[x86, MemCmpExpansion] allow 2 pairs of loads per block (PR33325)

[spatel]

Summary

This is the last step needed to fix PR33325:
https://bugs.llvm.org/show_bug.cgi?id=33325

We're trading branch and compares for loads and logic ops. This makes the code smaller and hopefully faster in most cases.

The 24-byte case shows an interesting construct: we load the trailing scalar elements into vector registers and generate the same pcmpeq+movmsk code that we expected for a pair of full vector elements (see the 32- and 64-byte tests)

[courbet]

Great! One minor comment.

test/Transforms/ExpandMemCmp/X86/memcmp.ll

3 ↗

(On Diff #128553)

We're losing coverage for the case where we're testing for equality with only one load per block. What about adding a line with:
-memcmp-num-loads-per-block=1 to keep these alive ?

[spatel]

test/Transforms/ExpandMemCmp/X86/memcmp.ll

3 ↗

(On Diff #128553)

Yes, that sounds good. Update coming soon...

[spatel]

Patch updated:
Add a RUN to the IR test for expansion so we see exactly how the IR differs between the old and new settings. I just did that for x64 because x32 would be the same in most cases.

llvm/trunk/lib/CodeGen/ExpandMemCmp.cpp

Value *MemCmpExpansion::getMemCmpOneBlock() {
   Value *ZextUGT = Builder.CreateZExt(CmpUGT, Builder.getInt32Ty());
   Value *ZextULT = Builder.CreateZExt(CmpULT, Builder.getInt32Ty());
   return Builder.CreateSub(ZextUGT, ZextULT);
 }
 
 // This function expands the memcmp call into an inline expansion and returns
 // the memcmp result.
 Value *MemCmpExpansion::getMemCmpExpansion() {
-  // A memcmp with zero-comparison with only one block of load and compare does
-  // not need to set up any extra blocks. This case could be handled in the DAG,
-  // but since we have all of the machinery to flexibly expand any memcpy here,
-  // we choose to handle this case too to avoid fragmented lowering.
-  if ((!IsUsedForZeroCmp && NumLoadsPerBlockForZeroCmp != 1) ||
-      getNumBlocks() != 1) {
+  // Create the basic block framework for a multi-block expansion.
+  if (getNumBlocks() != 1) {
     BasicBlock *StartBlock = CI->getParent();
     EndBlock = StartBlock->splitBasicBlock(CI, "endblock");
     setupEndBlockPHINodes();
     createResultBlock();
 
     // If return value of memcmp is not used in a zero equality, we need to
     // calculate which source was larger. The calculation requires the
     // two loaded source values of each load compare block.

llvm/trunk/lib/Target/X86/X86ISelLowering.h

public:
 
     bool convertSetCCLogicToBitwiseLogic(EVT VT) const override {
       return VT.isScalarInteger();
     }
 
     /// Vector-sized comparisons are fast using PCMPEQ + PMOVMSK or PTEST.
     MVT hasFastEqualityCompare(unsigned NumBits) const override;
 
+    /// Allow multiple load pairs per block for smaller and faster code.
+    unsigned getMemcmpEqZeroLoadsPerBlock() const override {
+      return 2;
+    }
+
     /// Return the value type to use for ISD::SETCC.
     EVT getSetCCResultType(const DataLayout &DL, LLVMContext &Context,
                            EVT VT) const override;
 
     /// Determine which of the bits specified in Mask are known to be either
     /// zero or one and return them in the KnownZero/KnownOne bitsets.
     void computeKnownBitsForTargetNode(const SDValue Op,
                                        KnownBits &Known,

llvm/trunk/test/CodeGen/X86/memcmp-optsize.ll

 }
 
 define i1 @length3_eq(i8* %X, i8* %Y) nounwind optsize {
 ; X86-LABEL: length3_eq:
 ; X86:       # %bb.0:
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movzwl (%ecx), %edx
-; X86-NEXT:    cmpw (%eax), %dx
-; X86-NEXT:    jne .LBB5_2
-; X86-NEXT:  # %bb.1: # %loadbb1
-; X86-NEXT:    movb 2(%ecx), %dl
-; X86-NEXT:    xorl %ecx, %ecx
-; X86-NEXT:    cmpb 2(%eax), %dl
-; X86-NEXT:    je .LBB5_3
-; X86-NEXT:  .LBB5_2: # %res_block
-; X86-NEXT:    xorl %ecx, %ecx
-; X86-NEXT:    incl %ecx
-; X86-NEXT:  .LBB5_3: # %endblock
-; X86-NEXT:    testl %ecx, %ecx
+; X86-NEXT:    xorw (%eax), %dx
+; X86-NEXT:    movb 2(%ecx), %cl
+; X86-NEXT:    xorb 2(%eax), %cl
+; X86-NEXT:    movzbl %cl, %eax
+; X86-NEXT:    orw %dx, %ax
 ; X86-NEXT:    setne %al
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: length3_eq:
 ; X64:       # %bb.0:
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    cmpw (%rsi), %ax
-; X64-NEXT:    jne .LBB5_2
-; X64-NEXT:  # %bb.1: # %loadbb1
+; X64-NEXT:    xorw (%rsi), %ax
 ; X64-NEXT:    movb 2(%rdi), %cl
-; X64-NEXT:    xorl %eax, %eax
-; X64-NEXT:    cmpb 2(%rsi), %cl
-; X64-NEXT:    je .LBB5_3
-; X64-NEXT:  .LBB5_2: # %res_block
-; X64-NEXT:    movl $1, %eax
-; X64-NEXT:  .LBB5_3: # %endblock
-; X64-NEXT:    testl %eax, %eax
+; X64-NEXT:    xorb 2(%rsi), %cl
+; X64-NEXT:    movzbl %cl, %ecx
+; X64-NEXT:    orw %ax, %cx
 ; X64-NEXT:    setne %al
 ; X64-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 3) nounwind
   %c = icmp ne i32 %m, 0
   ret i1 %c
 }
 
 define i32 @length4(i8* %X, i8* %Y) nounwind optsize {

 }
 
 define i1 @length5_eq(i8* %X, i8* %Y) nounwind optsize {
 ; X86-LABEL: length5_eq:
 ; X86:       # %bb.0:
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movl (%ecx), %edx
-; X86-NEXT:    cmpl (%eax), %edx
-; X86-NEXT:    jne .LBB10_2
-; X86-NEXT:  # %bb.1: # %loadbb1
-; X86-NEXT:    movb 4(%ecx), %dl
-; X86-NEXT:    xorl %ecx, %ecx
-; X86-NEXT:    cmpb 4(%eax), %dl
-; X86-NEXT:    je .LBB10_3
-; X86-NEXT:  .LBB10_2: # %res_block
-; X86-NEXT:    xorl %ecx, %ecx
-; X86-NEXT:    incl %ecx
-; X86-NEXT:  .LBB10_3: # %endblock
-; X86-NEXT:    testl %ecx, %ecx
+; X86-NEXT:    xorl (%eax), %edx
+; X86-NEXT:    movb 4(%ecx), %cl
+; X86-NEXT:    xorb 4(%eax), %cl
+; X86-NEXT:    movzbl %cl, %eax
+; X86-NEXT:    orl %edx, %eax
 ; X86-NEXT:    setne %al
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: length5_eq:
 ; X64:       # %bb.0:
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    cmpl (%rsi), %eax
-; X64-NEXT:    jne .LBB10_2
-; X64-NEXT:  # %bb.1: # %loadbb1
+; X64-NEXT:    xorl (%rsi), %eax
 ; X64-NEXT:    movb 4(%rdi), %cl
-; X64-NEXT:    xorl %eax, %eax
-; X64-NEXT:    cmpb 4(%rsi), %cl
-; X64-NEXT:    je .LBB10_3
-; X64-NEXT:  .LBB10_2: # %res_block
-; X64-NEXT:    movl $1, %eax
-; X64-NEXT:  .LBB10_3: # %endblock
-; X64-NEXT:    testl %eax, %eax
+; X64-NEXT:    xorb 4(%rsi), %cl
+; X64-NEXT:    movzbl %cl, %ecx
+; X64-NEXT:    orl %eax, %ecx
 ; X64-NEXT:    setne %al
 ; X64-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 5) nounwind
   %c = icmp ne i32 %m, 0
   ret i1 %c
 }
 
 define i32 @length8(i8* %X, i8* %Y) nounwind optsize {

 }
 
 define i1 @length8_eq(i8* %X, i8* %Y) nounwind optsize {
 ; X86-LABEL: length8_eq:
 ; X86:       # %bb.0:
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movl (%ecx), %edx
-; X86-NEXT:    cmpl (%eax), %edx
-; X86-NEXT:    jne .LBB12_2
-; X86-NEXT:  # %bb.1: # %loadbb1
-; X86-NEXT:    movl 4(%ecx), %edx
-; X86-NEXT:    xorl %ecx, %ecx
-; X86-NEXT:    cmpl 4(%eax), %edx
-; X86-NEXT:    je .LBB12_3
-; X86-NEXT:  .LBB12_2: # %res_block
-; X86-NEXT:    xorl %ecx, %ecx
-; X86-NEXT:    incl %ecx
-; X86-NEXT:  .LBB12_3: # %endblock
-; X86-NEXT:    testl %ecx, %ecx
+; X86-NEXT:    movl 4(%ecx), %ecx
+; X86-NEXT:    xorl (%eax), %edx
+; X86-NEXT:    xorl 4(%eax), %ecx
+; X86-NEXT:    orl %edx, %ecx
 ; X86-NEXT:    sete %al
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: length8_eq:
 ; X64:       # %bb.0:
 ; X64-NEXT:    movq (%rdi), %rax
 ; X64-NEXT:    cmpq (%rsi), %rax
 ; X64-NEXT:    sete %al
 ; X64-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 8) nounwind
   %c = icmp eq i32 %m, 0
   ret i1 %c
 }
 
 define i1 @length8_eq_const(i8* %X) nounwind optsize {
 ; X86-LABEL: length8_eq_const:
 ; X86:       # %bb.0:
-; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X86-NEXT:    cmpl $858927408, (%ecx) # imm = 0x33323130
-; X86-NEXT:    jne .LBB13_2
-; X86-NEXT:  # %bb.1: # %loadbb1
-; X86-NEXT:    xorl %eax, %eax
-; X86-NEXT:    cmpl $926299444, 4(%ecx) # imm = 0x37363534
-; X86-NEXT:    je .LBB13_3
-; X86-NEXT:  .LBB13_2: # %res_block
-; X86-NEXT:    xorl %eax, %eax
-; X86-NEXT:    incl %eax
-; X86-NEXT:  .LBB13_3: # %endblock
-; X86-NEXT:    testl %eax, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl $858927408, %ecx # imm = 0x33323130
+; X86-NEXT:    xorl (%eax), %ecx
+; X86-NEXT:    movl $926299444, %edx # imm = 0x37363534
+; X86-NEXT:    xorl 4(%eax), %edx
+; X86-NEXT:    orl %ecx, %edx
 ; X86-NEXT:    setne %al
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: length8_eq_const:
 ; X64:       # %bb.0:
 ; X64-NEXT:    movabsq $3978425819141910832, %rax # imm = 0x3736353433323130
 ; X64-NEXT:    cmpq %rax, (%rdi)
 ; X64-NEXT:    setne %al

 ; X86-NEXT:    addl $16, %esp
 ; X86-NEXT:    testl %eax, %eax
 ; X86-NEXT:    setne %al
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: length12_eq:
 ; X64:       # %bb.0:
 ; X64-NEXT:    movq (%rdi), %rax
-; X64-NEXT:    cmpq (%rsi), %rax
-; X64-NEXT:    jne .LBB14_2
-; X64-NEXT:  # %bb.1: # %loadbb1
+; X64-NEXT:    xorq (%rsi), %rax
 ; X64-NEXT:    movl 8(%rdi), %ecx
-; X64-NEXT:    xorl %eax, %eax
-; X64-NEXT:    cmpl 8(%rsi), %ecx
-; X64-NEXT:    je .LBB14_3
-; X64-NEXT:  .LBB14_2: # %res_block
-; X64-NEXT:    movl $1, %eax
-; X64-NEXT:  .LBB14_3: # %endblock
-; X64-NEXT:    testl %eax, %eax
+; X64-NEXT:    xorl 8(%rsi), %ecx
+; X64-NEXT:    orq %rax, %rcx
 ; X64-NEXT:    setne %al
 ; X64-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 12) nounwind
   %c = icmp ne i32 %m, 0
   ret i1 %c
 }
 
