summaryrefslogtreecommitdiffstats
path: root/llvm/test
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/test')
-rw-r--r--llvm/test/CodeGen/PowerPC/memcmpIR.ll24
-rw-r--r--llvm/test/CodeGen/X86/memcmp-optsize.ll73
-rw-r--r--llvm/test/CodeGen/X86/memcmp.ll161
-rw-r--r--llvm/test/Transforms/ExpandMemCmp/X86/memcmp.ll424
4 files changed, 508 insertions, 174 deletions
diff --git a/llvm/test/CodeGen/PowerPC/memcmpIR.ll b/llvm/test/CodeGen/PowerPC/memcmpIR.ll
index 9888519d8b6..4c0de720fc6 100644
--- a/llvm/test/CodeGen/PowerPC/memcmpIR.ll
+++ b/llvm/test/CodeGen/PowerPC/memcmpIR.ll
@@ -17,10 +17,14 @@ entry:
; CHECK-NEXT: br label %endblock
; CHECK-LABEL: loadbb1:{{.*}}
- ; CHECK: [[GEP1:%[0-9]+]] = getelementptr i64, i64* {{.*}}, i64 1
- ; CHECK-NEXT: [[GEP2:%[0-9]+]] = getelementptr i64, i64* {{.*}}, i64 1
- ; CHECK-NEXT: [[LOAD1:%[0-9]+]] = load i64, i64* [[GEP1]]
- ; CHECK-NEXT: [[LOAD2:%[0-9]+]] = load i64, i64* [[GEP2]]
+ ; CHECK: [[BCC1:%[0-9]+]] = bitcast i32* {{.*}} to i8*
+ ; CHECK-NEXT: [[BCC2:%[0-9]+]] = bitcast i32* {{.*}} to i8*
+ ; CHECK-NEXT: [[GEP1:%[0-9]+]] = getelementptr i8, i8* [[BCC2]], i8 8
+ ; CHECK-NEXT: [[BCL1:%[0-9]+]] = bitcast i8* [[GEP1]] to i64*
+ ; CHECK-NEXT: [[GEP2:%[0-9]+]] = getelementptr i8, i8* [[BCC1]], i8 8
+ ; CHECK-NEXT: [[BCL2:%[0-9]+]] = bitcast i8* [[GEP2]] to i64*
+ ; CHECK-NEXT: [[LOAD1:%[0-9]+]] = load i64, i64* [[BCL1]]
+ ; CHECK-NEXT: [[LOAD2:%[0-9]+]] = load i64, i64* [[BCL2]]
; CHECK-NEXT: [[BSWAP1:%[0-9]+]] = call i64 @llvm.bswap.i64(i64 [[LOAD1]])
; CHECK-NEXT: [[BSWAP2:%[0-9]+]] = call i64 @llvm.bswap.i64(i64 [[LOAD2]])
; CHECK-NEXT: [[ICMP:%[0-9]+]] = icmp eq i64 [[BSWAP1]], [[BSWAP2]]
@@ -38,10 +42,14 @@ entry:
; CHECK-BE-NEXT: br label %endblock
; CHECK-BE-LABEL: loadbb1:{{.*}}
- ; CHECK-BE: [[GEP1:%[0-9]+]] = getelementptr i64, i64* {{.*}}, i64 1
- ; CHECK-BE-NEXT: [[GEP2:%[0-9]+]] = getelementptr i64, i64* {{.*}}, i64 1
- ; CHECK-BE-NEXT: [[LOAD1:%[0-9]+]] = load i64, i64* [[GEP1]]
- ; CHECK-BE-NEXT: [[LOAD2:%[0-9]+]] = load i64, i64* [[GEP2]]
+ ; CHECK-BE: [[BCC1:%[0-9]+]] = bitcast i32* {{.*}} to i8*
+ ; CHECK-BE-NEXT: [[BCC2:%[0-9]+]] = bitcast i32* {{.*}} to i8*
+ ; CHECK-BE-NEXT: [[GEP1:%[0-9]+]] = getelementptr i8, i8* [[BCC2]], i8 8
+ ; CHECK-BE-NEXT: [[BCL1:%[0-9]+]] = bitcast i8* [[GEP1]] to i64*
+ ; CHECK-BE-NEXT: [[GEP2:%[0-9]+]] = getelementptr i8, i8* [[BCC1]], i8 8
+ ; CHECK-BE-NEXT: [[BCL2:%[0-9]+]] = bitcast i8* [[GEP2]] to i64*
+ ; CHECK-BE-NEXT: [[LOAD1:%[0-9]+]] = load i64, i64* [[BCL1]]
+ ; CHECK-BE-NEXT: [[LOAD2:%[0-9]+]] = load i64, i64* [[BCL2]]
; CHECK-BE-NEXT: [[ICMP:%[0-9]+]] = icmp eq i64 [[LOAD1]], [[LOAD2]]
; CHECK-BE-NEXT: br i1 [[ICMP]], label %endblock, label %res_block
diff --git a/llvm/test/CodeGen/X86/memcmp-optsize.ll b/llvm/test/CodeGen/X86/memcmp-optsize.ll
index 7683d1a4b31..d2b390f0943 100644
--- a/llvm/test/CodeGen/X86/memcmp-optsize.ll
+++ b/llvm/test/CodeGen/X86/memcmp-optsize.ll
@@ -639,17 +639,33 @@ define i32 @length24(i8* %X, i8* %Y) nounwind optsize {
}
define i1 @length24_eq(i8* %x, i8* %y) nounwind optsize {
-; X86-LABEL: length24_eq:
-; X86: # %bb.0:
-; X86-NEXT: pushl $0
-; X86-NEXT: pushl $24
-; X86-NEXT: pushl {{[0-9]+}}(%esp)
-; X86-NEXT: pushl {{[0-9]+}}(%esp)
-; X86-NEXT: calll memcmp
-; X86-NEXT: addl $16, %esp
-; X86-NEXT: testl %eax, %eax
-; X86-NEXT: sete %al
-; X86-NEXT: retl
+; X86-NOSSE-LABEL: length24_eq:
+; X86-NOSSE: # %bb.0:
+; X86-NOSSE-NEXT: pushl $0
+; X86-NOSSE-NEXT: pushl $24
+; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp)
+; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp)
