Handle physreg input/outputs.  We now compile this:

int %test_cpuid(int %op) {
        %B = alloca int
        %C = alloca int
        %D = alloca int
        %A = call int asm "cpuid", "=eax,==ebx,==ecx,==edx,eax"(int* %B, int* %C, int* %D, int %op)
        %Bv = load int* %B
        %Cv = load int* %C
        %Dv = load int* %D
        %x = add int %A, %Bv
        %y = add int %x, %Cv
        %z = add int %y, %Dv
        ret int %z
}

to this:

_test_cpuid:
        sub %ESP, 16
        mov DWORD PTR [%ESP], %EBX
        mov %EAX, DWORD PTR [%ESP + 20]
        cpuid
        mov DWORD PTR [%ESP + 8], %ECX
        mov DWORD PTR [%ESP + 12], %EBX
        mov DWORD PTR [%ESP + 4], %EDX
        mov %ECX, DWORD PTR [%ESP + 12]
        add %EAX, %ECX
        mov %ECX, DWORD PTR [%ESP + 8]
        add %EAX, %ECX
        mov %ECX, DWORD PTR [%ESP + 4]
        add %EAX, %ECX
        mov %EBX, DWORD PTR [%ESP]
        add %ESP, 16
        ret

... note the proper register allocation.  :)

it is unclear to me why the loads aren't folded into the adds.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@25827 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/CodeGen/SelectionDAG/ScheduleDAG.cpp b/lib/CodeGen/SelectionDAG/ScheduleDAG.cpp
index 4e45bd6..9f285d5 100644
--- a/lib/CodeGen/SelectionDAG/ScheduleDAG.cpp
+++ b/lib/CodeGen/SelectionDAG/ScheduleDAG.cpp
@@ -300,7 +300,7 @@
       // Add all of the operand registers to the instruction.
       for (unsigned i = 2; i != NumOps; i += 2) {
         unsigned Reg = cast<RegisterSDNode>(Node->getOperand(i))->getReg();
-        unsigned Flags = cast<ConstantSDNode>(Node->getOperand(i))->getValue();
+        unsigned Flags =cast<ConstantSDNode>(Node->getOperand(i+1))->getValue();
         MachineOperand::UseType UseTy;
         switch (Flags) {
         default: assert(0 && "Bad flags!");