 define i32 @length12(i8* %X, i8* %Y) nounwind optsize {

 ; X86-NEXT:    sete %al
 ; X86-NEXT:    retl
 ;
 ; X64-SSE2-LABEL: length24_eq:
 ; X64-SSE2:       # %bb.0:
 ; X64-SSE2-NEXT:    movdqu (%rdi), %xmm0
 ; X64-SSE2-NEXT:    movdqu (%rsi), %xmm1
 ; X64-SSE2-NEXT:    pcmpeqb %xmm0, %xmm1
-; X64-SSE2-NEXT:    pmovmskb %xmm1, %eax
+; X64-SSE2-NEXT:    movq {{.*#+}} xmm0 = mem[0],zero
+; X64-SSE2-NEXT:    movq {{.*#+}} xmm2 = mem[0],zero
+; X64-SSE2-NEXT:    pcmpeqb %xmm0, %xmm2
+; X64-SSE2-NEXT:    pand %xmm1, %xmm2
+; X64-SSE2-NEXT:    pmovmskb %xmm2, %eax
 ; X64-SSE2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
-; X64-SSE2-NEXT:    jne .LBB20_2
-; X64-SSE2-NEXT:  # %bb.1: # %loadbb1
-; X64-SSE2-NEXT:    movq 16(%rdi), %rcx
-; X64-SSE2-NEXT:    xorl %eax, %eax
-; X64-SSE2-NEXT:    cmpq 16(%rsi), %rcx
-; X64-SSE2-NEXT:    je .LBB20_3
-; X64-SSE2-NEXT:  .LBB20_2: # %res_block
-; X64-SSE2-NEXT:    movl $1, %eax
-; X64-SSE2-NEXT:  .LBB20_3: # %endblock
-; X64-SSE2-NEXT:    testl %eax, %eax
 ; X64-SSE2-NEXT:    sete %al
 ; X64-SSE2-NEXT:    retq
 ;
 ; X64-AVX2-LABEL: length24_eq:
 ; X64-AVX2:       # %bb.0:
 ; X64-AVX2-NEXT:    vmovdqu (%rdi), %xmm0
+; X64-AVX2-NEXT:    vmovq {{.*#+}} xmm1 = mem[0],zero
+; X64-AVX2-NEXT:    vmovq {{.*#+}} xmm2 = mem[0],zero
+; X64-AVX2-NEXT:    vpcmpeqb %xmm2, %xmm1, %xmm1
 ; X64-AVX2-NEXT:    vpcmpeqb (%rsi), %xmm0, %xmm0
+; X64-AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; X64-AVX2-NEXT:    vpmovmskb %xmm0, %eax
 ; X64-AVX2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
-; X64-AVX2-NEXT:    jne .LBB20_2
-; X64-AVX2-NEXT:  # %bb.1: # %loadbb1
-; X64-AVX2-NEXT:    movq 16(%rdi), %rcx
-; X64-AVX2-NEXT:    xorl %eax, %eax
-; X64-AVX2-NEXT:    cmpq 16(%rsi), %rcx
-; X64-AVX2-NEXT:    je .LBB20_3
-; X64-AVX2-NEXT:  .LBB20_2: # %res_block
-; X64-AVX2-NEXT:    movl $1, %eax
-; X64-AVX2-NEXT:  .LBB20_3: # %endblock
-; X64-AVX2-NEXT:    testl %eax, %eax
 ; X64-AVX2-NEXT:    sete %al
 ; X64-AVX2-NEXT:    retq
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 24) nounwind
   %cmp = icmp eq i32 %call, 0
   ret i1 %cmp
 }
 
 define i1 @length24_eq_const(i8* %X) nounwind optsize {
 ; X86-LABEL: length24_eq_const:
 ; X86:       # %bb.0:
 ; X86-NEXT:    pushl $0
 ; X86-NEXT:    pushl $24
 ; X86-NEXT:    pushl $.L.str
 ; X86-NEXT:    pushl {{[0-9]+}}(%esp)
 ; X86-NEXT:    calll memcmp
 ; X86-NEXT:    addl $16, %esp
 ; X86-NEXT:    testl %eax, %eax
 ; X86-NEXT:    setne %al
 ; X86-NEXT:    retl
 ;
 ; X64-SSE2-LABEL: length24_eq_const:
 ; X64-SSE2:       # %bb.0:
 ; X64-SSE2-NEXT:    movdqu (%rdi), %xmm0
+; X64-SSE2-NEXT:    movq {{.*#+}} xmm1 = mem[0],zero
+; X64-SSE2-NEXT:    movabsq $3689065127958034230, %rax # imm = 0x3332313039383736
+; X64-SSE2-NEXT:    movq %rax, %xmm2
+; X64-SSE2-NEXT:    pcmpeqb %xmm1, %xmm2
 ; X64-SSE2-NEXT:    pcmpeqb {{.*}}(%rip), %xmm0
+; X64-SSE2-NEXT:    pand %xmm2, %xmm0
 ; X64-SSE2-NEXT:    pmovmskb %xmm0, %eax
 ; X64-SSE2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
-; X64-SSE2-NEXT:    jne .LBB21_2
-; X64-SSE2-NEXT:  # %bb.1: # %loadbb1
-; X64-SSE2-NEXT:    xorl %eax, %eax
-; X64-SSE2-NEXT:    movabsq $3689065127958034230, %rcx # imm = 0x3332313039383736
-; X64-SSE2-NEXT:    cmpq %rcx, 16(%rdi)
-; X64-SSE2-NEXT:    je .LBB21_3
-; X64-SSE2-NEXT:  .LBB21_2: # %res_block
-; X64-SSE2-NEXT:    movl $1, %eax
-; X64-SSE2-NEXT:  .LBB21_3: # %endblock
-; X64-SSE2-NEXT:    testl %eax, %eax
 ; X64-SSE2-NEXT:    setne %al
 ; X64-SSE2-NEXT:    retq
 ;
 ; X64-AVX2-LABEL: length24_eq_const:
 ; X64-AVX2:       # %bb.0:
 ; X64-AVX2-NEXT:    vmovdqu (%rdi), %xmm0
+; X64-AVX2-NEXT:    vmovq {{.*#+}} xmm1 = mem[0],zero
+; X64-AVX2-NEXT:    movabsq $3689065127958034230, %rax # imm = 0x3332313039383736
+; X64-AVX2-NEXT:    vmovq %rax, %xmm2
+; X64-AVX2-NEXT:    vpcmpeqb %xmm2, %xmm1, %xmm1
 ; X64-AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0
+; X64-AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; X64-AVX2-NEXT:    vpmovmskb %xmm0, %eax
 ; X64-AVX2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
-; X64-AVX2-NEXT:    jne .LBB21_2
-; X64-AVX2-NEXT:  # %bb.1: # %loadbb1
-; X64-AVX2-NEXT:    xorl %eax, %eax
-; X64-AVX2-NEXT:    movabsq $3689065127958034230, %rcx # imm = 0x3332313039383736
-; X64-AVX2-NEXT:    cmpq %rcx, 16(%rdi)
-; X64-AVX2-NEXT:    je .LBB21_3
-; X64-AVX2-NEXT:  .LBB21_2: # %res_block
-; X64-AVX2-NEXT:    movl $1, %eax
-; X64-AVX2-NEXT:  .LBB21_3: # %endblock
-; X64-AVX2-NEXT:    testl %eax, %eax
 ; X64-AVX2-NEXT:    setne %al
 ; X64-AVX2-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 24) nounwind
   %c = icmp ne i32 %m, 0
   ret i1 %c
 }
 
 define i32 @length32(i8* %X, i8* %Y) nounwind optsize {

 ; X86-NOSSE-NEXT:    sete %al
 ; X86-NOSSE-NEXT:    retl
 ;
 ; X86-SSE2-LABEL: length32_eq:
 ; X86-SSE2:       # %bb.0:
 ; X86-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X86-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-SSE2-NEXT:    movdqu (%ecx), %xmm0
-; X86-SSE2-NEXT:    movdqu (%eax), %xmm1
-; X86-SSE2-NEXT:    pcmpeqb %xmm0, %xmm1
-; X86-SSE2-NEXT:    pmovmskb %xmm1, %edx
-; X86-SSE2-NEXT:    cmpl $65535, %edx # imm = 0xFFFF
-; X86-SSE2-NEXT:    jne .LBB23_2
-; X86-SSE2-NEXT:  # %bb.1: # %loadbb1
-; X86-SSE2-NEXT:    movdqu 16(%ecx), %xmm0
-; X86-SSE2-NEXT:    movdqu 16(%eax), %xmm1
-; X86-SSE2-NEXT:    pcmpeqb %xmm0, %xmm1
-; X86-SSE2-NEXT:    pmovmskb %xmm1, %ecx
-; X86-SSE2-NEXT:    xorl %eax, %eax
-; X86-SSE2-NEXT:    cmpl $65535, %ecx # imm = 0xFFFF
-; X86-SSE2-NEXT:    je .LBB23_3
-; X86-SSE2-NEXT:  .LBB23_2: # %res_block
-; X86-SSE2-NEXT:    xorl %eax, %eax
-; X86-SSE2-NEXT:    incl %eax
-; X86-SSE2-NEXT:  .LBB23_3: # %endblock
-; X86-SSE2-NEXT:    testl %eax, %eax
+; X86-SSE2-NEXT:    movdqu 16(%ecx), %xmm1
+; X86-SSE2-NEXT:    movdqu (%eax), %xmm2
+; X86-SSE2-NEXT:    pcmpeqb %xmm0, %xmm2
+; X86-SSE2-NEXT:    movdqu 16(%eax), %xmm0
+; X86-SSE2-NEXT:    pcmpeqb %xmm1, %xmm0
+; X86-SSE2-NEXT:    pand %xmm2, %xmm0
+; X86-SSE2-NEXT:    pmovmskb %xmm0, %eax
+; X86-SSE2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
 ; X86-SSE2-NEXT:    sete %al
 ; X86-SSE2-NEXT:    retl
 ;
 ; X64-SSE2-LABEL: length32_eq:
 ; X64-SSE2:       # %bb.0:
 ; X64-SSE2-NEXT:    movdqu (%rdi), %xmm0
-; X64-SSE2-NEXT:    movdqu (%rsi), %xmm1
-; X64-SSE2-NEXT:    pcmpeqb %xmm0, %xmm1
-; X64-SSE2-NEXT:    pmovmskb %xmm1, %eax
+; X64-SSE2-NEXT:    movdqu 16(%rdi), %xmm1
+; X64-SSE2-NEXT:    movdqu (%rsi), %xmm2
+; X64-SSE2-NEXT:    pcmpeqb %xmm0, %xmm2
+; X64-SSE2-NEXT:    movdqu 16(%rsi), %xmm0
+; X64-SSE2-NEXT:    pcmpeqb %xmm1, %xmm0
+; X64-SSE2-NEXT:    pand %xmm2, %xmm0
+; X64-SSE2-NEXT:    pmovmskb %xmm0, %eax
 ; X64-SSE2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
-; X64-SSE2-NEXT:    jne .LBB23_2
-; X64-SSE2-NEXT:  # %bb.1: # %loadbb1
-; X64-SSE2-NEXT:    movdqu 16(%rdi), %xmm0
-; X64-SSE2-NEXT:    movdqu 16(%rsi), %xmm1
-; X64-SSE2-NEXT:    pcmpeqb %xmm0, %xmm1
-; X64-SSE2-NEXT:    pmovmskb %xmm1, %ecx
-; X64-SSE2-NEXT:    xorl %eax, %eax
-; X64-SSE2-NEXT:    cmpl $65535, %ecx # imm = 0xFFFF
-; X64-SSE2-NEXT:    je .LBB23_3
-; X64-SSE2-NEXT:  .LBB23_2: # %res_block
-; X64-SSE2-NEXT:    movl $1, %eax
-; X64-SSE2-NEXT:  .LBB23_3: # %endblock
-; X64-SSE2-NEXT:    testl %eax, %eax
 ; X64-SSE2-NEXT:    sete %al
 ; X64-SSE2-NEXT:    retq
 ;
 ; X64-AVX2-LABEL: length32_eq:
 ; X64-AVX2:       # %bb.0:
 ; X64-AVX2-NEXT:    vmovdqu (%rdi), %ymm0
 ; X64-AVX2-NEXT:    vpcmpeqb (%rsi), %ymm0, %ymm0
 ; X64-AVX2-NEXT:    vpmovmskb %ymm0, %eax

