Emit long comparison against -1 better. Instead of this (x86):

test2:
        movl 8(%esp), %eax
        notl %eax
        movl 4(%esp), %ecx
        notl %ecx
        orl %eax, %ecx
        cmpl $0, %ecx
        sete %al
        movzbl %al, %eax
        ret

or this (PPC):

_test2:
        nor r2, r4, r4
        nor r3, r3, r3
        or r2, r2, r3
        cntlzw r2, r2
        srwi r3, r2, 5
        blr

Emit this:

test2:
        movl 8(%esp), %eax
        andl 4(%esp), %eax
        cmpl $-1, %eax
        sete %al
        movzbl %al, %eax
        ret

or this:

_test2:
.LBB_test2_0:   ;
        and r2, r4, r3
        cmpwi cr0, r2, -1
        li r3, 1
        li r2, 0
        beq .LBB_test2_2        ;
.LBB_test2_1:   ;
        or r3, r2, r2
.LBB_test2_2:   ;
        blr

it seems like the PPC isel could do better for R32 == -1 case.

llvm-svn: 21242

1 files changed, 10 insertions, 0 deletions

diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
index a9329cf8769..3bd2494ceaa 100644
--- a/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
@@ -750,6 +750,16 @@ SDOperand SelectionDAGLegalize::LegalizeOp(SDOperand Op) {
       switch (cast<SetCCSDNode>(Node)->getCondition()) {
       case ISD::SETEQ:
       case ISD::SETNE:
+        if (RHSLo == RHSHi)
+          if (ConstantSDNode *RHSCST = dyn_cast<ConstantSDNode>(RHSLo))
+            if (RHSCST->isAllOnesValue()) {
+              // Comparison to -1.
+              Tmp1 = DAG.getNode(ISD::AND, LHSLo.getValueType(), LHSLo, LHSHi);
+              Result = DAG.getSetCC(cast<SetCCSDNode>(Node)->getCondition(), 
+                                    Node->getValueType(0), Tmp1, RHSLo);
+              break;                                    
+            }
+
         Tmp1 = DAG.getNode(ISD::XOR, LHSLo.getValueType(), LHSLo, RHSLo);
         Tmp2 = DAG.getNode(ISD::XOR, LHSLo.getValueType(), LHSHi, RHSHi);
         Tmp1 = DAG.getNode(ISD::OR, Tmp1.getValueType(), Tmp1, Tmp2);