+; X86-NOSSE-NEXT: calll memcmp
+; X86-NOSSE-NEXT: addl $16, %esp
+; X86-NOSSE-NEXT: testl %eax, %eax
+; X86-NOSSE-NEXT: sete %al
+; X86-NOSSE-NEXT: retl
+;
+; X86-SSE2-LABEL: length24_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 8(%ecx), %xmm1
+; X86-SSE2-NEXT: movdqu (%eax), %xmm2
+; X86-SSE2-NEXT: pcmpeqb %xmm0, %xmm2
+; X86-SSE2-NEXT: movdqu 8(%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: length24_eq:
; X64-SSE2: # %bb.0:
@@ -683,17 +699,30 @@ define i1 @length24_eq(i8* %x, i8* %y) nounwind optsize {
}
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
+; X86-NOSSE-LABEL: length24_eq_const:
+; X86-NOSSE: # %bb.0:
+; X86-NOSSE-NEXT: pushl $0
+; X86-NOSSE-NEXT: pushl $24
+; X86-NOSSE-NEXT: pushl $.L.str
+; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp)
+; X86-NOSSE-NEXT: calll memcmp
+; X86-NOSSE-NEXT: addl $16, %esp
+; X86-NOSSE-NEXT: testl %eax, %eax
+; X86-NOSSE-NEXT: setne %al
+; X86-NOSSE-NEXT: retl
+;
+; X86-SSE2-LABEL: length24_eq_const:
+; X86-SSE2: # %bb.0:
+; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-SSE2-NEXT: movdqu (%eax), %xmm0
+; X86-SSE2-NEXT: movdqu 8(%eax), %xmm1
+; X86-SSE2-NEXT: pcmpeqb {{\.LCPI.*}}, %xmm1
+; X86-SSE2-NEXT: pcmpeqb {{\.LCPI.*}}, %xmm0
+; 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: length24_eq_const:
; X64-SSE2: # %bb.0:
diff --git a/llvm/test/CodeGen/X86/memcmp.ll b/llvm/test/CodeGen/X86/memcmp.ll
index 0bb46eeeac9..371c16881ff 100644
--- a/llvm/test/CodeGen/X86/memcmp.ll
+++ b/llvm/test/CodeGen/X86/memcmp.ll
@@ -362,24 +362,24 @@ define i1 @length5_eq(i8* %X, i8* %Y) nounwind {
define i1 @length7_eq(i8* %X, i8* %Y) nounwind {
; X86-LABEL: length7_eq:
; X86: # %bb.0:
-; X86-NEXT: pushl $0
-; X86-NEXT: pushl $7
-; X86-NEXT: pushl {{[0-9]+}}(%esp)
-; X86-NEXT: pushl {{[0-9]+}}(%esp)
-; X86-NEXT: calll memcmp
-; X86-NEXT: addl $16, %esp
-; X86-NEXT: testl %eax, %eax
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl (%ecx), %edx
+; X86-NEXT: movl 3(%ecx), %ecx
+; X86-NEXT: xorl (%eax), %edx
+; X86-NEXT: xorl 3(%eax), %ecx
+; X86-NEXT: orl %edx, %ecx
; X86-NEXT: setne %al
; X86-NEXT: retl
;
; X64-LABEL: length7_eq:
; X64: # %bb.0:
-; X64-NEXT: pushq %rax
-; X64-NEXT: movl $7, %edx
-; X64-NEXT: callq memcmp
-; X64-NEXT: testl %eax, %eax
+; X64-NEXT: movl (%rdi), %eax
+; X64-NEXT: movl 3(%rdi), %ecx
+; X64-NEXT: xorl (%rsi), %eax
+; X64-NEXT: xorl 3(%rsi), %ecx
+; X64-NEXT: orl %eax, %ecx
; X64-NEXT: setne %al
-; X64-NEXT: popq %rcx
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 7) nounwind
%c = icmp ne i32 %m, 0
@@ -548,12 +548,12 @@ define i1 @length11_eq(i8* %X, i8* %Y) nounwind {
;
; X64-LABEL: length11_eq:
; X64: # %bb.0:
-; X64-NEXT: pushq %rax
-; X64-NEXT: movl $11, %edx
-; X64-NEXT: callq memcmp
-; X64-NEXT: testl %eax, %eax
+; X64-NEXT: movq (%rdi), %rax
+; X64-NEXT: movq 3(%rdi), %rcx
+; X64-NEXT: xorq (%rsi), %rax
+; X64-NEXT: xorq 3(%rsi), %rcx
+; X64-NEXT: orq %rax, %rcx
; X64-NEXT: sete %al
-; X64-NEXT: popq %rcx
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 11) nounwind
%c = icmp eq i32 %m, 0
@@ -640,12 +640,12 @@ define i1 @length13_eq(i8* %X, i8* %Y) nounwind {
;
; X64-LABEL: length13_eq:
; X64: # %bb.0:
-; X64-NEXT: pushq %rax
-; X64-NEXT: movl $13, %edx
-; X64-NEXT: callq memcmp
-; X64-NEXT: testl %eax, %eax
+; X64-NEXT: movq (%rdi), %rax
+; X64-NEXT: movq 5(%rdi), %rcx
+; X64-NEXT: xorq (%rsi), %rax
+; X64-NEXT: xorq 5(%rsi), %rcx
+; X64-NEXT: orq %rax, %rcx
; X64-NEXT: sete %al
-; X64-NEXT: popq %rcx
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 13) nounwind