 ; X86-NOSSE-NEXT:    testl %eax, %eax
 ; X86-NOSSE-NEXT:    setne %al
 ; X86-NOSSE-NEXT:    retl
 ;
 ; X86-SSE2-LABEL: length32_eq_const:
 ; X86-SSE2:       # %bb.0:
 ; X86-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X86-SSE2-NEXT:    movdqu (%eax), %xmm0
+; X86-SSE2-NEXT:    movdqu 16(%eax), %xmm1
+; X86-SSE2-NEXT:    pcmpeqb {{\.LCPI.*}}, %xmm1
 ; X86-SSE2-NEXT:    pcmpeqb {{\.LCPI.*}}, %xmm0
-; X86-SSE2-NEXT:    pmovmskb %xmm0, %ecx
-; X86-SSE2-NEXT:    cmpl $65535, %ecx # imm = 0xFFFF
-; X86-SSE2-NEXT:    jne .LBB24_2
-; X86-SSE2-NEXT:  # %bb.1: # %loadbb1
-; X86-SSE2-NEXT:    movdqu 16(%eax), %xmm0
-; X86-SSE2-NEXT:    pcmpeqb {{\.LCPI.*}}, %xmm0
-; X86-SSE2-NEXT:    pmovmskb %xmm0, %ecx
-; X86-SSE2-NEXT:    xorl %eax, %eax
-; X86-SSE2-NEXT:    cmpl $65535, %ecx # imm = 0xFFFF
-; X86-SSE2-NEXT:    je .LBB24_3
-; X86-SSE2-NEXT:  .LBB24_2: # %res_block
-; X86-SSE2-NEXT:    xorl %eax, %eax
-; X86-SSE2-NEXT:    incl %eax
-; X86-SSE2-NEXT:  .LBB24_3: # %endblock
-; X86-SSE2-NEXT:    testl %eax, %eax
+; X86-SSE2-NEXT:    pand %xmm1, %xmm0
+; X86-SSE2-NEXT:    pmovmskb %xmm0, %eax
+; X86-SSE2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
 ; X86-SSE2-NEXT:    setne %al
 ; X86-SSE2-NEXT:    retl
 ;
 ; X64-SSE2-LABEL: length32_eq_const:
 ; X64-SSE2:       # %bb.0:
 ; X64-SSE2-NEXT:    movdqu (%rdi), %xmm0
+; X64-SSE2-NEXT:    movdqu 16(%rdi), %xmm1
+; X64-SSE2-NEXT:    pcmpeqb {{.*}}(%rip), %xmm1
 ; X64-SSE2-NEXT:    pcmpeqb {{.*}}(%rip), %xmm0
+; X64-SSE2-NEXT:    pand %xmm1, %xmm0
 ; X64-SSE2-NEXT:    pmovmskb %xmm0, %eax
 ; X64-SSE2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
-; X64-SSE2-NEXT:    jne .LBB24_2
-; X64-SSE2-NEXT:  # %bb.1: # %loadbb1
-; X64-SSE2-NEXT:    movdqu 16(%rdi), %xmm0
-; X64-SSE2-NEXT:    pcmpeqb {{.*}}(%rip), %xmm0
-; X64-SSE2-NEXT:    pmovmskb %xmm0, %ecx
-; X64-SSE2-NEXT:    xorl %eax, %eax
-; X64-SSE2-NEXT:    cmpl $65535, %ecx # imm = 0xFFFF
-; X64-SSE2-NEXT:    je .LBB24_3
-; X64-SSE2-NEXT:  .LBB24_2: # %res_block
-; X64-SSE2-NEXT:    movl $1, %eax
-; X64-SSE2-NEXT:  .LBB24_3: # %endblock
-; X64-SSE2-NEXT:    testl %eax, %eax
 ; X64-SSE2-NEXT:    setne %al
 ; X64-SSE2-NEXT:    retq
 ;
 ; X64-AVX2-LABEL: length32_eq_const:
 ; X64-AVX2:       # %bb.0:
 ; X64-AVX2-NEXT:    vmovdqu (%rdi), %ymm0
 ; X64-AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
 ; X64-AVX2-NEXT:    vpmovmskb %ymm0, %eax

 ; X64-SSE2-NEXT:    testl %eax, %eax
 ; X64-SSE2-NEXT:    setne %al
 ; X64-SSE2-NEXT:    popq %rcx
 ; X64-SSE2-NEXT:    retq
 ;
 ; X64-AVX2-LABEL: length64_eq:
 ; X64-AVX2:       # %bb.0:
 ; X64-AVX2-NEXT:    vmovdqu (%rdi), %ymm0
+; X64-AVX2-NEXT:    vmovdqu 32(%rdi), %ymm1
+; X64-AVX2-NEXT:    vpcmpeqb 32(%rsi), %ymm1, %ymm1
 ; X64-AVX2-NEXT:    vpcmpeqb (%rsi), %ymm0, %ymm0
+; X64-AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
 ; X64-AVX2-NEXT:    vpmovmskb %ymm0, %eax
 ; X64-AVX2-NEXT:    cmpl $-1, %eax
-; X64-AVX2-NEXT:    jne .LBB26_2
-; X64-AVX2-NEXT:  # %bb.1: # %loadbb1
-; X64-AVX2-NEXT:    vmovdqu 32(%rdi), %ymm0
-; X64-AVX2-NEXT:    vpcmpeqb 32(%rsi), %ymm0, %ymm0
-; X64-AVX2-NEXT:    vpmovmskb %ymm0, %ecx
-; X64-AVX2-NEXT:    xorl %eax, %eax
-; X64-AVX2-NEXT:    cmpl $-1, %ecx
-; X64-AVX2-NEXT:    je .LBB26_3
-; X64-AVX2-NEXT:  .LBB26_2: # %res_block
-; X64-AVX2-NEXT:    movl $1, %eax
-; X64-AVX2-NEXT:  .LBB26_3: # %endblock
-; X64-AVX2-NEXT:    testl %eax, %eax
 ; X64-AVX2-NEXT:    setne %al
 ; X64-AVX2-NEXT:    vzeroupper
 ; X64-AVX2-NEXT:    retq
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 64) nounwind
   %cmp = icmp ne i32 %call, 0
   ret i1 %cmp
 }
 

 ; X64-SSE2-NEXT:    testl %eax, %eax
 ; X64-SSE2-NEXT:    sete %al
 ; X64-SSE2-NEXT:    popq %rcx
 ; X64-SSE2-NEXT:    retq
 ;
 ; X64-AVX2-LABEL: length64_eq_const:
 ; X64-AVX2:       # %bb.0:
 ; X64-AVX2-NEXT:    vmovdqu (%rdi), %ymm0
+; X64-AVX2-NEXT:    vmovdqu 32(%rdi), %ymm1
+; X64-AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm1, %ymm1
 ; X64-AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
+; X64-AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
 ; X64-AVX2-NEXT:    vpmovmskb %ymm0, %eax
 ; X64-AVX2-NEXT:    cmpl $-1, %eax
-; X64-AVX2-NEXT:    jne .LBB27_2
-; X64-AVX2-NEXT:  # %bb.1: # %loadbb1
-; X64-AVX2-NEXT:    vmovdqu 32(%rdi), %ymm0
-; X64-AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
-; X64-AVX2-NEXT:    vpmovmskb %ymm0, %ecx
-; X64-AVX2-NEXT:    xorl %eax, %eax
-; X64-AVX2-NEXT:    cmpl $-1, %ecx
-; X64-AVX2-NEXT:    je .LBB27_3
-; X64-AVX2-NEXT:  .LBB27_2: # %res_block
-; X64-AVX2-NEXT:    movl $1, %eax
-; X64-AVX2-NEXT:  .LBB27_3: # %endblock
-; X64-AVX2-NEXT:    testl %eax, %eax
 ; X64-AVX2-NEXT:    sete %al
 ; X64-AVX2-NEXT:    vzeroupper
 ; X64-AVX2-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 64) nounwind
   %c = icmp eq i32 %m, 0
   ret i1 %c
 }
 

llvm/trunk/test/CodeGen/X86/memcmp.ll

 }
 
 define i1 @length3_eq(i8* %X, i8* %Y) nounwind {
 ; X86-LABEL: length3_eq:
 ; X86:       # %bb.0:
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movzwl (%ecx), %edx
-; X86-NEXT:    cmpw (%eax), %dx
-; X86-NEXT:    jne .LBB7_2
-; X86-NEXT:  # %bb.1: # %loadbb1
-; X86-NEXT:    movb 2(%ecx), %dl
-; X86-NEXT:    xorl %ecx, %ecx
-; X86-NEXT:    cmpb 2(%eax), %dl
-; X86-NEXT:    je .LBB7_3
-; X86-NEXT:  .LBB7_2: # %res_block
-; X86-NEXT:    movl $1, %ecx
-; X86-NEXT:  .LBB7_3: # %endblock
-; X86-NEXT:    testl %ecx, %ecx
+; X86-NEXT:    xorw (%eax), %dx
+; X86-NEXT:    movb 2(%ecx), %cl
+; X86-NEXT:    xorb 2(%eax), %cl
+; X86-NEXT:    movzbl %cl, %eax
+; X86-NEXT:    orw %dx, %ax
 ; X86-NEXT:    setne %al
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: length3_eq:
 ; X64:       # %bb.0:
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    cmpw (%rsi), %ax
-; X64-NEXT:    jne .LBB7_2
-; X64-NEXT:  # %bb.1: # %loadbb1
+; X64-NEXT:    xorw (%rsi), %ax
 ; X64-NEXT:    movb 2(%rdi), %cl
-; X64-NEXT:    xorl %eax, %eax
-; X64-NEXT:    cmpb 2(%rsi), %cl
-; X64-NEXT:    je .LBB7_3
-; X64-NEXT:  .LBB7_2: # %res_block
-; X64-NEXT:    movl $1, %eax
-; X64-NEXT:  .LBB7_3: # %endblock
-; X64-NEXT:    testl %eax, %eax
+; X64-NEXT:    xorb 2(%rsi), %cl
+; X64-NEXT:    movzbl %cl, %ecx
+; X64-NEXT:    orw %ax, %cx
 ; X64-NEXT:    setne %al
 ; X64-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 3) nounwind
   %c = icmp ne i32 %m, 0
   ret i1 %c
 }
 
 define i32 @length4(i8* %X, i8* %Y) nounwind {

 }
 
 define i1 @length5_eq(i8* %X, i8* %Y) nounwind {
 ; X86-LABEL: length5_eq:
 ; X86:       # %bb.0:
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movl (%ecx), %edx
-; X86-NEXT:    cmpl (%eax), %edx
-; X86-NEXT:    jne .LBB12_2
-; X86-NEXT:  # %bb.1: # %loadbb1
-; X86-NEXT:    movb 4(%ecx), %dl
-; X86-NEXT:    xorl %ecx, %ecx
-; X86-NEXT:    cmpb 4(%eax), %dl
-; X86-NEXT:    je .LBB12_3
-; X86-NEXT:  .LBB12_2: # %res_block
-; X86-NEXT:    movl $1, %ecx
-; X86-NEXT:  .LBB12_3: # %endblock
-; X86-NEXT:    testl %ecx, %ecx
+; X86-NEXT:    xorl (%eax), %edx
+; X86-NEXT:    movb 4(%ecx), %cl
+; X86-NEXT:    xorb 4(%eax), %cl
+; X86-NEXT:    movzbl %cl, %eax
+; X86-NEXT:    orl %edx, %eax
 ; X86-NEXT:    setne %al
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: length5_eq:
 ; X64:       # %bb.0:
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    cmpl (%rsi), %eax
-; X64-NEXT:    jne .LBB12_2
-; X64-NEXT:  # %bb.1: # %loadbb1
+; X64-NEXT:    xorl (%rsi), %eax
 ; X64-NEXT:    movb 4(%rdi), %cl
-; X64-NEXT:    xorl %eax, %eax
-; X64-NEXT:    cmpb 4(%rsi), %cl
-; X64-NEXT:    je .LBB12_3
-; X64-NEXT:  .LBB12_2: # %res_block
-; X64-NEXT:    movl $1, %eax
-; X64-NEXT:  .LBB12_3: # %endblock
-; X64-NEXT:    testl %eax, %eax
+; X64-NEXT:    xorb 4(%rsi), %cl
+; X64-NEXT:    movzbl %cl, %ecx
+; X64-NEXT:    orl %eax, %ecx
 ; X64-NEXT:    setne %al
 ; X64-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 5) nounwind
   %c = icmp ne i32 %m, 0
   ret i1 %c
 }
 
 define i32 @length8(i8* %X, i8* %Y) nounwind {

 }
 
 define i1 @length8_eq(i8* %X, i8* %Y) nounwind {
 ; X86-LABEL: length8_eq:
 ; X86:       # %bb.0:
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movl (%ecx), %edx
-; X86-NEXT:    cmpl (%eax), %edx
-; X86-NEXT:    jne .LBB14_2
-; X86-NEXT:  # %bb.1: # %loadbb1
-; X86-NEXT:    movl 4(%ecx), %edx
-; X86-NEXT:    xorl %ecx, %ecx
-; X86-NEXT:    cmpl 4(%eax), %edx
-; X86-NEXT:    je .LBB14_3
-; X86-NEXT:  .LBB14_2: # %res_block
-; X86-NEXT:    movl $1, %ecx
-; X86-NEXT:  .LBB14_3: # %endblock
-; X86-NEXT:    testl %ecx, %ecx
+; X86-NEXT:    movl 4(%ecx), %ecx
+; X86-NEXT:    xorl (%eax), %edx
+; X86-NEXT:    xorl 4(%eax), %ecx
+; X86-NEXT:    orl %edx, %ecx
 ; X86-NEXT:    sete %al
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: length8_eq:
 ; X64:       # %bb.0:
 ; X64-NEXT:    movq (%rdi), %rax
 ; X64-NEXT:    cmpq (%rsi), %rax
 ; X64-NEXT:    sete %al
 ; X64-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 8) nounwind
   %c = icmp eq i32 %m, 0
   ret i1 %c
 }
 
 define i1 @length8_eq_const(i8* %X) nounwind {
 ; X86-LABEL: length8_eq_const:
 ; X86:       # %bb.0:
-; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X86-NEXT:    cmpl $858927408, (%ecx) # imm = 0x33323130
-; X86-NEXT:    jne .LBB15_2
-; X86-NEXT:  # %bb.1: # %loadbb1
-; X86-NEXT:    xorl %eax, %eax
-; X86-NEXT:    cmpl $926299444, 4(%ecx) # imm = 0x37363534
-; X86-NEXT:    je .LBB15_3
-; X86-NEXT:  .LBB15_2: # %res_block
-; X86-NEXT:    movl $1, %eax
-; X86-NEXT:  .LBB15_3: # %endblock
-; X86-NEXT:    testl %eax, %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl $858927408, %ecx # imm = 0x33323130
+; X86-NEXT:    xorl (%eax), %ecx
+; X86-NEXT:    movl $926299444, %edx # imm = 0x37363534
+; X86-NEXT:    xorl 4(%eax), %edx
+; X86-NEXT:    orl %ecx, %edx
 ; X86-NEXT:    setne %al
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: length8_eq_const:
 ; X64:       # %bb.0:
 ; X64-NEXT:    movabsq $3978425819141910832, %rax # imm = 0x3736353433323130
 ; X64-NEXT:    cmpq %rax, (%rdi)
 ; X64-NEXT:    setne %al

