When target costs are available, use them to account for the costs of
shuffles on internal edges of the DAG of candidate pairs.

Because the shuffle costs here are currently for only the internal edges,
the current target cost model is trivial, and the chain depth requirement
is still in place, I don't yet have an easy test
case. Nevertheless, by looking at the debug output, it does seem to do the right
think to the effective "size" of each DAG of candidate pairs.

llvm-svn: 167217

llvm-svn: 167209

llvm-svn: 167200

The static compose() function in RegisterCoalescer was doing the exact
same thing.

llvm-svn: 167198

llvm-svn: 167196

Patch by Ashok Thirumurthi

llvm-svn: 167192

llvm-svn: 167191

  The adc/sbb optimization is to able to convert following expression
into a single adc/sbb instruction:
  (ult) ... = x + 1 // where the ult is unsigned-less-than comparison
  (ult) ... = x - 1

  This change is to flip the "x >u y" (i.e. ugt comparison) in order 
to expose the adc/sbb opportunity.

llvm-svn: 167180

llvm-svn: 167174

llvm-svn: 167170

llvm-svn: 167157

re-materialization of immediate loads.

llvm-svn: 167153

- Use value handle tricks to communicate use replacements instead of forgetLoop, this is a lot faster.
- Move the "big hammer" out of the main loop so it's not called for every instruction.

This should recover most (if not all) compile time regressions introduced by this code.

llvm-svn: 167136

llvm-svn: 167134

SimplifyCFG will have removed those cases for us.

llvm-svn: 167132

llvm-svn: 167131

llvm-svn: 167130

BBVectorize would, except for loads and stores, always fuse instructions
so that the first instruction (in the current source order) would always
represent the low part of the input vectors and the second instruction
would always represent the high part. This lead to too many shuffles
being produced because sometimes the opposite order produces fewer of them.

With this change, BBVectorize tracks the kind of pair connections that form
the DAG of candidate pairs, and uses that information to reorder the pairs to
avoid excess shuffles. Using this information, a future commit will be able
to add VTTI-based shuffle costs to the pair selection procedure. Importantly,
the number of remaining shuffles can now be estimated during pair selection.

There are some trivial instruction reorderings in the test cases, and one
simple additional test where we certainly want to do a reordering to
avoid an unnecessary shuffle.

llvm-svn: 167122

 - Use 0 instead of NULL
 - Helper function for "dyn_cast, else lookup in the constant pool".

llvm-svn: 167121

This patch migrates the strto* optimizations from the simplify-libcalls
pass into the instcombine library call simplifier.

llvm-svn: 167119

llvm-svn: 167117

No functionality change.

llvm-svn: 167116

By propagating the value for the switch condition, LLVM can now build
lookup tables for code such as:

  switch (x) {
    case 1: return 5;
    case 2: return 42;
    case 3: case 4: case 5:
      return x - 123;
    default:
      return 123;
  }

Given that x is known for each case, "x - 123" becomes a constant for
cases 3, 4, and 5.

llvm-svn: 167115

llvm-svn: 167113

I'm not entirely happy with this solution, but I don't see a smarter way currently.
Fixes PR14214.

llvm-svn: 167112

This makes the code match the comments. Resolves a crash in loop idiom (PR14219).

llvm-svn: 167110

No testcase, as this is only testable on a C-A15 board.

llvm-svn: 167108

llvm-svn: 167107

llvm-svn: 167106

This patch migrates the strpbrk optimizations from the simplify-libcalls
pass into the instcombine library call simplifier.

llvm-svn: 167105

llvm-svn: 167104

This patch migrates the strlen optimizations from the simplify-libcalls
pass into the instcombine library call simplifier.

llvm-svn: 167103

This patch migrates the strncpy optimizations from the simplify-libcalls
pass into the instcombine library call simplifier.

llvm-svn: 167102

llvm-svn: 167101

parameters.  Examples of these are:

  struct { } a;
  union { } b[256];
  int a[0];

An empty aggregate has an address, although dereferencing that address is
pointless.  When passed as a parameter, an empty aggregate does not consume
a protocol register, nor does it consume a doubleword in the parameter save
area.  Passing an empty aggregate by reference passes an address just as
for any other aggregate.  Returning an empty aggregate uses GPR3 as a hidden
address of the return value location, just as for any other aggregate.

The patch modifies PPCTargetLowering::LowerFormalArguments_64SVR4 and
PPCTargetLowering::LowerCall_64SVR4 to properly skip empty aggregate
parameters passed by value.  The handling of return values and by-reference
parameters was already correct.

Built on powerpc64-unknown-linux-gnu and tested with no new regressions.
A test case is included to test proper handling of empty aggregate
parameters on both sides of the function call protocol.

llvm-svn: 167090

type MachineInstr* and MachineBasicBlock::iterator.

llvm-svn: 167088

llvm-svn: 167086

This is important for loops in the LAPACK test-suite.
These loops start at 1 because they are auto-converted from fortran.

llvm-svn: 167084

This patch migrates the stpcpy optimizations from the simplify-libcalls
pass into the instcombine library call simplifier.  Note that the
__stpcpy_chk simplifications were migrated in a previous commit.

llvm-svn: 167083

r166198 migrated the strcpy optimization to instcombine.  The strcpy
simplifier that was migrated from Transforms/Scalar/SimplifyLibCalls.cpp
was also doing some __strcpy_chk simplifications.  Those fortified
simplifications were migrated as well, but introduced a bug in the
__stpcpy_chk simplifier in the process.  This happened because the
__strcpy_chk and __stpcpy_chk simplifiers were both mapped to StrCpyChkOpt
which was updated with simplifications that worked for __strcpy_chk, but
not __stpcpy_chk.

This patch fixes the problem by adding proper test coverage and creating a
new simplifier for __stpcpy_chk (instead of sharing one with __strcpy_chk).

llvm-svn: 167082