Implement dynamic allocas correctly. In particular, because we were copying

directly out of R1 (without using a CopyFromReg, which uses a chain), multiple
allocas were getting CSE'd together, producing bogus code.  For this:

int %foo(bool %X, int %A, int %B) {
        br bool %X, label %T, label %F
F:
        %G = alloca int
        %H = alloca int
        store int %A, int* %G
        store int %B, int* %H
        %R = load int* %G
        ret int %R
T:
        ret int 0
}

We were generating:

_foo:
        stwu r1, -16(r1)
        stw r31, 4(r1)
        or r31, r1, r1
        stw r1, 12(r31)
        cmpwi cr0, r3, 0
        bne cr0, .LBB_foo_2     ; T
.LBB_foo_1:     ; F
        li r2, 16
        subf r2, r2, r1   ;; One alloca
        or r1, r2, r2
        or r3, r1, r1
        or r1, r2, r2
        or r2, r1, r1
        stw r4, 0(r3)
        stw r5, 0(r2)
        lwz r3, 0(r3)
        lwz r1, 12(r31)
        lwz r31, 4(r31)
        lwz r1, 0(r1)
        blr
.LBB_foo_2:     ; T
        li r3, 0
        lwz r1, 12(r31)
        lwz r31, 4(r31)
        lwz r1, 0(r1)
        blr

Now we generate:

_foo:
        stwu r1, -16(r1)
        stw r31, 4(r1)
        or r31, r1, r1
        stw r1, 12(r31)
        cmpwi cr0, r3, 0
        bne cr0, .LBB_foo_2     ; T
.LBB_foo_1:     ; F
        or r2, r1, r1
        li r3, 16
        subf r2, r3, r2  ;; Alloca 1
        or r1, r2, r2
        or r2, r1, r1
        or r6, r1, r1
        subf r3, r3, r6  ;; Alloca 2
        or r1, r3, r3
        or r3, r1, r1
        stw r4, 0(r2)
        stw r5, 0(r3)
        lwz r3, 0(r2)
        lwz r1, 12(r31)
        lwz r31, 4(r31)
        lwz r1, 0(r1)
        blr
.LBB_foo_2:     ; T
        li r3, 0
        lwz r1, 12(r31)
        lwz r31, 4(r31)
        lwz r1, 0(r1)
        blr

This fixes Povray and SPASS with the dag isel, the last two failing cases.
Tommorow we will hopefully turn it on by default! :)


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23190 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 4 insertions, 1 deletions

diff --git a/lib/Target/PowerPC/PPCISelDAGToDAG.cpp b/lib/Target/PowerPC/PPCISelDAGToDAG.cpp
index c650c0f308..abb9c1fe24 100644
--- a/lib/Target/PowerPC/PPCISelDAGToDAG.cpp
+++ b/lib/Target/PowerPC/PPCISelDAGToDAG.cpp
@@ -754,9 +754,12 @@ SDOperand PPC32DAGToDAGISel::Select(SDOperand Op) {
     
     SDOperand R1Reg = CurDAG->getRegister(PPC::R1, MVT::i32);
     
+    SDOperand R1Val = CurDAG->getCopyFromReg(Chain, PPC::R1, MVT::i32);
+    Chain = R1Val.getValue(1);
+    
     // Subtract the amount (guaranteed to be a multiple of the stack alignment)
     // from the stack pointer, giving us the result pointer.
-    SDOperand Result = CurDAG->getTargetNode(PPC::SUBF, MVT::i32, Amt, R1Reg);
+    SDOperand Result = CurDAG->getTargetNode(PPC::SUBF, MVT::i32, Amt, R1Val);
 
     // Copy this result back into R1.
     Chain = CurDAG->getNode(ISD::CopyToReg, MVT::Other, Chain, R1Reg, Result);