llvm-svn: 30606

int x __attribute__((used));

to:

        .data
.comm _x,4              ; 'x'
        .no_dead_strip  _x

on both x86 and ppc darwin targets.

llvm-svn: 30605

because they have an aggressive linker that does dead code stripping.

llvm-svn: 30604

llvm-svn: 30601

llvm-svn: 30600

llvm-svn: 30598

llvm-svn: 30597

llvm-svn: 30594

llvm-svn: 30593

llvm-svn: 30591

llvm-svn: 30590

llvm-svn: 30588

or when splitting loops with a common header into multiple loops.  In particular
the old code would always insert the preheader before the old loop header.  This
is disasterous in cases where the loop hasn't been rotated.  For example, it can
produce code like:

        .. outside the loop...
        jmp LBB1_2      #bb13.outer
LBB1_1: #bb1
        movsd 8(%esp,%esi,8), %xmm1
        mulsd (%edi), %xmm1
        addsd %xmm0, %xmm1
        addl $24, %edi
        incl %esi
        jmp LBB1_3      #bb13
LBB1_2: #bb13.outer
        leal (%edx,%eax,8), %edi
        pxor %xmm1, %xmm1
        xorl %esi, %esi
LBB1_3: #bb13
        movapd %xmm1, %xmm0
        cmpl $4, %esi
        jl LBB1_1       #bb1

Note that the loop body is actually LBB1_1 + LBB1_3, which means that the
loop now contains an uncond branch WITHIN it to jump around the inserted
loop header (LBB1_2).  Doh.

This patch changes the preheader insertion code to insert it in the right
spot, producing this code:

        ... outside the loop, fall into the header ...
LBB1_1: #bb13.outer
        leal (%edx,%eax,8), %esi
        pxor %xmm0, %xmm0
        xorl %edi, %edi
        jmp LBB1_3      #bb13
LBB1_2: #bb1
        movsd 8(%esp,%edi,8), %xmm0
        mulsd (%esi), %xmm0
        addsd %xmm1, %xmm0
        addl $24, %esi
        incl %edi
LBB1_3: #bb13
        movapd %xmm0, %xmm1
        cmpl $4, %edi
        jl LBB1_2       #bb1

Totally crazy, no branch in the loop! :)

llvm-svn: 30587

reachable, making it general purpose enough for use by InsertPreheaderForLoop.
Eliminate custom dominfo updating code in InsertPreheaderForLoop, using
UpdateDomInfoForRevectoredPreds instead.

llvm-svn: 30586

llvm-svn: 30584

llvm-svn: 30583

llvm-svn: 30581

llvm-svn: 30577

llvm-svn: 30576

call stack depth.

llvm-svn: 30575

llvm-svn: 30573

llvm-svn: 30570

llvm-svn: 30568

llvm-svn: 30567

llvm-svn: 30566

llvm-svn: 30561

llvm-svn: 30560

llvm-svn: 30559

int %test(ulong *%tmp) {
        %tmp = load ulong* %tmp         ; <ulong> [#uses=1]
        %tmp.mask = shr ulong %tmp, ubyte 50            ; <ulong> [#uses=1]
        %tmp.mask = cast ulong %tmp.mask to ubyte
        %tmp2 = and ubyte %tmp.mask, 3          ; <ubyte> [#uses=1]
        %tmp2 = cast ubyte %tmp2 to int         ; <int> [#uses=1]
        ret int %tmp2
}

to:

_test:
        movl 4(%esp), %eax
        movl 4(%eax), %eax
        shrl $18, %eax
        andl $3, %eax
        ret

instead of:

_test:
        movl 4(%esp), %eax
        movl 4(%eax), %eax
        shrl $18, %eax
        # TRUNCATE movb %al, %al
        andb $3, %al
        movzbl %al, %eax
        ret

llvm-svn: 30558

the src/dst are not the same size.  This catches things like "truncate
32-bit X to 8 bits, then zext to 16", which happens a bit on X86.

llvm-svn: 30557

llvm-svn: 30556

llvm-svn: 30555

llvm-svn: 30553

llvm-svn: 30552

with the right answer.

llvm-svn: 30550

llvm-svn: 30549

llvm-svn: 30548

should create the right asmprinter subclass.

llvm-svn: 30542

llvm-svn: 30541

Fixes infinite loop in resolve().

llvm-svn: 30540