Where previously LLVM might emit code like this:

        ucomisd %xmm1, %xmm0
        setne   %al
        setp    %cl
        orb     %al, %cl
        jne     .LBB4_2

it now emits this:

        ucomisd %xmm1, %xmm0
        jne     .LBB4_2
        jp      .LBB4_2

It has fewer instructions and uses fewer registers, but it does
have more branches. And in the case that this code is followed by
a non-fallthrough edge, it may be followed by a jmp instruction,
resulting in three branch instructions in sequence. Some effort
is made to avoid this situation.

To achieve this, X86ISelLowering.cpp now recognizes FCMP_OEQ and
FCMP_UNE in lowered form, and replace them with code that emits
two branches, except in the case where it would require converting
a fall-through edge to an explicit branch.

Also, X86InstrInfo.cpp's branch analysis and transform code now
knows now to handle blocks with multiple conditional branches. It
uses loops instead of having fixed checks for up to two
instructions. It can now analyze and transform code generated
from FCMP_OEQ and FCMP_UNE.

llvm-svn: 57873

llvm-svn: 55779

handled correctly, and change a few SmallVector uses to use
size 0 to more clearly reflect their intent.

llvm-svn: 55181

Convert uses of std::vector in TargetInstrInfo to SmallVector.  This change had to be propoagated down into all the targets and up into all clients of this API.

llvm-svn: 54802

MachineMemOperands. The pools are owned by MachineFunctions.

This drastically reduces the number of calls to malloc/free made
during the "Emit" phase of scheduling, as well as later phases
in CodeGen. Combined with other changes, this speeds up the
"instruction selection" phase of CodeGen by 10% in some cases.

llvm-svn: 53212

llvm-svn: 51931

llvm-svn: 47703

llvm-svn: 47368

llvm-svn: 46514

Make MachineInstr::getDesc return a reference instead
of a pointer, since it can never be null.

llvm-svn: 45695

llvm-svn: 45689

that it is cheap and efficient to get.

Move a variety of predicates from TargetInstrInfo into 
TargetInstrDescriptor, which makes it much easier to query a predicate
when you don't have TII around.  Now you can use MI->getDesc()->isBranch()
instead of going through TII, and this is much more efficient anyway. Not
all of the predicates have been moved over yet.

Update old code that used MI->getInstrDescriptor()->Flags to use the
new predicates in many places.

llvm-svn: 45674

llvm-svn: 45418

llvm-svn: 38495

llvm-svn: 37964

Avoid if-converting simple block that ends with unconditional branch or fallthrough unless it branches / falls to the 'false' block. Not profitable, may end up increasing code size.

llvm-svn: 37660

llvm-svn: 37643

llvm-svn: 37634

llvm-svn: 37623

1. Consider all possible ifcvt cases at once. No longer restricted to bottom
   up iterative approach.
2. Sort all possible cases based on a cost function. Perform the most profitable
   ones first invalidate others that target the same blocks.
3. Fixed a number of bugs related to block duplication.

llvm-svn: 37613

llvm-svn: 37607

llvm-svn: 37599

llvm-svn: 37593

llvm-svn: 37590

llvm-svn: 37581

If BB is predicated, invalidate its predecessor(s) which would if-convert it. It needs to be re-analyzed.

llvm-svn: 37580

llvm-svn: 37577

llvm-svn: 37575

llvm-svn: 37566

llvm-svn: 37565

llvm-svn: 37543

llvm-svn: 37537

llvm-svn: 37531

llvm-svn: 37529

llvm-svn: 37524

llvm-svn: 37523

llvm-svn: 37518

llvm-svn: 37503

ifcvt a triangle: don't merge ifcvt block with rejoin block if it can fall through to it. If merged, the resulting block is not a candidate for iterative ifcvting since it contains both predicated and non-predicated code.

llvm-svn: 37487

llvm-svn: 37485