llvm-svn: 30570

llvm-svn: 30569

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: 30554

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

llvm-svn: 30535

llvm-svn: 30534

llvm-svn: 30533

llvm-svn: 30531

llvm-svn: 30530

llvm-svn: 30519

llvm-svn: 30518

int test3(int a, int b) { return (a < 0) ? a : 0; }

to:

_test3:
        srawi r2, r3, 31
        and r3, r2, r3
        blr

instead of:

_test3:
        cmpwi cr0, r3, 1
        li r2, 0
        blt cr0, LBB2_2 ;entry
LBB2_1: ;entry
        mr r3, r2
LBB2_2: ;entry
        blr


This implements: PowerPC/select_lt0.ll:seli32_a_a

llvm-svn: 30517

llvm-svn: 30516

llvm-svn: 30515

llvm-svn: 30514

1. teach SimplifySetCC that '(srl (ctlz x), 5) == 0' is really x != 0.
2. Teach visitSELECT_CC to use SimplifySetCC instead of calling it and
   ignoring the result.  This allows us to compile:

bool %test(ulong %x) {
  %tmp = setlt ulong %x, 4294967296
  ret bool %tmp
}

to:

_test:
        cntlzw r2, r3
        cmplwi cr0, r3, 1
        srwi r2, r2, 5
        li r3, 0
        beq cr0, LBB1_2 ;
LBB1_1: ;
        mr r3, r2
LBB1_2: ;
        blr

instead of:

_test:
        addi r2, r3, -1
        cntlzw r2, r2
        cntlzw r3, r3
        srwi r2, r2, 5
        cmplwi cr0, r2, 0
        srwi r2, r3, 5
        li r3, 0
        bne cr0, LBB1_2 ;
LBB1_1: ;
        mr r3, r2
LBB1_2: ;
        blr

This isn't wonderful, but it's an improvement.

llvm-svn: 30513

llvm-svn: 30512

this comparison, but never checked it.  Whoops, no wonder we miscompiled
177.mesa!

llvm-svn: 30511

llvm-svn: 30510

1. Codegen this comparison:
     if (X == 0x8000)

as:

        cmplwi cr0, r3, 32768
        bne cr0, LBB1_2 ;cond_next

instead of:

        lis r2, 0
        ori r2, r2, 32768
        cmpw cr0, r3, r2
        bne cr0, LBB1_2 ;cond_next


2. Codegen this comparison:
      if (X == 0x12345678)

as:

        xoris r2, r3, 4660
        cmplwi cr0, r2, 22136
        bne cr0, LBB1_2 ;cond_next

instead of:

        lis r2, 4660
        ori r2, r2, 22136
        cmpw cr0, r3, r2
        bne cr0, LBB1_2 ;cond_next

llvm-svn: 30509

llvm-svn: 30508

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