: