diff --git a/llvm/test/CodeGen/X86/shift-avx2-crash.ll b/llvm/test/CodeGen/X86/shift-avx2-crash.ll
index b23d6e3359ee..868c013bf2b0 100644
--- a/llvm/test/CodeGen/X86/shift-avx2-crash.ll
+++ b/llvm/test/CodeGen/X86/shift-avx2-crash.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc < %s  -mcpu=core-avx2 > /dev/null
 ; This test crashed on variable shift creation on AVX2
 
@@ -29,7 +30,7 @@ if_then18.i:
   br label %__fast_idiv___UM_vyuunu.exit
 
 
-__fast_idiv___UM_vyuunu.exit:                   
+__fast_idiv___UM_vyuunu.exit:
   %calltmp_to_float = uitofp <8 x i32> %bitop22_to_uint32.i to <8 x float>
   %ptrcast = bitcast float* %RET to <8 x float>*
   store <8 x float> %calltmp_to_float, <8 x float>* %ptrcast, align 4
diff --git a/llvm/test/CodeGen/X86/shift-coalesce.ll b/llvm/test/CodeGen/X86/shift-coalesce.ll
index 7f2c3b5a0752..53becca69ef3 100644
--- a/llvm/test/CodeGen/X86/shift-coalesce.ll
+++ b/llvm/test/CodeGen/X86/shift-coalesce.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc < %s -mtriple=i686-- -x86-asm-syntax=intel | \
 ; RUN:   grep "shld.*cl"
 ; RUN: llc < %s -mtriple=i686-- -x86-asm-syntax=intel | \
diff --git a/llvm/test/CodeGen/X86/shift-combine-crash.ll b/llvm/test/CodeGen/X86/shift-combine-crash.ll
index a69a907d41b0..5db2ac978042 100644
--- a/llvm/test/CodeGen/X86/shift-combine-crash.ll
+++ b/llvm/test/CodeGen/X86/shift-combine-crash.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7 > /dev/null
 
 ; Verify that DAGCombiner doesn't crash with an assertion failure in the
diff --git a/llvm/test/CodeGen/X86/shift-i128.ll b/llvm/test/CodeGen/X86/shift-i128.ll
index 9c69aab5b3d1..9f9d75cb36ca 100644
--- a/llvm/test/CodeGen/X86/shift-i128.ll
+++ b/llvm/test/CodeGen/X86/shift-i128.ll
@@ -1,11 +1,142 @@
-; RUN: llc < %s -mtriple=i686--
-; RUN: llc < %s -mtriple=x86_64--
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=i686-- | FileCheck %s --check-prefixes=CHECK,X86
+; RUN: llc < %s -mtriple=x86_64-- | FileCheck %s --check-prefixes=CHECK,X64
 
 ;
 ; Scalars
 ;
 
 define void @test_lshr_i128(i128 %x, i128 %a, i128* nocapture %r) nounwind {
+; X86-LABEL: test_lshr_i128:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %ebp
+; X86-NEXT:    pushl %ebx
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movb {{[0-9]+}}(%esp), %al
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    movl %ebp, %esi
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    shrdl %cl, %edi, %esi
+; X86-NEXT:    shrl %cl, %edx
+; X86-NEXT:    shrl %cl, %edi
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:    testb $32, %al
+; X86-NEXT:    jne .LBB0_1
+; X86-NEXT:  # %bb.2: # %entry
+; X86-NEXT:    movl %edx, (%esp) # 4-byte Spill
+; X86-NEXT:    jmp .LBB0_3
+; X86-NEXT:  .LBB0_1:
+; X86-NEXT:    movl %edi, %esi
+; X86-NEXT:    movl $0, (%esp) # 4-byte Folded Spill
+; X86-NEXT:    xorl %edi, %edi
+; X86-NEXT:  .LBB0_3: # %entry
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %eax, %edx
+; X86-NEXT:    subb $64, %dl
+; X86-NEXT:    jb .LBB0_5
+; X86-NEXT:  # %bb.4: # %entry
+; X86-NEXT:    xorl %edi, %edi
+; X86-NEXT:  .LBB0_5: # %entry
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    negb %dl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    shldl %cl, %ebp, %edi
+; X86-NEXT:    movl %ebp, %esi
+; X86-NEXT:    shll %cl, %esi
+; X86-NEXT:    testb $32, %dl
+; X86-NEXT:    movl %esi, %ebx
+; X86-NEXT:    jne .LBB0_7
+; X86-NEXT:  # %bb.6: # %entry
+; X86-NEXT:    movl %edi, %ebx
+; X86-NEXT:  .LBB0_7: # %entry
+; X86-NEXT:    movb %al, %ah
+; X86-NEXT:    addb $-64, %ah
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movb %ah, %cl
+; X86-NEXT:    shrl %cl, %edi
+; X86-NEXT:    testb $32, %ah
+; X86-NEXT:    movl $0, %ecx
+; X86-NEXT:    jne .LBB0_9
+; X86-NEXT:  # %bb.8: # %entry
+; X86-NEXT:    movl %edi, %ecx
+; X86-NEXT:  .LBB0_9: # %entry
+; X86-NEXT:    cmpb $64, %al
+; X86-NEXT:    jb .LBB0_10
+; X86-NEXT:  # %bb.11: # %entry
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:    jmp .LBB0_12
+; X86-NEXT:  .LBB0_10:
+; X86-NEXT:    movl (%esp), %ecx # 4-byte Reload
+; X86-NEXT:    orl %ebx, %ecx
+; X86-NEXT:  .LBB0_12: # %entry
+; X86-NEXT:    movl %ecx, (%esp) # 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    testb $32, %dl
+; X86-NEXT:    jne .LBB0_14
+; X86-NEXT:  # %bb.13: # %entry
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB0_14: # %entry
+; X86-NEXT:    movl %ebx, %edx
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    shrdl %cl, %esi, %edx
+; X86-NEXT:    testb $32, %al
+; X86-NEXT:    jne .LBB0_16
+; X86-NEXT:  # %bb.15: # %entry
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB0_16: # %entry
+; X86-NEXT:    movb %ah, %cl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    shrdl %cl, %edx, %ebp
+; X86-NEXT:    testb $32, %ah
+; X86-NEXT:    jne .LBB0_18
+; X86-NEXT:  # %bb.17: # %entry
+; X86-NEXT:    movl %ebp, %edi
+; X86-NEXT:  .LBB0_18: # %entry
+; X86-NEXT:    cmpb $64, %al
+; X86-NEXT:    jae .LBB0_20
+; X86-NEXT:  # %bb.19:
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X86-NEXT:    orl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X86-NEXT:  .LBB0_20: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    testb %al, %al
+; X86-NEXT:    je .LBB0_22
+; X86-NEXT:  # %bb.21: # %entry
+; X86-NEXT:    movl %edi, %ebx
+; X86-NEXT:    movl (%esp), %esi # 4-byte Reload
+; X86-NEXT:  .LBB0_22: # %entry
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT:    movl %eax, 12(%ecx)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT:    movl %eax, 8(%ecx)
+; X86-NEXT:    movl %esi, 4(%ecx)
+; X86-NEXT:    movl %ebx, (%ecx)
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    popl %ebx
+; X86-NEXT:    popl %ebp
+; X86-NEXT:    retl
+;
+; X64-LABEL: test_lshr_i128:
+; X64:       # %bb.0: # %entry
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    shrdq %cl, %rsi, %rdi
+; X64-NEXT:    shrq %cl, %rsi
+; X64-NEXT:    xorl %eax, %eax
+; X64-NEXT:    testb $64, %cl
+; X64-NEXT:    cmovneq %rsi, %rdi
+; X64-NEXT:    cmoveq %rsi, %rax
+; X64-NEXT:    movq %rax, 8(%r8)
+; X64-NEXT:    movq %rdi, (%r8)
+; X64-NEXT:    retq
 entry:
 	%0 = lshr i128 %x, %a
 	store i128 %0, i128* %r, align 16
@@ -13,6 +144,141 @@ entry:
 }
 
 define void @test_ashr_i128(i128 %x, i128 %a, i128* nocapture %r) nounwind {
+; X86-LABEL: test_ashr_i128:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %ebp
+; X86-NEXT:    pushl %ebx
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $24, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movb {{[0-9]+}}(%esp), %al
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    movl %ebp, %esi
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    shrdl %cl, %ebx, %esi
+; X86-NEXT:    shrl %cl, %edx
+; X86-NEXT:    movl %ebx, %edi
+; X86-NEXT:    sarl %cl, %edi
+; X86-NEXT:    sarl $31, %ebx
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:    testb $32, %al
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    jne .LBB1_1
+; X86-NEXT:  # %bb.2: # %entry
+; X86-NEXT:    movl %edx, (%esp) # 4-byte Spill
+; X86-NEXT:    jmp .LBB1_3
+; X86-NEXT:  .LBB1_1:
+; X86-NEXT:    movl %edi, %esi
+; X86-NEXT:    movl $0, (%esp) # 4-byte Folded Spill
+; X86-NEXT:    movl %ebx, %edi
+; X86-NEXT:  .LBB1_3: # %entry
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %eax, %edx
+; X86-NEXT:    subb $64, %dl
+; X86-NEXT:    jb .LBB1_5
+; X86-NEXT:  # %bb.4: # %entry
+; X86-NEXT:    movl %ebx, %edi
+; X86-NEXT:  .LBB1_5: # %entry
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    negb %dl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    shldl %cl, %ebp, %edi
+; X86-NEXT:    movl %ebp, %esi
+; X86-NEXT:    shll %cl, %esi
+; X86-NEXT:    testb $32, %dl
+; X86-NEXT:    movl %esi, %ecx
+; X86-NEXT:    jne .LBB1_7
+; X86-NEXT:  # %bb.6: # %entry
+; X86-NEXT:    movl %edi, %ecx
+; X86-NEXT:  .LBB1_7: # %entry
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movb %al, %ah
+; X86-NEXT:    addb $-64, %ah
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movb %ah, %cl
+; X86-NEXT:    sarl %cl, %edi
+; X86-NEXT:    testb $32, %ah
+; X86-NEXT:    movl %ebx, %ecx
+; X86-NEXT:    jne .LBB1_9
+; X86-NEXT:  # %bb.8: # %entry
+; X86-NEXT:    movl %edi, %ecx
+; X86-NEXT:  .LBB1_9: # %entry
+; X86-NEXT:    cmpb $64, %al
+; X86-NEXT:    jb .LBB1_10
+; X86-NEXT:  # %bb.11: # %entry
+; X86-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    jmp .LBB1_12
+; X86-NEXT:  .LBB1_10:
+; X86-NEXT:    movl (%esp), %ecx # 4-byte Reload
+; X86-NEXT:    orl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X86-NEXT:  .LBB1_12: # %entry
+; X86-NEXT:    movl %ecx, (%esp) # 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    testb $32, %dl
+; X86-NEXT:    jne .LBB1_14
+; X86-NEXT:  # %bb.13: # %entry
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB1_14: # %entry
+; X86-NEXT:    movl %ebx, %edx
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    shrdl %cl, %esi, %edx
+; X86-NEXT:    testb $32, %al
+; X86-NEXT:    jne .LBB1_16
+; X86-NEXT:  # %bb.15: # %entry
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB1_16: # %entry
+; X86-NEXT:    movb %ah, %cl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    shrdl %cl, %edx, %ebp
+; X86-NEXT:    testb $32, %ah
+; X86-NEXT:    jne .LBB1_18
+; X86-NEXT:  # %bb.17: # %entry
+; X86-NEXT:    movl %ebp, %edi
+; X86-NEXT:  .LBB1_18: # %entry
+; X86-NEXT:    cmpb $64, %al
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    jae .LBB1_20
+; X86-NEXT:  # %bb.19:
+; X86-NEXT:    orl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X86-NEXT:    movl %ecx, %edi
+; X86-NEXT:  .LBB1_20: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    testb %al, %al
+; X86-NEXT:    je .LBB1_22
+; X86-NEXT:  # %bb.21: # %entry
+; X86-NEXT:    movl %edi, %ebx
+; X86-NEXT:    movl (%esp), %esi # 4-byte Reload
+; X86-NEXT:  .LBB1_22: # %entry
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT:    movl %eax, 12(%ecx)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT:    movl %eax, 8(%ecx)
+; X86-NEXT:    movl %esi, 4(%ecx)
+; X86-NEXT:    movl %ebx, (%ecx)
+; X86-NEXT:    addl $24, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    popl %ebx
+; X86-NEXT:    popl %ebp
+; X86-NEXT:    retl
+;
+; X64-LABEL: test_ashr_i128:
+; X64:       # %bb.0: # %entry
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    shrdq %cl, %rsi, %rdi
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    sarq %cl, %rax
+; X64-NEXT:    sarq $63, %rsi
+; X64-NEXT:    testb $64, %cl
+; X64-NEXT:    cmovneq %rax, %rdi
+; X64-NEXT:    cmoveq %rax, %rsi
+; X64-NEXT:    movq %rsi, 8(%r8)
+; X64-NEXT:    movq %rdi, (%r8)
+; X64-NEXT:    retq
 entry:
 	%0 = ashr i128 %x, %a
 	store i128 %0, i128* %r, align 16
@@ -20,6 +286,138 @@ entry:
 }
 
 define void @test_shl_i128(i128 %x, i128 %a, i128* nocapture %r) nounwind {
+; X86-LABEL: test_shl_i128:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %ebp
+; X86-NEXT:    pushl %ebx
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movb {{[0-9]+}}(%esp), %al
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl %ecx, %ebx
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    shll %cl, %ebx
+; X86-NEXT:    movl %ebp, %esi
+; X86-NEXT:    shll %cl, %esi
+; X86-NEXT:    movl %edi, %edx
+; X86-NEXT:    shldl %cl, %ebp, %edx
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:    testb $32, %al
+; X86-NEXT:    jne .LBB2_1
+; X86-NEXT:  # %bb.2: # %entry
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %ebx, (%esp) # 4-byte Spill
+; X86-NEXT:    jmp .LBB2_3
+; X86-NEXT:  .LBB2_1:
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl $0, (%esp) # 4-byte Folded Spill
+; X86-NEXT:    xorl %esi, %esi
+; X86-NEXT:  .LBB2_3: # %entry
+; X86-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %eax, %edx
+; X86-NEXT:    subb $64, %dl
+; X86-NEXT:    jb .LBB2_5
+; X86-NEXT:  # %bb.4: # %entry
+; X86-NEXT:    xorl %esi, %esi
+; X86-NEXT:  .LBB2_5: # %entry
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    negb %dl
+; X86-NEXT:    movl %edi, %esi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    shrl %cl, %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    shrdl %cl, %edi, %ebx
+; X86-NEXT:    testb $32, %dl
+; X86-NEXT:    movl %esi, %ebp
+; X86-NEXT:    jne .LBB2_7
+; X86-NEXT:  # %bb.6: # %entry
+; X86-NEXT:    movl %ebx, %ebp
+; X86-NEXT:  .LBB2_7: # %entry
+; X86-NEXT:    movb %al, %ah
+; X86-NEXT:    addb $-64, %ah
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    movb %ah, %cl
+; X86-NEXT:    shll %cl, %ebx
+; X86-NEXT:    testb $32, %ah
+; X86-NEXT:    movl $0, %ecx
+; X86-NEXT:    jne .LBB2_9
+; X86-NEXT:  # %bb.8: # %entry
+; X86-NEXT:    movl %ebx, %ecx
+; X86-NEXT:  .LBB2_9: # %entry
+; X86-NEXT:    cmpb $64, %al
+; X86-NEXT:    jb .LBB2_10
+; X86-NEXT:  # %bb.11: # %entry
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:    jmp .LBB2_12
+; X86-NEXT:  .LBB2_10:
+; X86-NEXT:    movl (%esp), %ecx # 4-byte Reload
+; X86-NEXT:    orl %ebp, %ecx
+; X86-NEXT:  .LBB2_12: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    movl %ecx, (%esp) # 4-byte Spill
+; X86-NEXT:    testb $32, %dl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    jne .LBB2_14
+; X86-NEXT:  # %bb.13: # %entry
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB2_14: # %entry
+; X86-NEXT:    movl %edx, %esi
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    shldl %cl, %ebp, %esi
+; X86-NEXT:    testb $32, %al
+; X86-NEXT:    jne .LBB2_16
+; X86-NEXT:  # %bb.15: # %entry
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB2_16: # %entry
+; X86-NEXT:    movb %ah, %cl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    shldl %cl, %esi, %edi
+; X86-NEXT:    testb $32, %ah
+; X86-NEXT:    jne .LBB2_18
+; X86-NEXT:  # %bb.17: # %entry
+; X86-NEXT:    movl %edi, %ebx
+; X86-NEXT:  .LBB2_18: # %entry
+; X86-NEXT:    cmpb $64, %al
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X86-NEXT:    jae .LBB2_20
+; X86-NEXT:  # %bb.19:
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X86-NEXT:    orl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X86-NEXT:  .LBB2_20: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    testb %al, %al
+; X86-NEXT:    je .LBB2_22
+; X86-NEXT:  # %bb.21: # %entry
+; X86-NEXT:    movl %ebx, %edx
+; X86-NEXT:    movl (%esp), %ebp # 4-byte Reload
+; X86-NEXT:  .LBB2_22: # %entry
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT:    movl %eax, 4(%ecx)
+; X86-NEXT:    movl %esi, (%ecx)
+; X86-NEXT:    movl %edx, 12(%ecx)
+; X86-NEXT:    movl %ebp, 8(%ecx)
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    popl %ebx
+; X86-NEXT:    popl %ebp
+; X86-NEXT:    retl
+;
+; X64-LABEL: test_shl_i128:
+; X64:       # %bb.0: # %entry
+; X64-NEXT:    movq %rdx, %rcx
+; X64-NEXT:    shldq %cl, %rdi, %rsi
+; X64-NEXT:    shlq %cl, %rdi
+; X64-NEXT:    xorl %eax, %eax
+; X64-NEXT:    testb $64, %cl
+; X64-NEXT:    cmovneq %rdi, %rsi
+; X64-NEXT:    cmoveq %rdi, %rax
+; X64-NEXT:    movq %rsi, 8(%r8)
+; X64-NEXT:    movq %rax, (%r8)
+; X64-NEXT:    retq
 entry:
 	%0 = shl i128 %x, %a
 	store i128 %0, i128* %r, align 16
@@ -27,6 +425,9 @@ entry:
 }
 
 define void @test_lshr_i128_outofrange(i128 %x, i128* nocapture %r) nounwind {
+; CHECK-LABEL: test_lshr_i128_outofrange:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    ret{{[l|q]}}
 entry:
 	%0 = lshr i128 %x, -1
 	store i128 %0, i128* %r, align 16
@@ -34,6 +435,9 @@ entry:
 }
 
 define void @test_ashr_i128_outofrange(i128 %x, i128* nocapture %r) nounwind {
+; CHECK-LABEL: test_ashr_i128_outofrange:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    ret{{[l|q]}}
 entry:
 	%0 = ashr i128 %x, -1
 	store i128 %0, i128* %r, align 16
@@ -41,6 +445,9 @@ entry:
 }
 
 define void @test_shl_i128_outofrange(i128 %x, i128* nocapture %r) nounwind {
+; CHECK-LABEL: test_shl_i128_outofrange:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    ret{{[l|q]}}
 entry:
 	%0 = shl i128 %x, -1
 	store i128 %0, i128* %r, align 16
@@ -52,6 +459,291 @@ entry:
 ;
 