 ; X86-NEXT:    addl $16, %esp
 ; X86-NEXT:    testl %eax, %eax
 ; X86-NEXT:    setne %al
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: length12_eq:
 ; X64:       # %bb.0:
 ; X64-NEXT:    movq (%rdi), %rax
-; X64-NEXT:    cmpq (%rsi), %rax
-; X64-NEXT:    jne .LBB16_2
-; X64-NEXT:  # %bb.1: # %loadbb1
+; X64-NEXT:    xorq (%rsi), %rax
 ; X64-NEXT:    movl 8(%rdi), %ecx
-; X64-NEXT:    xorl %eax, %eax
-; X64-NEXT:    cmpl 8(%rsi), %ecx
-; X64-NEXT:    je .LBB16_3
-; X64-NEXT:  .LBB16_2: # %res_block
-; X64-NEXT:    movl $1, %eax
-; X64-NEXT:  .LBB16_3: # %endblock
-; X64-NEXT:    testl %eax, %eax
+; X64-NEXT:    xorl 8(%rsi), %ecx
+; X64-NEXT:    orq %rax, %rcx
 ; X64-NEXT:    setne %al
 ; X64-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 12) nounwind
   %c = icmp ne i32 %m, 0
   ret i1 %c
 }
 
 define i32 @length12(i8* %X, i8* %Y) nounwind {

 ; X86-NEXT:    sete %al
 ; X86-NEXT:    retl
 ;
 ; X64-SSE2-LABEL: length24_eq:
 ; X64-SSE2:       # %bb.0:
 ; X64-SSE2-NEXT:    movdqu (%rdi), %xmm0
 ; X64-SSE2-NEXT:    movdqu (%rsi), %xmm1
 ; X64-SSE2-NEXT:    pcmpeqb %xmm0, %xmm1
-; X64-SSE2-NEXT:    pmovmskb %xmm1, %eax
+; X64-SSE2-NEXT:    movq {{.*#+}} xmm0 = mem[0],zero
+; X64-SSE2-NEXT:    movq {{.*#+}} xmm2 = mem[0],zero
+; X64-SSE2-NEXT:    pcmpeqb %xmm0, %xmm2
+; X64-SSE2-NEXT:    pand %xmm1, %xmm2
+; X64-SSE2-NEXT:    pmovmskb %xmm2, %eax
 ; X64-SSE2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
-; X64-SSE2-NEXT:    jne .LBB22_2
-; X64-SSE2-NEXT:  # %bb.1: # %loadbb1
-; X64-SSE2-NEXT:    movq 16(%rdi), %rcx
-; X64-SSE2-NEXT:    xorl %eax, %eax
-; X64-SSE2-NEXT:    cmpq 16(%rsi), %rcx
-; X64-SSE2-NEXT:    je .LBB22_3
-; X64-SSE2-NEXT:  .LBB22_2: # %res_block
-; X64-SSE2-NEXT:    movl $1, %eax
-; X64-SSE2-NEXT:  .LBB22_3: # %endblock
-; X64-SSE2-NEXT:    testl %eax, %eax
 ; X64-SSE2-NEXT:    sete %al
 ; X64-SSE2-NEXT:    retq
 ;
 ; X64-AVX-LABEL: length24_eq:
 ; X64-AVX:       # %bb.0:
 ; X64-AVX-NEXT:    vmovdqu (%rdi), %xmm0
+; X64-AVX-NEXT:    vmovq {{.*#+}} xmm1 = mem[0],zero
+; X64-AVX-NEXT:    vmovq {{.*#+}} xmm2 = mem[0],zero
+; X64-AVX-NEXT:    vpcmpeqb %xmm2, %xmm1, %xmm1
 ; X64-AVX-NEXT:    vpcmpeqb (%rsi), %xmm0, %xmm0
+; X64-AVX-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; X64-AVX-NEXT:    vpmovmskb %xmm0, %eax
 ; X64-AVX-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
-; X64-AVX-NEXT:    jne .LBB22_2
-; X64-AVX-NEXT:  # %bb.1: # %loadbb1
-; X64-AVX-NEXT:    movq 16(%rdi), %rcx
-; X64-AVX-NEXT:    xorl %eax, %eax
-; X64-AVX-NEXT:    cmpq 16(%rsi), %rcx
-; X64-AVX-NEXT:    je .LBB22_3
-; X64-AVX-NEXT:  .LBB22_2: # %res_block
-; X64-AVX-NEXT:    movl $1, %eax
-; X64-AVX-NEXT:  .LBB22_3: # %endblock
-; X64-AVX-NEXT:    testl %eax, %eax
 ; X64-AVX-NEXT:    sete %al
 ; X64-AVX-NEXT:    retq
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 24) nounwind
   %cmp = icmp eq i32 %call, 0
   ret i1 %cmp
 }
 
 define i1 @length24_eq_const(i8* %X) nounwind {
 ; X86-LABEL: length24_eq_const:
 ; X86:       # %bb.0:
 ; X86-NEXT:    pushl $0
 ; X86-NEXT:    pushl $24
 ; X86-NEXT:    pushl $.L.str
 ; X86-NEXT:    pushl {{[0-9]+}}(%esp)
 ; X86-NEXT:    calll memcmp
 ; X86-NEXT:    addl $16, %esp
 ; X86-NEXT:    testl %eax, %eax
 ; X86-NEXT:    setne %al
 ; X86-NEXT:    retl
 ;
 ; X64-SSE2-LABEL: length24_eq_const:
 ; X64-SSE2:       # %bb.0:
 ; X64-SSE2-NEXT:    movdqu (%rdi), %xmm0
+; X64-SSE2-NEXT:    movq {{.*#+}} xmm1 = mem[0],zero
+; X64-SSE2-NEXT:    movabsq $3689065127958034230, %rax # imm = 0x3332313039383736
+; X64-SSE2-NEXT:    movq %rax, %xmm2
+; X64-SSE2-NEXT:    pcmpeqb %xmm1, %xmm2
 ; X64-SSE2-NEXT:    pcmpeqb {{.*}}(%rip), %xmm0
+; X64-SSE2-NEXT:    pand %xmm2, %xmm0
 ; X64-SSE2-NEXT:    pmovmskb %xmm0, %eax
 ; X64-SSE2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
-; X64-SSE2-NEXT:    jne .LBB23_2
-; X64-SSE2-NEXT:  # %bb.1: # %loadbb1
-; X64-SSE2-NEXT:    xorl %eax, %eax
-; X64-SSE2-NEXT:    movabsq $3689065127958034230, %rcx # imm = 0x3332313039383736
-; X64-SSE2-NEXT:    cmpq %rcx, 16(%rdi)
-; X64-SSE2-NEXT:    je .LBB23_3
-; X64-SSE2-NEXT:  .LBB23_2: # %res_block
-; X64-SSE2-NEXT:    movl $1, %eax
-; X64-SSE2-NEXT:  .LBB23_3: # %endblock
-; X64-SSE2-NEXT:    testl %eax, %eax
 ; X64-SSE2-NEXT:    setne %al
 ; X64-SSE2-NEXT:    retq
 ;
 ; X64-AVX-LABEL: length24_eq_const:
 ; X64-AVX:       # %bb.0:
 ; X64-AVX-NEXT:    vmovdqu (%rdi), %xmm0
+; X64-AVX-NEXT:    vmovq {{.*#+}} xmm1 = mem[0],zero
+; X64-AVX-NEXT:    movabsq $3689065127958034230, %rax # imm = 0x3332313039383736
+; X64-AVX-NEXT:    vmovq %rax, %xmm2
+; X64-AVX-NEXT:    vpcmpeqb %xmm2, %xmm1, %xmm1
 ; X64-AVX-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0
+; X64-AVX-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; X64-AVX-NEXT:    vpmovmskb %xmm0, %eax
 ; X64-AVX-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
-; X64-AVX-NEXT:    jne .LBB23_2
-; X64-AVX-NEXT:  # %bb.1: # %loadbb1
-; X64-AVX-NEXT:    xorl %eax, %eax
-; X64-AVX-NEXT:    movabsq $3689065127958034230, %rcx # imm = 0x3332313039383736
-; X64-AVX-NEXT:    cmpq %rcx, 16(%rdi)
-; X64-AVX-NEXT:    je .LBB23_3
-; X64-AVX-NEXT:  .LBB23_2: # %res_block
-; X64-AVX-NEXT:    movl $1, %eax
-; X64-AVX-NEXT:  .LBB23_3: # %endblock
-; X64-AVX-NEXT:    testl %eax, %eax
 ; X64-AVX-NEXT:    setne %al
 ; X64-AVX-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 24) nounwind
   %c = icmp ne i32 %m, 0
   ret i1 %c
 }
 
 define i32 @length32(i8* %X, i8* %Y) nounwind {

 ; X86-SSE1-NEXT:    sete %al
 ; X86-SSE1-NEXT:    retl
 ;
 ; X86-SSE2-LABEL: length32_eq:
 ; X86-SSE2:       # %bb.0:
 ; X86-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X86-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-SSE2-NEXT:    movdqu (%ecx), %xmm0
-; X86-SSE2-NEXT:    movdqu (%eax), %xmm1
-; X86-SSE2-NEXT:    pcmpeqb %xmm0, %xmm1
-; X86-SSE2-NEXT:    pmovmskb %xmm1, %edx
-; X86-SSE2-NEXT:    cmpl $65535, %edx # imm = 0xFFFF
-; X86-SSE2-NEXT:    jne .LBB25_2
-; X86-SSE2-NEXT:  # %bb.1: # %loadbb1
-; X86-SSE2-NEXT:    movdqu 16(%ecx), %xmm0
-; X86-SSE2-NEXT:    movdqu 16(%eax), %xmm1
-; X86-SSE2-NEXT:    pcmpeqb %xmm0, %xmm1
-; X86-SSE2-NEXT:    pmovmskb %xmm1, %ecx
-; X86-SSE2-NEXT:    xorl %eax, %eax
-; X86-SSE2-NEXT:    cmpl $65535, %ecx # imm = 0xFFFF
-; X86-SSE2-NEXT:    je .LBB25_3
-; X86-SSE2-NEXT:  .LBB25_2: # %res_block
-; X86-SSE2-NEXT:    movl $1, %eax
-; X86-SSE2-NEXT:  .LBB25_3: # %endblock
-; X86-SSE2-NEXT:    testl %eax, %eax
+; X86-SSE2-NEXT:    movdqu 16(%ecx), %xmm1
+; X86-SSE2-NEXT:    movdqu (%eax), %xmm2
+; X86-SSE2-NEXT:    pcmpeqb %xmm0, %xmm2
+; X86-SSE2-NEXT:    movdqu 16(%eax), %xmm0
+; X86-SSE2-NEXT:    pcmpeqb %xmm1, %xmm0
+; X86-SSE2-NEXT:    pand %xmm2, %xmm0
+; X86-SSE2-NEXT:    pmovmskb %xmm0, %eax
+; X86-SSE2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
 ; X86-SSE2-NEXT:    sete %al
 ; X86-SSE2-NEXT:    retl
 ;
 ; X64-SSE2-LABEL: length32_eq:
 ; X64-SSE2:       # %bb.0:
 ; X64-SSE2-NEXT:    movdqu (%rdi), %xmm0
-; X64-SSE2-NEXT:    movdqu (%rsi), %xmm1
-; X64-SSE2-NEXT:    pcmpeqb %xmm0, %xmm1
-; X64-SSE2-NEXT:    pmovmskb %xmm1, %eax
+; X64-SSE2-NEXT:    movdqu 16(%rdi), %xmm1
+; X64-SSE2-NEXT:    movdqu (%rsi), %xmm2
+; X64-SSE2-NEXT:    pcmpeqb %xmm0, %xmm2
+; X64-SSE2-NEXT:    movdqu 16(%rsi), %xmm0
+; X64-SSE2-NEXT:    pcmpeqb %xmm1, %xmm0
+; X64-SSE2-NEXT:    pand %xmm2, %xmm0
+; X64-SSE2-NEXT:    pmovmskb %xmm0, %eax
 ; X64-SSE2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
-; X64-SSE2-NEXT:    jne .LBB25_2
-; X64-SSE2-NEXT:  # %bb.1: # %loadbb1
-; X64-SSE2-NEXT:    movdqu 16(%rdi), %xmm0
-; X64-SSE2-NEXT:    movdqu 16(%rsi), %xmm1
-; X64-SSE2-NEXT:    pcmpeqb %xmm0, %xmm1
-; X64-SSE2-NEXT:    pmovmskb %xmm1, %ecx
-; X64-SSE2-NEXT:    xorl %eax, %eax
-; X64-SSE2-NEXT:    cmpl $65535, %ecx # imm = 0xFFFF
-; X64-SSE2-NEXT:    je .LBB25_3
-; X64-SSE2-NEXT:  .LBB25_2: # %res_block
-; X64-SSE2-NEXT:    movl $1, %eax
-; X64-SSE2-NEXT:  .LBB25_3: # %endblock
-; X64-SSE2-NEXT:    testl %eax, %eax
 ; X64-SSE2-NEXT:    sete %al
 ; X64-SSE2-NEXT:    retq
 ;
 ; X64-AVX1-LABEL: length32_eq:
 ; X64-AVX1:       # %bb.0:
 ; X64-AVX1-NEXT:    vmovdqu (%rdi), %xmm0
+; X64-AVX1-NEXT:    vmovdqu 16(%rdi), %xmm1
+; X64-AVX1-NEXT:    vpcmpeqb 16(%rsi), %xmm1, %xmm1
 ; X64-AVX1-NEXT:    vpcmpeqb (%rsi), %xmm0, %xmm0
+; X64-AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; X64-AVX1-NEXT:    vpmovmskb %xmm0, %eax
 ; X64-AVX1-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
-; X64-AVX1-NEXT:    jne .LBB25_2
-; X64-AVX1-NEXT:  # %bb.1: # %loadbb1
-; X64-AVX1-NEXT:    vmovdqu 16(%rdi), %xmm0
-; X64-AVX1-NEXT:    vpcmpeqb 16(%rsi), %xmm0, %xmm0
-; X64-AVX1-NEXT:    vpmovmskb %xmm0, %ecx
-; X64-AVX1-NEXT:    xorl %eax, %eax
-; X64-AVX1-NEXT:    cmpl $65535, %ecx # imm = 0xFFFF
-; X64-AVX1-NEXT:    je .LBB25_3
-; X64-AVX1-NEXT:  .LBB25_2: # %res_block
-; X64-AVX1-NEXT:    movl $1, %eax
-; X64-AVX1-NEXT:  .LBB25_3: # %endblock
-; X64-AVX1-NEXT:    testl %eax, %eax
 ; X64-AVX1-NEXT:    sete %al
 ; X64-AVX1-NEXT:    retq
 ;
 ; X64-AVX2-LABEL: length32_eq:
 ; X64-AVX2:       # %bb.0:
 ; X64-AVX2-NEXT:    vmovdqu (%rdi), %ymm0
 ; X64-AVX2-NEXT:    vpcmpeqb (%rsi), %ymm0, %ymm0
 ; X64-AVX2-NEXT:    vpmovmskb %ymm0, %eax

