diff --git a/llvm/lib/Target/X86/X86FrameLowering.cpp b/llvm/lib/Target/X86/X86FrameLowering.cpp
--- a/llvm/lib/Target/X86/X86FrameLowering.cpp
+++ b/llvm/lib/Target/X86/X86FrameLowering.cpp
@@ -556,56 +556,33 @@
   const X86Subtarget &STI = MF.getSubtarget<X86Subtarget>();
   const X86TargetLowering &TLI = *STI.getTargetLowering();
   const unsigned Opc = getSUBriOpcode(Uses64BitFramePtr, Offset);
-  const unsigned MovMIOpc = Is64Bit ? X86::MOV64mi32 : X86::MOV32mi;
   const uint64_t StackProbeSize = TLI.getStackProbeSize(MF);
 
   uint64_t CurrentOffset = 0;
 
   assert(AlignOffset < StackProbeSize);
 
-  // If the offset is so small it fits within a page, there's nothing to do.
-  if (StackProbeSize < Offset + AlignOffset) {
-
-    MachineInstr *MI = BuildMI(MBB, MBBI, DL, TII.get(Opc), StackPtr)
-                           .addReg(StackPtr)
-                           .addImm(StackProbeSize - AlignOffset)
-                           .setMIFlag(MachineInstr::FrameSetup);
-    MI->getOperand(3).setIsDead(); // The EFLAGS implicit def is dead.
-
-    addRegOffset(BuildMI(MBB, MBBI, DL, TII.get(MovMIOpc))
-                     .setMIFlag(MachineInstr::FrameSetup),
-                 StackPtr, false, 0)
-        .addImm(0)
-        .setMIFlag(MachineInstr::FrameSetup);
-    NumFrameExtraProbe++;
-    CurrentOffset = StackProbeSize - AlignOffset;
-  }
-
-  // For the next N - 1 pages, just probe. I tried to take advantage of
-  // natural probes but it implies much more logic and there was very few
-  // interesting natural probes to interleave.
+  // For the first N - 1 pages, probe.
+  //
+  // We emit the most basic `movb $0, -offset(%rsp)` instruction which is good
+  // for offsets of up-to 2GB. This is also most throughput and space efficient
+  // encoding that I (nagisa) could come up.
+  //
+  // It also naturally doesn't need any special handling for precise uwtables.
   while (CurrentOffset + StackProbeSize < Offset) {
-    MachineInstr *MI = BuildMI(MBB, MBBI, DL, TII.get(Opc), StackPtr)
-                           .addReg(StackPtr)
-                           .addImm(StackProbeSize)
-                           .setMIFlag(MachineInstr::FrameSetup);
-    MI->getOperand(3).setIsDead(); // The EFLAGS implicit def is dead.
-
-
-    addRegOffset(BuildMI(MBB, MBBI, DL, TII.get(MovMIOpc))
+    NumFrameExtraProbe++;
+    CurrentOffset += StackProbeSize;
+    addRegOffset(BuildMI(MBB, MBBI, DL, TII.get(X86::MOV8mi))
                      .setMIFlag(MachineInstr::FrameSetup),
-                 StackPtr, false, 0)
+                 StackPtr, false, -CurrentOffset)
         .addImm(0)
         .setMIFlag(MachineInstr::FrameSetup);
-    NumFrameExtraProbe++;
-    CurrentOffset += StackProbeSize;
   }
 
   // No need to probe the tail, it is smaller than a Page.
-  uint64_t ChunkSize = Offset - CurrentOffset;
   MachineInstr *MI = BuildMI(MBB, MBBI, DL, TII.get(Opc), StackPtr)
                          .addReg(StackPtr)
-                         .addImm(ChunkSize)
+                         .addImm(Offset)
                          .setMIFlag(MachineInstr::FrameSetup);
   MI->getOperand(3).setIsDead(); // The EFLAGS implicit def is dead.
 }
diff --git a/llvm/test/CodeGen/X86/stack-clash-dynamic-alloca.ll b/llvm/test/CodeGen/X86/stack-clash-dynamic-alloca.ll
--- a/llvm/test/CodeGen/X86/stack-clash-dynamic-alloca.ll
+++ b/llvm/test/CodeGen/X86/stack-clash-dynamic-alloca.ll
@@ -1,7 +1,64 @@
-; RUN: llc -mtriple=x86_64-linux-android < %s | FileCheck -check-prefix=CHECK-X86-64 %s 
-; RUN: llc -mtriple=i686-linux-android < %s | FileCheck -check-prefix=CHECK-X86-32 %s 
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --no_x86_scrub_sp
+; RUN: llc -mtriple=x86_64-linux-android < %s | FileCheck -check-prefix=CHECK-X86-64 %s
+; RUN: llc -mtriple=i686-linux-android < %s | FileCheck -check-prefix=CHECK-X86-32 %s
 