 define void @test_lshr_v2i128(<2 x i128> %x, <2 x i128> %a, <2 x i128>* nocapture %r) nounwind {
+; X86-LABEL: test_lshr_v2i128:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %ebp
+; X86-NEXT:    pushl %ebx
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $68, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl %ebx, %edi
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    shrl %cl, %edi
+; X86-NEXT:    movl %esi, %ebp
+; X86-NEXT:    shrl %cl, %ebp
+; X86-NEXT:    shrdl %cl, %esi, %edx
+; X86-NEXT:    testb $32, %al
+; X86-NEXT:    jne .LBB6_1
+; X86-NEXT:  # %bb.2: # %entry
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    jmp .LBB6_3
+; X86-NEXT:  .LBB6_1:
+; X86-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:  .LBB6_3: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    shrdl %cl, %ebx, %esi
+; X86-NEXT:    testb $32, %al
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    jne .LBB6_5
+; X86-NEXT:  # %bb.4: # %entry
+; X86-NEXT:    movl %esi, %edi
+; X86-NEXT:  .LBB6_5: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    shrl %cl, %ebx
+; X86-NEXT:    shrl %cl, %ebp
+; X86-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    subl $64, %ecx
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    sbbl $0, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    sbbl $0, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    sbbl $0, %ecx
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X86-NEXT:    testb $32, %dl
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:    movl $0, %ecx
+; X86-NEXT:    jne .LBB6_7
+; X86-NEXT:  # %bb.6: # %entry
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %ebx, %ecx
+; X86-NEXT:  .LBB6_7: # %entry
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    shrdl %cl, %ebp, %esi
+; X86-NEXT:    testb $32, %dl
+; X86-NEXT:    jne .LBB6_9
+; X86-NEXT:  # %bb.8: # %entry
+; X86-NEXT:    movl %esi, %ebx
+; X86-NEXT:  .LBB6_9: # %entry
+; X86-NEXT:    movl %edi, %esi
+; X86-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl %ecx, %ebp
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    shrl %cl, %ebp
+; X86-NEXT:    testb $32, %cl
+; X86-NEXT:    movl $0, %ecx
+; X86-NEXT:    jne .LBB6_11
+; X86-NEXT:  # %bb.10: # %entry
+; X86-NEXT:    movl %ebp, %ecx
+; X86-NEXT:  .LBB6_11: # %entry
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movb $64, %cl
+; X86-NEXT:    subb %dl, %cl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    shldl %cl, %ebx, %edi
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %ebx, %edi
+; X86-NEXT:    shll %cl, %edi
+; X86-NEXT:    testb $32, %cl
+; X86-NEXT:    movb $64, %bl
+; X86-NEXT:    jne .LBB6_12
+; X86-NEXT:  # %bb.13: # %entry
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    jmp .LBB6_14
+; X86-NEXT:  .LBB6_12:
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:  .LBB6_14: # %entry
+; X86-NEXT:    movl %esi, %edi
+; X86-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    shrdl %cl, %ebp, %esi
+; X86-NEXT:    testb $32, %dl
+; X86-NEXT:    jne .LBB6_16
+; X86-NEXT:  # %bb.15: # %entry
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB6_16: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subb %al, %bl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    movl %ebx, %ecx
+; X86-NEXT:    shll %cl, %ebp
+; X86-NEXT:    testb $32, %bl
+; X86-NEXT:    movl $0, %ecx
+; X86-NEXT:    jne .LBB6_18
+; X86-NEXT:  # %bb.17: # %entry
+; X86-NEXT:    movl %ebp, %ecx
+; X86-NEXT:  .LBB6_18: # %entry
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    subl $64, %ecx
+; X86-NEXT:    sbbl $0, %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    sbbl $0, %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    sbbl $0, %esi
+; X86-NEXT:    setae %bh
+; X86-NEXT:    jb .LBB6_20
+; X86-NEXT:  # %bb.19: # %entry
+; X86-NEXT:    xorl %edi, %edi
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:  .LBB6_20: # %entry
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    shrdl %cl, %esi, %edi
+; X86-NEXT:    shrl %cl, %esi
+; X86-NEXT:    testb $32, %cl
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    jne .LBB6_22
+; X86-NEXT:  # %bb.21: # %entry
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB6_22: # %entry
+; X86-NEXT:    testb %bh, %bh
+; X86-NEXT:    jne .LBB6_24
+; X86-NEXT:  # %bb.23:
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X86-NEXT:    orl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB6_24: # %entry
+; X86-NEXT:    testb $32, %cl
+; X86-NEXT:    movl $0, %ecx
+; X86-NEXT:    jne .LBB6_26
+; X86-NEXT:  # %bb.25: # %entry
+; X86-NEXT:    movl %esi, %ecx
+; X86-NEXT:  .LBB6_26: # %entry
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %ebx, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    shldl %cl, %edi, %esi
+; X86-NEXT:    testb $32, %bl
+; X86-NEXT:    jne .LBB6_28
+; X86-NEXT:  # %bb.27: # %entry
+; X86-NEXT:    movl %esi, %ebp
+; X86-NEXT:  .LBB6_28: # %entry
+; X86-NEXT:    testb %bh, %bh
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    jne .LBB6_30
+; X86-NEXT:  # %bb.29:
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    orl %ebp, %ecx
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB6_30: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    cmpb $0, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Reload
+; X86-NEXT:    jne .LBB6_32
+; X86-NEXT:  # %bb.31: # %entry
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:  .LBB6_32: # %entry
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    shrdl %cl, %ebp, %edi
+; X86-NEXT:    movl %edi, %ebp
+; X86-NEXT:    testb $32, %cl
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X86-NEXT:    je .LBB6_33
+; X86-NEXT:  # %bb.34: # %entry
+; X86-NEXT:    cmpb $0, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Reload
+; X86-NEXT:    jne .LBB6_35
+; X86-NEXT:  .LBB6_36: # %entry
+; X86-NEXT:    cmpb $0, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Reload
+; X86-NEXT:    je .LBB6_38
+; X86-NEXT:  .LBB6_37:
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    orl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB6_38: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    orl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    orl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    orl %ecx, %edx
+; X86-NEXT:    je .LBB6_40
+; X86-NEXT:  # %bb.39: # %entry
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X86-NEXT:  .LBB6_40: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    orl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    orl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    orl %edx, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    je .LBB6_42
+; X86-NEXT:  # %bb.41: # %entry
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X86-NEXT:  .LBB6_42: # %entry
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT:    movl %edx, 28(%ecx)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT:    movl %edx, 24(%ecx)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT:    movl %edx, 12(%ecx)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT:    movl %edx, 8(%ecx)
+; X86-NEXT:    movl %esi, 20(%ecx)
+; X86-NEXT:    movl %eax, 16(%ecx)
+; X86-NEXT:    movl %ebx, 4(%ecx)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT:    movl %eax, (%ecx)
+; X86-NEXT:    addl $68, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    popl %ebx
+; X86-NEXT:    popl %ebp
+; X86-NEXT:    retl
+; X86-NEXT:  .LBB6_33: # %entry
+; X86-NEXT:    movl %ebp, %edi
+; X86-NEXT:    cmpb $0, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Reload
+; X86-NEXT:    je .LBB6_36
+; X86-NEXT:  .LBB6_35:
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    orl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X86-NEXT:    movl %ecx, %edi
+; X86-NEXT:    cmpb $0, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Reload
+; X86-NEXT:    jne .LBB6_37
+; X86-NEXT:    jmp .LBB6_38
+;
+; X64-LABEL: test_lshr_v2i128:
+; X64:       # %bb.0: # %entry
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r10
+; X64-NEXT:    movb {{[0-9]+}}(%rsp), %r9b
+; X64-NEXT:    movl %r9d, %ecx
+; X64-NEXT:    shrdq %cl, %rax, %rdx
+; X64-NEXT:    movl %r8d, %ecx
+; X64-NEXT:    shrdq %cl, %rsi, %rdi
+; X64-NEXT:    shrq %cl, %rsi
+; X64-NEXT:    xorl %r11d, %r11d
+; X64-NEXT:    testb $64, %r8b
+; X64-NEXT:    cmovneq %rsi, %rdi
+; X64-NEXT:    cmovneq %r11, %rsi
+; X64-NEXT:    movl %r9d, %ecx
+; X64-NEXT:    shrq %cl, %rax
+; X64-NEXT:    testb $64, %r9b
+; X64-NEXT:    cmovneq %rax, %rdx
+; X64-NEXT:    cmovneq %r11, %rax
+; X64-NEXT:    movq %rax, 24(%r10)
+; X64-NEXT:    movq %rdx, 16(%r10)
+; X64-NEXT:    movq %rsi, 8(%r10)
+; X64-NEXT:    movq %rdi, (%r10)
+; X64-NEXT:    retq
 entry:
 	%0 = lshr <2 x i128> %x, %a
 	store <2 x i128> %0, <2 x i128>* %r, align 16
@@ -59,6 +751,299 @@ entry:
 }
 