%c = icmp eq i32 %m, 0
@@ -667,12 +667,12 @@ define i1 @length14_eq(i8* %X, i8* %Y) nounwind {
;
; X64-LABEL: length14_eq:
; X64: # %bb.0:
-; X64-NEXT: pushq %rax
-; X64-NEXT: movl $14, %edx
-; X64-NEXT: callq memcmp
-; X64-NEXT: testl %eax, %eax
+; X64-NEXT: movq (%rdi), %rax
+; X64-NEXT: movq 6(%rdi), %rcx
+; X64-NEXT: xorq (%rsi), %rax
+; X64-NEXT: xorq 6(%rsi), %rcx
+; X64-NEXT: orq %rax, %rcx
; X64-NEXT: sete %al
-; X64-NEXT: popq %rcx
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 14) nounwind
%c = icmp eq i32 %m, 0
@@ -694,12 +694,12 @@ define i1 @length15_eq(i8* %X, i8* %Y) nounwind {
;
; X64-LABEL: length15_eq:
; X64: # %bb.0:
-; X64-NEXT: pushq %rax
-; X64-NEXT: movl $15, %edx
-; X64-NEXT: callq memcmp
-; X64-NEXT: testl %eax, %eax
+; X64-NEXT: movq (%rdi), %rax
+; X64-NEXT: movq 7(%rdi), %rcx
+; X64-NEXT: xorq (%rsi), %rax
+; X64-NEXT: xorq 7(%rsi), %rcx
+; X64-NEXT: orq %rax, %rcx
; X64-NEXT: sete %al
-; X64-NEXT: popq %rcx
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 15) nounwind
%c = icmp eq i32 %m, 0
@@ -885,17 +885,45 @@ define i32 @length24(i8* %X, i8* %Y) nounwind {
}
define i1 @length24_eq(i8* %x, i8* %y) nounwind {
-; X86-LABEL: length24_eq:
-; X86: # %bb.0:
-; X86-NEXT: pushl $0
-; X86-NEXT: pushl $24
-; X86-NEXT: pushl {{[0-9]+}}(%esp)
-; X86-NEXT: pushl {{[0-9]+}}(%esp)
-; X86-NEXT: calll memcmp
-; X86-NEXT: addl $16, %esp
-; X86-NEXT: testl %eax, %eax
-; X86-NEXT: sete %al
-; X86-NEXT: retl
+; X86-NOSSE-LABEL: length24_eq:
+; X86-NOSSE: # %bb.0:
+; X86-NOSSE-NEXT: pushl $0
+; X86-NOSSE-NEXT: pushl $24
+; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp)
+; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp)
+; X86-NOSSE-NEXT: calll memcmp
+; X86-NOSSE-NEXT: addl $16, %esp
+; X86-NOSSE-NEXT: testl %eax, %eax
+; X86-NOSSE-NEXT: sete %al
+; X86-NOSSE-NEXT: retl
+;
+; X86-SSE1-LABEL: length24_eq:
+; X86-SSE1: # %bb.0:
+; X86-SSE1-NEXT: pushl $0
+; X86-SSE1-NEXT: pushl $24
+; X86-SSE1-NEXT: pushl {{[0-9]+}}(%esp)
+; X86-SSE1-NEXT: pushl {{[0-9]+}}(%esp)
+; X86-SSE1-NEXT: calll memcmp
+; X86-SSE1-NEXT: addl $16, %esp
+; X86-SSE1-NEXT: testl %eax, %eax
+; X86-SSE1-NEXT: sete %al
+; X86-SSE1-NEXT: retl
+;
+; X86-SSE2-LABEL: length24_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 8(%ecx), %xmm1
+; X86-SSE2-NEXT: movdqu (%eax), %xmm2
+; X86-SSE2-NEXT: pcmpeqb %xmm0, %xmm2
+; X86-SSE2-NEXT: movdqu 8(%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: length24_eq:
; X64-SSE2: # %bb.0:
@@ -929,17 +957,42 @@ define i1 @length24_eq(i8* %x, i8* %y) nounwind {
}
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
+; X86-NOSSE-LABEL: length24_eq_const:
+; X86-NOSSE: # %bb.0:
+; X86-NOSSE-NEXT: pushl $0
+; X86-NOSSE-NEXT: pushl $24
+; X86-NOSSE-NEXT: pushl $.L.str
+; X86-NOSSE-NEXT: pushl {{[0-9]+}}(%esp)
+; X86-NOSSE-NEXT: calll memcmp
+; X86-NOSSE-NEXT: addl $16, %esp
+; X86-NOSSE-NEXT: testl %eax, %eax
+; X86-NOSSE-NEXT: setne %al
+; X86-NOSSE-NEXT: retl
+;
+; X86-SSE1-LABEL: length24_eq_const:
+; X86-SSE1: # %bb.0:
+; X86-SSE1-NEXT: pushl $0
+; X86-SSE1-NEXT: pushl $24
+; X86-SSE1-NEXT: pushl $.L.str
+; X86-SSE1-NEXT: pushl {{[0-9]+}}(%esp)
+; X86-SSE1-NEXT: calll memcmp
+; X86-SSE1-NEXT: addl $16, %esp
+; X86-SSE1-NEXT: testl %eax, %eax
+; X86-SSE1-NEXT: setne %al
+; X86-SSE1-NEXT: retl
+;
+; X86-SSE2-LABEL: length24_eq_const:
+; X86-SSE2: # %bb.0:
+; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-SSE2-NEXT: movdqu (%eax), %xmm0
+; X86-SSE2-NEXT: movdqu 8(%eax), %xmm1
+; X86-SSE2-NEXT: pcmpeqb {{\.LCPI.*}}, %xmm1
+; X86-SSE2-NEXT: pcmpeqb {{\.LCPI.*}}, %xmm0
