speeds up idom by about 45% and postidom by about 33%.

Some extra precautions must be taken not to invalidate densemap iterators.

llvm-svn: 40827

DenseMap instead of an std::map.  This speeds up postdomtree
by about 25% and domtree by about 23%.  It also speeds up clients,
for example, domfrontier by 11%, mem2reg by 4% and ADCE by 6%.

llvm-svn: 40826

In the old way, we computed and inserted phi nodes for the whole IDF of 
the definitions of the alloca, then computed which ones were dead and
removed them.

In the new method, we first compute the region where the value is live,
and use that information to only insert phi nodes that are live.  This
eliminates the need to compute liveness later, and stops the algorithm
from inserting a bunch of phis which it then later removes.

This speeds up the testcase in PR1432 from 2.00s to 0.15s (14x) in a
release build and 6.84s->0.50s (14x) in a debug build.

llvm-svn: 40825

llvm-svn: 40824

measurable speedup.

llvm-svn: 40823

to the worklist, and handling the last one with a 'tail call'.  This speeds
up PR1432 from 2.0578s to 2.0012s (2.8%)

llvm-svn: 40822

mem2reg from 2.0742->2.0522s on PR1432.

llvm-svn: 40821

llvm-svn: 40820

llvm-svn: 40819

faster than with the 'local to a block' fastpath.  This speeds
up PR1432 from 2.1232 to 2.0686s (2.6%)

llvm-svn: 40818

to increment NumLocalPromoted, and didn't actually delete the
dead alloca, leading to an extra iteration of mem2reg.

llvm-svn: 40817

llvm-svn: 40816

Predsimplify fails llvm-gcc bootstrap.

llvm-svn: 40815

stored value was a non-instruction value.  Doh.

This increase the # single store allocas from 8982 to 9026, and
speeds up mem2reg on the testcase in PR1432 from 2.17 to 2.13s.

llvm-svn: 40813

and the alloca so they don't get reprocessed.

This speeds up PR1432 from 2.20s to 2.17s.

llvm-svn: 40812

  1. Check for revisiting a block before checking domination, which is faster.
  2. If the stored value isn't an instruction, we don't have to check for domination.
  3. If we have a value used in the same block more than once, make sure to remove the
     block from the UsingBlocks vector.  Not doing so forces us to go through the slow
     path for the alloca.

The combination of these improvements increases the number of allocas on the fastpath
from 8935 to 8982 on PR1432.  This speeds it up from 2.90s to 2.20s (31%)

llvm-svn: 40811

testcase in PR1432 from 6.33s to 2.90s (2.22x)

llvm-svn: 40810

a using block from the list if we handle it.  Not doing this caused us
to not be able to promote (with the fast path) allocas which have uses (whoops).

This increases the # allocas hitting this fastpath from 4042 to 8935 on the
testcase in PR1432, speeding up mem2reg by 2.6x

llvm-svn: 40809

llvm-svn: 40808

This is the patch to provide clean intrinsic function overloading support in LLVM. It cleans up the intrinsic definitions and generally smooths the process for more complicated intrinsic writing. It will be used by the upcoming atomic intrinsics as well as vector and float intrinsics in the future.

This also changes the syntax for llvm.bswap, llvm.part.set, llvm.part.select, and llvm.ct* intrinsics. They are automatically upgraded by both the LLVM ASM reader and the bitcode reader. The test cases have been updated, with special tests added to ensure the automatic upgrading is supported.

llvm-svn: 40807

method.

llvm-svn: 40806

llvm-svn: 40805

llvm-svn: 40804

in PR1432 by 6%

llvm-svn: 40803

llvm-svn: 40802

struct X { int A; };

void foo() {
  struct X s;
  int i;
  i = __builtin_choose_expr(0, s, i);
}

compiles to:

        %tmp = load i32* %i             ; <i32> [#uses=1]
        store i32 %tmp, i32* %i

wow :)

llvm-svn: 40801

llvm-svn: 40800

llvm-svn: 40799

llvm-svn: 40798

Darwin (which makes size within a struct==96)

llvm-svn: 40796

Chris suggested this, since it simplifies the code generator.
If this features is needed (and we don't think it is), we can revisit.

The following test case now produces an error.
[dylan:~/llvm/tools/clang] admin% cat t.c

typedef __attribute__(( ocu_vector_type(4) )) float float4;

static void test() {
    float4 vec4;

    vec4.rg.g;
    vec4.rg[1];
}
[dylan:~/llvm/tools/clang] admin% ../../Debug/bin/clang t.c
t.c:8:12: error: vector component access limited to variables
    vec4.rg.g;
           ^~
t.c:9:12: error: vector component access limited to variables
    vec4.rg[1];
           ^~~
2 diagnostics generated.

llvm-svn: 40795

Implement __builtin_choose_expr.

llvm-svn: 40794

llvm-svn: 40793

(I've tried to get the info right for all targets,
but I'm not expert on all of them - check yours.)

llvm-svn: 40792

llvm-svn: 40791

Add a test case to validate code gen for typeof/builtin_types_compatible.

This test case currently generates the following unexpected warnings (when compared with gcc).

[dylan:clang/test/Parser] admin% ../../../../Debug/bin/clang -parse-ast-check builtin_types_compatible.c
Warnings seen but not expected:
  Line 28: expression result unused
  Line 29: expression result unused
  Line 30: expression result unused
  Line 31: expression result unused
  Line 32: expression result unused
  Line 33: expression result unused

llvm-svn: 40789

llvm-svn: 40788

llvm-svn: 40787

Rename AddrLabel and OCUVectorComponent -> AddrLabelExpr and OCUVectorElementExpr respectively.  This is for consistency with other expr nodes end with *Expr.

llvm-svn: 40785

llvm-svn: 40783