 define void @test_ashr_v2i128(<2 x i128> %x, <2 x i128> %a, <2 x i128>* nocapture %r) nounwind {
+; X86-LABEL: test_ashr_v2i128:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %ebp
+; X86-NEXT:    pushl %ebx
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $80, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl %ebp, %ebx
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    sarl %cl, %ebx
+; X86-NEXT:    movl %esi, %edi
+; X86-NEXT:    shrl %cl, %edi
+; X86-NEXT:    shrdl %cl, %esi, %edx
+; X86-NEXT:    sarl $31, %ebp
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:    testb $32, %al
+; X86-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    jne .LBB7_1
+; X86-NEXT:  # %bb.2: # %entry
+; X86-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    jmp .LBB7_3
+; X86-NEXT:  .LBB7_1:
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB7_3: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    shrdl %cl, %edx, %edi
+; X86-NEXT:    testb $32, %al
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    jne .LBB7_5
+; X86-NEXT:  # %bb.4: # %entry
+; X86-NEXT:    movl %edi, %ebx
+; X86-NEXT:  .LBB7_5: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl %ecx, %ebp
+; X86-NEXT:    movl %ecx, %edi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    sarl %cl, %edi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    shrl %cl, %esi
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    sarl $31, %ebp
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    subl $64, %ecx
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    sbbl $0, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    sbbl $0, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    sbbl $0, %ecx
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X86-NEXT:    testb $32, %dl
+; X86-NEXT:    movl $0, %esi
+; X86-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %ebp, %ecx
+; X86-NEXT:    jne .LBB7_7
+; X86-NEXT:  # %bb.6: # %entry
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X86-NEXT:    movl %edi, %ecx
+; X86-NEXT:  .LBB7_7: # %entry
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    shrdl %cl, %ebp, %esi
+; X86-NEXT:    testb $32, %dl
+; X86-NEXT:    jne .LBB7_9
+; X86-NEXT:  # %bb.8: # %entry
+; X86-NEXT:    movl %esi, %edi
+; X86-NEXT:  .LBB7_9: # %entry
+; X86-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl %ecx, %esi
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    sarl %cl, %esi
+; X86-NEXT:    testb $32, %cl
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    jne .LBB7_11
+; X86-NEXT:  # %bb.10: # %entry
+; X86-NEXT:    movl %esi, %ecx
+; X86-NEXT:  .LBB7_11: # %entry
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    movb $64, %cl
+; X86-NEXT:    subb %dl, %cl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    movl %ebx, %ebp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    shldl %cl, %ebx, %ebp
+; X86-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %ebx, %ebp
+; X86-NEXT:    shll %cl, %ebp
+; X86-NEXT:    testb $32, %cl
+; X86-NEXT:    movb $64, %bl
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    je .LBB7_13
+; X86-NEXT:  # %bb.12:
+; X86-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    xorl %ebp, %ebp
+; X86-NEXT:  .LBB7_13: # %entry
+; X86-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    shrdl %cl, %edi, %esi
+; X86-NEXT:    testb $32, %dl
+; X86-NEXT:    jne .LBB7_15
+; X86-NEXT:  # %bb.14: # %entry
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB7_15: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subb %al, %bl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    movl %ebx, %ecx
+; X86-NEXT:    shll %cl, %ebp
+; X86-NEXT:    testb $32, %bl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    jne .LBB7_17
+; X86-NEXT:  # %bb.16: # %entry
+; X86-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB7_17: # %entry
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    subl $64, %ecx
+; X86-NEXT:    sbbl $0, %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    sbbl $0, %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    sbbl $0, %esi
+; X86-NEXT:    setae %bh
+; X86-NEXT:    jb .LBB7_19
+; X86-NEXT:  # %bb.18: # %entry
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB7_19: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    shrdl %cl, %edi, %esi
+; X86-NEXT:    sarl %cl, %edi
+; X86-NEXT:    testb $32, %cl
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    je .LBB7_20
+; X86-NEXT:  # %bb.21: # %entry
+; X86-NEXT:    testb %bh, %bh
+; X86-NEXT:    je .LBB7_22
+; X86-NEXT:  .LBB7_23: # %entry
+; X86-NEXT:    testb $32, %cl
+; X86-NEXT:    jne .LBB7_25
+; X86-NEXT:  .LBB7_24: # %entry
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB7_25: # %entry
+; X86-NEXT:    movl %ebx, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    shldl %cl, %esi, %edi
+; X86-NEXT:    testb $32, %bl
+; X86-NEXT:    jne .LBB7_27
+; X86-NEXT:  # %bb.26: # %entry
+; X86-NEXT:    movl %edi, %ebp
+; X86-NEXT:  .LBB7_27: # %entry
+; X86-NEXT:    testb %bh, %bh
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X86-NEXT:    jne .LBB7_29
+; X86-NEXT:  # %bb.28:
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X86-NEXT:    orl %ebp, %ebx
+; X86-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB7_29: # %entry
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X86-NEXT:    cmpb $0, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Reload
+; X86-NEXT:    jne .LBB7_31
+; X86-NEXT:  # %bb.30: # %entry
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB7_31: # %entry
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    shrdl %cl, %ebp, %ebx
+; X86-NEXT:    testb $32, %cl
+; X86-NEXT:    jne .LBB7_33
+; X86-NEXT:  # %bb.32: # %entry
+; X86-NEXT:    movl %ebx, %esi
+; X86-NEXT:  .LBB7_33: # %entry
+; X86-NEXT:    cmpb $0, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Reload
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X86-NEXT:    je .LBB7_35
+; X86-NEXT:  # %bb.34:
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    orl %ebx, %ecx
+; X86-NEXT:    movl %ecx, %esi
+; X86-NEXT:  .LBB7_35: # %entry
+; X86-NEXT:    cmpb $0, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Reload
+; X86-NEXT:    je .LBB7_37
+; X86-NEXT:  # %bb.36:
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    orl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB7_37: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    orl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    orl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    orl %ecx, %edx
+; X86-NEXT:    je .LBB7_39
+; X86-NEXT:  # %bb.38: # %entry
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB7_39: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    orl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    orl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    orl %edx, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    je .LBB7_41
+; X86-NEXT:  # %bb.40: # %entry
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X86-NEXT:  .LBB7_41: # %entry
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT:    movl %edx, 28(%ecx)
+; X86-NEXT:    movl %edi, 24(%ecx)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT:    movl %edx, 12(%ecx)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT:    movl %edx, 8(%ecx)
+; X86-NEXT:    movl %esi, 20(%ecx)
+; X86-NEXT:    movl %eax, 16(%ecx)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT:    movl %eax, 4(%ecx)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT:    movl %eax, (%ecx)
+; X86-NEXT:    addl $80, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    popl %ebx
+; X86-NEXT:    popl %ebp
+; X86-NEXT:    retl
+; X86-NEXT:  .LBB7_20: # %entry
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    testb %bh, %bh
+; X86-NEXT:    jne .LBB7_23
+; X86-NEXT:  .LBB7_22:
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X86-NEXT:    orl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    testb $32, %cl
+; X86-NEXT:    je .LBB7_24
+; X86-NEXT:    jmp .LBB7_25
+;
+; X64-LABEL: test_ashr_v2i128:
+; X64:       # %bb.0: # %entry
+; X64-NEXT:    movq %rcx, %r11
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r10
+; X64-NEXT:    movb {{[0-9]+}}(%rsp), %r9b
+; X64-NEXT:    movl %r9d, %ecx
+; X64-NEXT:    shrdq %cl, %r11, %rdx
+; X64-NEXT:    movl %r8d, %ecx
+; X64-NEXT:    shrdq %cl, %rsi, %rdi
+; X64-NEXT:    movq %rsi, %rax
+; X64-NEXT:    sarq %cl, %rax
+; X64-NEXT:    sarq $63, %rsi
+; X64-NEXT:    testb $64, %r8b
+; X64-NEXT:    cmovneq %rax, %rdi
+; X64-NEXT:    cmoveq %rax, %rsi
+; X64-NEXT:    movq %r11, %rax
+; X64-NEXT:    movl %r9d, %ecx
+; X64-NEXT:    sarq %cl, %rax
+; X64-NEXT:    sarq $63, %r11
+; X64-NEXT:    testb $64, %r9b
+; X64-NEXT:    cmovneq %rax, %rdx
+; X64-NEXT:    cmoveq %rax, %r11
+; X64-NEXT:    movq %r11, 24(%r10)
+; X64-NEXT:    movq %rdx, 16(%r10)
+; X64-NEXT:    movq %rsi, 8(%r10)
+; X64-NEXT:    movq %rdi, (%r10)
+; X64-NEXT:    retq
 entry:
 	%0 = ashr <2 x i128> %x, %a
 	store <2 x i128> %0, <2 x i128>* %r, align 16
@@ -66,6 +1051,311 @@ entry:
 }
 
