We cannot use a normal call here since it has extra unmodelled side
effects (it changes stack pointer). This should fix PR5292.

llvm-svn: 97884

llvm-svn: 97818

Fix an oops in x86 sibcall optimization. If the ByVal callee argument is itself passed as a pointer, then it's obviously not safe to do a tail call.

llvm-svn: 97797

llvm-svn: 97782

llvm-svn: 97768

This code:

float floatingPointComparison(float x, float y) {
    double product = (double)x * y;
    if (product == 0.0)
        return product;
    return product - 1.0;
}

produces this:

_floatingPointComparison:
0000000000000000        cvtss2sd        %xmm1,%xmm1
0000000000000004        cvtss2sd        %xmm0,%xmm0
0000000000000008        mulsd           %xmm1,%xmm0
000000000000000c        pxor            %xmm1,%xmm1
0000000000000010        ucomisd         %xmm1,%xmm0
0000000000000014        jne             0x00000004
0000000000000016        jp              0x00000002
0000000000000018        jmp             0x00000008
000000000000001a        addsd           0x00000006(%rip),%xmm0
0000000000000022        cvtsd2ss        %xmm0,%xmm0
0000000000000026        ret

The "jne/jp/jmp" sequence can be reduced to this instead:

_floatingPointComparison:
0000000000000000        cvtss2sd        %xmm1,%xmm1
0000000000000004        cvtss2sd        %xmm0,%xmm0
0000000000000008        mulsd           %xmm1,%xmm0
000000000000000c        pxor            %xmm1,%xmm1
0000000000000010        ucomisd         %xmm1,%xmm0
0000000000000014        jp              0x00000002
0000000000000016        je              0x00000008
0000000000000018        addsd           0x00000006(%rip),%xmm0
0000000000000020        cvtsd2ss        %xmm0,%xmm0
0000000000000024        ret

for a savings of 2 bytes.

This xform can happen when we recognize that jne and jp jump to the same "true"
MBB, the unconditional jump would jump to the "false" MBB, and the "true" branch
is the fall-through MBB.

llvm-svn: 97766

These instructions technically define AL,AH, but a trick in X86ISelDAGToDAG
reads AX in order to avoid reading AH with a REX instruction.

Fix PR6489.

llvm-svn: 97742

clobber registers in a different order.

llvm-svn: 97741

llvm-svn: 97740

register if it isn't possible to match the indexes *and* the base.
This fixes some fast isel rejects of load instructions on oggenc.

llvm-svn: 97739

llvm-svn: 97709

better done by dag combine.

llvm-svn: 97633

'dsload' pattern.  tblgen doesn't check patterns to see if they're
textually identical.  This allows better factoring.

llvm-svn: 97630

that they are not destination type specific.  This allows
tblgen to factor them and the type check is redundant with
what the isel does anyway.

llvm-svn: 97629

llvm-svn: 97606

We still preprocess calls and fp return stuff.

llvm-svn: 97598

CopyToReg/CopyFromReg/INLINEASM.  These are annoying because
they have the same opcode before an after isel.  Fix this by
setting their NodeID to -1 to indicate that they are selected,
just like what automatically happens when selecting things that
end up being machine nodes.

With that done, give IsLegalToFold a new flag that causes it to
ignore chains.  This lets the HandleMergeInputChains routine be
the one place that validates chains after a match is successful,
enabling the new hotness in chain processing.  This smarter
chain processing eliminates the need for "PreprocessRMW" in the
X86 and MSP430 backends and enables MSP to start matching it's
multiple mem operand instructions more aggressively.

I currently #if out the dead code in the X86 backend and MSP 
backend, I'll remove it for real in a follow-on patch.

The testcase changes are:
  test/CodeGen/X86/sse3.ll: we generate better code
  test/CodeGen/X86/store_op_load_fold2.ll: PreprocessRMW was 
      miscompiling this before, we now generate correct code
      Convert it to filecheck while I'm at it.
  test/CodeGen/MSP430/Inst16mm.ll: Add a testcase for mem/mem
      folding to make anton happy. :)

llvm-svn: 97596

DoInstructionSelection.  Inline "SelectRoot" into it from DAGISelHeader.
Sink some other stuff out of DAGISelHeader into SDISel.

Eliminate the various 'Indent' stuff from various targets, which dates
to when isel was recursive.

 17 files changed, 114 insertions(+), 430 deletions(-)

llvm-svn: 97555

llvm-svn: 97536

respectively.

llvm-svn: 97531

now that it is gone.

llvm-svn: 97516

Remove the optimize for code size limitation on r67917. Optimize 64-bit imul by constants into leas + shl regardless if optimizing for code size. The size saving from using imulq isn't worth it. Also, the lea and shl instructions may expose further optimization.

llvm-svn: 97507

problems.  rdar://7697850.

llvm-svn: 97500

llvm-svn: 97450

llvm-svn: 97427

Extracting the low element of a vector is now done with EXTRACT_SUBREG,
and the zero-extension performed by load movss is now modeled with
SUBREG_TO_REG, and so on.

Register-to-register movss and movsd are no longer considered copies;
they are two-address instructions which insert a scalar into a vector.

llvm-svn: 97354

llvm-svn: 97348

llvm-svn: 97316

llvm-svn: 97310

as X86 is currently the only FastISel target.  Per review.

llvm-svn: 97255

llvm-svn: 97227

llvm-svn: 97201

llvm-svn: 97151

just discarding one of the registers.

llvm-svn: 97100

the hopes of fixing PPC bootstrap.

llvm-svn: 97040

necessary to swap the operands to handle NaN and negative zero properly.

Also, reintroduce logic for checking for NaN conditions when forming
SSE min and max instructions, fixed to take into consideration NaNs and
negative zeros. This allows forming min and max instructions in more
cases.

llvm-svn: 97025

llvm-svn: 97011

instead of %AL/%AH.

llvm-svn: 97006

llvm-svn: 96990

disables load folding at -O0.

llvm-svn: 96973