+; 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: length24_eq_const:
; X64-SSE2: # %bb.0:
diff --git a/llvm/test/Transforms/ExpandMemCmp/X86/memcmp.ll b/llvm/test/Transforms/ExpandMemCmp/X86/memcmp.ll
index 37bd85029b9..c1cbcc3272c 100644
--- a/llvm/test/Transforms/ExpandMemCmp/X86/memcmp.ll
+++ b/llvm/test/Transforms/ExpandMemCmp/X86/memcmp.ll
@@ -130,11 +130,11 @@ define i32 @cmp6(i8* nocapture readonly %x, i8* nocapture readonly %y) {
; ALL-NEXT: [[TMP9:%.*]] = icmp eq i32 [[TMP7]], [[TMP8]]
; ALL-NEXT: br i1 [[TMP9]], label [[LOADBB1]], label [[RES_BLOCK:%.*]]
; ALL: loadbb1:
-; ALL-NEXT: [[TMP10:%.*]] = bitcast i8* [[X]] to i16*
-; ALL-NEXT: [[TMP11:%.*]] = bitcast i8* [[Y]] to i16*
-; ALL-NEXT: [[TMP12:%.*]] = getelementptr i16, i16* [[TMP10]], i16 2
-; ALL-NEXT: [[TMP13:%.*]] = getelementptr i16, i16* [[TMP11]], i16 2
-; ALL-NEXT: [[TMP14:%.*]] = load i16, i16* [[TMP12]]
+; ALL-NEXT: [[TMP10:%.*]] = getelementptr i8, i8* [[X]], i8 4
+; ALL-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i16*
+; ALL-NEXT: [[TMP12:%.*]] = getelementptr i8, i8* [[Y]], i8 4
+; ALL-NEXT: [[TMP13:%.*]] = bitcast i8* [[TMP12]] to i16*
+; ALL-NEXT: [[TMP14:%.*]] = load i16, i16* [[TMP11]]
; ALL-NEXT: [[TMP15:%.*]] = load i16, i16* [[TMP13]]
; ALL-NEXT: [[TMP16:%.*]] = call i16 @llvm.bswap.i16(i16 [[TMP14]])
; ALL-NEXT: [[TMP17:%.*]] = call i16 @llvm.bswap.i16(i16 [[TMP15]])
@@ -178,11 +178,11 @@ define i32 @cmp8(i8* nocapture readonly %x, i8* nocapture readonly %y) {
; X32-NEXT: [[TMP9:%.*]] = icmp eq i32 [[TMP7]], [[TMP8]]
; X32-NEXT: br i1 [[TMP9]], label [[LOADBB1]], label [[RES_BLOCK:%.*]]
; X32: loadbb1:
-; X32-NEXT: [[TMP10:%.*]] = bitcast i8* [[X]] to i32*
-; X32-NEXT: [[TMP11:%.*]] = bitcast i8* [[Y]] to i32*
-; X32-NEXT: [[TMP12:%.*]] = getelementptr i32, i32* [[TMP10]], i32 1
-; X32-NEXT: [[TMP13:%.*]] = getelementptr i32, i32* [[TMP11]], i32 1
-; X32-NEXT: [[TMP14:%.*]] = load i32, i32* [[TMP12]]
+; X32-NEXT: [[TMP10:%.*]] = getelementptr i8, i8* [[X]], i8 4
+; X32-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
+; X32-NEXT: [[TMP12:%.*]] = getelementptr i8, i8* [[Y]], i8 4
+; X32-NEXT: [[TMP13:%.*]] = bitcast i8* [[TMP12]] to i32*
+; X32-NEXT: [[TMP14:%.*]] = load i32, i32* [[TMP11]]
; X32-NEXT: [[TMP15:%.*]] = load i32, i32* [[TMP13]]
; X32-NEXT: [[TMP16]] = call i32 @llvm.bswap.i32(i32 [[TMP14]])
; X32-NEXT: [[TMP17]] = call i32 @llvm.bswap.i32(i32 [[TMP15]])
@@ -272,11 +272,11 @@ define i32 @cmp10(i8* nocapture readonly %x, i8* nocapture readonly %y) {
; X64-NEXT: [[TMP9:%.*]] = icmp eq i64 [[TMP7]], [[TMP8]]
; X64-NEXT: br i1 [[TMP9]], label [[LOADBB1]], label [[RES_BLOCK:%.*]]
; X64: loadbb1:
-; X64-NEXT: [[TMP10:%.*]] = bitcast i8* [[X]] to i16*
-; X64-NEXT: [[TMP11:%.*]] = bitcast i8* [[Y]] to i16*
-; X64-NEXT: [[TMP12:%.*]] = getelementptr i16, i16* [[TMP10]], i16 4
-; X64-NEXT: [[TMP13:%.*]] = getelementptr i16, i16* [[TMP11]], i16 4
-; X64-NEXT: [[TMP14:%.*]] = load i16, i16* [[TMP12]]
+; X64-NEXT: [[TMP10:%.*]] = getelementptr i8, i8* [[X]], i8 8
+; X64-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i16*
+; X64-NEXT: [[TMP12:%.*]] = getelementptr i8, i8* [[Y]], i8 8
+; X64-NEXT: [[TMP13:%.*]] = bitcast i8* [[TMP12]] to i16*
+; X64-NEXT: [[TMP14:%.*]] = load i16, i16* [[TMP11]]
; X64-NEXT: [[TMP15:%.*]] = load i16, i16* [[TMP13]]
; X64-NEXT: [[TMP16:%.*]] = call i16 @llvm.bswap.i16(i16 [[TMP14]])
; X64-NEXT: [[TMP17:%.*]] = call i16 @llvm.bswap.i16(i16 [[TMP15]])
@@ -324,11 +324,11 @@ define i32 @cmp12(i8* nocapture readonly %x, i8* nocapture readonly %y) {
; X64-NEXT: [[TMP9:%.*]] = icmp eq i64 [[TMP7]], [[TMP8]]
; X64-NEXT: br i1 [[TMP9]], label [[LOADBB1]], label [[RES_BLOCK:%.*]]
; X64: loadbb1:
-; X64-NEXT: [[TMP10:%.*]] = bitcast i8* [[X]] to i32*
-; X64-NEXT: [[TMP11:%.*]] = bitcast i8* [[Y]] to i32*
-; X64-NEXT: [[TMP12:%.*]] = getelementptr i32, i32* [[TMP10]], i32 2
-; X64-NEXT: [[TMP13:%.*]] = getelementptr i32, i32* [[TMP11]], i32 2
-; X64-NEXT: [[TMP14:%.*]] = load i32, i32* [[TMP12]]
+; X64-NEXT: [[TMP10:%.*]] = getelementptr i8, i8* [[X]], i8 8
+; X64-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
+; X64-NEXT: [[TMP12:%.*]] = getelementptr i8, i8* [[Y]], i8 8
+; X64-NEXT: [[TMP13:%.*]] = bitcast i8* [[TMP12]] to i32*
+; X64-NEXT: [[TMP14:%.*]] = load i32, i32* [[TMP11]]
; X64-NEXT: [[TMP15:%.*]] = load i32, i32* [[TMP13]]
; X64-NEXT: [[TMP16:%.*]] = call i32 @llvm.bswap.i32(i32 [[TMP14]])
; X64-NEXT: [[TMP17:%.*]] = call i32 @llvm.bswap.i32(i32 [[TMP15]])
@@ -394,11 +394,11 @@ define i32 @cmp16(i8* nocapture readonly %x, i8* nocapture readonly %y) {
; X64-NEXT: [[TMP9:%.*]] = icmp eq i64 [[TMP7]], [[TMP8]]
; X64-NEXT: br i1 [[TMP9]], label [[LOADBB1]], label [[RES_BLOCK:%.*]]
; X64: loadbb1:
-; X64-NEXT: [[TMP10:%.*]] = bitcast i8* [[X]] to i64*
-; X64-NEXT: [[TMP11:%.*]] = bitcast i8* [[Y]] to i64*
-; X64-NEXT: [[TMP12:%.*]] = getelementptr i64, i64* [[TMP10]], i64 1
-; X64-NEXT: [[TMP13:%.*]] = getelementptr i64, i64* [[TMP11]], i64 1
-; X64-NEXT: [[TMP14:%.*]] = load i64, i64* [[TMP12]]
+; X64-NEXT: [[TMP10:%.*]] = getelementptr i8, i8* [[X]], i8 8
+; X64-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i64*
+; X64-NEXT: [[TMP12:%.*]] = getelementptr i8, i8* [[Y]], i8 8
+; X64-NEXT: [[TMP13:%.*]] = bitcast i8* [[TMP12]] to i64*
+; X64-NEXT: [[TMP14:%.*]] = load i64, i64* [[TMP11]]
; X64-NEXT: [[TMP15:%.*]] = load i64, i64* [[TMP13]]
; X64-NEXT: [[TMP16]] = call i64 @llvm.bswap.i64(i64 [[TMP14]])
; X64-NEXT: [[TMP17]] = call i64 @llvm.bswap.i64(i64 [[TMP15]])
@@ -597,11 +597,11 @@ define i32 @cmp_eq6(i8* nocapture readonly %x, i8* nocapture readonly %y) {
; 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: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 4
+; X32-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i16*
+; X32-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 4
+; X32-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i16*
+; X32-NEXT: [[TMP10:%.*]] = load i16, i16* [[TMP7]]
; X32-NEXT: [[TMP11:%.*]] = load i16, i16* [[TMP9]]
; X32-NEXT: [[TMP12:%.*]] = zext i16 [[TMP10]] to i32
; X32-NEXT: [[TMP13:%.*]] = zext i16 [[TMP11]] to i32
@@ -625,11 +625,11 @@ define i32 @cmp_eq6(i8* nocapture readonly %x, i8* nocapture readonly %y) {
; 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: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 4
+; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i16*
+; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 4
+; X64_1LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i16*
+; X64_1LD-NEXT: [[TMP10:%.*]] = load i16, i16* [[TMP7]]
; 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]]
@@ -645,11 +645,11 @@ define i32 @cmp_eq6(i8* nocapture readonly %x, i8* nocapture readonly %y) {
; 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: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 4
+; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i16*
+; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 4
+; X64_2LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i16*
+; X64_2LD-NEXT: [[TMP10:%.*]] = load i16, i16* [[TMP7]]
; 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
