llvm-svn: 30606

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

llvm-svn: 30604

llvm-svn: 30601

llvm-svn: 30600

llvm-svn: 30597

llvm-svn: 30593

llvm-svn: 30590

llvm-svn: 30573

llvm-svn: 30570

llvm-svn: 30568

llvm-svn: 30561

llvm-svn: 30560

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

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: 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

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

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

llvm-svn: 30494

llvm-svn: 30478

llvm-svn: 30477

llvm-svn: 30474

llvm-svn: 30470

llvm-svn: 30462

llvm-svn: 30461

llvm-svn: 30460

llvm-svn: 30407

llvm-svn: 30403

llvm-svn: 30402

is faster and is needed for future improvements.

llvm-svn: 30383

This implements CodeGen/X86/and-or-fold.ll

llvm-svn: 30379

matching things like ((x >> c1) & c2) | ((x << c3) & c4) to (rot x, c5) & c6

llvm-svn: 30376

llvm-svn: 30327

llvm-svn: 30326

llvm-svn: 30316

in a specific BB, don't undo this!).  This allows us to compile
CodeGen/X86/loop-hoist.ll into:

_foo:
        xorl %eax, %eax
***     movl L_Arr$non_lazy_ptr, %ecx
        movl 4(%esp), %edx
LBB1_1: #cond_true
        movl %eax, (%ecx,%eax,4)
        incl %eax
        cmpl %edx, %eax
        jne LBB1_1      #cond_true
LBB1_2: #return
        ret

instead of:

_foo:
        xorl %eax, %eax
        movl 4(%esp), %ecx
LBB1_1: #cond_true
***     movl L_Arr$non_lazy_ptr, %edx
        movl %eax, (%edx,%eax,4)
        incl %eax
        cmpl %ecx, %eax
        jne LBB1_1      #cond_true
LBB1_2: #return
        ret

This was noticed in 464.h264ref.  This doesn't usually affect PPC,
but strikes X86 all the time.

llvm-svn: 30290

        addl %ecx, %ecx
        adcl %eax, %eax

instead of:

        movl %ecx, %edx
        addl %edx, %edx
        shrl $31, %ecx
        addl %eax, %eax
        orl %ecx, %eax

and to:

        addc r5, r5, r5
        adde r4, r4, r4

instead of:

        slwi r2,r9,1
        srwi r0,r11,31
        slwi r3,r11,1
        or r2,r0,r2

on PPC.

llvm-svn: 30284

representing expressions that can only be resolved at link time, etc.

llvm-svn: 30278

llvm-svn: 30240

due to switch cases going to the same place, it make #pred != #phi entries,
breaking live interval analysis.

This fixes 458.sjeng on x86 with llc.

llvm-svn: 30236