stack slots and giving them different PseudoSourceValue's did not fix the
problem of post-alloc scheduling miscompiling llvm itself.
- Apply Dan's conservative workaround by assuming any non fixed stack slots can
alias other memory locations. This means a load from spill slot #1 cannot 
move above a store of spill slot #2. 
- Enable post-alloc scheduling for x86 at optimization leverl Default and above.

llvm-svn: 84424

Distinquish stack slots from other stack objects. They (and fixed objects) get FixedStack PseudoSourceValues.

llvm-svn: 84326

llvm-svn: 84321

necessarily fixed. Only those will negative frame indices are "fixed."

llvm-svn: 84315

and register spills.

llvm-svn: 83435

unused DECLARE instruction.

KILL is not yet used anywhere, it will replace TargetInstrInfo::IMPLICIT_DEF
in the places where IMPLICIT_DEF is just used to alter liveness of physical
registers.

llvm-svn: 83006

instruction. This makes it re-materializable.

Thumb2 will split it back out into two instructions so IT pass will generate the
right mask. Also, this expose opportunies to optimize the movw to a 16-bit move.

llvm-svn: 82982

constraint the register usage.

llvm-svn: 81635

makes the code faster.

llvm-svn: 81220

Fix PR4789. Teach eliminateFrameIndex how to handle VLDRQ and VSTRQ which cannot fold any immediate offset.

llvm-svn: 80191

llvm-svn: 79777

llvm-svn: 79763

llvm-svn: 79742

llvm-svn: 78701

llvm-svn: 78683

llvm-svn: 78666

llvm-svn: 78558

llvm-svn: 78557

llvm-svn: 78468

llvm-svn: 78455

llvm-svn: 78397

It turns out most of the thumb2 instructions are not allowed to touch SP. The semantics of such instructions are unpredictable. We have just been lucky that tests have been passing.

This patch takes pain to ensure all the PEI lowering code does the right thing when lowering frame indices, insert code to manipulate stack pointers, etc. It's also custom lowering dynamic stack alloc into pseudo instructions so we can insert the right instructions at scheduling time.

This fixes PR4659 and PR4682.

llvm-svn: 78361

When using NEON for single-precision FP, the NEON result must be placed in D0-D15 as these are the only D registers with S subregs. Introduce a new regclass to represent D0-D15 and use it in the NEON single-precision FP patterns.

llvm-svn: 78244

the only real caller (GetFunctionSizeInBytes) uses it.

The custom ARM implementation of this is basically reimplementing
an assembler poorly for negligible gain.  It should be removed 
IMNSHO, but I'll leave that to ARMish folks to decide.

llvm-svn: 77877

llvm-svn: 77781

llvm-svn: 77744

  is scaled by two.
- Teach GetInstSizeInBytes about TBB and TBH.

llvm-svn: 77701

- This change also makes it possible to switch between ARM / Thumb on a
  per-function basis.
- Fixed thumb2 routine which expand reg + arbitrary immediate. It was using
  using ARM so_imm logic.
- Use movw and movt to do reg + imm when profitable.
- Other code clean ups and minor optimizations.

llvm-svn: 77300

convertToThreeAddress can't handle Thumb2 instructions (which don't have same address mode as ARM instructions).

llvm-svn: 77230

llvm-svn: 77221

This also fixes potential problems in ARMBaseInstrInfo routines not recognizing thumb1 instructions when 32-bit and 16-bit instructions mix.

llvm-svn: 77218

llvm-svn: 77182

llvm-svn: 77181

Use the right instructions to copy between GPR and the more strictive tGPR classes. t2MOV does not match the RC requirements.

llvm-svn: 77175

llvm-svn: 77174

llvm-svn: 77173

Before:
      adr r12, #LJTI3_0_0
      ldr pc, [r12, +r0, lsl #2]
LJTI3_0_0:
      .long    LBB3_24
      .long    LBB3_30
      .long    LBB3_31
      .long    LBB3_32

After:
      adr r12, #LJTI3_0_0
      add pc, r12, +r0, lsl #2
LJTI3_0_0:
      b.w    LBB3_24
      b.w    LBB3_30
      b.w    LBB3_31
      b.w    LBB3_32

This has several advantages.
1. This will make it easier to optimize this to a TBB / TBH instruction +
   (smaller) table.
2. This eliminate the need for ugly asm printer hack to force the address
   into thumb addresses (bit 0 is one).
3. Same codegen for pic and non-pic.
4. This eliminate the need to align the table so constantpool island pass
   won't have to over-estimate the size.

Based on my calculation, the later is probably slightly faster as well since
ldr pc with shifter address is very slow. That is, it should be a win as long
as the HW implementation can do a reasonable job of branch predict the second
branch.

llvm-svn: 77024

llvm-svn: 76986

llvm-svn: 76960

FLDD, FLDS, FCPYD, FCPYS, FSTD, FSTS, VMOVD, VMOVQ maps to the same instructions on all sub-targets.

llvm-svn: 76925