 define void @test_shl_v2i128(<2 x i128> %x, <2 x i128> %a, <2 x i128>* nocapture %r) nounwind {
+; X86-LABEL: test_shl_v2i128:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %ebp
+; X86-NEXT:    pushl %ebx
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $72, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    movl %ebx, %ecx
+; X86-NEXT:    shll %cl, %ebp
+; X86-NEXT:    movl %eax, %esi
+; X86-NEXT:    shll %cl, %esi
+; X86-NEXT:    movl %edx, %eax
+; X86-NEXT:    subl $64, %eax
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    sbbl $0, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    sbbl $0, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    sbbl $0, %eax
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:    testb $32, %bl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl $0, %eax
+; X86-NEXT:    movl $0, %ecx
+; X86-NEXT:    jne .LBB8_2
+; X86-NEXT:  # %bb.1: # %entry
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    movl %ebp, %ecx
+; X86-NEXT:  .LBB8_2: # %entry
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %edi, %eax
+; X86-NEXT:    movl %ebx, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    shldl %cl, %edi, %eax
+; X86-NEXT:    testb $32, %bl
+; X86-NEXT:    jne .LBB8_4
+; X86-NEXT:  # %bb.3: # %entry
+; X86-NEXT:    movl %eax, %esi
+; X86-NEXT:  .LBB8_4: # %entry
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movb $64, %cl
+; X86-NEXT:    subb %bl, %cl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, %esi
+; X86-NEXT:    shrl %cl, %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    shrdl %cl, %edi, %eax
+; X86-NEXT:    testb $32, %cl
+; X86-NEXT:    jne .LBB8_5
+; X86-NEXT:  # %bb.6: # %entry
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    jmp .LBB8_7
+; X86-NEXT:  .LBB8_5:
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:  .LBB8_7: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %ebx, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    shldl %cl, %esi, %edi
+; X86-NEXT:    testb $32, %bl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    jne .LBB8_9
+; X86-NEXT:  # %bb.8: # %entry
+; X86-NEXT:    movl %edi, %ebp
+; X86-NEXT:  .LBB8_9: # %entry
+; X86-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %ecx, %ebp
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    shll %cl, %ebp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl %ecx, %esi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    shll %cl, %esi
+; X86-NEXT:    testb $32, %dl
+; X86-NEXT:    movl $0, %edi
+; X86-NEXT:    movl $0, %ecx
+; X86-NEXT:    jne .LBB8_11
+; X86-NEXT:  # %bb.10: # %entry
+; X86-NEXT:    movl %esi, %edi
+; X86-NEXT:    movl %ebp, %ecx
+; X86-NEXT:  .LBB8_11: # %entry
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    shldl %cl, %ebx, %edi
+; X86-NEXT:    testb $32, %dl
+; X86-NEXT:    jne .LBB8_13
+; X86-NEXT:  # %bb.12: # %entry
+; X86-NEXT:    movl %edi, %ebp
+; X86-NEXT:  .LBB8_13: # %entry
+; X86-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movb $64, %cl
+; X86-NEXT:    subb %dl, %cl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    shrl %cl, %ebx
+; X86-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movb %cl, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
+; X86-NEXT:    testb $32, %cl
+; X86-NEXT:    movl $0, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    jne .LBB8_15
+; X86-NEXT:  # %bb.14: # %entry
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:  .LBB8_15: # %entry
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl %edx, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    shldl %cl, %ebp, %edi
+; X86-NEXT:    testb $32, %dl
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    jne .LBB8_17
+; X86-NEXT:  # %bb.16: # %entry
+; X86-NEXT:    movl %edi, %esi
+; X86-NEXT:  .LBB8_17: # %entry
+; X86-NEXT:    orl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:    movl %ebx, %eax
+; X86-NEXT:    subl $64, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    sbbl $0, %ecx
+; X86-NEXT:    movl %ebp, %ecx
+; X86-NEXT:    sbbl $0, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    sbbl $0, %ecx
+; X86-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X86-NEXT:    jb .LBB8_19
+; X86-NEXT:  # %bb.18: # %entry
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:  .LBB8_19: # %entry
+; X86-NEXT:    jb .LBB8_21
+; X86-NEXT:  # %bb.20: # %entry
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:  .LBB8_21: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT:    movl %ebp, %ebx
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    shll %cl, %ebx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    shldl %cl, %ebp, %edi
+; X86-NEXT:    testb $32, %cl
+; X86-NEXT:    movl %ebx, %ecx
+; X86-NEXT:    jne .LBB8_23
+; X86-NEXT:  # %bb.22: # %entry
+; X86-NEXT:    movl %edi, %ecx
+; X86-NEXT:  .LBB8_23: # %entry
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl %ecx, %edi
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    shll %cl, %edi
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    testb $32, %al
+; X86-NEXT:    movl $0, %edi
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X86-NEXT:    jne .LBB8_25
+; X86-NEXT:  # %bb.24: # %entry
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X86-NEXT:  .LBB8_25: # %entry
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    cmpb $0, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Reload
+; X86-NEXT:    jne .LBB8_27
+; X86-NEXT:  # %bb.26: # %entry
+; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB8_27: # %entry
+; X86-NEXT:    movl %eax, %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    shldl %cl, %edi, %esi
+; X86-NEXT:    testb $32, %al
+; X86-NEXT:    jne .LBB8_29
+; X86-NEXT:  # %bb.28: # %entry
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB8_29: # %entry
+; X86-NEXT:    cmpb $0, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Reload
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movb {{[-0-9]+}}(%e{{[sb]}}p), %al # 1-byte Reload
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    jne .LBB8_30
+; X86-NEXT:  # %bb.31: # %entry
+; X86-NEXT:    testb %al, %al
+; X86-NEXT:    je .LBB8_32
+; X86-NEXT:  .LBB8_33: # %entry
+; X86-NEXT:    testb $32, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Reload
+; X86-NEXT:    jne .LBB8_35
+; X86-NEXT:  .LBB8_34: # %entry
+; X86-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB8_35: # %entry
+; X86-NEXT:    movb {{[-0-9]+}}(%e{{[sb]}}p), %cl # 1-byte Reload
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    shrdl %cl, %ebx, %esi
+; X86-NEXT:    testb $32, %cl
+; X86-NEXT:    jne .LBB8_37
+; X86-NEXT:  # %bb.36: # %entry
+; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB8_37: # %entry
+; X86-NEXT:    testb %al, %al
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    jne .LBB8_38
+; X86-NEXT:  # %bb.39: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X86-NEXT:    testb %al, %al
+; X86-NEXT:    jne .LBB8_41
+; X86-NEXT:    jmp .LBB8_42
+; X86-NEXT:  .LBB8_30:
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    orl %ebp, %ecx
+; X86-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    testb %al, %al
+; X86-NEXT:    jne .LBB8_33
+; X86-NEXT:  .LBB8_32: # %entry
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT:    testb $32, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Reload
+; X86-NEXT:    je .LBB8_34
+; X86-NEXT:    jmp .LBB8_35
+; X86-NEXT:  .LBB8_38:
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X86-NEXT:    orl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    testb %al, %al
+; X86-NEXT:    je .LBB8_42
+; X86-NEXT:  .LBB8_41:
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT:    orl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB8_42: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    orl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    orl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    orl %eax, %edx
+; X86-NEXT:    je .LBB8_44
+; X86-NEXT:  # %bb.43: # %entry
+; X86-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT:  .LBB8_44: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    orl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    orl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT:    orl %edx, %ebx
+; X86-NEXT:    je .LBB8_46
+; X86-NEXT:  # %bb.45: # %entry
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X86-NEXT:  .LBB8_46: # %entry
+; X86-NEXT:    movl %esi, 20(%eax)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT:    movl %edx, 16(%eax)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT:    movl %edx, 4(%eax)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT:    movl %edx, (%eax)
+; X86-NEXT:    movl %edi, 28(%eax)
+; X86-NEXT:    movl %ecx, 24(%eax)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    movl %ecx, 12(%eax)
+; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT:    movl %ecx, 8(%eax)
+; X86-NEXT:    addl $72, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    popl %ebx
+; X86-NEXT:    popl %ebp
+; X86-NEXT:    retl
+;
+; X64-LABEL: test_shl_v2i128:
+; X64:       # %bb.0: # %entry
+; X64-NEXT:    movq %rcx, %rax
+; X64-NEXT:    movq {{[0-9]+}}(%rsp), %r10
+; X64-NEXT:    movb {{[0-9]+}}(%rsp), %r9b
+; X64-NEXT:    movl %r9d, %ecx
+; X64-NEXT:    shldq %cl, %rdx, %rax
+; X64-NEXT:    movl %r8d, %ecx
+; X64-NEXT:    shldq %cl, %rdi, %rsi
+; X64-NEXT:    shlq %cl, %rdi
+; X64-NEXT:    xorl %r11d, %r11d
+; X64-NEXT:    testb $64, %r8b
+; X64-NEXT:    cmovneq %rdi, %rsi
+; X64-NEXT:    cmovneq %r11, %rdi
+; X64-NEXT:    movl %r9d, %ecx
+; X64-NEXT:    shlq %cl, %rdx
+; X64-NEXT:    testb $64, %r9b
+; X64-NEXT:    cmovneq %rdx, %rax
+; X64-NEXT:    cmovneq %r11, %rdx
+; X64-NEXT:    movq %rax, 24(%r10)
+; X64-NEXT:    movq %rdx, 16(%r10)
+; X64-NEXT:    movq %rsi, 8(%r10)
+; X64-NEXT:    movq %rdi, (%r10)
+; X64-NEXT:    retq
 entry:
 	%0 = shl <2 x i128> %x, %a
 	store <2 x i128> %0, <2 x i128>* %r, align 16
@@ -73,6 +1363,9 @@ entry:
 }
 