 define i32 @foo(i32 %n) local_unnamed_addr #0 {
+; CHECK-X86-64-LABEL: foo:
+; CHECK-X86-64:       # %bb.0:
+; CHECK-X86-64-NEXT:    pushq %rbp
+; CHECK-X86-64-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-X86-64-NEXT:    .cfi_offset %rbp, -16
+; CHECK-X86-64-NEXT:    movq %rsp, %rbp
+; CHECK-X86-64-NEXT:    .cfi_def_cfa_register %rbp
+; CHECK-X86-64-NEXT:    movq %rsp, %rax
+; CHECK-X86-64-NEXT:    movl %edi, %ecx
+; CHECK-X86-64-NEXT:    leaq 15(,%rcx,4), %rcx
+; CHECK-X86-64-NEXT:    andq $-16, %rcx
+; CHECK-X86-64-NEXT:    subq %rcx, %rax
+; CHECK-X86-64-NEXT:    cmpq %rsp, %rax
+; CHECK-X86-64-NEXT:    jge .LBB0_3
+; CHECK-X86-64-NEXT:  .LBB0_2: # =>This Inner Loop Header: Depth=1
+; CHECK-X86-64-NEXT:    xorq $0, (%rsp)
+; CHECK-X86-64-NEXT:    subq $4096, %rsp # imm = 0x1000
+; CHECK-X86-64-NEXT:    cmpq %rsp, %rax
+; CHECK-X86-64-NEXT:    jl .LBB0_2
+; CHECK-X86-64-NEXT:  .LBB0_3:
+; CHECK-X86-64-NEXT:    movq %rax, %rsp
+; CHECK-X86-64-NEXT:    movl $1, 4792(%rax)
+; CHECK-X86-64-NEXT:    movl (%rax), %eax
+; CHECK-X86-64-NEXT:    movq %rbp, %rsp
+; CHECK-X86-64-NEXT:    popq %rbp
+; CHECK-X86-64-NEXT:    .cfi_def_cfa %rsp, 8
+; CHECK-X86-64-NEXT:    retq
+;
+; CHECK-X86-32-LABEL: foo:
+; CHECK-X86-32:       # %bb.0:
+; CHECK-X86-32-NEXT:    pushl %ebp
+; CHECK-X86-32-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-X86-32-NEXT:    .cfi_offset %ebp, -8
+; CHECK-X86-32-NEXT:    movl %esp, %ebp
+; CHECK-X86-32-NEXT:    .cfi_def_cfa_register %ebp
+; CHECK-X86-32-NEXT:    subl $8, %esp
+; CHECK-X86-32-NEXT:    movl 8(%ebp), %ecx
+; CHECK-X86-32-NEXT:    movl %esp, %eax
+; CHECK-X86-32-NEXT:    leal 15(,%ecx,4), %ecx
+; CHECK-X86-32-NEXT:    andl $-16, %ecx
+; CHECK-X86-32-NEXT:    subl %ecx, %eax
+; CHECK-X86-32-NEXT:    cmpl %esp, %eax
+; CHECK-X86-32-NEXT:    jge .LBB0_3
+; CHECK-X86-32-NEXT:  .LBB0_2: # =>This Inner Loop Header: Depth=1
+; CHECK-X86-32-NEXT:    xorl $0, (%esp)
+; CHECK-X86-32-NEXT:    subl $4096, %esp # imm = 0x1000
+; CHECK-X86-32-NEXT:    cmpl %esp, %eax
+; CHECK-X86-32-NEXT:    jl .LBB0_2
+; CHECK-X86-32-NEXT:  .LBB0_3:
+; CHECK-X86-32-NEXT:    movl %eax, %esp
+; CHECK-X86-32-NEXT:    movl $1, 4792(%eax)
+; CHECK-X86-32-NEXT:    movl (%eax), %eax
+; CHECK-X86-32-NEXT:    movl %ebp, %esp
+; CHECK-X86-32-NEXT:    popl %ebp
+; CHECK-X86-32-NEXT:    .cfi_def_cfa %esp, 4
+; CHECK-X86-32-NEXT:    retl
   %a = alloca i32, i32 %n, align 16
   %b = getelementptr inbounds i32, i32* %a, i64 1198
   store volatile i32 1, i32* %b
diff --git a/llvm/test/CodeGen/X86/stack-clash-large-large-align.ll b/llvm/test/CodeGen/X86/stack-clash-large-large-align.ll
--- a/llvm/test/CodeGen/X86/stack-clash-large-large-align.ll
+++ b/llvm/test/CodeGen/X86/stack-clash-large-large-align.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --no_x86_scrub_sp
 ; RUN: llc < %s | FileCheck %s
 
 
@@ -7,20 +8,20 @@
 define i32 @foo_noprotect() local_unnamed_addr {
 ; CHECK-LABEL: foo_noprotect:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:	pushq	%rbp
-; CHECK-NEXT:   .cfi_def_cfa_offset 16
-; CHECK-NEXT:   .cfi_offset %rbp, -16
-; CHECK-NEXT:   movq	%rsp, %rbp
-; CHECK-NEXT:   .cfi_def_cfa_register %rbp
-; CHECK-NEXT:   andq	$-4096, %rsp                    # imm = 0xF000
-; CHECK-NEXT:   subq	$73728, %rsp                    # imm = 0x12000
-; CHECK-NEXT:   movl	$1, 392(%rsp)
-; CHECK-NEXT:   movl	$1, 28792(%rsp)
-; CHECK-NEXT:   movl	(%rsp), %eax
-; CHECK-NEXT:   movq	%rbp, %rsp
-; CHECK-NEXT:   popq	%rbp
-; CHECK-NEXT:   .cfi_def_cfa %rsp, 8
-; CHECK-NEXT:   retq
+; CHECK-NEXT:    pushq %rbp
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset %rbp, -16
+; CHECK-NEXT:    movq %rsp, %rbp
+; CHECK-NEXT:    .cfi_def_cfa_register %rbp
+; CHECK-NEXT:    andq $-4096, %rsp # imm = 0xF000
+; CHECK-NEXT:    subq $73728, %rsp # imm = 0x12000
+; CHECK-NEXT:    movl $1, 392(%rsp)
+; CHECK-NEXT:    movl $1, 28792(%rsp)
+; CHECK-NEXT:    movl (%rsp), %eax
+; CHECK-NEXT:    movq %rbp, %rsp
+; CHECK-NEXT:    popq %rbp
+; CHECK-NEXT:    .cfi_def_cfa %rsp, 8
+; CHECK-NEXT:    retq
 