 ; X86-SSE1-NEXT:    testl %eax, %eax
 ; X86-SSE1-NEXT:    setne %al
 ; X86-SSE1-NEXT:    retl
 ;
 ; X86-SSE2-LABEL: length32_eq_const:
 ; X86-SSE2:       # %bb.0:
 ; X86-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X86-SSE2-NEXT:    movdqu (%eax), %xmm0
+; X86-SSE2-NEXT:    movdqu 16(%eax), %xmm1
+; X86-SSE2-NEXT:    pcmpeqb {{\.LCPI.*}}, %xmm1
 ; X86-SSE2-NEXT:    pcmpeqb {{\.LCPI.*}}, %xmm0
-; X86-SSE2-NEXT:    pmovmskb %xmm0, %ecx
-; X86-SSE2-NEXT:    cmpl $65535, %ecx # imm = 0xFFFF
-; X86-SSE2-NEXT:    jne .LBB26_2
-; X86-SSE2-NEXT:  # %bb.1: # %loadbb1
-; X86-SSE2-NEXT:    movdqu 16(%eax), %xmm0
-; X86-SSE2-NEXT:    pcmpeqb {{\.LCPI.*}}, %xmm0
-; X86-SSE2-NEXT:    pmovmskb %xmm0, %ecx
-; X86-SSE2-NEXT:    xorl %eax, %eax
-; X86-SSE2-NEXT:    cmpl $65535, %ecx # imm = 0xFFFF
-; X86-SSE2-NEXT:    je .LBB26_3
-; X86-SSE2-NEXT:  .LBB26_2: # %res_block
-; X86-SSE2-NEXT:    movl $1, %eax
-; X86-SSE2-NEXT:  .LBB26_3: # %endblock
-; X86-SSE2-NEXT:    testl %eax, %eax
+; X86-SSE2-NEXT:    pand %xmm1, %xmm0
+; X86-SSE2-NEXT:    pmovmskb %xmm0, %eax
+; X86-SSE2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
 ; X86-SSE2-NEXT:    setne %al
 ; X86-SSE2-NEXT:    retl
 ;
 ; X64-SSE2-LABEL: length32_eq_const:
 ; X64-SSE2:       # %bb.0:
 ; X64-SSE2-NEXT:    movdqu (%rdi), %xmm0
+; X64-SSE2-NEXT:    movdqu 16(%rdi), %xmm1
+; X64-SSE2-NEXT:    pcmpeqb {{.*}}(%rip), %xmm1
 ; X64-SSE2-NEXT:    pcmpeqb {{.*}}(%rip), %xmm0
+; X64-SSE2-NEXT:    pand %xmm1, %xmm0
 ; X64-SSE2-NEXT:    pmovmskb %xmm0, %eax
 ; X64-SSE2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
-; X64-SSE2-NEXT:    jne .LBB26_2
-; X64-SSE2-NEXT:  # %bb.1: # %loadbb1
-; X64-SSE2-NEXT:    movdqu 16(%rdi), %xmm0
-; X64-SSE2-NEXT:    pcmpeqb {{.*}}(%rip), %xmm0
-; X64-SSE2-NEXT:    pmovmskb %xmm0, %ecx
-; X64-SSE2-NEXT:    xorl %eax, %eax
-; X64-SSE2-NEXT:    cmpl $65535, %ecx # imm = 0xFFFF
-; X64-SSE2-NEXT:    je .LBB26_3
-; X64-SSE2-NEXT:  .LBB26_2: # %res_block
-; X64-SSE2-NEXT:    movl $1, %eax
-; X64-SSE2-NEXT:  .LBB26_3: # %endblock
-; X64-SSE2-NEXT:    testl %eax, %eax
 ; X64-SSE2-NEXT:    setne %al
 ; X64-SSE2-NEXT:    retq
 ;
 ; X64-AVX1-LABEL: length32_eq_const:
 ; X64-AVX1:       # %bb.0:
 ; X64-AVX1-NEXT:    vmovdqu (%rdi), %xmm0
+; X64-AVX1-NEXT:    vmovdqu 16(%rdi), %xmm1
+; X64-AVX1-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm1, %xmm1
 ; X64-AVX1-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0
+; X64-AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; X64-AVX1-NEXT:    vpmovmskb %xmm0, %eax
 ; X64-AVX1-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
-; X64-AVX1-NEXT:    jne .LBB26_2
-; X64-AVX1-NEXT:  # %bb.1: # %loadbb1
-; X64-AVX1-NEXT:    vmovdqu 16(%rdi), %xmm0
-; X64-AVX1-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0
-; X64-AVX1-NEXT:    vpmovmskb %xmm0, %ecx
-; X64-AVX1-NEXT:    xorl %eax, %eax
-; X64-AVX1-NEXT:    cmpl $65535, %ecx # imm = 0xFFFF
-; X64-AVX1-NEXT:    je .LBB26_3
-; X64-AVX1-NEXT:  .LBB26_2: # %res_block
-; X64-AVX1-NEXT:    movl $1, %eax
-; X64-AVX1-NEXT:  .LBB26_3: # %endblock
-; X64-AVX1-NEXT:    testl %eax, %eax
 ; X64-AVX1-NEXT:    setne %al
 ; X64-AVX1-NEXT:    retq
 ;
 ; X64-AVX2-LABEL: length32_eq_const:
 ; X64-AVX2:       # %bb.0:
 ; X64-AVX2-NEXT:    vmovdqu (%rdi), %ymm0
 ; X64-AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
 ; X64-AVX2-NEXT:    vpmovmskb %ymm0, %eax

 ; X64-AVX1-NEXT:    testl %eax, %eax
 ; X64-AVX1-NEXT:    setne %al
 ; X64-AVX1-NEXT:    popq %rcx
 ; X64-AVX1-NEXT:    retq
 ;
 ; X64-AVX2-LABEL: length64_eq:
 ; X64-AVX2:       # %bb.0:
 ; X64-AVX2-NEXT:    vmovdqu (%rdi), %ymm0
+; X64-AVX2-NEXT:    vmovdqu 32(%rdi), %ymm1
+; X64-AVX2-NEXT:    vpcmpeqb 32(%rsi), %ymm1, %ymm1
 ; X64-AVX2-NEXT:    vpcmpeqb (%rsi), %ymm0, %ymm0
+; X64-AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
 ; X64-AVX2-NEXT:    vpmovmskb %ymm0, %eax
 ; X64-AVX2-NEXT:    cmpl $-1, %eax
-; X64-AVX2-NEXT:    jne .LBB28_2
-; X64-AVX2-NEXT:  # %bb.1: # %loadbb1
-; X64-AVX2-NEXT:    vmovdqu 32(%rdi), %ymm0
-; X64-AVX2-NEXT:    vpcmpeqb 32(%rsi), %ymm0, %ymm0
-; X64-AVX2-NEXT:    vpmovmskb %ymm0, %ecx
-; X64-AVX2-NEXT:    xorl %eax, %eax
-; X64-AVX2-NEXT:    cmpl $-1, %ecx
-; X64-AVX2-NEXT:    je .LBB28_3
-; X64-AVX2-NEXT:  .LBB28_2: # %res_block
-; X64-AVX2-NEXT:    movl $1, %eax
-; X64-AVX2-NEXT:  .LBB28_3: # %endblock
-; X64-AVX2-NEXT:    testl %eax, %eax
 ; X64-AVX2-NEXT:    setne %al
 ; X64-AVX2-NEXT:    vzeroupper
 ; X64-AVX2-NEXT:    retq
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 64) nounwind
   %cmp = icmp ne i32 %call, 0
   ret i1 %cmp
 }
 

 ; X64-AVX1-NEXT:    testl %eax, %eax
 ; X64-AVX1-NEXT:    sete %al
 ; X64-AVX1-NEXT:    popq %rcx
 ; X64-AVX1-NEXT:    retq
 ;
 ; X64-AVX2-LABEL: length64_eq_const:
 ; X64-AVX2:       # %bb.0:
 ; X64-AVX2-NEXT:    vmovdqu (%rdi), %ymm0
+; X64-AVX2-NEXT:    vmovdqu 32(%rdi), %ymm1
+; X64-AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm1, %ymm1
 ; X64-AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
+; X64-AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
 ; X64-AVX2-NEXT:    vpmovmskb %ymm0, %eax
 ; X64-AVX2-NEXT:    cmpl $-1, %eax
-; X64-AVX2-NEXT:    jne .LBB29_2
-; X64-AVX2-NEXT:  # %bb.1: # %loadbb1
-; X64-AVX2-NEXT:    vmovdqu 32(%rdi), %ymm0
-; X64-AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
-; X64-AVX2-NEXT:    vpmovmskb %ymm0, %ecx
-; X64-AVX2-NEXT:    xorl %eax, %eax
-; X64-AVX2-NEXT:    cmpl $-1, %ecx
-; X64-AVX2-NEXT:    je .LBB29_3
-; X64-AVX2-NEXT:  .LBB29_2: # %res_block
-; X64-AVX2-NEXT:    movl $1, %eax
-; X64-AVX2-NEXT:  .LBB29_3: # %endblock
-; X64-AVX2-NEXT:    testl %eax, %eax
 ; X64-AVX2-NEXT:    sete %al
 ; X64-AVX2-NEXT:    vzeroupper
 ; X64-AVX2-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 64) nounwind
   %c = icmp eq i32 %m, 0
   ret i1 %c
 }
 

llvm/trunk/test/Transforms/ExpandMemCmp/X86/memcmp.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -S -expandmemcmp -mtriple=i686-unknown-unknown   -data-layout=e-m:o-p:32:32-f64:32:64-f80:128-n8:16:32-S128 < %s | FileCheck %s --check-prefix=ALL --check-prefix=X32
-; RUN: opt -S -expandmemcmp -mtriple=x86_64-unknown-unknown -data-layout=e-m:o-i64:64-f80:128-n8:16:32:64-S128         < %s | FileCheck %s --check-prefix=ALL --check-prefix=X64
+; RUN: opt -S -expandmemcmp -memcmp-num-loads-per-block=1 -mtriple=x86_64-unknown-unknown -data-layout=e-m:o-i64:64-f80:128-n8:16:32:64-S128         < %s | FileCheck %s --check-prefix=ALL --check-prefix=X64 --check-prefix=X64_1LD
+; RUN: opt -S -expandmemcmp -memcmp-num-loads-per-block=2 -mtriple=x86_64-unknown-unknown -data-layout=e-m:o-i64:64-f80:128-n8:16:32:64-S128         < %s | FileCheck %s --check-prefix=ALL --check-prefix=X64 --check-prefix=X64_2LD
 
 declare i32 @memcmp(i8* nocapture, i8* nocapture, i64)
 
 define i32 @cmp2(i8* nocapture readonly %x, i8* nocapture readonly %y)  {
 ; ALL-LABEL: @cmp2(
 ; ALL-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i16*
 ; ALL-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i16*
 ; ALL-NEXT:    [[TMP3:%.*]] = load i16, i16* [[TMP1]]

