of code to be unified.

llvm-svn: 28191

Don't prefix section directives with a tab.  Doing so causes blank lines to
be emitted to the .s file.

llvm-svn: 28189

llvm-svn: 28188

llvm-svn: 28186

llvm-svn: 28184

short test2(short X, short x) {
  int Y = (short)(X+x);
  return Y >> 1;
}

to:

_test2:
        add r2, r3, r4
        extsh r2, r2
        srawi r3, r2, 1
        blr

instead of:

_test2:
        add r2, r3, r4
        extsh r2, r2
        srwi r2, r2, 1
        extsh r3, r2
        blr

llvm-svn: 28175

_test4:
        srawi r3, r3, 16
        blr

instead of:

_test4:
        srwi r2, r3, 16
        extsh r3, r2
        blr

for:

short test4(unsigned X) {
  return (X >> 16);
}

llvm-svn: 28174

short test4(unsigned X) {
  return (X >> 16);
}

to:

_test4:
        movl 4(%esp), %eax
        sarl $16, %eax
        ret

instead of:

_test4:
        movl $-65536, %eax
        andl 4(%esp), %eax
        sarl $16, %eax
        ret

llvm-svn: 28171

llvm-svn: 28167

to be only 31.25% dense, rather than 75% dense.

llvm-svn: 28165

llvm-svn: 28161

llvm-svn: 28152

llvm-svn: 28151

llvm-svn: 28150

llvm-svn: 28148

sign_extend_inreg operations.  Though ComputeNumSignBits is still rudimentary,
this is enough to compile this:

short test(short X, short x) {
  int Y = X+x;
  return (Y >> 1);
}
short test2(short X, short x) {
  int Y = (short)(X+x);
  return Y >> 1;
}

into:

_test:
        add r2, r3, r4
        srawi r3, r2, 1
        blr
_test2:
        add r2, r3, r4
        extsh r2, r2
        srawi r3, r2, 1
        blr

instead of:

_test:
        add r2, r3, r4
        srawi r2, r2, 1
        extsh r3, r2
        blr
_test2:
        add r2, r3, r4
        extsh r2, r2
        srawi r2, r2, 1
        extsh r3, r2
        blr

llvm-svn: 28146

a cast immediately before a PHI node.

This fixes Regression/CodeGen/Generic/2006-05-06-GEP-Cast-Sink-Crash.ll

llvm-svn: 28143

27,28c27
<       movzwl %di, %edi
<       movl %edi, %ebx
---
>       movw %di, %bx

llvm-svn: 28137

llvm-svn: 28136

llvm-svn: 28132

llvm-svn: 28130

generated:

        movl 8(%esp), %eax
        movl %eax, %edx
        addl $4316, %edx
        cmpb $1, %cl
        ja LBB1_2       #cond_false
LBB1_1: #cond_true
        movl L_QuantizationTables720$non_lazy_ptr, %ecx
        movl %ecx, (%edx)
        movl L_QNOtoQuantTableShift720$non_lazy_ptr, %edx
        movl %edx, 4460(%eax)
        ret
...

Now we generate:

        movl 8(%esp), %eax
        cmpb $1, %cl
        ja LBB1_2       #cond_false
LBB1_1: #cond_true
        movl L_QuantizationTables720$non_lazy_ptr, %ecx
        movl %ecx, 4316(%eax)
        movl L_QNOtoQuantTableShift720$non_lazy_ptr, %ecx
        movl %ecx, 4460(%eax)
        ret

... which uses one fewer register.