 
   %a = alloca i32, i64 18000, align 4096
@@ -35,43 +36,43 @@
 define i32 @foo_protect() local_unnamed_addr #0 {
 ; CHECK-LABEL: foo_protect:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:	pushq	%rbp
-; CHECK-NEXT:	.cfi_def_cfa_offset 16
-; CHECK-NEXT:	.cfi_offset %rbp, -16
-; CHECK-NEXT:	movq	%rsp, %rbp
-; CHECK-NEXT:	.cfi_def_cfa_register %rbp
-; CHECK-NEXT:	movq	%rsp, %r11
-; CHECK-NEXT:	andq	$-4096, %r11                    # imm = 0xF000
-; CHECK-NEXT:	cmpq	%rsp, %r11
-; CHECK-NEXT:	je	.LBB1_4
-; CHECK-NEXT:# %bb.1:
-; CHECK-NEXT:	subq	$4096, %rsp                     # imm = 0x1000
-; CHECK-NEXT:	cmpq	%rsp, %r11
-; CHECK-NEXT:	jb	.LBB1_3
-; CHECK-NEXT:.LBB1_2:                                # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:	movq	$0, (%rsp)
-; CHECK-NEXT:	subq	$4096, %rsp                     # imm = 0x1000
-; CHECK-NEXT:	cmpq	%rsp, %r11
-; CHECK-NEXT:	jb	.LBB1_2
-; CHECK-NEXT:.LBB1_3:
-; CHECK-NEXT:	movq	%r11, %rsp
-; CHECK-NEXT:	movq	$0, (%rsp)
-; CHECK-NEXT:.LBB1_4:
-; CHECK-NEXT:	movq	%rsp, %r11
-; CHECK-NEXT:	subq	$73728, %r11                    # imm = 0x12000
-; CHECK-NEXT:.LBB1_5:                                # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:	subq	$4096, %rsp                     # imm = 0x1000
-; CHECK-NEXT:	movq	$0, (%rsp)
-; CHECK-NEXT:	cmpq	%r11, %rsp
-; CHECK-NEXT:	jne	.LBB1_5
-; CHECK-NEXT:# %bb.6:
-; CHECK-NEXT:	movl	$1, 392(%rsp)
-; CHECK-NEXT:	movl	$1, 28792(%rsp)
-; CHECK-NEXT:	movl	(%rsp), %eax
-; CHECK-NEXT:	movq	%rbp, %rsp
-; CHECK-NEXT:	popq	%rbp
-; CHECK-NEXT:	.cfi_def_cfa %rsp, 8
-; CHECK-NEXT:	retq
+; CHECK-NEXT:    pushq %rbp
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset %rbp, -16
+; CHECK-NEXT:    movq %rsp, %rbp
+; CHECK-NEXT:    .cfi_def_cfa_register %rbp
+; CHECK-NEXT:    movq %rsp, %r11
+; CHECK-NEXT:    andq $-4096, %r11 # imm = 0xF000
+; CHECK-NEXT:    cmpq %rsp, %r11
+; CHECK-NEXT:    je .LBB1_4
+; CHECK-NEXT:  # %bb.1:
+; CHECK-NEXT:    subq $4096, %rsp # imm = 0x1000
+; CHECK-NEXT:    cmpq %rsp, %r11
+; CHECK-NEXT:    jb .LBB1_3
+; CHECK-NEXT:  .LBB1_2: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    movq $0, (%rsp)
+; CHECK-NEXT:    subq $4096, %rsp # imm = 0x1000
+; CHECK-NEXT:    cmpq %rsp, %r11
+; CHECK-NEXT:    jb .LBB1_2
+; CHECK-NEXT:  .LBB1_3:
+; CHECK-NEXT:    movq %r11, %rsp
+; CHECK-NEXT:    movq $0, (%rsp)
+; CHECK-NEXT:  .LBB1_4:
+; CHECK-NEXT:    movq %rsp, %r11
+; CHECK-NEXT:    subq $73728, %r11 # imm = 0x12000
+; CHECK-NEXT:  .LBB1_5: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    subq $4096, %rsp # imm = 0x1000
+; CHECK-NEXT:    movq $0, (%rsp)
+; CHECK-NEXT:    cmpq %r11, %rsp
+; CHECK-NEXT:    jne .LBB1_5
+; CHECK-NEXT:  # %bb.6:
+; CHECK-NEXT:    movl $1, 392(%rsp)
+; CHECK-NEXT:    movl $1, 28792(%rsp)
+; CHECK-NEXT:    movl (%rsp), %eax
+; CHECK-NEXT:    movq %rbp, %rsp
+; CHECK-NEXT:    popq %rbp
+; CHECK-NEXT:    .cfi_def_cfa %rsp, 8
+; CHECK-NEXT:    retq
 
 
 
diff --git a/llvm/test/CodeGen/X86/stack-clash-large.ll b/llvm/test/CodeGen/X86/stack-clash-large.ll
--- a/llvm/test/CodeGen/X86/stack-clash-large.ll
+++ b/llvm/test/CodeGen/X86/stack-clash-large.ll
@@ -1,8 +1,45 @@
-; RUN: llc -mtriple=x86_64-linux-android < %s | FileCheck -check-prefix=CHECK-X86-64 %s 
-; RUN: llc -mtriple=i686-linux-android < %s | FileCheck -check-prefix=CHECK-X86-32 %s 
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --no_x86_scrub_sp
+; RUN: llc -mtriple=x86_64-linux-android < %s | FileCheck -check-prefix=CHECK-X86-64 %s
+; RUN: llc -mtriple=i686-linux-android < %s | FileCheck -check-prefix=CHECK-X86-32 %s
 