 ;
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 2)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @cmp_eq3(i8* nocapture readonly %x, i8* nocapture readonly %y)  {
-; ALL-LABEL: @cmp_eq3(
-; ALL-NEXT:    br label [[LOADBB:%.*]]
-; ALL:       res_block:
-; ALL-NEXT:    br label [[ENDBLOCK:%.*]]
-; ALL:       loadbb:
-; ALL-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i16*
-; ALL-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i16*
-; ALL-NEXT:    [[TMP3:%.*]] = load i16, i16* [[TMP1]]
-; ALL-NEXT:    [[TMP4:%.*]] = load i16, i16* [[TMP2]]
-; ALL-NEXT:    [[TMP5:%.*]] = icmp ne i16 [[TMP3]], [[TMP4]]
-; ALL-NEXT:    br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]]
-; ALL:       loadbb1:
-; ALL-NEXT:    [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 2
-; ALL-NEXT:    [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 2
-; ALL-NEXT:    [[TMP8:%.*]] = load i8, i8* [[TMP6]]
-; ALL-NEXT:    [[TMP9:%.*]] = load i8, i8* [[TMP7]]
-; ALL-NEXT:    [[TMP10:%.*]] = icmp ne i8 [[TMP8]], [[TMP9]]
-; ALL-NEXT:    br i1 [[TMP10]], label [[RES_BLOCK]], label [[ENDBLOCK]]
-; ALL:       endblock:
-; ALL-NEXT:    [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ]
-; ALL-NEXT:    [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0
-; ALL-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
-; ALL-NEXT:    ret i32 [[CONV]]
+; X32-LABEL: @cmp_eq3(
+; X32-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i16*
+; X32-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i16*
+; X32-NEXT:    [[TMP3:%.*]] = load i16, i16* [[TMP1]]
+; X32-NEXT:    [[TMP4:%.*]] = load i16, i16* [[TMP2]]
+; X32-NEXT:    [[TMP5:%.*]] = xor i16 [[TMP3]], [[TMP4]]
+; X32-NEXT:    [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 2
+; X32-NEXT:    [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 2
+; X32-NEXT:    [[TMP8:%.*]] = load i8, i8* [[TMP6]]
+; X32-NEXT:    [[TMP9:%.*]] = load i8, i8* [[TMP7]]
+; X32-NEXT:    [[TMP10:%.*]] = zext i8 [[TMP8]] to i16
+; X32-NEXT:    [[TMP11:%.*]] = zext i8 [[TMP9]] to i16
+; X32-NEXT:    [[TMP12:%.*]] = xor i16 [[TMP10]], [[TMP11]]
+; X32-NEXT:    [[TMP13:%.*]] = or i16 [[TMP5]], [[TMP12]]
+; X32-NEXT:    [[TMP14:%.*]] = icmp ne i16 [[TMP13]], 0
+; X32-NEXT:    [[TMP15:%.*]] = zext i1 [[TMP14]] to i32
+; X32-NEXT:    [[CMP:%.*]] = icmp eq i32 [[TMP15]], 0
+; X32-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X32-NEXT:    ret i32 [[CONV]]
+;
+; X64_1LD-LABEL: @cmp_eq3(
+; X64_1LD-NEXT:    br label [[LOADBB:%.*]]
+; X64_1LD:       res_block:
+; X64_1LD-NEXT:    br label [[ENDBLOCK:%.*]]
+; X64_1LD:       loadbb:
+; X64_1LD-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i16*
+; X64_1LD-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i16*
+; X64_1LD-NEXT:    [[TMP3:%.*]] = load i16, i16* [[TMP1]]
+; X64_1LD-NEXT:    [[TMP4:%.*]] = load i16, i16* [[TMP2]]
+; X64_1LD-NEXT:    [[TMP5:%.*]] = icmp ne i16 [[TMP3]], [[TMP4]]
+; X64_1LD-NEXT:    br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]]
+; X64_1LD:       loadbb1:
+; X64_1LD-NEXT:    [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 2
+; X64_1LD-NEXT:    [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 2
+; X64_1LD-NEXT:    [[TMP8:%.*]] = load i8, i8* [[TMP6]]
+; X64_1LD-NEXT:    [[TMP9:%.*]] = load i8, i8* [[TMP7]]
+; X64_1LD-NEXT:    [[TMP10:%.*]] = icmp ne i8 [[TMP8]], [[TMP9]]
+; X64_1LD-NEXT:    br i1 [[TMP10]], label [[RES_BLOCK]], label [[ENDBLOCK]]
+; X64_1LD:       endblock:
+; X64_1LD-NEXT:    [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ]
+; X64_1LD-NEXT:    [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0
+; X64_1LD-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X64_1LD-NEXT:    ret i32 [[CONV]]
+;
+; X64_2LD-LABEL: @cmp_eq3(
+; X64_2LD-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i16*
+; X64_2LD-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i16*
+; X64_2LD-NEXT:    [[TMP3:%.*]] = load i16, i16* [[TMP1]]
+; X64_2LD-NEXT:    [[TMP4:%.*]] = load i16, i16* [[TMP2]]
+; X64_2LD-NEXT:    [[TMP5:%.*]] = xor i16 [[TMP3]], [[TMP4]]
+; X64_2LD-NEXT:    [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 2
+; X64_2LD-NEXT:    [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 2
+; X64_2LD-NEXT:    [[TMP8:%.*]] = load i8, i8* [[TMP6]]
+; X64_2LD-NEXT:    [[TMP9:%.*]] = load i8, i8* [[TMP7]]
+; X64_2LD-NEXT:    [[TMP10:%.*]] = zext i8 [[TMP8]] to i16
+; X64_2LD-NEXT:    [[TMP11:%.*]] = zext i8 [[TMP9]] to i16
+; X64_2LD-NEXT:    [[TMP12:%.*]] = xor i16 [[TMP10]], [[TMP11]]
+; X64_2LD-NEXT:    [[TMP13:%.*]] = or i16 [[TMP5]], [[TMP12]]
+; X64_2LD-NEXT:    [[TMP14:%.*]] = icmp ne i16 [[TMP13]], 0
+; X64_2LD-NEXT:    [[TMP15:%.*]] = zext i1 [[TMP14]] to i32
+; X64_2LD-NEXT:    [[CMP:%.*]] = icmp eq i32 [[TMP15]], 0
+; X64_2LD-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X64_2LD-NEXT:    ret i32 [[CONV]]
 ;
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 3)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @cmp_eq4(i8* nocapture readonly %x, i8* nocapture readonly %y)  {