@@ -668,11 +668,71 @@ define i32 @cmp_eq6(i8* nocapture readonly %x, i8* nocapture readonly %y) {
}
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]]
+; X32-LABEL: @cmp_eq7(
+; 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 3
+; X32-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i32*
+; X32-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 3
+; X32-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i32*
+; X32-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP7]]
+; X32-NEXT: [[TMP11:%.*]] = load i32, i32* [[TMP9]]
+; 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_eq7(
+; 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 3
+; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i32*
+; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 3
+; X64_1LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i32*
+; X64_1LD-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP7]]
+; 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_eq7(
+; 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 3
+; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i32*
+; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 3
+; X64_2LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i32*
+; X64_2LD-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP7]]
+; X64_2LD-NEXT: [[TMP11:%.*]] = load i32, i32* [[TMP9]]
+; 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 7)
%cmp = icmp eq i32 %call, 0
@@ -687,11 +747,11 @@ define i32 @cmp_eq8(i8* nocapture readonly %x, i8* nocapture readonly %y) {
; 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 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: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 4
+; X32-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i32*
+; X32-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 4
+; X32-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i32*
+; X32-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP7]]
; X32-NEXT: [[TMP11:%.*]] = load i32, i32* [[TMP9]]
; X32-NEXT: [[TMP12:%.*]] = xor i32 [[TMP10]], [[TMP11]]
; X32-NEXT: [[TMP13:%.*]] = or i32 [[TMP5]], [[TMP12]]
@@ -794,11 +854,11 @@ define i32 @cmp_eq10(i8* nocapture readonly %x, i8* nocapture readonly %y) {
; 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: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 8
+; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i16*
+; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 8
+; X64_1LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i16*
+; X64_1LD-NEXT: [[TMP10:%.*]] = load i16, i16* [[TMP7]]
; 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]]
@@ -814,11 +874,11 @@ define i32 @cmp_eq10(i8* nocapture readonly %x, i8* nocapture readonly %y) {
; 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: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 8
+; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i16*
+; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 8
+; X64_2LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i16*
+; X64_2LD-NEXT: [[TMP10:%.*]] = load i16, i16* [[TMP7]]
; 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
@@ -837,11 +897,57 @@ define i32 @cmp_eq10(i8* nocapture readonly %x, i8* nocapture readonly %y) {
}
define i32 @cmp_eq11(i8* nocapture readonly %x, i8* nocapture readonly %y) {
-; ALL-LABEL: @cmp_eq11(
-; ALL-NEXT: [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 11)
-; ALL-NEXT: [[CMP:%.*]] = icmp eq i32 [[CALL]], 0
-; ALL-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32
-; ALL-NEXT: ret i32 [[CONV]]
