From e2244b79d64045ca2524dff00a3bafc20a707d06 Mon Sep 17 00:00:00 2001
From: Clement Courbet <courbet@google.com>
Date: Fri, 5 Apr 2019 15:03:25 +0000
Subject: [PATCH] [ExpandMemCmp][NFC] Add tests for `memcmp(p, q, n) < 0` case.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@357767 91177308-0d34-0410-b5e6-96231b3b80d8
---
 test/CodeGen/X86/memcmp.ll | 245 ++++++++++++++++++++++++++++++++++---
 1 file changed, 225 insertions(+), 20 deletions(-)

diff --git a/test/CodeGen/X86/memcmp.ll b/test/CodeGen/X86/memcmp.ll
index 06e1cda15d6..4910ef25c8f 100644
--- a/test/CodeGen/X86/memcmp.ll
+++ b/test/CodeGen/X86/memcmp.ll
@@ -42,6 +42,21 @@ define i1 @length0_eq(i8* %X, i8* %Y) nounwind {
   ret i1 %c
 }
 
+define i1 @length0_lt(i8* %X, i8* %Y) nounwind {
+; X86-LABEL: length0_lt:
+; X86:       # %bb.0:
+; X86-NEXT:    xorl %eax, %eax
+; X86-NEXT:    retl
+;
+; X64-LABEL: length0_lt:
+; X64:       # %bb.0:
+; X64-NEXT:    xorl %eax, %eax
+; X64-NEXT:    retq
+  %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 0) nounwind
+  %c = icmp slt i32 %m, 0
+  ret i1 %c
+}
+
 define i32 @length2(i8* %X, i8* %Y) nounwind {
 ; X86-LABEL: length2:
 ; X86:       # %bb.0:
@@ -91,6 +106,72 @@ define i1 @length2_eq(i8* %X, i8* %Y) nounwind {
   ret i1 %c
 }
 
+define i1 @length2_lt(i8* %X, i8* %Y) nounwind {
+; X86-LABEL: length2_lt:
+; X86:       # %bb.0:
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movzwl (%ecx), %ecx
+; X86-NEXT:    movzwl (%eax), %edx
+; X86-NEXT:    rolw $8, %cx
+; X86-NEXT:    rolw $8, %dx
+; X86-NEXT:    movzwl %cx, %eax
+; X86-NEXT:    movzwl %dx, %ecx
+; X86-NEXT:    subl %ecx, %eax
+; X86-NEXT:    shrl $31, %eax
+; X86-NEXT:    # kill: def $al killed $al killed $eax
+; X86-NEXT:    retl
+;
+; X64-LABEL: length2_lt:
+; X64:       # %bb.0:
+; X64-NEXT:    movzwl (%rdi), %eax
+; X64-NEXT:    movzwl (%rsi), %ecx
+; X64-NEXT:    rolw $8, %ax
+; X64-NEXT:    rolw $8, %cx
+; X64-NEXT:    movzwl %ax, %eax
+; X64-NEXT:    movzwl %cx, %ecx
+; X64-NEXT:    subl %ecx, %eax
+; X64-NEXT:    shrl $31, %eax
+; X64-NEXT:    # kill: def $al killed $al killed $eax
+; X64-NEXT:    retq
+  %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 2) nounwind
+  %c = icmp slt i32 %m, 0
+  ret i1 %c
+}
+
+define i1 @length2_gt(i8* %X, i8* %Y) nounwind {
+; X86-LABEL: length2_gt:
+; X86:       # %bb.0:
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movzwl (%ecx), %ecx
+; X86-NEXT:    movzwl (%eax), %eax
+; X86-NEXT:    rolw $8, %cx
+; X86-NEXT:    rolw $8, %ax
+; X86-NEXT:    movzwl %cx, %ecx
+; X86-NEXT:    movzwl %ax, %eax
+; X86-NEXT:    subl %eax, %ecx
+; X86-NEXT:    testl %ecx, %ecx
+; X86-NEXT:    setg %al
+; X86-NEXT:    retl
+;
+; X64-LABEL: length2_gt:
+; X64:       # %bb.0:
+; X64-NEXT:    movzwl (%rdi), %eax
+; X64-NEXT:    movzwl (%rsi), %ecx
+; X64-NEXT:    rolw $8, %ax
+; X64-NEXT:    rolw $8, %cx
+; X64-NEXT:    movzwl %ax, %eax
+; X64-NEXT:    movzwl %cx, %ecx
+; X64-NEXT:    subl %ecx, %eax
+; X64-NEXT:    testl %eax, %eax
+; X64-NEXT:    setg %al
+; X64-NEXT:    retq
+  %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 2) nounwind
+  %c = icmp sgt i32 %m, 0
+  ret i1 %c
+}
+
 define i1 @length2_eq_const(i8* %X) nounwind {
 ; X86-LABEL: length2_eq_const:
 ; X86:       # %bb.0:
@@ -149,14 +230,14 @@ define i32 @length3(i8* %X, i8* %Y) nounwind {
 ; X86-NEXT:    rolw $8, %dx
 ; X86-NEXT:    rolw $8, %si
 ; X86-NEXT:    cmpw %si, %dx
-; X86-NEXT:    jne .LBB6_1
+; X86-NEXT:    jne .LBB9_1
 ; X86-NEXT:  # %bb.2: # %loadbb1
 ; X86-NEXT:    movzbl 2(%eax), %eax
 ; X86-NEXT:    movzbl 2(%ecx), %ecx
 ; X86-NEXT:    subl %ecx, %eax
 ; X86-NEXT:    popl %esi
 ; X86-NEXT:    retl
-; X86-NEXT:  .LBB6_1: # %res_block
+; X86-NEXT:  .LBB9_1: # %res_block
 ; X86-NEXT:    setae %al
 ; X86-NEXT:    movzbl %al, %eax
 ; X86-NEXT:    leal -1(%eax,%eax), %eax
@@ -170,13 +251,13 @@ define i32 @length3(i8* %X, i8* %Y) nounwind {
 ; X64-NEXT:    rolw $8, %ax
 ; X64-NEXT:    rolw $8, %cx
 ; X64-NEXT:    cmpw %cx, %ax
-; X64-NEXT:    jne .LBB6_1
+; X64-NEXT:    jne .LBB9_1
 ; X64-NEXT:  # %bb.2: # %loadbb1
 ; X64-NEXT:    movzbl 2(%rdi), %eax
 ; X64-NEXT:    movzbl 2(%rsi), %ecx
 ; X64-NEXT:    subl %ecx, %eax
 ; X64-NEXT:    retq
-; X64-NEXT:  .LBB6_1: # %res_block
+; X64-NEXT:  .LBB9_1: # %res_block
 ; X64-NEXT:    setae %al
 ; X64-NEXT:    movzbl %al, %eax
 ; X64-NEXT:    leal -1(%rax,%rax), %eax
@@ -265,6 +346,76 @@ define i1 @length4_eq(i8* %X, i8* %Y) nounwind {
   ret i1 %c
 }
 
+define i1 @length4_lt(i8* %X, i8* %Y) nounwind {
+; X86-LABEL: length4_lt:
+; X86:       # %bb.0:
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl (%ecx), %ecx
+; X86-NEXT:    movl (%eax), %edx
+; X86-NEXT:    bswapl %ecx
+; X86-NEXT:    bswapl %edx
+; X86-NEXT:    xorl %eax, %eax
+; X86-NEXT:    cmpl %edx, %ecx
+; X86-NEXT:    seta %al
+; X86-NEXT:    sbbl $0, %eax
+; X86-NEXT:    shrl $31, %eax
+; X86-NEXT:    # kill: def $al killed $al killed $eax
+; X86-NEXT:    retl
+;
+; X64-LABEL: length4_lt:
+; X64:       # %bb.0:
+; X64-NEXT:    movl (%rdi), %ecx
+; X64-NEXT:    movl (%rsi), %edx
+; X64-NEXT:    bswapl %ecx
+; X64-NEXT:    bswapl %edx
+; X64-NEXT:    xorl %eax, %eax
+; X64-NEXT:    cmpl %edx, %ecx
+; X64-NEXT:    seta %al
+; X64-NEXT:    sbbl $0, %eax
+; X64-NEXT:    shrl $31, %eax
+; X64-NEXT:    # kill: def $al killed $al killed $eax
+; X64-NEXT:    retq
+  %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 4) nounwind
+  %c = icmp slt i32 %m, 0
+  ret i1 %c
+}
+
+define i1 @length4_gt(i8* %X, i8* %Y) nounwind {
+; X86-LABEL: length4_gt:
+; X86:       # %bb.0:
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl (%ecx), %ecx
+; X86-NEXT:    movl (%eax), %eax
+; X86-NEXT:    bswapl %ecx
+; X86-NEXT:    bswapl %eax
+; X86-NEXT:    xorl %edx, %edx
+; X86-NEXT:    cmpl %eax, %ecx
+; X86-NEXT:    seta %dl
+; X86-NEXT:    sbbl $0, %edx
+; X86-NEXT:    testl %edx, %edx
+; X86-NEXT:    setg %al
+; X86-NEXT:    retl
+;
+; X64-LABEL: length4_gt:
+; X64:       # %bb.0:
+; X64-NEXT:    movl (%rdi), %eax
+; X64-NEXT:    movl (%rsi), %ecx
+; X64-NEXT:    bswapl %eax
+; X64-NEXT:    bswapl %ecx
+; X64-NEXT:    xorl %edx, %edx
+; X64-NEXT:    cmpl %ecx, %eax
+; X64-NEXT:    seta %dl
+; X64-NEXT:    sbbl $0, %edx
+; X64-NEXT:    testl %edx, %edx
+; X64-NEXT:    setg %al
+; X64-NEXT:    retq
+  %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 4) nounwind
+  %c = icmp sgt i32 %m, 0
+  ret i1 %c
+}
+
 define i1 @length4_eq_const(i8* %X) nounwind {
 ; X86-LABEL: length4_eq_const:
 ; X86:       # %bb.0:
@@ -294,14 +445,14 @@ define i32 @length5(i8* %X, i8* %Y) nounwind {
 ; X86-NEXT:    bswapl %edx
 ; X86-NEXT:    bswapl %esi
 ; X86-NEXT:    cmpl %esi, %edx
-; X86-NEXT:    jne .LBB11_1
+; X86-NEXT:    jne .LBB16_1
 ; X86-NEXT:  # %bb.2: # %loadbb1
 ; X86-NEXT:    movzbl 4(%eax), %eax
 ; X86-NEXT:    movzbl 4(%ecx), %ecx
 ; X86-NEXT:    subl %ecx, %eax
 ; X86-NEXT:    popl %esi
 ; X86-NEXT:    retl
-; X86-NEXT:  .LBB11_1: # %res_block
+; X86-NEXT:  .LBB16_1: # %res_block
 ; X86-NEXT:    setae %al
 ; X86-NEXT:    movzbl %al, %eax
 ; X86-NEXT:    leal -1(%eax,%eax), %eax
@@ -315,13 +466,13 @@ define i32 @length5(i8* %X, i8* %Y) nounwind {
 ; X64-NEXT:    bswapl %eax
 ; X64-NEXT:    bswapl %ecx
 ; X64-NEXT:    cmpl %ecx, %eax
-; X64-NEXT:    jne .LBB11_1
+; X64-NEXT:    jne .LBB16_1