 define i32 @foo() local_unnamed_addr #0 {
-
+; CHECK-X86-64-LABEL: foo:
+; CHECK-X86-64:       # %bb.0:
+; CHECK-X86-64-NEXT:    movq %rsp, %r11
+; CHECK-X86-64-NEXT:    subq $69632, %r11 # imm = 0x11000
+; CHECK-X86-64-NEXT:  .LBB0_1: # =>This Inner Loop Header: Depth=1
+; CHECK-X86-64-NEXT:    subq $4096, %rsp # imm = 0x1000
+; CHECK-X86-64-NEXT:    movq $0, (%rsp)
+; CHECK-X86-64-NEXT:    cmpq %r11, %rsp
+; CHECK-X86-64-NEXT:    jne .LBB0_1
+; CHECK-X86-64-NEXT:  # %bb.2:
+; CHECK-X86-64-NEXT:    subq $2248, %rsp # imm = 0x8C8
+; CHECK-X86-64-NEXT:    .cfi_def_cfa_offset 71888
+; CHECK-X86-64-NEXT:    movl $1, 264(%rsp)
+; CHECK-X86-64-NEXT:    movl $1, 28664(%rsp)
+; CHECK-X86-64-NEXT:    movl -128(%rsp), %eax
+; CHECK-X86-64-NEXT:    addq $71880, %rsp # imm = 0x118C8
+; CHECK-X86-64-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-X86-64-NEXT:    retq
+;
+; CHECK-X86-32-LABEL: foo:
+; CHECK-X86-32:       # %bb.0:
+; CHECK-X86-32-NEXT:    movl %esp, %r11d
+; CHECK-X86-32-NEXT:    subl $69632, %r11d # imm = 0x11000
+; CHECK-X86-32-NEXT:  .LBB0_1: # =>This Inner Loop Header: Depth=1
+; CHECK-X86-32-NEXT:    subl $4096, %esp # imm = 0x1000
+; CHECK-X86-32-NEXT:    movl $0, (%esp)
+; CHECK-X86-32-NEXT:    cmpl %r11d, %esp
+; CHECK-X86-32-NEXT:    jne .LBB0_1
+; CHECK-X86-32-NEXT:  # %bb.2:
+; CHECK-X86-32-NEXT:    subl $2380, %esp # imm = 0x94C
+; CHECK-X86-32-NEXT:    .cfi_def_cfa_offset 72016
+; CHECK-X86-32-NEXT:    movl $1, 392(%esp)
+; CHECK-X86-32-NEXT:    movl $1, 28792(%esp)
+; CHECK-X86-32-NEXT:    movl (%esp), %eax
+; CHECK-X86-32-NEXT:    addl $72012, %esp # imm = 0x1194C
+; CHECK-X86-32-NEXT:    .cfi_def_cfa_offset 4
+; CHECK-X86-32-NEXT:    retl
   %a = alloca i32, i64 18000, align 16
   %b0 = getelementptr inbounds i32, i32* %a, i64 98
   %b1 = getelementptr inbounds i32, i32* %a, i64 7198
diff --git a/llvm/test/CodeGen/X86/stack-clash-medium-natural-probes-mutliple-objects.ll b/llvm/test/CodeGen/X86/stack-clash-medium-natural-probes-mutliple-objects.ll
--- a/llvm/test/CodeGen/X86/stack-clash-medium-natural-probes-mutliple-objects.ll
+++ b/llvm/test/CodeGen/X86/stack-clash-medium-natural-probes-mutliple-objects.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --no_x86_scrub_sp
 ; RUN: llc < %s | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
@@ -7,13 +7,12 @@
 define i32 @foo() local_unnamed_addr #0 {
 ; CHECK-LABEL: foo:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    subq $4096, %rsp # imm = 0x1000
-; CHECK-NEXT:    movq $0, (%rsp)
-; CHECK-NEXT:    subq $1784, %rsp # imm = 0x6F8
+; CHECK-NEXT:    movb $0, -4096(%rsp)
+; CHECK-NEXT:    subq $5880, %rsp # imm = 0x16F8
 ; CHECK-NEXT:    .cfi_def_cfa_offset 5888
-; CHECK-NEXT:    movl $1, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    movl $2, {{[0-9]+}}(%rsp)
-; CHECK-NEXT:    movl {{[0-9]+}}(%rsp), %eax
+; CHECK-NEXT:    movl $1, 3872(%rsp)
+; CHECK-NEXT:    movl $2, 672(%rsp)
+; CHECK-NEXT:    movl 1872(%rsp), %eax
 ; CHECK-NEXT:    addq $5880, %rsp # imm = 0x16F8
 ; CHECK-NEXT:    .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    retq
diff --git a/llvm/test/CodeGen/X86/stack-clash-medium-natural-probes.ll b/llvm/test/CodeGen/X86/stack-clash-medium-natural-probes.ll
--- a/llvm/test/CodeGen/X86/stack-clash-medium-natural-probes.ll
+++ b/llvm/test/CodeGen/X86/stack-clash-medium-natural-probes.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --no_x86_scrub_sp
 ; RUN: llc < %s | FileCheck %s
 
 
@@ -5,19 +6,17 @@
 target triple = "x86_64-unknown-linux-gnu"
 
 define i32 @foo() local_unnamed_addr #0 {
-
 ; CHECK-LABEL: foo:
-; CHECK:         # %bb.0:
-; CHECK-NEXT:	subq	$4096, %rsp             # imm = 0x1000
-; CHECK-NEXT:	movq	$0, (%rsp)
-; CHECK-NEXT:	subq	$3784, %rsp             # imm = 0xEC8
-; CHECK-NEXT:	.cfi_def_cfa_offset 7888
-; CHECK-NEXT:	movl	$1, 264(%rsp)
-; CHECK-NEXT:	movl	$1, 4664(%rsp)
-; CHECK-NEXT:	movl	-128(%rsp), %eax
-; CHECK-NEXT:	addq	$7880, %rsp             # imm = 0x1EC8
-; CHECK-NEXT:	.cfi_def_cfa_offset 8
-; CHECK-NEXT:	retq
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    movb $0, -4096(%rsp)
+; CHECK-NEXT:    subq $7880, %rsp # imm = 0x1EC8
+; CHECK-NEXT:    .cfi_def_cfa_offset 7888
+; CHECK-NEXT:    movl $1, 264(%rsp)
+; CHECK-NEXT:    movl $1, 4664(%rsp)
+; CHECK-NEXT:    movl -128(%rsp), %eax
+; CHECK-NEXT:    addq $7880, %rsp # imm = 0x1EC8
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:    retq
 