llvm-svn: 28129

llvm-svn: 28124

  // fold (and (sext x), (sext y)) -> (sext (and x, y))
  // fold (or  (sext x), (sext y)) -> (sext (or  x, y))
  // fold (xor (sext x), (sext y)) -> (sext (xor x, y))
  // fold (and (aext x), (aext y)) -> (aext (and x, y))
  // fold (or  (aext x), (aext y)) -> (aext (or  x, y))
  // fold (xor (aext x), (aext y)) -> (aext (xor x, y))

llvm-svn: 28123

        mov EAX, DWORD PTR [ESP + 4]
        mov ECX, DWORD PTR [EAX]
        mov EDX, ECX
        add EDX, EDX
        or EDX, ECX
        and EDX, -2147483648
        and ECX, 2147483647
        or EDX, ECX
        mov DWORD PTR [EAX], EDX
        ret

instead of:

        sub ESP, 4
        mov DWORD PTR [ESP], ESI
        mov EAX, DWORD PTR [ESP + 8]
        mov ECX, DWORD PTR [EAX]
        mov EDX, ECX
        add EDX, EDX
        mov ESI, ECX
        and ESI, -2147483648
        and EDX, -2147483648
        or EDX, ESI
        and ECX, 2147483647
        or EDX, ECX
        mov DWORD PTR [EAX], EDX
        mov ESI, DWORD PTR [ESP]
        add ESP, 4
        ret

llvm-svn: 28122

llvm-svn: 28121

  // fold (and (trunc x), (trunc y)) -> (trunc (and x, y))
  // fold (or  (trunc x), (trunc y)) -> (trunc (or  x, y))
  // fold (xor (trunc x), (trunc y)) -> (trunc (xor x, y))

llvm-svn: 28120

llvm-svn: 28117

of cross-block live ranges, and allows the bb-at-a-time selector to always
coallesce these away, at isel time.

This reduces the load on the coallescer and register allocator.  For example
on a codec on X86, we went from:

   1643 asm-printer           - Number of machine instrs printed
    419 liveintervals         - Number of loads/stores folded into instructions
   1144 liveintervals         - Number of identity moves eliminated after coalescing
   1022 liveintervals         - Number of interval joins performed
    282 liveintervals         - Number of intervals after coalescing
   1304 liveintervals         - Number of original intervals
     86 regalloc              - Number of times we had to backtrack
1.90232 regalloc              - Ratio of intervals processed over total intervals
     40 spiller               - Number of values reused
    182 spiller               - Number of loads added
    121 spiller               - Number of stores added
    132 spiller               - Number of register spills
      6 twoaddressinstruction - Number of instructions commuted to coalesce
    360 twoaddressinstruction - Number of two-address instructions

to:

   1636 asm-printer           - Number of machine instrs printed
    403 liveintervals         - Number of loads/stores folded into instructions
   1155 liveintervals         - Number of identity moves eliminated after coalescing
   1033 liveintervals         - Number of interval joins performed
    279 liveintervals         - Number of intervals after coalescing
   1312 liveintervals         - Number of original intervals
     76 regalloc              - Number of times we had to backtrack
1.88998 regalloc              - Ratio of intervals processed over total intervals
      1 spiller               - Number of copies elided
     41 spiller               - Number of values reused
    191 spiller               - Number of loads added
    114 spiller               - Number of stores added
    128 spiller               - Number of register spills
      4 twoaddressinstruction - Number of instructions commuted to coalesce
    356 twoaddressinstruction - Number of two-address instructions

On this testcase, this change provides a modest reduction in spill code,
regalloc iterations, and total instructions emitted.  It increases the number
of register coallesces.

llvm-svn: 28115

llvm-svn: 28110

scheduler can go into a "vertical mode" (i.e. traversing up the two-address
chain, etc.) when the register pressure is low.
This does seem to reduce the number of spills in the cases I've looked at. But
with x86, it's no guarantee the performance of the code improves.
It can be turned on with -sched-vertically option.

llvm-svn: 28108

llvm-svn: 28107

llvm-svn: 28105

llvm-svn: 28104

llvm-svn: 28102

llvm-svn: 28099

thing that can be in it.  Remove a dead method.

llvm-svn: 28098

llvm-svn: 28094

llvm-svn: 28093

llvm-svn: 28092