 ; X64-NEXT:  # %bb.2: # %loadbb1
 ; X64-NEXT:    movzbl 4(%rdi), %eax
 ; X64-NEXT:    movzbl 4(%rsi), %ecx
 ; X64-NEXT:    subl %ecx, %eax
 ; X64-NEXT:    retq
-; X64-NEXT:  .LBB11_1: # %res_block
+; X64-NEXT:  .LBB16_1: # %res_block
 ; X64-NEXT:    setae %al
 ; X64-NEXT:    movzbl %al, %eax
 ; X64-NEXT:    leal -1(%rax,%rax), %eax
@@ -359,6 +510,60 @@ define i1 @length5_eq(i8* %X, i8* %Y) nounwind {
   ret i1 %c
 }
 
+define i1 @length5_lt(i8* %X, i8* %Y) nounwind {
+; X86-LABEL: length5_lt:
+; X86:       # %bb.0: # %loadbb
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl (%eax), %edx
+; X86-NEXT:    movl (%ecx), %esi
+; X86-NEXT:    bswapl %edx
+; X86-NEXT:    bswapl %esi
+; X86-NEXT:    cmpl %esi, %edx
+; X86-NEXT:    jne .LBB18_1
+; X86-NEXT:  # %bb.2: # %loadbb1
+; X86-NEXT:    movzbl 4(%eax), %eax
+; X86-NEXT:    movzbl 4(%ecx), %ecx
+; X86-NEXT:    subl %ecx, %eax
+; X86-NEXT:    jmp .LBB18_3
+; X86-NEXT:  .LBB18_1: # %res_block
+; X86-NEXT:    setae %al
+; X86-NEXT:    movzbl %al, %eax
+; X86-NEXT:    leal -1(%eax,%eax), %eax
+; X86-NEXT:  .LBB18_3: # %endblock
+; X86-NEXT:    shrl $31, %eax
+; X86-NEXT:    # kill: def $al killed $al killed $eax
+; X86-NEXT:    popl %esi
+; X86-NEXT:    retl
+;
+; X64-LABEL: length5_lt:
+; X64:       # %bb.0: # %loadbb
+; X64-NEXT:    movl (%rdi), %eax
+; X64-NEXT:    movl (%rsi), %ecx
+; X64-NEXT:    bswapl %eax
+; X64-NEXT:    bswapl %ecx
+; X64-NEXT:    cmpl %ecx, %eax
+; X64-NEXT:    jne .LBB18_1
+; X64-NEXT:  # %bb.2: # %loadbb1
+; X64-NEXT:    movzbl 4(%rdi), %eax
+; X64-NEXT:    movzbl 4(%rsi), %ecx
+; X64-NEXT:    subl %ecx, %eax
+; X64-NEXT:    shrl $31, %eax
+; X64-NEXT:    # kill: def $al killed $al killed $eax
+; X64-NEXT:    retq
+; X64-NEXT:  .LBB18_1: # %res_block
+; X64-NEXT:    setae %al
+; X64-NEXT:    movzbl %al, %eax
+; X64-NEXT:    leal -1(%rax,%rax), %eax
+; X64-NEXT:    shrl $31, %eax
+; X64-NEXT:    # kill: def $al killed $al killed $eax
+; X64-NEXT:    retq
+  %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 5) nounwind
+  %c = icmp slt i32 %m, 0
+  ret i1 %c
+}
+
 define i1 @length7_eq(i8* %X, i8* %Y) nounwind {
 ; X86-LABEL: length7_eq:
 ; X86:       # %bb.0:
@@ -397,7 +602,7 @@ define i32 @length8(i8* %X, i8* %Y) nounwind {
 ; X86-NEXT:    bswapl %ecx
 ; X86-NEXT:    bswapl %edx
 ; X86-NEXT:    cmpl %edx, %ecx
-; X86-NEXT:    jne .LBB14_2
+; X86-NEXT:    jne .LBB20_2
 ; X86-NEXT:  # %bb.1: # %loadbb1