 
 
diff --git a/llvm/test/CodeGen/X86/stack-clash-medium.ll b/llvm/test/CodeGen/X86/stack-clash-medium.ll
--- a/llvm/test/CodeGen/X86/stack-clash-medium.ll
+++ b/llvm/test/CodeGen/X86/stack-clash-medium.ll
@@ -1,7 +1,29 @@
-; RUN: llc -mtriple=x86_64-linux-android < %s | FileCheck -check-prefix=CHECK-X86-64 %s 
-; RUN: llc -mtriple=i686-linux-android < %s | FileCheck -check-prefix=CHECK-X86-32 %s 
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --no_x86_scrub_sp
+; RUN: llc -mtriple=x86_64-linux-android < %s | FileCheck -check-prefix=CHECK-X86-64 %s
+; RUN: llc -mtriple=i686-linux-android < %s | FileCheck -check-prefix=CHECK-X86-32 %s
 
 define i32 @foo() local_unnamed_addr #0 {
+; CHECK-X86-64-LABEL: foo:
+; CHECK-X86-64:       # %bb.0:
+; CHECK-X86-64-NEXT:    movb $0, -4096(%rsp)
+; CHECK-X86-64-NEXT:    subq $7880, %rsp # imm = 0x1EC8
+; CHECK-X86-64-NEXT:    .cfi_def_cfa_offset 7888
+; CHECK-X86-64-NEXT:    movl $1, 672(%rsp)
+; CHECK-X86-64-NEXT:    movl -128(%rsp), %eax
+; CHECK-X86-64-NEXT:    addq $7880, %rsp # imm = 0x1EC8
+; CHECK-X86-64-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-X86-64-NEXT:    retq
+;
+; CHECK-X86-32-LABEL: foo:
+; CHECK-X86-32:       # %bb.0:
+; CHECK-X86-32-NEXT:    movb $0, -4096(%esp)
+; CHECK-X86-32-NEXT:    subl $8012, %esp # imm = 0x1F4C
+; CHECK-X86-32-NEXT:    .cfi_def_cfa_offset 8016
+; CHECK-X86-32-NEXT:    movl $1, 800(%esp)
+; CHECK-X86-32-NEXT:    movl (%esp), %eax
+; CHECK-X86-32-NEXT:    addl $8012, %esp # imm = 0x1F4C
+; CHECK-X86-32-NEXT:    .cfi_def_cfa_offset 4
+; CHECK-X86-32-NEXT:    retl
   %a = alloca i32, i64 2000, align 16
   %b = getelementptr inbounds i32, i32* %a, i64 200
   store volatile i32 1, i32* %b
diff --git a/llvm/test/CodeGen/X86/stack-clash-small-alloc-medium-align.ll b/llvm/test/CodeGen/X86/stack-clash-small-alloc-medium-align.ll
--- a/llvm/test/CodeGen/X86/stack-clash-small-alloc-medium-align.ll
+++ b/llvm/test/CodeGen/X86/stack-clash-small-alloc-medium-align.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --no_x86_scrub_sp
 ; RUN: llc < %s | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
@@ -6,20 +7,20 @@
 ; | case1 | alloca + align < probe_size
 define i32 @foo1(i64 %i) local_unnamed_addr #0 {
 ; CHECK-LABEL: foo1:
-; CHECK:        # %bb.0:
-; CHECK-NEXT:	pushq	%rbp
-; CHECK-NEXT:	.cfi_def_cfa_offset 16
-; CHECK-NEXT:	.cfi_offset %rbp, -16
-; CHECK-NEXT:	movq	%rsp, %rbp
-; CHECK-NEXT:	.cfi_def_cfa_register %rbp
-; CHECK-NEXT:   andq    $-64, %rsp
-; CHECK-NEXT:   subq    $832, %rsp                      # imm = 0x340
-; CHECK-NEXT:   movl    $1, (%rsp,%rdi,4)
-; CHECK-NEXT:   movl    (%rsp), %eax
-; CHECK-NEXT:   movq    %rbp, %rsp
-; CHECK-NEXT:   popq    %rbp
-; CHECK-NEXT:	.cfi_def_cfa %rsp, 8
-; CHECK-NEXT:	retq
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    pushq %rbp
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset %rbp, -16
+; CHECK-NEXT:    movq %rsp, %rbp
+; CHECK-NEXT:    .cfi_def_cfa_register %rbp
+; CHECK-NEXT:    andq $-64, %rsp
+; CHECK-NEXT:    subq $832, %rsp # imm = 0x340
+; CHECK-NEXT:    movl $1, (%rsp,%rdi,4)
+; CHECK-NEXT:    movl (%rsp), %eax
+; CHECK-NEXT:    movq %rbp, %rsp
+; CHECK-NEXT:    popq %rbp
+; CHECK-NEXT:    .cfi_def_cfa %rsp, 8
+; CHECK-NEXT:    retq
 
   %a = alloca i32, i32 200, align 64
   %b = getelementptr inbounds i32, i32* %a, i64 %i
@@ -31,24 +32,21 @@
 ; | case2 | alloca > probe_size, align > probe_size
 define i32 @foo2(i64 %i) local_unnamed_addr #0 {
 ; CHECK-LABEL: foo2:
-; CHECK:        # %bb.0:
-; CHECK-NEXT:	pushq	%rbp
-; CHECK-NEXT:	.cfi_def_cfa_offset 16
-; CHECK-NEXT:	.cfi_offset %rbp, -16
-; CHECK-NEXT:	movq	%rsp, %rbp
-; CHECK-NEXT:	.cfi_def_cfa_register %rbp
-; CHECK-NEXT:   andq    $-2048, %rsp                    # imm = 0xF800
-; CHECK-NEXT:   subq    $2048, %rsp                     # imm = 0x800
-; CHECK-NEXT:   movq    $0, (%rsp)
-; CHECK-NEXT:   subq    $4096, %rsp                     # imm = 0x1000
-; CHECK-NEXT:   movq    $0, (%rsp)
-; CHECK-NEXT:   subq    $2048, %rsp                     # imm = 0x800
-; CHECK-NEXT:   movl    $1, (%rsp,%rdi,4)
-; CHECK-NEXT:   movl    (%rsp), %eax
-; CHECK-NEXT:   movq    %rbp, %rsp
-; CHECK-NEXT:   popq    %rbp
-; CHECK-NEXT:   .cfi_def_cfa %rsp, 8
-; CHECK-NEXT:   retq
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    pushq %rbp
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset %rbp, -16
+; CHECK-NEXT:    movq %rsp, %rbp
+; CHECK-NEXT:    .cfi_def_cfa_register %rbp
+; CHECK-NEXT:    andq $-2048, %rsp # imm = 0xF800
+; CHECK-NEXT:    movb $0, -4096(%rsp)
+; CHECK-NEXT:    subq $8192, %rsp # imm = 0x2000
+; CHECK-NEXT:    movl $1, (%rsp,%rdi,4)
+; CHECK-NEXT:    movl (%rsp), %eax
+; CHECK-NEXT:    movq %rbp, %rsp
+; CHECK-NEXT:    popq %rbp
+; CHECK-NEXT:    .cfi_def_cfa %rsp, 8
+; CHECK-NEXT:    retq
 
