[CGP] use subtract or subtract-of-cmps for result of memcmp expansion

As noted in the code comment, transforming this in the other direction might require 
a separate transform here in CGP given the block-at-a-time DAG constraint.

Besides that theoretical motivation, there are 2 practical motivations for the 
subtract-of-cmps form:

1. The codegen for both x86 and PPC is better for this IR (though PPC could be better still). 
   There is discussion about canonicalizing IR to the select form 
   ( http://lists.llvm.org/pipermail/llvm-dev/2017-July/114885.html ), 
   so we probably need to add DAG transforms for those patterns anyway, but this improves the 
   memcmp output without waiting for that step.

2. If we allow vector-sized chunks for the load and compare, x86 is better prepared to convert
   that to optimal code when using subtract-of-cmps, so another prerequisite patch is avoided
   if we choose to enable that.

Differential Revision: https://reviews.llvm.org/D34904

llvm-svn: 309597

1 files changed, 28 insertions, 40 deletions

diff --git a/llvm/test/CodeGen/X86/memcmp.ll b/llvm/test/CodeGen/X86/memcmp.ll
index 889f6a74bf7..409bd7147c5 100644
--- a/llvm/test/CodeGen/X86/memcmp.ll
+++ b/llvm/test/CodeGen/X86/memcmp.ll
@@ -17,15 +17,12 @@ define i32 @length2(i8* %X, i8* %Y) nounwind {
 ; 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:    movzwl (%eax), %edx
 ; X86-NEXT:    rolw $8, %cx
-; X86-NEXT:    rolw $8, %ax
-; X86-NEXT:    xorl %edx, %edx
-; X86-NEXT:    cmpw %ax, %cx
-; X86-NEXT:    movl $-1, %ecx
-; X86-NEXT:    movl $1, %eax
-; X86-NEXT:    cmovbl %ecx, %eax
-; X86-NEXT:    cmovel %edx, %eax
+; X86-NEXT:    rolw $8, %dx
+; X86-NEXT:    movzwl %cx, %eax
+; X86-NEXT:    movzwl %dx, %ecx
+; X86-NEXT:    subl %ecx, %eax
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: length2:
@@ -34,12 +31,9 @@ define i32 @length2(i8* %X, i8* %Y) nounwind {
 ; X64-NEXT:    movzwl (%rsi), %ecx
 ; X64-NEXT:    rolw $8, %ax
 ; X64-NEXT:    rolw $8, %cx
-; X64-NEXT:    xorl %edx, %edx
-; X64-NEXT:    cmpw %cx, %ax
-; X64-NEXT:    movl $-1, %ecx
-; X64-NEXT:    movl $1, %eax
-; X64-NEXT:    cmovbl %ecx, %eax
-; X64-NEXT:    cmovel %edx, %eax
+; X64-NEXT:    movzwl %ax, %eax
+; X64-NEXT:    movzwl %cx, %ecx
+; X64-NEXT:    subl %ecx, %eax
 ; X64-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 2) nounwind
   ret i32 %m
@@ -211,29 +205,25 @@ define i32 @length4(i8* %X, i8* %Y) nounwind {
 ; 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:    movl (%eax), %edx
 ; X86-NEXT:    bswapl %ecx
-; X86-NEXT:    bswapl %eax
-; X86-NEXT:    xorl %edx, %edx
-; X86-NEXT:    cmpl %eax, %ecx
-; X86-NEXT:    movl $-1, %ecx
-; X86-NEXT:    movl $1, %eax
-; X86-NEXT:    cmovbl %ecx, %eax
-; X86-NEXT:    cmovel %edx, %eax
+; 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:    retl
 ;
 ; X64-LABEL: length4:
 ; X64:       # BB#0:
-; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    movl (%rsi), %ecx
-; X64-NEXT:    bswapl %eax
+; X64-NEXT:    movl (%rdi), %ecx
+; X64-NEXT:    movl (%rsi), %edx
 ; X64-NEXT:    bswapl %ecx
-; X64-NEXT:    xorl %edx, %edx
-; X64-NEXT:    cmpl %ecx, %eax
-; X64-NEXT:    movl $-1, %ecx
-; X64-NEXT:    movl $1, %eax
-; X64-NEXT:    cmovbl %ecx, %eax
-; X64-NEXT:    cmovel %edx, %eax
+; 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:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 4) nounwind
   ret i32 %m
@@ -399,16 +389,14 @@ define i32 @length8(i8* %X, i8* %Y) nounwind {
 ;
 ; X64-LABEL: length8:
 ; X64:       # BB#0:
-; X64-NEXT:    movq (%rdi), %rax
-; X64-NEXT:    movq (%rsi), %rcx
-; X64-NEXT:    bswapq %rax
+; X64-NEXT:    movq (%rdi), %rcx
+; X64-NEXT:    movq (%rsi), %rdx
 ; X64-NEXT:    bswapq %rcx
-; X64-NEXT:    xorl %edx, %edx
-; X64-NEXT:    cmpq %rcx, %rax
-; X64-NEXT:    movl $-1, %ecx
-; X64-NEXT:    movl $1, %eax
-; X64-NEXT:    cmovbl %ecx, %eax
-; X64-NEXT:    cmovel %edx, %eax
+; X64-NEXT:    bswapq %rdx
+; X64-NEXT:    xorl %eax, %eax
+; X64-NEXT:    cmpq %rdx, %rcx
+; X64-NEXT:    seta %al
+; X64-NEXT:    sbbl $0, %eax
 ; X64-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 8) nounwind
   ret i32 %m