[CGP / PowerPC] avoid multi-block overhead for simple memcmp expansion

The test diff for PowerPC shows we can better optimize if this case is one block.

For x86, there's would be a substantial difference if CGP expansion was enabled because branches are assumed 
cheap and SDAG can't optimize across blocks. 

Instead of this:

_cmp_eq8:
  movq  (%rdi), %rax
  cmpq  (%rsi), %rax
  je  LBB23_1
## BB#2:                                ## %res_block
  movl  $1, %ecx
  jmp LBB23_3
LBB23_1:
  xorl  %ecx, %ecx
LBB23_3:                                ## %endblock
  xorl  %eax, %eax
  testl %ecx, %ecx
  sete  %al
  retq

We get this:

cmp_eq8:   
  movq  (%rdi), %rcx
  xorl  %eax, %eax
  cmpq  (%rsi), %rcx
  sete  %al
  retq

And that matches the optimal codegen that we get from the current expansion in SelectionDAGBuilder::visitMemCmpCall(). 
If this looks right, then I just need to confirm that vector-sized expansion will work from here, and we can enable 
CGP memcmp() expansion for x86. Ie, we'll bypass the power-of-2 special cases currently optimized in SDAG because we 
can lower the IR produced here optimally.

Differential Revision: https://reviews.llvm.org/D34005

llvm-svn: 304987

1 files changed, 5 insertions, 5 deletions

diff --git a/llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityComparison.ll b/llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityComparison.ll
index 84d3e884102..e2c842f25b9 100644
--- a/llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityComparison.ll
+++ b/llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityComparison.ll
@@ -17,13 +17,13 @@ declare signext i32 @memcmp(i8* nocapture, i8* nocapture, i64) local_unnamed_add
 ; Check 4 bytes - requires 1 load for each param.
 define signext i32 @zeroEqualityTest02(i8* %x, i8* %y) {
 ; CHECK-LABEL: zeroEqualityTest02:
-; CHECK:       # BB#0: # %loadbb
+; CHECK:       # BB#0:
 ; CHECK-NEXT:    lwz 3, 0(3)
 ; CHECK-NEXT:    lwz 4, 0(4)
-; CHECK-NEXT:    li 5, 1
-; CHECK-NEXT:    cmplw 3, 4
-; CHECK-NEXT:    isel 3, 0, 5, 2
-; CHECK-NEXT:    clrldi 3, 3, 32
+; CHECK-NEXT:    xor 3, 3, 4
+; CHECK-NEXT:    cntlzw 3, 3
+; CHECK-NEXT:    srwi 3, 3, 5
+; CHECK-NEXT:    xori 3, 3, 1
 ; CHECK-NEXT:    blr
   %call = tail call signext i32 @memcmp(i8* %x, i8* %y, i64 4)
   %not.cmp = icmp ne i32 %call, 0