   %a = alloca i32, i32 2000, align 2048
   %b = getelementptr inbounds i32, i32* %a, i64 %i
@@ -60,22 +58,20 @@
 ; | case3 | alloca < probe_size, align < probe_size, alloca + align > probe_size
 define i32 @foo3(i64 %i) local_unnamed_addr #0 {
 ; CHECK-LABEL: foo3:
-; CHECK:        # %bb.0:
-; CHECK-NEXT:   pushq   %rbp
-; CHECK-NEXT:   .cfi_def_cfa_offset 16
-; CHECK-NEXT:   .cfi_offset %rbp, -16
-; CHECK-NEXT:   movq    %rsp, %rbp
-; CHECK-NEXT:   .cfi_def_cfa_register %rbp
-; CHECK-NEXT:   andq    $-1024, %rsp                    # imm = 0xFC00
-; CHECK-NEXT:   subq    $3072, %rsp                     # imm = 0xC00
-; CHECK-NEXT:   movq    $0, (%rsp)
-; CHECK-NEXT:   subq    $1024, %rsp                     # imm = 0x400
-; CHECK-NEXT:   movl    $1, (%rsp,%rdi,4)
-; CHECK-NEXT:   movl    (%rsp), %eax
-; CHECK-NEXT:   movq    %rbp, %rsp
-; CHECK-NEXT:   popq    %rbp
-; CHECK-NEXT:   .cfi_def_cfa %rsp, 8
-; CHECK-NEXT:   retq
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    pushq %rbp
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset %rbp, -16
+; CHECK-NEXT:    movq %rsp, %rbp
+; CHECK-NEXT:    .cfi_def_cfa_register %rbp
+; CHECK-NEXT:    andq $-1024, %rsp # imm = 0xFC00
+; CHECK-NEXT:    subq $4096, %rsp # imm = 0x1000
+; CHECK-NEXT:    movl $1, (%rsp,%rdi,4)
+; CHECK-NEXT:    movl (%rsp), %eax
+; CHECK-NEXT:    movq %rbp, %rsp
+; CHECK-NEXT:    popq %rbp
+; CHECK-NEXT:    .cfi_def_cfa %rsp, 8
+; CHECK-NEXT:    retq
 
 
   %a = alloca i32, i32 1000, align 1024
@@ -88,39 +84,39 @@
 ; | case4 | alloca + probe_size < probe_size, followed by dynamic alloca
 define i32 @foo4(i64 %i) local_unnamed_addr #0 {
 ; CHECK-LABEL: foo4:
-; CHECK:        # %bb.0:
-; CHECK-NEXT:	pushq	%rbp
-; CHECK-NEXT:	.cfi_def_cfa_offset 16
-; CHECK-NEXT:	.cfi_offset %rbp, -16
-; CHECK-NEXT:	movq	%rsp, %rbp
-; CHECK-NEXT:	.cfi_def_cfa_register %rbp
-; CHECK-NEXT:	pushq	%rbx
-; CHECK-NEXT:	andq	$-64, %rsp
-; CHECK-NEXT:	subq	$896, %rsp                      # imm = 0x380
-; CHECK-NEXT:	movq	%rsp, %rbx
-; CHECK-NEXT:	.cfi_offset %rbx, -24
-; CHECK-NEXT:	movl	$1, (%rbx,%rdi,4)
-; CHECK-NEXT:	movl	(%rbx), %ecx
-; CHECK-NEXT:	movq	%rsp, %rax
-; CHECK-NEXT:	leaq	15(,%rcx,4), %rcx
-; CHECK-NEXT:	andq	$-16, %rcx
-; CHECK-NEXT:	subq	%rcx, %rax
-; CHECK-NEXT:	cmpq	%rsp, %rax
-; CHECK-NEXT:	jge	.LBB3_3
-; CHECK-NEXT:.LBB3_2:                                # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:	xorq	$0, (%rsp)
-; CHECK-NEXT:	subq	$4096, %rsp                     # imm = 0x1000
-; CHECK-NEXT:	cmpq	%rsp, %rax
-; CHECK-NEXT:	jl	.LBB3_2
-; CHECK-NEXT:.LBB3_3:
-; CHECK-NEXT:	andq	$-64, %rax
-; CHECK-NEXT:	movq	%rax, %rsp
-; CHECK-NEXT:	movl	(%rax), %eax
-; CHECK-NEXT:	leaq	-8(%rbp), %rsp
-; CHECK-NEXT:	popq	%rbx
-; CHECK-NEXT:	popq	%rbp
-; CHECK-NEXT:	.cfi_def_cfa %rsp, 8
-; CHECK-NEXT:	retq
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    pushq %rbp
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset %rbp, -16
+; CHECK-NEXT:    movq %rsp, %rbp
+; CHECK-NEXT:    .cfi_def_cfa_register %rbp
+; CHECK-NEXT:    pushq %rbx
+; CHECK-NEXT:    andq $-64, %rsp
+; CHECK-NEXT:    subq $896, %rsp # imm = 0x380
+; CHECK-NEXT:    movq %rsp, %rbx
+; CHECK-NEXT:    .cfi_offset %rbx, -24
+; CHECK-NEXT:    movl $1, (%rbx,%rdi,4)
+; CHECK-NEXT:    movl (%rbx), %ecx
+; CHECK-NEXT:    movq %rsp, %rax
+; CHECK-NEXT:    leaq 15(,%rcx,4), %rcx
+; CHECK-NEXT:    andq $-16, %rcx
+; CHECK-NEXT:    subq %rcx, %rax
+; CHECK-NEXT:    cmpq %rsp, %rax
+; CHECK-NEXT:    jge .LBB3_3
+; CHECK-NEXT:  .LBB3_2: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    xorq $0, (%rsp)
+; CHECK-NEXT:    subq $4096, %rsp # imm = 0x1000
+; CHECK-NEXT:    cmpq %rsp, %rax
+; CHECK-NEXT:    jl .LBB3_2
+; CHECK-NEXT:  .LBB3_3:
+; CHECK-NEXT:    andq $-64, %rax
+; CHECK-NEXT:    movq %rax, %rsp
+; CHECK-NEXT:    movl (%rax), %eax
+; CHECK-NEXT:    leaq -8(%rbp), %rsp
+; CHECK-NEXT:    popq %rbx
+; CHECK-NEXT:    popq %rbp
+; CHECK-NEXT:    .cfi_def_cfa %rsp, 8
+; CHECK-NEXT:    retq
 
