so that Dominators.h is *just* domtree.  Also prune #includes a bit.

llvm-svn: 122714

llvm-svn: 122713

sure that the loop we're promoting into a memcpy doesn't mutate the input
of the memcpy.  Before we were just checking that the dest of the memcpy
wasn't mod/ref'd by the loop.

llvm-svn: 122712

mess with it.  We'd rather peel/unroll it than convert all of its 
stores into memsets.

llvm-svn: 122711

This allows us to compile:
  void test(char *s, int a) {
    __builtin_memset(s, a, 15);
  }
into 1 mul + 3 stores instead of 3 muls + 3 stores.

llvm-svn: 122710

llvm-svn: 122709

llvm-svn: 122708

Lower the i8 extension in memset to a multiply instead of a potentially long series of shifts and ors.

We could implement a DAGCombine to turn x * 0x0101 back into logic operations
on targets that doesn't support the multiply or it is slow (p4) if someone cares
enough.

Example code:
  void test(char *s, int a) {
      __builtin_memset(s, a, 4);
  }
before:
  _test:                                  ## @test
    movzbl  8(%esp), %eax
    movl  %eax, %ecx
    shll  $8, %ecx
    orl %eax, %ecx
    movl  %ecx, %eax
    shll  $16, %eax
    orl %ecx, %eax
    movl  4(%esp), %ecx
    movl  %eax, 4(%ecx)
    movl  %eax, (%ecx)
    ret
after:
  _test:                                  ## @test
    movzbl  8(%esp), %eax
    imull $16843009, %eax, %eax   ## imm = 0x1010101
    movl  4(%esp), %ecx
    movl  %eax, 4(%ecx)
    movl  %eax, (%ecx)
    ret

llvm-svn: 122707

llvm-svn: 122706

another function.

llvm-svn: 122705

blocks in a loop, instead of just the header block.  This makes it more
aggressive, able to handle Duncan's Ada examples.

llvm-svn: 122704

llvm-svn: 122703

isExitBlockDominatedByBlockInLoop is a relic of the days when domtree was 
*just* a tree and didn't have DFS numbers.  Checking DFS numbers is faster
and easier than "limiting the search of the tree".

llvm-svn: 122702

llvm-svn: 122701

llvm-svn: 122700

in the PR, the pass could break LCSSA form when inserting preheaders.  It probably
would be easy enough to fix this, but since currently we always go into LCSSA form
after running this pass, doing so is not urgent.

llvm-svn: 122695

llvm-svn: 122693

llvm-svn: 122692

llvm-svn: 122691

llvm-svn: 122690

llvm-svn: 122689

llvm-svn: 122688

llvm-svn: 122687

llvm-svn: 122686

header for now for memset/memcpy opportunities.  It turns out that loop-rotate
is successfully rotating loops, but *DOESN'T MERGE THE BLOCKS*, turning "for 
loops" into 2 basic block loops that loop-idiom was ignoring.

With this fix, we form many *many* more memcpy and memsets than before, including
on the "history" loops in the viterbi benchmark, which look like this:

        for (j=0; j<MAX_history; ++j) {
          history_new[i][j+1] = history[2*i][j];
        }

Transforming these loops into memcpy's speeds up the viterbi benchmark from
11.98s to 3.55s on my machine.  Woo.

llvm-svn: 122685

compile, and everyone's tests have shown it to be slower in practice, even for
quite large graphs.

I also hope to do an optimization that is only correct with the simpler data
structure, which would break this even further.

llvm-svn: 122684

llvm-svn: 122683

llvm-svn: 122682

size of a loop header instead of its own code size estimator.
This allows it to handle bitcasts etc more precisely.

llvm-svn: 122681

naively implemented, the Lengauer-Tarjan algorithm requires a separate bucket
for each vertex. However, this is unnecessary, because each vertex is only
placed into a single bucket (that of its semidominator), and each vertex's
bucket is processed before it is added to any bucket itself.

Instead of using a bucket per vertex, we use a single array Buckets that has two
purposes. Before the vertex V with DFS number i is processed, Buckets[i] stores
the index of the first element in V's bucket. After V's bucket is processed,
Buckets[i] stores the index of the next element in the bucket to which V now
belongs, if any.

Reading from the buckets can also be optimized. Instead of processing the bucket
of V's parent at the end of processing V, we process the bucket of V itself at
the beginning of processing V. This means that the case of the root vertex can
be simplified somewhat. It also means that we don't need to look up the DFS
number of the semidominator of every node in the bucket we are processing,
since we know it is the current index being processed.

This is a 6.5% speedup running -domtree on test-suite + SPEC2000/2006, with
larger speedups of around 12% on the larger benchmarks like GCC.

llvm-svn: 122680

statements using the "x" constraint.

llvm-svn: 122679

llvm-svn: 122678

maintains the guarantee that the DenseSet expects two elements it contains to
not go from inequal to equal under its nose.

As a side-effect, this also lets us switch from iterating to a fixed-point to
actually maintaining a work queue of functions to look at again, and we don't
add thunks to our work queue so we don't need to detect and ignore them.

llvm-svn: 122677

llvm-svn: 122676

llvm-svn: 122675

loop idiom pass exposed.

llvm-svn: 122674

llvm-svn: 122672

llvm-svn: 122671

llvm-svn: 122670

llvm-svn: 122669