+; X32-LABEL: @cmp_eq11(
+; X32-NEXT: [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 11)
+; X32-NEXT: [[CMP:%.*]] = icmp eq i32 [[CALL]], 0
+; X32-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X32-NEXT: ret i32 [[CONV]]
+;
+; X64_1LD-LABEL: @cmp_eq11(
+; 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 3
+; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i64*
+; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 3
+; X64_1LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i64*
+; X64_1LD-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP7]]
+; X64_1LD-NEXT: [[TMP11:%.*]] = load i64, i64* [[TMP9]]
+; X64_1LD-NEXT: [[TMP12:%.*]] = icmp ne i64 [[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_eq11(
+; 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 3
+; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i64*
+; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 3
+; X64_2LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i64*
+; X64_2LD-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP7]]
+; X64_2LD-NEXT: [[TMP11:%.*]] = load i64, i64* [[TMP9]]
+; 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 11)
%cmp = icmp eq i32 %call, 0
@@ -868,11 +974,11 @@ define i32 @cmp_eq12(i8* nocapture readonly %x, i8* nocapture readonly %y) {
; 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: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 8
+; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i32*
+; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 8
+; X64_1LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i32*
+; X64_1LD-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP7]]
; 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]]
@@ -888,11 +994,11 @@ define i32 @cmp_eq12(i8* nocapture readonly %x, i8* nocapture readonly %y) {
; 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: [[TMP6:%.*]] = getelementptr i8, i8* [[X]], i8 8
+; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i32*
+; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 8
+; X64_2LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i32*
+; X64_2LD-NEXT: [[TMP10:%.*]] = load i32, i32* [[TMP7]]
; 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
@@ -911,11 +1017,57 @@ define i32 @cmp_eq12(i8* nocapture readonly %x, i8* nocapture readonly %y) {
}
define i32 @cmp_eq13(i8* nocapture readonly %x, i8* nocapture readonly %y) {
-; ALL-LABEL: @cmp_eq13(
-; ALL-NEXT: [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 13)
-; ALL-NEXT: [[CMP:%.*]] = icmp eq i32 [[CALL]], 0
-; ALL-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32
-; ALL-NEXT: ret i32 [[CONV]]
+; X32-LABEL: @cmp_eq13(
+; X32-NEXT: [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 13)
+; X32-NEXT: [[CMP:%.*]] = icmp eq i32 [[CALL]], 0
+; X32-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X32-NEXT: ret i32 [[CONV]]
+;
+; X64_1LD-LABEL: @cmp_eq13(
+; 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 5
+; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i64*
+; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 5
+; X64_1LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i64*
+; X64_1LD-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP7]]
+; X64_1LD-NEXT: [[TMP11:%.*]] = load i64, i64* [[TMP9]]
+; X64_1LD-NEXT: [[TMP12:%.*]] = icmp ne i64 [[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_eq13(
+; 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 5
+; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i64*
+; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 5