   %a = alloca i32, i32 200, align 64
   %b = getelementptr inbounds i32, i32* %a, i64 %i
diff --git a/llvm/test/CodeGen/X86/stack-clash-small-large-align.ll b/llvm/test/CodeGen/X86/stack-clash-small-large-align.ll
--- a/llvm/test/CodeGen/X86/stack-clash-small-large-align.ll
+++ b/llvm/test/CodeGen/X86/stack-clash-small-large-align.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --no_x86_scrub_sp
 ; RUN: llc < %s | FileCheck %s
 
 
@@ -7,19 +8,19 @@
 define i32 @foo_noprotect() local_unnamed_addr {
 ; CHECK-LABEL: foo_noprotect:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:	pushq	%rbp
-; CHECK-NEXT:	.cfi_def_cfa_offset 16
-; CHECK-NEXT:	.cfi_offset %rbp, -16
-; CHECK-NEXT:	movq	%rsp, %rbp
-; CHECK-NEXT:	.cfi_def_cfa_register %rbp
-; CHECK-NEXT:	andq	$-65536, %rsp
-; CHECK-NEXT:	subq	$65536, %rsp
-; CHECK-NEXT:	movl	$1, 392(%rsp)
-; CHECK-NEXT:	movl	(%rsp), %eax
-; CHECK-NEXT:	movq	%rbp, %rsp
-; CHECK-NEXT:	popq	%rbp
-; CHECK-NEXT:	.cfi_def_cfa %rsp, 8
-; CHECK-NEXT:	retq
+; CHECK-NEXT:    pushq %rbp
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset %rbp, -16
+; CHECK-NEXT:    movq %rsp, %rbp
+; CHECK-NEXT:    .cfi_def_cfa_register %rbp
+; CHECK-NEXT:    andq $-65536, %rsp # imm = 0xFFFF0000
+; CHECK-NEXT:    subq $65536, %rsp # imm = 0x10000
+; CHECK-NEXT:    movl $1, 392(%rsp)
+; CHECK-NEXT:    movl (%rsp), %eax
+; CHECK-NEXT:    movq %rbp, %rsp
+; CHECK-NEXT:    popq %rbp
+; CHECK-NEXT:    .cfi_def_cfa %rsp, 8
+; CHECK-NEXT:    retq
 
 
 
@@ -33,42 +34,42 @@
 define i32 @foo_protect() local_unnamed_addr #0 {
 ; CHECK-LABEL: foo_protect:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:	pushq	%rbp
-; CHECK-NEXT:	.cfi_def_cfa_offset 16
-; CHECK-NEXT:	.cfi_offset %rbp, -16
-; CHECK-NEXT:	movq	%rsp, %rbp
-; CHECK-NEXT:	.cfi_def_cfa_register %rbp
-; CHECK-NEXT:	movq	%rsp, %r11
-; CHECK-NEXT:	andq	$-65536, %r11                   # imm = 0xFFFF0000
-; CHECK-NEXT:	cmpq	%rsp, %r11
-; CHECK-NEXT:	je	.LBB1_4
-; CHECK-NEXT:# %bb.1:
-; CHECK-NEXT:	subq	$4096, %rsp                     # imm = 0x1000
-; CHECK-NEXT:	cmpq	%rsp, %r11
-; CHECK-NEXT:	jb	.LBB1_3
-; CHECK-NEXT:.LBB1_2:                                # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:	movq	$0, (%rsp)
-; CHECK-NEXT:	subq	$4096, %rsp                     # imm = 0x1000
-; CHECK-NEXT:	cmpq	%rsp, %r11
-; CHECK-NEXT:	jb	.LBB1_2
-; CHECK-NEXT:.LBB1_3:
-; CHECK-NEXT:	movq	%r11, %rsp
-; CHECK-NEXT:	movq	$0, (%rsp)
-; CHECK-NEXT:.LBB1_4:
-; CHECK-NEXT:	movq	%rsp, %r11
-; CHECK-NEXT:	subq	$65536, %r11                    # imm = 0x10000
-; CHECK-NEXT:.LBB1_5:                                # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:	subq	$4096, %rsp                     # imm = 0x1000
-; CHECK-NEXT:	movq	$0, (%rsp)
-; CHECK-NEXT:	cmpq	%r11, %rsp
-; CHECK-NEXT:	jne	.LBB1_5
-; CHECK-NEXT:# %bb.6:
-; CHECK-NEXT:	movl	$1, 392(%rsp)
-; CHECK-NEXT:	movl	(%rsp), %eax
-; CHECK-NEXT:	movq	%rbp, %rsp
-; CHECK-NEXT:	popq	%rbp
-; CHECK-NEXT:	.cfi_def_cfa %rsp, 8
-; CHECK-NEXT:	retq
+; CHECK-NEXT:    pushq %rbp
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset %rbp, -16
+; CHECK-NEXT:    movq %rsp, %rbp
+; CHECK-NEXT:    .cfi_def_cfa_register %rbp
+; CHECK-NEXT:    movq %rsp, %r11
+; CHECK-NEXT:    andq $-65536, %r11 # imm = 0xFFFF0000
+; CHECK-NEXT:    cmpq %rsp, %r11
+; CHECK-NEXT:    je .LBB1_4
+; CHECK-NEXT:  # %bb.1:
+; CHECK-NEXT:    subq $4096, %rsp # imm = 0x1000
+; CHECK-NEXT:    cmpq %rsp, %r11
+; CHECK-NEXT:    jb .LBB1_3
+; CHECK-NEXT:  .LBB1_2: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    movq $0, (%rsp)
+; CHECK-NEXT:    subq $4096, %rsp # imm = 0x1000
+; CHECK-NEXT:    cmpq %rsp, %r11
+; CHECK-NEXT:    jb .LBB1_2
+; CHECK-NEXT:  .LBB1_3:
+; CHECK-NEXT:    movq %r11, %rsp
+; CHECK-NEXT:    movq $0, (%rsp)
+; CHECK-NEXT:  .LBB1_4:
+; CHECK-NEXT:    movq %rsp, %r11
+; CHECK-NEXT:    subq $65536, %r11 # imm = 0x10000
+; CHECK-NEXT:  .LBB1_5: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    subq $4096, %rsp # imm = 0x1000
+; CHECK-NEXT:    movq $0, (%rsp)
+; CHECK-NEXT:    cmpq %r11, %rsp
+; CHECK-NEXT:    jne .LBB1_5
+; CHECK-NEXT:  # %bb.6:
+; CHECK-NEXT:    movl $1, 392(%rsp)
+; CHECK-NEXT:    movl (%rsp), %eax
+; CHECK-NEXT:    movq %rbp, %rsp
+; CHECK-NEXT:    popq %rbp
+; CHECK-NEXT:    .cfi_def_cfa %rsp, 8
+; CHECK-NEXT:    retq
 