 ; X86-NEXT:    movl 4(%esi), %ecx
 ; X86-NEXT:    movl 4(%eax), %edx
@@ -405,13 +610,13 @@ define i32 @length8(i8* %X, i8* %Y) nounwind {
 ; X86-NEXT:    bswapl %edx
 ; X86-NEXT:    xorl %eax, %eax
 ; X86-NEXT:    cmpl %edx, %ecx
-; X86-NEXT:    je .LBB14_3
-; X86-NEXT:  .LBB14_2: # %res_block
+; X86-NEXT:    je .LBB20_3
+; X86-NEXT:  .LBB20_2: # %res_block
 ; X86-NEXT:    xorl %eax, %eax
 ; X86-NEXT:    cmpl %edx, %ecx
 ; X86-NEXT:    setae %al
 ; X86-NEXT:    leal -1(%eax,%eax), %eax
-; X86-NEXT:  .LBB14_3: # %endblock
+; X86-NEXT:  .LBB20_3: # %endblock
 ; X86-NEXT:    popl %esi
 ; X86-NEXT:    retl
 ;
@@ -605,7 +810,7 @@ define i32 @length12(i8* %X, i8* %Y) nounwind {
 ; X64-NEXT:    bswapq %rcx
 ; X64-NEXT:    bswapq %rdx
 ; X64-NEXT:    cmpq %rdx, %rcx
-; X64-NEXT:    jne .LBB21_2
+; X64-NEXT:    jne .LBB27_2
 ; X64-NEXT:  # %bb.1: # %loadbb1
 ; X64-NEXT:    movl 8(%rdi), %ecx
 ; X64-NEXT:    movl 8(%rsi), %edx
@@ -613,13 +818,13 @@ define i32 @length12(i8* %X, i8* %Y) nounwind {
 ; X64-NEXT:    bswapl %edx
 ; X64-NEXT:    xorl %eax, %eax
 ; X64-NEXT:    cmpq %rdx, %rcx
-; X64-NEXT:    je .LBB21_3
-; X64-NEXT:  .LBB21_2: # %res_block
+; X64-NEXT:    je .LBB27_3
+; X64-NEXT:  .LBB27_2: # %res_block
 ; X64-NEXT:    xorl %eax, %eax
 ; X64-NEXT:    cmpq %rdx, %rcx
 ; X64-NEXT:    setae %al
 ; X64-NEXT:    leal -1(%rax,%rax), %eax
-; X64-NEXT:  .LBB21_3: # %endblock
+; X64-NEXT:  .LBB27_3: # %endblock
 ; X64-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 12) nounwind
   ret i32 %m
@@ -726,7 +931,7 @@ define i32 @length16(i8* %X, i8* %Y) nounwind {
 ; X64-NEXT:    bswapq %rcx
 ; X64-NEXT:    bswapq %rdx
 ; X64-NEXT:    cmpq %rdx, %rcx
-; X64-NEXT:    jne .LBB25_2
+; X64-NEXT:    jne .LBB31_2
 ; X64-NEXT:  # %bb.1: # %loadbb1
 ; X64-NEXT:    movq 8(%rdi), %rcx
 ; X64-NEXT:    movq 8(%rsi), %rdx
@@ -734,13 +939,13 @@ define i32 @length16(i8* %X, i8* %Y) nounwind {
 ; X64-NEXT:    bswapq %rdx
 ; X64-NEXT:    xorl %eax, %eax
 ; X64-NEXT:    cmpq %rdx, %rcx
-; X64-NEXT:    je .LBB25_3
-; X64-NEXT:  .LBB25_2: # %res_block
+; X64-NEXT:    je .LBB31_3
+; X64-NEXT:  .LBB31_2: # %res_block
 ; X64-NEXT:    xorl %eax, %eax
 ; X64-NEXT:    cmpq %rdx, %rcx
 ; X64-NEXT:    setae %al
 ; X64-NEXT:    leal -1(%rax,%rax), %eax
-; X64-NEXT:  .LBB25_3: # %endblock
+; X64-NEXT:  .LBB31_3: # %endblock
 ; X64-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 16) nounwind
   ret i32 %m
-- 
2.50.1