 ;
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 4)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @cmp_eq5(i8* nocapture readonly %x, i8* nocapture readonly %y)  {
-; ALL-LABEL: @cmp_eq5(
-; ALL-NEXT:    br label [[LOADBB:%.*]]
-; ALL:       res_block:
-; ALL-NEXT:    br label [[ENDBLOCK:%.*]]
-; ALL:       loadbb:
-; ALL-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32*
-; ALL-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i32*
-; ALL-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1]]
-; ALL-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP2]]
-; ALL-NEXT:    [[TMP5:%.*]] = icmp ne i32 [[TMP3]], [[TMP4]]
-; ALL-NEXT:    br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]]
-; ALL:       loadbb1:
-; ALL-NEXT:    [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 4
-; ALL-NEXT:    [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 4
-; ALL-NEXT:    [[TMP8:%.*]] = load i8, i8* [[TMP6]]
-; ALL-NEXT:    [[TMP9:%.*]] = load i8, i8* [[TMP7]]
-; ALL-NEXT:    [[TMP10:%.*]] = icmp ne i8 [[TMP8]], [[TMP9]]
-; ALL-NEXT:    br i1 [[TMP10]], label [[RES_BLOCK]], label [[ENDBLOCK]]
-; ALL:       endblock:
-; ALL-NEXT:    [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ]
-; ALL-NEXT:    [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0
-; ALL-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
-; ALL-NEXT:    ret i32 [[CONV]]
+; X32-LABEL: @cmp_eq5(
+; X32-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32*
+; X32-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i32*
+; X32-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1]]
+; X32-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP2]]
+; X32-NEXT:    [[TMP5:%.*]] = xor i32 [[TMP3]], [[TMP4]]
+; X32-NEXT:    [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 4
+; X32-NEXT:    [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 4
+; X32-NEXT:    [[TMP8:%.*]] = load i8, i8* [[TMP6]]
+; X32-NEXT:    [[TMP9:%.*]] = load i8, i8* [[TMP7]]
+; X32-NEXT:    [[TMP10:%.*]] = zext i8 [[TMP8]] to i32
+; X32-NEXT:    [[TMP11:%.*]] = zext i8 [[TMP9]] to i32
+; X32-NEXT:    [[TMP12:%.*]] = xor i32 [[TMP10]], [[TMP11]]
+; X32-NEXT:    [[TMP13:%.*]] = or i32 [[TMP5]], [[TMP12]]
+; X32-NEXT:    [[TMP14:%.*]] = icmp ne i32 [[TMP13]], 0
+; X32-NEXT:    [[TMP15:%.*]] = zext i1 [[TMP14]] to i32
+; X32-NEXT:    [[CMP:%.*]] = icmp eq i32 [[TMP15]], 0
+; X32-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X32-NEXT:    ret i32 [[CONV]]
+;
+; X64_1LD-LABEL: @cmp_eq5(
+; X64_1LD-NEXT:    br label [[LOADBB:%.*]]
+; X64_1LD:       res_block:
+; X64_1LD-NEXT:    br label [[ENDBLOCK:%.*]]
+; X64_1LD:       loadbb:
+; X64_1LD-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32*
+; X64_1LD-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i32*
+; X64_1LD-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1]]
+; X64_1LD-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP2]]
+; X64_1LD-NEXT:    [[TMP5:%.*]] = icmp ne i32 [[TMP3]], [[TMP4]]
+; X64_1LD-NEXT:    br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]]
+; X64_1LD:       loadbb1:
+; X64_1LD-NEXT:    [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 4
+; X64_1LD-NEXT:    [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 4
+; X64_1LD-NEXT:    [[TMP8:%.*]] = load i8, i8* [[TMP6]]
+; X64_1LD-NEXT:    [[TMP9:%.*]] = load i8, i8* [[TMP7]]
+; X64_1LD-NEXT:    [[TMP10:%.*]] = icmp ne i8 [[TMP8]], [[TMP9]]
+; X64_1LD-NEXT:    br i1 [[TMP10]], label [[RES_BLOCK]], label [[ENDBLOCK]]
+; X64_1LD:       endblock:
+; X64_1LD-NEXT:    [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ]
+; X64_1LD-NEXT:    [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0
+; X64_1LD-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X64_1LD-NEXT:    ret i32 [[CONV]]
+;
+; X64_2LD-LABEL: @cmp_eq5(
+; X64_2LD-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32*
+; X64_2LD-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i32*
+; X64_2LD-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1]]
+; X64_2LD-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP2]]
+; X64_2LD-NEXT:    [[TMP5:%.*]] = xor i32 [[TMP3]], [[TMP4]]
+; X64_2LD-NEXT:    [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 4
+; X64_2LD-NEXT:    [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 4
+; X64_2LD-NEXT:    [[TMP8:%.*]] = load i8, i8* [[TMP6]]
+; X64_2LD-NEXT:    [[TMP9:%.*]] = load i8, i8* [[TMP7]]
+; X64_2LD-NEXT:    [[TMP10:%.*]] = zext i8 [[TMP8]] to i32
+; X64_2LD-NEXT:    [[TMP11:%.*]] = zext i8 [[TMP9]] to i32
+; X64_2LD-NEXT:    [[TMP12:%.*]] = xor i32 [[TMP10]], [[TMP11]]
+; X64_2LD-NEXT:    [[TMP13:%.*]] = or i32 [[TMP5]], [[TMP12]]
+; X64_2LD-NEXT:    [[TMP14:%.*]] = icmp ne i32 [[TMP13]], 0
+; X64_2LD-NEXT:    [[TMP15:%.*]] = zext i1 [[TMP14]] to i32
+; X64_2LD-NEXT:    [[CMP:%.*]] = icmp eq i32 [[TMP15]], 0
+; X64_2LD-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X64_2LD-NEXT:    ret i32 [[CONV]]
 ;
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 5)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @cmp_eq6(i8* nocapture readonly %x, i8* nocapture readonly %y)  {
-; ALL-LABEL: @cmp_eq6(
-; ALL-NEXT:    br label [[LOADBB:%.*]]
-; ALL:       res_block:
-; ALL-NEXT:    br label [[ENDBLOCK:%.*]]
-; ALL:       loadbb:
-; ALL-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32*
-; ALL-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i32*
-; ALL-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1]]
-; ALL-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP2]]
-; ALL-NEXT:    [[TMP5:%.*]] = icmp ne i32 [[TMP3]], [[TMP4]]
-; ALL-NEXT:    br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]]
-; ALL:       loadbb1:
-; ALL-NEXT:    [[TMP6:%.*]] = bitcast i8* [[X]] to i16*
-; ALL-NEXT:    [[TMP7:%.*]] = bitcast i8* [[Y]] to i16*
-; ALL-NEXT:    [[TMP8:%.*]] = getelementptr i16, i16* [[TMP6]], i16 2
-; ALL-NEXT:    [[TMP9:%.*]] = getelementptr i16, i16* [[TMP7]], i16 2
-; ALL-NEXT:    [[TMP10:%.*]] = load i16, i16* [[TMP8]]
-; ALL-NEXT:    [[TMP11:%.*]] = load i16, i16* [[TMP9]]
-; ALL-NEXT:    [[TMP12:%.*]] = icmp ne i16 [[TMP10]], [[TMP11]]
-; ALL-NEXT:    br i1 [[TMP12]], label [[RES_BLOCK]], label [[ENDBLOCK]]
-; ALL:       endblock:
-; ALL-NEXT:    [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ]
-; ALL-NEXT:    [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0
-; ALL-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
-; ALL-NEXT:    ret i32 [[CONV]]
+; X32-LABEL: @cmp_eq6(
+; X32-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32*
+; X32-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i32*
+; X32-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1]]
+; X32-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP2]]
+; X32-NEXT:    [[TMP5:%.*]] = xor i32 [[TMP3]], [[TMP4]]
+; X32-NEXT:    [[TMP6:%.*]] = bitcast i8* [[X]] to i16*
+; X32-NEXT:    [[TMP7:%.*]] = bitcast i8* [[Y]] to i16*
+; X32-NEXT:    [[TMP8:%.*]] = getelementptr i16, i16* [[TMP6]], i16 2
+; X32-NEXT:    [[TMP9:%.*]] = getelementptr i16, i16* [[TMP7]], i16 2
+; X32-NEXT:    [[TMP10:%.*]] = load i16, i16* [[TMP8]]
+; X32-NEXT:    [[TMP11:%.*]] = load i16, i16* [[TMP9]]
+; X32-NEXT:    [[TMP12:%.*]] = zext i16 [[TMP10]] to i32
+; X32-NEXT:    [[TMP13:%.*]] = zext i16 [[TMP11]] to i32
+; X32-NEXT:    [[TMP14:%.*]] = xor i32 [[TMP12]], [[TMP13]]
+; X32-NEXT:    [[TMP15:%.*]] = or i32 [[TMP5]], [[TMP14]]
+; X32-NEXT:    [[TMP16:%.*]] = icmp ne i32 [[TMP15]], 0
+; X32-NEXT:    [[TMP17:%.*]] = zext i1 [[TMP16]] to i32
+; X32-NEXT:    [[CMP:%.*]] = icmp eq i32 [[TMP17]], 0
+; X32-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X32-NEXT:    ret i32 [[CONV]]
+;
+; X64_1LD-LABEL: @cmp_eq6(
+; X64_1LD-NEXT:    br label [[LOADBB:%.*]]
+; X64_1LD:       res_block:
+; X64_1LD-NEXT:    br label [[ENDBLOCK:%.*]]
+; X64_1LD:       loadbb:
+; X64_1LD-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32*
+; X64_1LD-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i32*
+; X64_1LD-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1]]
+; X64_1LD-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP2]]
+; X64_1LD-NEXT:    [[TMP5:%.*]] = icmp ne i32 [[TMP3]], [[TMP4]]
+; X64_1LD-NEXT:    br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]]
+; X64_1LD:       loadbb1:
+; X64_1LD-NEXT:    [[TMP6:%.*]] = bitcast i8* [[X]] to i16*
+; X64_1LD-NEXT:    [[TMP7:%.*]] = bitcast i8* [[Y]] to i16*
+; X64_1LD-NEXT:    [[TMP8:%.*]] = getelementptr i16, i16* [[TMP6]], i16 2
+; X64_1LD-NEXT:    [[TMP9:%.*]] = getelementptr i16, i16* [[TMP7]], i16 2
+; X64_1LD-NEXT:    [[TMP10:%.*]] = load i16, i16* [[TMP8]]
+; X64_1LD-NEXT:    [[TMP11:%.*]] = load i16, i16* [[TMP9]]
+; X64_1LD-NEXT:    [[TMP12:%.*]] = icmp ne i16 [[TMP10]], [[TMP11]]
+; X64_1LD-NEXT:    br i1 [[TMP12]], label [[RES_BLOCK]], label [[ENDBLOCK]]
+; X64_1LD:       endblock:
+; X64_1LD-NEXT:    [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ]
+; X64_1LD-NEXT:    [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0
+; X64_1LD-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X64_1LD-NEXT:    ret i32 [[CONV]]
+;
+; X64_2LD-LABEL: @cmp_eq6(
+; X64_2LD-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32*
+; X64_2LD-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i32*
+; X64_2LD-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1]]
+; X64_2LD-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP2]]
+; X64_2LD-NEXT:    [[TMP5:%.*]] = xor i32 [[TMP3]], [[TMP4]]
+; X64_2LD-NEXT:    [[TMP6:%.*]] = bitcast i8* [[X]] to i16*
+; X64_2LD-NEXT:    [[TMP7:%.*]] = bitcast i8* [[Y]] to i16*
+; X64_2LD-NEXT:    [[TMP8:%.*]] = getelementptr i16, i16* [[TMP6]], i16 2
+; X64_2LD-NEXT:    [[TMP9:%.*]] = getelementptr i16, i16* [[TMP7]], i16 2
+; X64_2LD-NEXT:    [[TMP10:%.*]] = load i16, i16* [[TMP8]]
+; X64_2LD-NEXT:    [[TMP11:%.*]] = load i16, i16* [[TMP9]]
+; X64_2LD-NEXT:    [[TMP12:%.*]] = zext i16 [[TMP10]] to i32
+; X64_2LD-NEXT:    [[TMP13:%.*]] = zext i16 [[TMP11]] to i32
+; X64_2LD-NEXT:    [[TMP14:%.*]] = xor i32 [[TMP12]], [[TMP13]]
+; X64_2LD-NEXT:    [[TMP15:%.*]] = or i32 [[TMP5]], [[TMP14]]
+; X64_2LD-NEXT:    [[TMP16:%.*]] = icmp ne i32 [[TMP15]], 0
+; X64_2LD-NEXT:    [[TMP17:%.*]] = zext i1 [[TMP16]] to i32
+; X64_2LD-NEXT:    [[CMP:%.*]] = icmp eq i32 [[TMP17]], 0
+; X64_2LD-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X64_2LD-NEXT:    ret i32 [[CONV]]
 ;
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 6)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @cmp_eq7(i8* nocapture readonly %x, i8* nocapture readonly %y)  {
 ; ALL-LABEL: @cmp_eq7(
 ; ALL-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 7)
 ; ALL-NEXT:    [[CMP:%.*]] = icmp eq i32 [[CALL]], 0
 ; ALL-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; ALL-NEXT:    ret i32 [[CONV]]
 ;
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 7)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @cmp_eq8(i8* nocapture readonly %x, i8* nocapture readonly %y)  {
 ; X32-LABEL: @cmp_eq8(
-; X32-NEXT:    br label [[LOADBB:%.*]]
-; X32:       res_block:
-; X32-NEXT:    br label [[ENDBLOCK:%.*]]
-; X32:       loadbb:
 ; X32-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i32*
 ; X32-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i32*
 ; X32-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1]]
 ; X32-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP2]]
-; X32-NEXT:    [[TMP5:%.*]] = icmp ne i32 [[TMP3]], [[TMP4]]
-; X32-NEXT:    br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]]
-; X32:       loadbb1:
+; X32-NEXT:    [[TMP5:%.*]] = xor i32 [[TMP3]], [[TMP4]]
 ; X32-NEXT:    [[TMP6:%.*]] = bitcast i8* [[X]] to i32*
 ; X32-NEXT:    [[TMP7:%.*]] = bitcast i8* [[Y]] to i32*
 ; X32-NEXT:    [[TMP8:%.*]] = getelementptr i32, i32* [[TMP6]], i32 1
 ; X32-NEXT:    [[TMP9:%.*]] = getelementptr i32, i32* [[TMP7]], i32 1
 ; X32-NEXT:    [[TMP10:%.*]] = load i32, i32* [[TMP8]]
 ; X32-NEXT:    [[TMP11:%.*]] = load i32, i32* [[TMP9]]
-; X32-NEXT:    [[TMP12:%.*]] = icmp ne i32 [[TMP10]], [[TMP11]]
-; X32-NEXT:    br i1 [[TMP12]], label [[RES_BLOCK]], label [[ENDBLOCK]]
-; X32:       endblock:
-; X32-NEXT:    [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ]
-; X32-NEXT:    [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0
+; X32-NEXT:    [[TMP12:%.*]] = xor i32 [[TMP10]], [[TMP11]]
+; X32-NEXT:    [[TMP13:%.*]] = or i32 [[TMP5]], [[TMP12]]
+; X32-NEXT:    [[TMP14:%.*]] = icmp ne i32 [[TMP13]], 0
+; X32-NEXT:    [[TMP15:%.*]] = zext i1 [[TMP14]] to i32
+; X32-NEXT:    [[CMP:%.*]] = icmp eq i32 [[TMP15]], 0
 ; X32-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; X32-NEXT:    ret i32 [[CONV]]
 ;
 ; X64-LABEL: @cmp_eq8(
 ; X64-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64*
 ; X64-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64*
 ; X64-NEXT:    [[TMP3:%.*]] = load i64, i64* [[TMP1]]
 ; X64-NEXT:    [[TMP4:%.*]] = load i64, i64* [[TMP2]]