 
 
diff --git a/llvm/test/CodeGen/X86/stack-clash-small.ll b/llvm/test/CodeGen/X86/stack-clash-small.ll
--- a/llvm/test/CodeGen/X86/stack-clash-small.ll
+++ b/llvm/test/CodeGen/X86/stack-clash-small.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --no_x86_scrub_sp
 ; RUN: llc < %s | FileCheck %s
 
 
@@ -7,13 +8,13 @@
 define i32 @foo() local_unnamed_addr #0 {
 ; CHECK-LABEL: foo:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:  subq	$280, %rsp # imm = 0x118
-; CHECK-NEXT:  .cfi_def_cfa_offset 288
-; CHECK-NEXT:  movl	$1, 264(%rsp)
-; CHECK-NEXT:  movl	-128(%rsp), %eax
-; CHECK-NEXT:  addq	$280, %rsp # imm = 0x118
-; CHECK-NEXT:  .cfi_def_cfa_offset 8
-; CHECK-NEXT:  retq
+; CHECK-NEXT:    subq $280, %rsp # imm = 0x118
+; CHECK-NEXT:    .cfi_def_cfa_offset 288
+; CHECK-NEXT:    movl $1, 264(%rsp)
+; CHECK-NEXT:    movl -128(%rsp), %eax
+; CHECK-NEXT:    addq $280, %rsp # imm = 0x118
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:    retq
 
   %a = alloca i32, i64 100, align 16
   %b = getelementptr inbounds i32, i32* %a, i64 98
diff --git a/llvm/test/CodeGen/X86/stack-clash-unknown-call.ll b/llvm/test/CodeGen/X86/stack-clash-unknown-call.ll
--- a/llvm/test/CodeGen/X86/stack-clash-unknown-call.ll
+++ b/llvm/test/CodeGen/X86/stack-clash-unknown-call.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --no_x86_scrub_sp
 ; RUN: llc < %s | FileCheck %s
 
 
@@ -7,21 +8,19 @@
 declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1 immarg);
 
 define void @foo() local_unnamed_addr #0 {
-
-;CHECK-LABEL: foo:
-;CHECK:         # %bb.0:
-;CHECK-NEXT:	subq	$4096, %rsp # imm = 0x1000
+; CHECK-LABEL: foo:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    movb $0, -4096(%rsp)
+; CHECK-NEXT:    subq $8008, %rsp # imm = 0x1F48
+; CHECK-NEXT:    .cfi_def_cfa_offset 8016
+; CHECK-NEXT:    movq %rsp, %rdi
+; CHECK-NEXT:    movl $8000, %edx # imm = 0x1F40
+; CHECK-NEXT:    xorl %esi, %esi
+; CHECK-NEXT:    callq memset@PLT
+; CHECK-NEXT:    addq $8008, %rsp # imm = 0x1F48
+; CHECK-NEXT:    .cfi_def_cfa_offset 8
+; CHECK-NEXT:    retq
 ; it's important that we don't use the call as a probe here
-;CHECK-NEXT:	movq	$0, (%rsp)
-;CHECK-NEXT:	subq	$3912, %rsp # imm = 0xF48
-;CHECK-NEXT:	.cfi_def_cfa_offset 8016
-;CHECK-NEXT:	movq	%rsp, %rdi
-;CHECK-NEXT:	movl	$8000, %edx # imm = 0x1F40
-;CHECK-NEXT:	xorl	%esi, %esi
-;CHECK-NEXT:	callq	memset
-;CHECK-NEXT:	addq	$8008, %rsp # imm = 0x1F48
-;CHECK-NEXT:	.cfi_def_cfa_offset 8
-;CHECK-NEXT:	retq
 
   %a = alloca i8, i64 8000, align 16
   call void @llvm.memset.p0i8.i64(i8* align 16 %a, i8 0, i64 8000, i1 false)