Adds an instruction itinerary to all x86 instructions, giving each a default latency of 1, using the InstrItinClass IIC_DEFAULT.

Sets specific latencies for Atom for the instructions in files X86InstrCMovSetCC.td, X86InstrArithmetic.td, X86InstrControl.td, and X86InstrShiftRotate.td. The Atom latencies for the remainder of the x86 instructions will be set in subsequent patches.

Adds a test to verify that the scheduler is working.

Also changes the scheduling preference to "Hybrid" for i386 Atom, while leaving x86_64 as ILP.

Patch by Preston Gurd!

llvm-svn: 149558

llvm-svn: 149557

It is simpler to define a composite index directly:

  def ssub_2 : SubRegIndex<[dsub_1, ssub_0]>;
  def ssub_3 : SubRegIndex<[dsub_1, ssub_1]>;

Than specifying the composite indices on each register:

  CompositeIndices = [(ssub_2 dsub_1, ssub_0),
                      (ssub_3 dsub_1, ssub_1)] in ...

This also makes it clear that SubRegIndex composition is supposed to be
unique.

llvm-svn: 149556

llvm-svn: 149553

The final tie breaker comparison also needs to return +/-1, or 0.
This is not a less() function.

This could cause otherwise identical super-classes to be ordered
unstably, depending on what the system qsort routine does with a bad
compare function.

llvm-svn: 149549

llvm-svn: 149548

This new scheduler plugs into the existing selection DAG scheduling framework. It is a top-down critical path scheduler that tracks register pressure and uses a DFA for pipeline modeling.

Patch by Sergei Larin!

llvm-svn: 149547

It's only by luck that we haven't produced any yet, and clang refuses to
compile them.

llvm-svn: 149546

llvm-svn: 149521

It could only be specified on the commandline, and wouldn't show
up as an option in the GUI or when invoked via `cmake -i` at all.

This also tells CMake that it's a BOOL, rather than "UNINITIALIZED".

llvm-svn: 149506

test/CodeGen/X86/avx-minmax.ll: Relax expressions for Win32 targets. YMM arguments are passed as indirect on Win32 x64.

llvm-svn: 149505

The CMake build already generated one. Follows clang r149497.

This brings us one step closer to compiling and configuring clang
separately from LLVM using the autoconf build, too.

(I lack the right version of autoconf et al. to regen, but it
was a simple change, so I just updated configure manually.)

llvm-svn: 149498

Fixed Win64 calling conventions.

llvm-svn: 149494

llvm-svn: 149493

Truncating v4i64 -> v4i32 and v8i32 -> v8i16 may be done with set of shuffles.

llvm-svn: 149485

The purpose of refactoring is to hide operand roles from SwitchInst user (programmer). If you want to play with operands directly, probably you will need lower level methods than SwitchInst ones (TerminatorInst or may be User). After this patch we can reorganize SwitchInst operands and successors as we want.

What was done:

1. Changed semantics of index inside the getCaseValue method:
getCaseValue(0) means "get first case", not a condition. Use getCondition() if you want to resolve the condition. I propose don't mix SwitchInst case indexing with low level indexing (TI successors indexing, User's operands indexing), since it may be dangerous.
2. By the same reason findCaseValue(ConstantInt*) returns actual number of case value. 0 means first case, not default. If there is no case with given value, ErrorIndex will returned.
3. Added getCaseSuccessor method. I propose to avoid usage of TerminatorInst::getSuccessor if you want to resolve case successor BB. Use getCaseSuccessor instead, since internal SwitchInst organization of operands/successors is hidden and may be changed in any moment.
4. Added resolveSuccessorIndex and resolveCaseIndex. The main purpose of these methods is to see how case successors are really mapped in TerminatorInst.
4.1 "resolveSuccessorIndex" was created if you need to level down from SwitchInst to TerminatorInst. It returns TerminatorInst's successor index for given case successor.
4.2 "resolveCaseIndex" converts low level successors index to case index that curresponds to the given successor.

Note: There are also related compatability fix patches for dragonegg, klee, llvm-gcc-4.0, llvm-gcc-4.2, safecode, clang.
llvm-svn: 149481

The pass pointer should never be referenced after sending it to
schedulePass(), which may delete the pass. To fix this bug I had to
clean up the design leading to more goodness.

You may notice now that any non-analysis pass is printed. So things like loop-simplify and lcssa show up, while target lib, target data, alias analysis do not show up. Normally, analysis don't mutate the IR, but you can now check this by using both -print-after and -print-before. The effects of analysis will now show up in between the two.

The llc path is still in bad shape. But I'll be improving it in my next checkin. Meanwhile, print-machineinstrs still works the same way. With print-before/after, many llc passes that were not printed before now are, some of these should be converted to analysis. A few very important passes, isel and scheduler, are not properly initialized, so not printed.

llvm-svn: 149480

llvm-svn: 149479

llvm-svn: 149478

llvm-svn: 149475

llvm-svn: 149472

These are:

r149348
r149351
r149352
r149354
r149356
r149357
r149361
r149362
r149364
r149365

llvm-svn: 149470

This is the initial checkin of the basic-block autovectorization pass along with some supporting vectorization infrastructure.
Special thanks to everyone who helped review this code over the last several months (especially Tobias Grosser).

llvm-svn: 149468

Changing arguments from being passed as fixed to varargs is unsafe, as
the ABI may require they be handled differently (stack vs. register, for
example).

Remove two tests which rely on the bitcast being folded into the direct
call, which is exactly the transformation that's unsafe.

llvm-svn: 149457

llvm-svn: 149452

llvm-svn: 149446

Make the EarlyCSE optimizer not use recursion to do a depth first iteration.

llvm-svn: 149445

llvm-svn: 149444

symbol from an assignment.  In this case the symbol did not have a fragment so
MCObjectWriter::IsSymbolRefDifferenceFullyResolved() should not have been
calling IsSymbolRefDifferenceFullyResolvedImpl() with a NULL fragment and should
just have returned false in that case.

llvm-svn: 149442

This new function provides a way to get the Mac OS X version number from
either generic "darwin" triples of macosx triples.

llvm-svn: 149438

It was wrong and completely unused.

llvm-svn: 149433

Each SubRegIndex keeps track of how it composes.

llvm-svn: 149423

This class is used to represent SubRegIndex instances instead of the raw
Record pointers that were used before.

No functional change intended.

llvm-svn: 149418

Excellent suggestion from Ben Kramer.

llvm-svn: 149417

llvm-svn: 149416

now that this handles the release / retain calls.

Adds a regression test for that bug (which is a compile-time
regression) and for the last two changes to the IntrusiveRefCntPtr,
especially tests for the memory leak due to copy construction of the
ref-counted object and ensuring that the traits are used for release /
retain calls.

llvm-svn: 149411

llvm-svn: 149408

llvm-svn: 149398

Add assembler dialect attribute in asm parser which lets target specific asm parser change dialect on the fly.

llvm-svn: 149396

llvm-svn: 149391