 
 define i32 @cmp_eq9(i8* nocapture readonly %x, i8* nocapture readonly %y)  {
 ; X32-LABEL: @cmp_eq9(
 ; X32-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 9)
 ; X32-NEXT:    [[CMP:%.*]] = icmp eq i32 [[CALL]], 0
 ; X32-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; X32-NEXT:    ret i32 [[CONV]]
 ;
-; X64-LABEL: @cmp_eq9(
-; X64-NEXT:    br label [[LOADBB:%.*]]
-; X64:       res_block:
-; X64-NEXT:    br label [[ENDBLOCK:%.*]]
-; X64:       loadbb:
-; X64-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64*
-; X64-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64*
-; X64-NEXT:    [[TMP3:%.*]] = load i64, i64* [[TMP1]]
-; X64-NEXT:    [[TMP4:%.*]] = load i64, i64* [[TMP2]]
-; X64-NEXT:    [[TMP5:%.*]] = icmp ne i64 [[TMP3]], [[TMP4]]
-; X64-NEXT:    br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]]
-; X64:       loadbb1:
-; X64-NEXT:    [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 8
-; X64-NEXT:    [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 8
-; X64-NEXT:    [[TMP8:%.*]] = load i8, i8* [[TMP6]]
-; X64-NEXT:    [[TMP9:%.*]] = load i8, i8* [[TMP7]]
-; X64-NEXT:    [[TMP10:%.*]] = icmp ne i8 [[TMP8]], [[TMP9]]
-; X64-NEXT:    br i1 [[TMP10]], label [[RES_BLOCK]], label [[ENDBLOCK]]
-; X64:       endblock:
-; X64-NEXT:    [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ]
-; X64-NEXT:    [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0
-; X64-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
-; X64-NEXT:    ret i32 [[CONV]]
+; X64_1LD-LABEL: @cmp_eq9(
+; X64_1LD-NEXT:    br label [[LOADBB:%.*]]
+; X64_1LD:       res_block:
+; X64_1LD-NEXT:    br label [[ENDBLOCK:%.*]]
+; X64_1LD:       loadbb:
+; X64_1LD-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64*
+; X64_1LD-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64*
+; X64_1LD-NEXT:    [[TMP3:%.*]] = load i64, i64* [[TMP1]]
+; X64_1LD-NEXT:    [[TMP4:%.*]] = load i64, i64* [[TMP2]]
+; X64_1LD-NEXT:    [[TMP5:%.*]] = icmp ne i64 [[TMP3]], [[TMP4]]
+; X64_1LD-NEXT:    br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]]
+; X64_1LD:       loadbb1:
+; X64_1LD-NEXT:    [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 8
+; X64_1LD-NEXT:    [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 8
+; X64_1LD-NEXT:    [[TMP8:%.*]] = load i8, i8* [[TMP6]]
+; X64_1LD-NEXT:    [[TMP9:%.*]] = load i8, i8* [[TMP7]]
+; X64_1LD-NEXT:    [[TMP10:%.*]] = icmp ne i8 [[TMP8]], [[TMP9]]
+; X64_1LD-NEXT:    br i1 [[TMP10]], label [[RES_BLOCK]], label [[ENDBLOCK]]
+; X64_1LD:       endblock:
+; X64_1LD-NEXT:    [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ]
+; X64_1LD-NEXT:    [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0
+; X64_1LD-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X64_1LD-NEXT:    ret i32 [[CONV]]
+;
+; X64_2LD-LABEL: @cmp_eq9(
+; X64_2LD-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64*
+; X64_2LD-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64*
+; X64_2LD-NEXT:    [[TMP3:%.*]] = load i64, i64* [[TMP1]]
+; X64_2LD-NEXT:    [[TMP4:%.*]] = load i64, i64* [[TMP2]]
+; X64_2LD-NEXT:    [[TMP5:%.*]] = xor i64 [[TMP3]], [[TMP4]]
+; X64_2LD-NEXT:    [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 8
+; X64_2LD-NEXT:    [[TMP7:%.*]] = getelementptr i8, i8* [[Y]], i8 8
+; X64_2LD-NEXT:    [[TMP8:%.*]] = load i8, i8* [[TMP6]]
+; X64_2LD-NEXT:    [[TMP9:%.*]] = load i8, i8* [[TMP7]]
+; X64_2LD-NEXT:    [[TMP10:%.*]] = zext i8 [[TMP8]] to i64
+; X64_2LD-NEXT:    [[TMP11:%.*]] = zext i8 [[TMP9]] to i64
+; X64_2LD-NEXT:    [[TMP12:%.*]] = xor i64 [[TMP10]], [[TMP11]]
+; X64_2LD-NEXT:    [[TMP13:%.*]] = or i64 [[TMP5]], [[TMP12]]
+; X64_2LD-NEXT:    [[TMP14:%.*]] = icmp ne i64 [[TMP13]], 0
+; X64_2LD-NEXT:    [[TMP15:%.*]] = zext i1 [[TMP14]] to i32
+; X64_2LD-NEXT:    [[CMP:%.*]] = icmp eq i32 [[TMP15]], 0
+; X64_2LD-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X64_2LD-NEXT:    ret i32 [[CONV]]
 ;
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 9)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @cmp_eq10(i8* nocapture readonly %x, i8* nocapture readonly %y)  {
 ; X32-LABEL: @cmp_eq10(
 ; X32-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 10)
 ; X32-NEXT:    [[CMP:%.*]] = icmp eq i32 [[CALL]], 0
 ; X32-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; X32-NEXT:    ret i32 [[CONV]]
 ;
-; X64-LABEL: @cmp_eq10(
-; X64-NEXT:    br label [[LOADBB:%.*]]
-; X64:       res_block:
-; X64-NEXT:    br label [[ENDBLOCK:%.*]]
-; X64:       loadbb:
-; X64-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64*
-; X64-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64*
-; X64-NEXT:    [[TMP3:%.*]] = load i64, i64* [[TMP1]]
-; X64-NEXT:    [[TMP4:%.*]] = load i64, i64* [[TMP2]]
-; X64-NEXT:    [[TMP5:%.*]] = icmp ne i64 [[TMP3]], [[TMP4]]
-; X64-NEXT:    br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]]
-; X64:       loadbb1:
-; X64-NEXT:    [[TMP6:%.*]] = bitcast i8* [[X]] to i16*
-; X64-NEXT:    [[TMP7:%.*]] = bitcast i8* [[Y]] to i16*
-; X64-NEXT:    [[TMP8:%.*]] = getelementptr i16, i16* [[TMP6]], i16 4
-; X64-NEXT:    [[TMP9:%.*]] = getelementptr i16, i16* [[TMP7]], i16 4
-; X64-NEXT:    [[TMP10:%.*]] = load i16, i16* [[TMP8]]
-; X64-NEXT:    [[TMP11:%.*]] = load i16, i16* [[TMP9]]
-; X64-NEXT:    [[TMP12:%.*]] = icmp ne i16 [[TMP10]], [[TMP11]]
-; X64-NEXT:    br i1 [[TMP12]], label [[RES_BLOCK]], label [[ENDBLOCK]]
-; X64:       endblock:
-; X64-NEXT:    [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ]
-; X64-NEXT:    [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0
-; X64-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
-; X64-NEXT:    ret i32 [[CONV]]
+; X64_1LD-LABEL: @cmp_eq10(
+; X64_1LD-NEXT:    br label [[LOADBB:%.*]]
+; X64_1LD:       res_block:
+; X64_1LD-NEXT:    br label [[ENDBLOCK:%.*]]
+; X64_1LD:       loadbb:
+; X64_1LD-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64*
+; X64_1LD-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64*
+; X64_1LD-NEXT:    [[TMP3:%.*]] = load i64, i64* [[TMP1]]
+; X64_1LD-NEXT:    [[TMP4:%.*]] = load i64, i64* [[TMP2]]
+; X64_1LD-NEXT:    [[TMP5:%.*]] = icmp ne i64 [[TMP3]], [[TMP4]]
+; X64_1LD-NEXT:    br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]]
+; X64_1LD:       loadbb1:
+; X64_1LD-NEXT:    [[TMP6:%.*]] = bitcast i8* [[X]] to i16*
+; X64_1LD-NEXT:    [[TMP7:%.*]] = bitcast i8* [[Y]] to i16*
+; X64_1LD-NEXT:    [[TMP8:%.*]] = getelementptr i16, i16* [[TMP6]], i16 4
+; X64_1LD-NEXT:    [[TMP9:%.*]] = getelementptr i16, i16* [[TMP7]], i16 4
+; X64_1LD-NEXT:    [[TMP10:%.*]] = load i16, i16* [[TMP8]]
+; X64_1LD-NEXT:    [[TMP11:%.*]] = load i16, i16* [[TMP9]]
+; X64_1LD-NEXT:    [[TMP12:%.*]] = icmp ne i16 [[TMP10]], [[TMP11]]
+; X64_1LD-NEXT:    br i1 [[TMP12]], label [[RES_BLOCK]], label [[ENDBLOCK]]
+; X64_1LD:       endblock:
+; X64_1LD-NEXT:    [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ]
+; X64_1LD-NEXT:    [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0
+; X64_1LD-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X64_1LD-NEXT:    ret i32 [[CONV]]
+;
+; X64_2LD-LABEL: @cmp_eq10(
+; X64_2LD-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64*
+; X64_2LD-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64*
+; X64_2LD-NEXT:    [[TMP3:%.*]] = load i64, i64* [[TMP1]]
+; X64_2LD-NEXT:    [[TMP4:%.*]] = load i64, i64* [[TMP2]]
+; X64_2LD-NEXT:    [[TMP5:%.*]] = xor i64 [[TMP3]], [[TMP4]]
+; X64_2LD-NEXT:    [[TMP6:%.*]] = bitcast i8* [[X]] to i16*
+; X64_2LD-NEXT:    [[TMP7:%.*]] = bitcast i8* [[Y]] to i16*
+; X64_2LD-NEXT:    [[TMP8:%.*]] = getelementptr i16, i16* [[TMP6]], i16 4
+; X64_2LD-NEXT:    [[TMP9:%.*]] = getelementptr i16, i16* [[TMP7]], i16 4
+; X64_2LD-NEXT:    [[TMP10:%.*]] = load i16, i16* [[TMP8]]
+; X64_2LD-NEXT:    [[TMP11:%.*]] = load i16, i16* [[TMP9]]
+; X64_2LD-NEXT:    [[TMP12:%.*]] = zext i16 [[TMP10]] to i64
+; X64_2LD-NEXT:    [[TMP13:%.*]] = zext i16 [[TMP11]] to i64
+; X64_2LD-NEXT:    [[TMP14:%.*]] = xor i64 [[TMP12]], [[TMP13]]
+; X64_2LD-NEXT:    [[TMP15:%.*]] = or i64 [[TMP5]], [[TMP14]]
+; X64_2LD-NEXT:    [[TMP16:%.*]] = icmp ne i64 [[TMP15]], 0
+; X64_2LD-NEXT:    [[TMP17:%.*]] = zext i1 [[TMP16]] to i32
+; X64_2LD-NEXT:    [[CMP:%.*]] = icmp eq i32 [[TMP17]], 0
+; X64_2LD-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X64_2LD-NEXT:    ret i32 [[CONV]]
 ;
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 10)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @cmp_eq11(i8* nocapture readonly %x, i8* nocapture readonly %y)  {

 
 define i32 @cmp_eq12(i8* nocapture readonly %x, i8* nocapture readonly %y)  {
 ; X32-LABEL: @cmp_eq12(
 ; X32-NEXT:    [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 12)
 ; X32-NEXT:    [[CMP:%.*]] = icmp eq i32 [[CALL]], 0
 ; X32-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; X32-NEXT:    ret i32 [[CONV]]
 ;
-; X64-LABEL: @cmp_eq12(
-; X64-NEXT:    br label [[LOADBB:%.*]]
-; X64:       res_block:
-; X64-NEXT:    br label [[ENDBLOCK:%.*]]
-; X64:       loadbb:
-; X64-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64*
-; X64-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64*
-; X64-NEXT:    [[TMP3:%.*]] = load i64, i64* [[TMP1]]
-; X64-NEXT:    [[TMP4:%.*]] = load i64, i64* [[TMP2]]
-; X64-NEXT:    [[TMP5:%.*]] = icmp ne i64 [[TMP3]], [[TMP4]]
-; X64-NEXT:    br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]]
-; X64:       loadbb1:
-; X64-NEXT:    [[TMP6:%.*]] = bitcast i8* [[X]] to i32*
-; X64-NEXT:    [[TMP7:%.*]] = bitcast i8* [[Y]] to i32*
-; X64-NEXT:    [[TMP8:%.*]] = getelementptr i32, i32* [[TMP6]], i32 2
-; X64-NEXT:    [[TMP9:%.*]] = getelementptr i32, i32* [[TMP7]], i32 2
-; X64-NEXT:    [[TMP10:%.*]] = load i32, i32* [[TMP8]]
-; X64-NEXT:    [[TMP11:%.*]] = load i32, i32* [[TMP9]]
-; X64-NEXT:    [[TMP12:%.*]] = icmp ne i32 [[TMP10]], [[TMP11]]
-; X64-NEXT:    br i1 [[TMP12]], label [[RES_BLOCK]], label [[ENDBLOCK]]
-; X64:       endblock:
-; X64-NEXT:    [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ]
-; X64-NEXT:    [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0
-; X64-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
-; X64-NEXT:    ret i32 [[CONV]]
+; X64_1LD-LABEL: @cmp_eq12(
+; X64_1LD-NEXT:    br label [[LOADBB:%.*]]
+; X64_1LD:       res_block:
+; X64_1LD-NEXT:    br label [[ENDBLOCK:%.*]]
+; X64_1LD:       loadbb:
+; X64_1LD-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64*
+; X64_1LD-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64*
+; X64_1LD-NEXT:    [[TMP3:%.*]] = load i64, i64* [[TMP1]]
+; X64_1LD-NEXT:    [[TMP4:%.*]] = load i64, i64* [[TMP2]]
+; X64_1LD-NEXT:    [[TMP5:%.*]] = icmp ne i64 [[TMP3]], [[TMP4]]
+; X64_1LD-NEXT:    br i1 [[TMP5]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]]
+; X64_1LD:       loadbb1:
+; X64_1LD-NEXT:    [[TMP6:%.*]] = bitcast i8* [[X]] to i32*
+; X64_1LD-NEXT:    [[TMP7:%.*]] = bitcast i8* [[Y]] to i32*
+; X64_1LD-NEXT:    [[TMP8:%.*]] = getelementptr i32, i32* [[TMP6]], i32 2
+; X64_1LD-NEXT:    [[TMP9:%.*]] = getelementptr i32, i32* [[TMP7]], i32 2
+; X64_1LD-NEXT:    [[TMP10:%.*]] = load i32, i32* [[TMP8]]
+; X64_1LD-NEXT:    [[TMP11:%.*]] = load i32, i32* [[TMP9]]
+; X64_1LD-NEXT:    [[TMP12:%.*]] = icmp ne i32 [[TMP10]], [[TMP11]]
+; X64_1LD-NEXT:    br i1 [[TMP12]], label [[RES_BLOCK]], label [[ENDBLOCK]]
+; X64_1LD:       endblock:
+; X64_1LD-NEXT:    [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ]
+; X64_1LD-NEXT:    [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0
+; X64_1LD-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X64_1LD-NEXT:    ret i32 [[CONV]]
+;
+; X64_2LD-LABEL: @cmp_eq12(
+; X64_2LD-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i64*
+; X64_2LD-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64*
+; X64_2LD-NEXT:    [[TMP3:%.*]] = load i64, i64* [[TMP1]]
+; X64_2LD-NEXT:    [[TMP4:%.*]] = load i64, i64* [[TMP2]]
+; X64_2LD-NEXT:    [[TMP5:%.*]] = xor i64 [[TMP3]], [[TMP4]]
+; X64_2LD-NEXT:    [[TMP6:%.*]] = bitcast i8* [[X]] to i32*
+; X64_2LD-NEXT:    [[TMP7:%.*]] = bitcast i8* [[Y]] to i32*
+; X64_2LD-NEXT:    [[TMP8:%.*]] = getelementptr i32, i32* [[TMP6]], i32 2
+; X64_2LD-NEXT:    [[TMP9:%.*]] = getelementptr i32, i32* [[TMP7]], i32 2
+; X64_2LD-NEXT:    [[TMP10:%.*]] = load i32, i32* [[TMP8]]
+; X64_2LD-NEXT:    [[TMP11:%.*]] = load i32, i32* [[TMP9]]
+; X64_2LD-NEXT:    [[TMP12:%.*]] = zext i32 [[TMP10]] to i64
+; X64_2LD-NEXT:    [[TMP13:%.*]] = zext i32 [[TMP11]] to i64
+; X64_2LD-NEXT:    [[TMP14:%.*]] = xor i64 [[TMP12]], [[TMP13]]
+; X64_2LD-NEXT:    [[TMP15:%.*]] = or i64 [[TMP5]], [[TMP14]]
+; X64_2LD-NEXT:    [[TMP16:%.*]] = icmp ne i64 [[TMP15]], 0
+; X64_2LD-NEXT:    [[TMP17:%.*]] = zext i1 [[TMP16]] to i32
+; X64_2LD-NEXT:    [[CMP:%.*]] = icmp eq i32 [[TMP17]], 0
+; X64_2LD-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X64_2LD-NEXT:    ret i32 [[CONV]]
 ;
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 12)
   %cmp = icmp eq i32 %call, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
 define i32 @cmp_eq13(i8* nocapture readonly %x, i8* nocapture readonly %y)  {