just issues an error for the moment. The front end won't yet generate these
intrinsics for ARM, so this is behind the scenes until complete.

llvm-svn: 91200

llvm-svn: 91090

Add memory barrier intrinsic support for ARM. Moving towards adding the atomic operations intrinsics.

llvm-svn: 91003

llvm-svn: 86964

Add TargetLowering::isLegalICmpImmediate. It tells LSR what immediate can be folded into target icmp instructions.

llvm-svn: 86858

llvm-svn: 86494

clang/test/CodeGen/indirect-goto.c runs! (unoptimized)

llvm-svn: 85577

llvm-svn: 85362

This fixes PR5031. Unfortunately, there is no small testcase :(

llvm-svn: 82643

Enhance EmitInstrWithCustomInserter() so target can specify CFG changes that sdisel will use to properly complete phi nodes.
Not functionality change yet.

llvm-svn: 82273

llvm-svn: 80773

The instructions can be selected directly from the intrinsics.  We will need
to add some ARM-specific nodes for VLD/VST of 3 and 4 128-bit vectors, but
those are not yet implemented.

llvm-svn: 80117

now using shuffles instead of intrinsics.

llvm-svn: 79673

llvm-svn: 79625

llvm-svn: 79624

Use masks not nodes for vector shuffle predicates. Provide set of 'legal' masks, so legalizer won't infinite cycle

llvm-svn: 79619

This is derived from a patch by Anton Korzh.  I modified it to recognize
the VEXT shuffles during legalization and lower them to a target-specific
DAG node.

llvm-svn: 79428

llvm-svn: 79136

llvm-svn: 79135

support unaligned mem access only for certain types. (Should it be size
instead?)

ARM v7 supports unaligned access for i16 and i32, some v6 variants support it
as well.

llvm-svn: 79127

llvm-svn: 79032

scalar_to_vector.  Generate these VDUP nodes during legalization instead
of trying to recognize the pattern during selection.

llvm-svn: 78994

target-specific VDUPLANE nodes.  This allows the subreg handling for the
quad-register version to be done easily with Pats in the .td file, instead
of with custom code in ARMISelDAGToDAG.cpp.

llvm-svn: 78993

to fix it tonight.

llvm-svn: 78896

llvm-svn: 78852

llvm-svn: 78850

llvm-svn: 78610

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

llvm-svn: 78330

Patch by Sandeep Patel!

llvm-svn: 78225

Instead of awkwardly encoding calling-convention information with ISD::CALL,
ISD::FORMAL_ARGUMENTS, ISD::RET, and ISD::ARG_FLAGS nodes, TargetLowering
provides three virtual functions for targets to override:
LowerFormalArguments, LowerCall, and LowerRet, which replace the custom
lowering done on the special nodes. They provide the same information, but
in a more immediately usable format.

This also reworks much of the target-independent tail call logic. The
decision of whether or not to perform a tail call is now cleanly split
between target-independent portions, and the target dependent portion
in IsEligibleForTailCallOptimization.

This also synchronizes all in-tree targets, to help enable future
refactoring and feature work.

llvm-svn: 78142

results to fixed registers.

llvm-svn: 78025

llvm-svn: 77422

In thumb2 mode, add pc is unpredictable. Use add + mov pc instead (that is until more optimization goes in).

llvm-svn: 77364

Patch by Anton Korzh, with some modifications from me.

llvm-svn: 77101

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: 75479

bytes and not bytes.

llvm-svn: 74624

have the alignment be calculated up front, and have the back-ends obey whatever
alignment is decided upon.

This allows for future work that would allow for precise no-op placement and the
like.

llvm-svn: 74564

Rename ARMcmpNZ to ARMcmpZ and use it to represent comparisons that set only the Z flag (i.e. eq and ne). Make ARMcmpZ commutative.

llvm-svn: 74423