+; X64_2LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i64*
+; X64_2LD-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP7]]
+; X64_2LD-NEXT: [[TMP11:%.*]] = load i64, i64* [[TMP9]]
+; 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 13)
%cmp = icmp eq i32 %call, 0
@@ -924,11 +1076,57 @@ define i32 @cmp_eq13(i8* nocapture readonly %x, i8* nocapture readonly %y) {
}
define i32 @cmp_eq14(i8* nocapture readonly %x, i8* nocapture readonly %y) {
-; ALL-LABEL: @cmp_eq14(
-; ALL-NEXT: [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 14)
-; ALL-NEXT: [[CMP:%.*]] = icmp eq i32 [[CALL]], 0
-; ALL-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32
-; ALL-NEXT: ret i32 [[CONV]]
+; X32-LABEL: @cmp_eq14(
+; X32-NEXT: [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 14)
+; X32-NEXT: [[CMP:%.*]] = icmp eq i32 [[CALL]], 0
+; X32-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X32-NEXT: ret i32 [[CONV]]
+;
+; X64_1LD-LABEL: @cmp_eq14(
+; 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 6
+; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i64*
+; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 6
+; X64_1LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i64*
+; X64_1LD-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP7]]
+; X64_1LD-NEXT: [[TMP11:%.*]] = load i64, i64* [[TMP9]]
+; X64_1LD-NEXT: [[TMP12:%.*]] = icmp ne i64 [[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_eq14(
+; 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 6
+; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i64*
+; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 6
+; X64_2LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i64*
+; X64_2LD-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP7]]
+; X64_2LD-NEXT: [[TMP11:%.*]] = load i64, i64* [[TMP9]]
+; 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 14)
%cmp = icmp eq i32 %call, 0
@@ -937,11 +1135,57 @@ define i32 @cmp_eq14(i8* nocapture readonly %x, i8* nocapture readonly %y) {
}
define i32 @cmp_eq15(i8* nocapture readonly %x, i8* nocapture readonly %y) {
-; ALL-LABEL: @cmp_eq15(
-; ALL-NEXT: [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 15)
-; ALL-NEXT: [[CMP:%.*]] = icmp eq i32 [[CALL]], 0
-; ALL-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32
-; ALL-NEXT: ret i32 [[CONV]]
+; X32-LABEL: @cmp_eq15(
+; X32-NEXT: [[CALL:%.*]] = tail call i32 @memcmp(i8* [[X:%.*]], i8* [[Y:%.*]], i64 15)
+; X32-NEXT: [[CMP:%.*]] = icmp eq i32 [[CALL]], 0
+; X32-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32
+; X32-NEXT: ret i32 [[CONV]]
+;
+; X64_1LD-LABEL: @cmp_eq15(
+; 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 7
+; X64_1LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i64*
+; X64_1LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 7
+; X64_1LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i64*
+; X64_1LD-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP7]]
+; X64_1LD-NEXT: [[TMP11:%.*]] = load i64, i64* [[TMP9]]
+; X64_1LD-NEXT: [[TMP12:%.*]] = icmp ne i64 [[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_eq15(
+; 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 7
+; X64_2LD-NEXT: [[TMP7:%.*]] = bitcast i8* [[TMP6]] to i64*
+; X64_2LD-NEXT: [[TMP8:%.*]] = getelementptr i8, i8* [[Y]], i8 7
+; X64_2LD-NEXT: [[TMP9:%.*]] = bitcast i8* [[TMP8]] to i64*
+; X64_2LD-NEXT: [[TMP10:%.*]] = load i64, i64* [[TMP7]]
+; X64_2LD-NEXT: [[TMP11:%.*]] = load i64, i64* [[TMP9]]
+; 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 15)
%cmp = icmp eq i32 %call, 0
OpenPOWER on IntegriCloud