 define void @test_lshr_v2i128_outofrange(<2 x i128> %x, <2 x i128>* nocapture %r) nounwind {
+; CHECK-LABEL: test_lshr_v2i128_outofrange:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    ret{{[l|q]}}
 entry:
 	%0 = lshr <2 x i128> %x, <i128 -1, i128 -1>
 	store <2 x i128> %0, <2 x i128>* %r, align 16
@@ -80,6 +1373,9 @@ entry:
 }
 
 define void @test_ashr_v2i128_outofrange(<2 x i128> %x, <2 x i128>* nocapture %r) nounwind {
+; CHECK-LABEL: test_ashr_v2i128_outofrange:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    ret{{[l|q]}}
 entry:
 	%0 = ashr <2 x i128> %x, <i128 -1, i128 -1>
 	store <2 x i128> %0, <2 x i128>* %r, align 16
@@ -87,6 +1383,9 @@ entry:
 }
 
 define void @test_shl_v2i128_outofrange(<2 x i128> %x, <2 x i128>* nocapture %r) nounwind {
+; CHECK-LABEL: test_shl_v2i128_outofrange:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    ret{{[l|q]}}
 entry:
 	%0 = shl <2 x i128> %x, <i128 -1, i128 -1>
 	store <2 x i128> %0, <2 x i128>* %r, align 16
@@ -94,6 +1393,25 @@ entry:
 }
 
 define void @test_lshr_v2i128_outofrange_sum(<2 x i128> %x, <2 x i128>* nocapture %r) nounwind {
+; X86-LABEL: test_lshr_v2i128_outofrange_sum:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl $0, 28(%eax)
+; X86-NEXT:    movl $0, 24(%eax)
+; X86-NEXT:    movl $0, 20(%eax)
+; X86-NEXT:    movl $0, 16(%eax)
+; X86-NEXT:    movl $0, 12(%eax)
+; X86-NEXT:    movl $0, 8(%eax)
+; X86-NEXT:    movl $0, 4(%eax)
+; X86-NEXT:    movl $0, (%eax)
+; X86-NEXT:    retl
+;
+; X64-LABEL: test_lshr_v2i128_outofrange_sum:
+; X64:       # %bb.0: # %entry
+; X64-NEXT:    xorps %xmm0, %xmm0
+; X64-NEXT:    movaps %xmm0, 16(%r8)
+; X64-NEXT:    movaps %xmm0, (%r8)
+; X64-NEXT:    retq
 entry:
 	%0 = lshr <2 x i128> %x, <i128 -1, i128 -1>
 	%1 = lshr <2 x i128> %0, <i128  1, i128  1>
@@ -102,6 +1420,25 @@ entry:
 }
 
 define void @test_ashr_v2i128_outofrange_sum(<2 x i128> %x, <2 x i128>* nocapture %r) nounwind {
+; X86-LABEL: test_ashr_v2i128_outofrange_sum:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl $0, 28(%eax)
+; X86-NEXT:    movl $0, 24(%eax)
+; X86-NEXT:    movl $0, 20(%eax)
+; X86-NEXT:    movl $0, 16(%eax)
+; X86-NEXT:    movl $0, 12(%eax)
+; X86-NEXT:    movl $0, 8(%eax)
+; X86-NEXT:    movl $0, 4(%eax)
+; X86-NEXT:    movl $0, (%eax)
+; X86-NEXT:    retl
+;
+; X64-LABEL: test_ashr_v2i128_outofrange_sum:
+; X64:       # %bb.0: # %entry
+; X64-NEXT:    xorps %xmm0, %xmm0
+; X64-NEXT:    movaps %xmm0, 16(%r8)
+; X64-NEXT:    movaps %xmm0, (%r8)
+; X64-NEXT:    retq
 entry:
 	%0 = ashr <2 x i128> %x, <i128 -1, i128 -1>
 	%1 = ashr <2 x i128> %0, <i128  1, i128  1>
@@ -110,6 +1447,25 @@ entry:
 }
 
 define void @test_shl_v2i128_outofrange_sum(<2 x i128> %x, <2 x i128>* nocapture %r) nounwind {
+; X86-LABEL: test_shl_v2i128_outofrange_sum:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl $0, 28(%eax)
+; X86-NEXT:    movl $0, 24(%eax)
+; X86-NEXT:    movl $0, 20(%eax)
+; X86-NEXT:    movl $0, 16(%eax)
+; X86-NEXT:    movl $0, 12(%eax)
+; X86-NEXT:    movl $0, 8(%eax)
+; X86-NEXT:    movl $0, 4(%eax)
+; X86-NEXT:    movl $0, (%eax)
+; X86-NEXT:    retl
+;
+; X64-LABEL: test_shl_v2i128_outofrange_sum:
+; X64:       # %bb.0: # %entry
+; X64-NEXT:    xorps %xmm0, %xmm0
+; X64-NEXT:    movaps %xmm0, 16(%r8)
+; X64-NEXT:    movaps %xmm0, (%r8)
+; X64-NEXT:    retq
 entry:
 	%0 = shl <2 x i128> %x, <i128 -1, i128 -1>
 	%1 = shl <2 x i128> %0, <i128  1, i128  1>
@@ -122,6 +1478,36 @@ entry:
 ;
 
 define <2 x i256> @shl_sext_shl_outofrange(<2 x i128> %a0) {
+; X86-LABEL: shl_sext_shl_outofrange:
+; X86:       # %bb.0:
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl $0, 60(%eax)
+; X86-NEXT:    movl $0, 56(%eax)
+; X86-NEXT:    movl $0, 52(%eax)
+; X86-NEXT:    movl $0, 48(%eax)
+; X86-NEXT:    movl $0, 44(%eax)
+; X86-NEXT:    movl $0, 40(%eax)
+; X86-NEXT:    movl $0, 36(%eax)
+; X86-NEXT:    movl $0, 32(%eax)
+; X86-NEXT:    movl $0, 28(%eax)
+; X86-NEXT:    movl $0, 24(%eax)
+; X86-NEXT:    movl $0, 20(%eax)
+; X86-NEXT:    movl $0, 16(%eax)
+; X86-NEXT:    movl $0, 12(%eax)
+; X86-NEXT:    movl $0, 8(%eax)
+; X86-NEXT:    movl $0, 4(%eax)
+; X86-NEXT:    movl $0, (%eax)
+; X86-NEXT:    retl $4
+;
+; X64-LABEL: shl_sext_shl_outofrange:
+; X64:       # %bb.0:
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    xorps %xmm0, %xmm0
+; X64-NEXT:    movaps %xmm0, 48(%rdi)
+; X64-NEXT:    movaps %xmm0, 32(%rdi)
+; X64-NEXT:    movaps %xmm0, 16(%rdi)
+; X64-NEXT:    movaps %xmm0, (%rdi)
+; X64-NEXT:    retq
   %1 = shl <2 x i128> %a0, <i128 -1, i128 -1>
   %2 = sext <2 x i128> %1 to <2 x i256>
   %3 = shl <2 x i256> %2, <i256 128, i256 128>
@@ -129,6 +1515,36 @@ define <2 x i256> @shl_sext_shl_outofrange(<2 x i128> %a0) {
 }
 
