Allow it to be clever when possible and fall back to the gross code when needed.

This allows us to compile:

long long foo1(long long X, int C) {
  return X << (C|32);
}
long long foo2(long long X, int C) {
  return X << (C&~32);
}

to:
_foo1:
        rlwinm r2, r5, 0, 27, 31
        slw r3, r4, r2
        li r4, 0
        blr


        .globl  _foo2
        .align  4
_foo2:
        rlwinm r2, r5, 0, 27, 25
        subfic r5, r2, 32
        slw r3, r3, r2
        srw r5, r4, r5
        or r3, r3, r5
        slw r4, r4, r2
        blr

instead of:

_foo1:
        ori r2, r5, 32
        subfic r5, r2, 32
        addi r6, r2, -32
        srw r5, r4, r5
        slw r3, r3, r2
        slw r6, r4, r6
        or r3, r3, r5
        slw r4, r4, r2
        or r3, r3, r6
        blr


        .globl  _foo2
        .align  4
_foo2:
        rlwinm r2, r5, 0, 27, 25
        subfic r5, r2, 32
        addi r6, r2, -32
        srw r5, r4, r5
        slw r3, r3, r2
        slw r6, r4, r6
        or r3, r3, r5
        slw r4, r4, r2
        or r3, r3, r6
        blr

llvm-svn: 30507

shift amount is one or zero.  For example, for:

long long foo1(long long X, int C) {
  return X << (C|32);
}

long long foo2(long long X, int C) {
  return X << (C&~32);
}

we get:

_foo1:
        movb $31, %cl
        movl 4(%esp), %edx
        andb 12(%esp), %cl
        shll %cl, %edx
        xorl %eax, %eax
        ret
_foo2:
        movb $223, %cl
        movl 4(%esp), %eax
        movl 8(%esp), %edx
        andb 12(%esp), %cl
        shldl %cl, %eax, %edx
        shll %cl, %eax
        ret

instead of:

_foo1:
        subl $4, %esp
        movl %ebx, (%esp)
        movb $32, %bl
        movl 8(%esp), %eax
        movl 12(%esp), %edx
        movb %bl, %cl
        orb 16(%esp), %cl
        shldl %cl, %eax, %edx
        shll %cl, %eax
        xorl %ecx, %ecx
        testb %bl, %bl
        cmovne %eax, %edx
        cmovne %ecx, %eax
        movl (%esp), %ebx
        addl $4, %esp
        ret
_foo2:
        subl $4, %esp
        movl %ebx, (%esp)
        movb $223, %cl
        movl 8(%esp), %eax
        movl 12(%esp), %edx
        andb 16(%esp), %cl
        shldl %cl, %eax, %edx
        shll %cl, %eax
        xorl %ecx, %ecx
        xorb %bl, %bl
        testb %bl, %bl
        cmovne %eax, %edx
        cmovne %ecx, %eax
        movl (%esp), %ebx
        addl $4, %esp
        ret

llvm-svn: 30506

llvm-svn: 30505

llvm-svn: 30504

llvm-svn: 30498

llvm-svn: 30497

If we have an add, do it in the pointer realm, not the int realm.  This is critical in the linux kernel for pointer analysis correctness

llvm-svn: 30496

Inspired by the linux kernel, the more we keep adds in the pointer realm, the better pointer analysis works.

llvm-svn: 30495

allow it to go into an infinite loop, filling up the disk!

llvm-svn: 30494

add comments
untabify

llvm-svn: 30486

llvm-svn: 30485

llvm-svn: 30484

llvm-svn: 30483

llvm-svn: 30482

llvm-svn: 30481

llvm-svn: 30480

like:
long long test(long long X, int Y) {
  return 1ULL << Y;
}
long long test2(long long X, int Y) {
  return -1LL << Y;
}

which we used to compile to:

_test:
        li r2, 1
        subfic r3, r5, 32
        li r4, 0
        addi r6, r5, -32
        srw r3, r2, r3
        slw r4, r4, r5
        slw r6, r2, r6
        or r3, r4, r3
        slw r4, r2, r5
        or r3, r3, r6
        blr
_test2:
        li r2, -1
        subfic r3, r5, 32
        addi r6, r5, -32
        srw r3, r2, r3
        slw r4, r2, r5
        slw r2, r2, r6
        or r3, r4, r3
        or r3, r3, r2
        blr

Now we produce:

_test:
        li r2, 1
        addi r3, r5, -32
        subfic r4, r5, 32
        slw r3, r2, r3
        srw r4, r2, r4
        or r3, r4, r3
        slw r4, r2, r5
        blr
_test2:
        li r2, -1
        subfic r3, r5, 32
        addi r6, r5, -32
        srw r3, r2, r3
        slw r4, r2, r5
        slw r2, r2, r6
        or r3, r4, r3
        or r3, r3, r2
        blr

llvm-svn: 30479

llvm-svn: 30478

llvm-svn: 30477

llvm-svn: 30476

llvm-svn: 30475

llvm-svn: 30474

llvm-svn: 30473

llvm-svn: 30472

llvm-svn: 30471

llvm-svn: 30470

that we can't modify the CFG any more, at least not until it's possible
to update the dominator tree (PR217).

llvm-svn: 30469

of the numeric cases.

llvm-svn: 30468

A pass to remove the worst of the replay trap offenders, and as a bonus, align basic blocks when it is free to do so

llvm-svn: 30467

somewhere (like the dominator graph) and would like to know which case it
came from.

llvm-svn: 30466

llvm-svn: 30465

llvm-svn: 30464

llvm-svn: 30463

llvm-svn: 30462

llvm-svn: 30461

llvm-svn: 30460

... args, remove the '...'.

This is Transforms/DeadArgElim/dead_vaargs.ll

llvm-svn: 30459

llvm-svn: 30458

llvm-svn: 30457

llvm-svn: 30456