 define <2 x i256> @shl_zext_shl_outofrange(<2 x i128> %a0) {
+; X86-LABEL: shl_zext_shl_outofrange:
+; X86:       # %bb.0:
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl $0, 60(%eax)
+; X86-NEXT:    movl $0, 56(%eax)
+; X86-NEXT:    movl $0, 52(%eax)
+; X86-NEXT:    movl $0, 48(%eax)
+; X86-NEXT:    movl $0, 44(%eax)
+; X86-NEXT:    movl $0, 40(%eax)
+; X86-NEXT:    movl $0, 36(%eax)
+; X86-NEXT:    movl $0, 32(%eax)
+; X86-NEXT:    movl $0, 28(%eax)
+; X86-NEXT:    movl $0, 24(%eax)
+; X86-NEXT:    movl $0, 20(%eax)
+; X86-NEXT:    movl $0, 16(%eax)
+; X86-NEXT:    movl $0, 12(%eax)
+; X86-NEXT:    movl $0, 8(%eax)
+; X86-NEXT:    movl $0, 4(%eax)
+; X86-NEXT:    movl $0, (%eax)
+; X86-NEXT:    retl $4
+;
+; X64-LABEL: shl_zext_shl_outofrange:
+; X64:       # %bb.0:
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    xorps %xmm0, %xmm0
+; X64-NEXT:    movaps %xmm0, 48(%rdi)
+; X64-NEXT:    movaps %xmm0, 32(%rdi)
+; X64-NEXT:    movaps %xmm0, 16(%rdi)
+; X64-NEXT:    movaps %xmm0, (%rdi)
+; X64-NEXT:    retq
   %1 = shl <2 x i128> %a0, <i128 -1, i128 -1>
   %2 = zext <2 x i128> %1 to <2 x i256>
   %3 = shl <2 x i256> %2, <i256 128, i256 128>
@@ -136,6 +1552,36 @@ define <2 x i256> @shl_zext_shl_outofrange(<2 x i128> %a0) {
 }
 
 define <2 x i256> @shl_zext_lshr_outofrange(<2 x i128> %a0) {
+; X86-LABEL: shl_zext_lshr_outofrange:
+; X86:       # %bb.0:
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl $0, 60(%eax)
+; X86-NEXT:    movl $0, 56(%eax)
+; X86-NEXT:    movl $0, 52(%eax)
+; X86-NEXT:    movl $0, 48(%eax)
+; X86-NEXT:    movl $0, 44(%eax)
+; X86-NEXT:    movl $0, 40(%eax)
+; X86-NEXT:    movl $0, 36(%eax)
+; X86-NEXT:    movl $0, 32(%eax)
+; X86-NEXT:    movl $0, 28(%eax)
+; X86-NEXT:    movl $0, 24(%eax)
+; X86-NEXT:    movl $0, 20(%eax)
+; X86-NEXT:    movl $0, 16(%eax)
+; X86-NEXT:    movl $0, 12(%eax)
+; X86-NEXT:    movl $0, 8(%eax)
+; X86-NEXT:    movl $0, 4(%eax)
+; X86-NEXT:    movl $0, (%eax)
+; X86-NEXT:    retl $4
+;
+; X64-LABEL: shl_zext_lshr_outofrange:
+; X64:       # %bb.0:
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    xorps %xmm0, %xmm0
+; X64-NEXT:    movaps %xmm0, 48(%rdi)
+; X64-NEXT:    movaps %xmm0, 32(%rdi)
+; X64-NEXT:    movaps %xmm0, 16(%rdi)
+; X64-NEXT:    movaps %xmm0, (%rdi)
+; X64-NEXT:    retq
   %1 = lshr <2 x i128> %a0, <i128 -1, i128 -1>
   %2 = zext <2 x i128> %1 to <2 x i256>
   %3 = shl <2 x i256> %2, <i256 128, i256 128>
@@ -143,6 +1589,36 @@ define <2 x i256> @shl_zext_lshr_outofrange(<2 x i128> %a0) {
 }
 
 define i128 @lshr_shl_mask(i128 %a0) {
+; X86-LABEL: lshr_shl_mask:
+; X86:       # %bb.0:
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    .cfi_def_cfa_offset 8
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    .cfi_def_cfa_offset 12
+; X86-NEXT:    .cfi_offset %esi, -12
+; X86-NEXT:    .cfi_offset %edi, -8
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    movl $2147483647, %edi # imm = 0x7FFFFFFF
+; X86-NEXT:    andl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 12(%eax)
+; X86-NEXT:    movl %esi, 8(%eax)
+; X86-NEXT:    movl %edx, 4(%eax)
+; X86-NEXT:    movl %ecx, (%eax)
+; X86-NEXT:    popl %esi
+; X86-NEXT:    .cfi_def_cfa_offset 8
+; X86-NEXT:    popl %edi
+; X86-NEXT:    .cfi_def_cfa_offset 4
+; X86-NEXT:    retl $4
+;
+; X64-LABEL: lshr_shl_mask:
+; X64:       # %bb.0:
+; X64-NEXT:    movq %rdi, %rax
+; X64-NEXT:    movabsq $9223372036854775807, %rdx # imm = 0x7FFFFFFFFFFFFFFF
+; X64-NEXT:    andq %rsi, %rdx
+; X64-NEXT:    retq
   %1 = shl i128 %a0, 1
   %2 = lshr i128 %1, 1
   ret i128 %2
diff --git a/llvm/test/CodeGen/X86/shift-one.ll b/llvm/test/CodeGen/X86/shift-one.ll
index d961eb1451b9..c4c50afb2634 100644
--- a/llvm/test/CodeGen/X86/shift-one.ll
+++ b/llvm/test/CodeGen/X86/shift-one.ll
@@ -1,8 +1,14 @@
-; RUN: llc < %s -mtriple=i686-- | not grep leal
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=i686-- | FileCheck %s
 
 @x = external global i32                ; <i32*> [#uses=1]
 
 define i32 @test() {
+; CHECK-LABEL: test:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    movl x, %eax
+; CHECK-NEXT:    addl %eax, %eax
+; CHECK-NEXT:    retl
         %tmp.0 = load i32, i32* @x           ; <i32> [#uses=1]
         %tmp.1 = shl i32 %tmp.0, 1              ; <i32> [#uses=1]
         ret i32 %tmp.1
diff --git a/llvm/test/CodeGen/X86/shift-parts.ll b/llvm/test/CodeGen/X86/shift-parts.ll
index 678866979814..2dc35f6bfef0 100644
--- a/llvm/test/CodeGen/X86/shift-parts.ll
+++ b/llvm/test/CodeGen/X86/shift-parts.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=x86_64-- < %s | FileCheck %s
 ; PR4736
 
@@ -5,9 +6,25 @@
 
 @g_144 = external global %0, align 8              ; <%0*> [#uses=1]
 
-; CHECK: shrdq
-
 define i32 @int87(i32 %uint64p_8, i1 %cond) nounwind {
+; CHECK-LABEL: int87:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    movq g_144+{{.*}}(%rip), %rax
+; CHECK-NEXT:    movq g_144+{{.*}}(%rip), %rdx
+; CHECK-NEXT:    movzbl %sil, %ecx
+; CHECK-NEXT:    shll $6, %ecx
+; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:  .LBB0_1: # %for.cond
+; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    movq %rdx, %rsi
+; CHECK-NEXT:    shrdq %cl, %rax, %rsi
+; CHECK-NEXT:    testb $64, %cl
+; CHECK-NEXT:    cmovneq %rax, %rsi
+; CHECK-NEXT:    orl $0, %esi
+; CHECK-NEXT:    je .LBB0_1
+; CHECK-NEXT:  # %bb.2: # %if.then
+; CHECK-NEXT:    movl $1, %eax
+; CHECK-NEXT:    retq
 entry:
   %srcval4 = load i320, i320* bitcast (%0* @g_144 to i320*), align 8 ; <i320> [#uses=1]
   br label %for.cond