Commit Graph

38667 Commits

Author SHA1 Message Date
Anders Carlsson d0113e4be3 Revert change that broke the build.
llvm-svn: 44808
2007-12-10 19:46:20 +00:00
Chris Lattner e665077f9a disable case that makes this fail.
llvm-svn: 44807
2007-12-10 19:44:50 +00:00
Anders Carlsson b9eb82c3ee Add EmitShuffleVector helper method.
llvm-svn: 44806
2007-12-10 19:35:18 +00:00
Chuck Rose III 900a13e82c Add StringPool + new CodeGen files to win32 build
llvm-svn: 44805
2007-12-10 19:31:09 +00:00
Anders Carlsson dc16e8f299 Address comments from Chris.
llvm-svn: 44804
2007-12-10 19:30:18 +00:00
Chris Lattner 8a72a7d586 Disable cfi directives for now, darwin does't support them.
These should probably be something like:

  CFI(".cfi_def_cfa_offset 16\n")

where CFI is defined to a noop on darwin and other platforms
that don't support those directives.

llvm-svn: 44803
2007-12-10 19:10:18 +00:00
Duncan Sands 9f76be61d1 Make PruneEH update the nounwind/noreturn attributes
on functions as it calculates them.

llvm-svn: 44802
2007-12-10 19:09:40 +00:00
Chris Lattner 456078d50d minor edits.
llvm-svn: 44801
2007-12-10 18:56:37 +00:00
Devang Patel b3ae8d7dc2 Add assert to flag incomplete bit-field support.
llvm-svn: 44800
2007-12-10 18:52:06 +00:00
Devang Patel 3c31b54b47 Use getABITypeSizeInBits() instead of getTypeSizeInBits() during struct layout.
llvm-svn: 44799
2007-12-10 18:37:40 +00:00
Devang Patel bb5c0d8960 Use getABITypeSizeInBits() instead of getTypeSizeInBits() during struct layout.
llvm-svn: 44798
2007-12-10 18:25:34 +00:00
Ted Kremenek 256a15d532 Added newline to end of file.
llvm-svn: 44797
2007-12-10 18:01:25 +00:00
Duncan Sands 5c65cb4633 Fix PR1836: in the interpreter, read and write apints
using the minimum possible number of bytes.  For little
endian targets run on little endian machines, apints are
stored in memory from LSB to MSB as before.  For big endian
targets on big endian machines they are stored from MSB to
LSB which wasn't always the case before (if the target and
host endianness doesn't match values are stored according
to the host's endianness).  Doing this requires knowing the
endianness of the host, which is determined when configuring -
thanks go to Anton for this.  Only having access to little
endian machines I was unable to properly test the big endian
part, which is also the most complicated...

llvm-svn: 44796
2007-12-10 17:43:13 +00:00
Chris Lattner 80c54698e8 be more clear about what we are comparing.
llvm-svn: 44795
2007-12-10 17:38:50 +00:00
Anton Korobeynikov 657be86229 And finally annotate X86-64 version of callback.
All bad stuff from SSE version is implicitely inherited :)

llvm-svn: 44794
2007-12-10 15:27:07 +00:00
Anton Korobeynikov 88e9d082d8 Provide annotation for SSE version of callback. It's even more
broken, because doesn't mark xmm regs properly

llvm-svn: 44793
2007-12-10 15:13:55 +00:00
Anton Korobeynikov 81e9dc4af7 Annotate JIT callback function with call frame infromation.
This will allow us (theoretically) to unwind through JITer.
The code wasn't verified, so I'm pretty sure offsets are wrong :)

llvm-svn: 44792
2007-12-10 14:54:42 +00:00
Duncan Sands 81b25817f9 It looks like this has been broken for some time -
get it to compile.

llvm-svn: 44791
2007-12-10 14:43:10 +00:00
Anders Carlsson 1b9853a9f8 Forgot this file.
llvm-svn: 44790
2007-12-10 08:48:18 +00:00
Chris Lattner c3307e2418 fixes, thanks to Nico Weber
llvm-svn: 44789
2007-12-10 08:21:12 +00:00
Chris Lattner 428760a6e6 clean up the TOC.
llvm-svn: 44788
2007-12-10 08:19:29 +00:00
Chris Lattner e396aaae28 finish the features description.
llvm-svn: 44787
2007-12-10 08:12:49 +00:00
Owen Anderson ba61806ef1 A little more progress on StrongPHIElimination, now that I have a better sense of
how the CodeGen machinery works.

llvm-svn: 44786
2007-12-10 08:07:09 +00:00
Christopher Lamb d202e03fe5 Improve branch folding by recgonizing that explict successor relationships impact the value of fall-through choices.
llvm-svn: 44785
2007-12-10 07:24:06 +00:00
Chris Lattner b6a8cfea24 now with hackability.
llvm-svn: 44784
2007-12-10 07:23:52 +00:00
Chris Lattner aa085d36e2 reorganize features, expound on a couple more.
llvm-svn: 44783
2007-12-10 07:14:08 +00:00
Chris Lattner e404df76c0 incorporate suggestions from Joel Nelson.
llvm-svn: 44782
2007-12-10 06:01:32 +00:00
Chris Lattner f572f3364d start making features be a more detailed description of the features/goals section on the main page.
llvm-svn: 44781
2007-12-10 05:52:05 +00:00
Chris Lattner 27a2709cfb add toc
llvm-svn: 44780
2007-12-10 05:23:01 +00:00
Chris Lattner b072569682 don't duplicate goals on the features page.
llvm-svn: 44779
2007-12-10 05:20:47 +00:00
Chris Lattner ab44e15ce7 update status
llvm-svn: 44778
2007-12-10 05:11:40 +00:00
Chris Lattner fdfd014270 edits, switch the goals/why section.
llvm-svn: 44777
2007-12-10 05:10:14 +00:00
Chris Lattner 5a7359c8c2 minor edits
llvm-svn: 44776
2007-12-10 05:06:15 +00:00
Gordon Henriksen 4b904b9627 Delete the CollectorNamePool if it should become empty.
llvm-svn: 44775
2007-12-10 03:35:18 +00:00
Gordon Henriksen dc5cafb74e Fix a typo spotted by Nick Lewycky.
llvm-svn: 44774
2007-12-10 03:30:21 +00:00
Gordon Henriksen 71183b6739 Adding a collector name attribute to Function in the IR. These
methods are new to Function:

  bool hasCollector() const;
  const std::string &getCollector() const;
  void setCollector(const std::string &);
  void clearCollector();

The assembly representation is as such:

  define void @f() gc "shadow-stack" { ...

The implementation uses an on-the-side table to map Functions to 
collector names, such that there is no overhead. A StringPool is 
further used to unique collector names, which are extremely
likely to be unique per process.

llvm-svn: 44769
2007-12-10 03:18:06 +00:00
Chris Lattner e31cd5b564 add link to comparison page.
llvm-svn: 44763
2007-12-10 02:25:51 +00:00
Chris Lattner 609f9ccb2c Be more positive! Add to sidebar.
llvm-svn: 44762
2007-12-10 02:24:44 +00:00
Chris Lattner 10ebf4dcb1 updates.
llvm-svn: 44761
2007-12-10 02:18:15 +00:00
Gordon Henriksen 14a5569f4e Reverting dtor devirtualization patch.
_sabre_: it has a major problem: by the time ~Value is run, all of the "parts" of the derived classes have been destroyed
_sabre_: the vtable lives to fight another day

llvm-svn: 44760
2007-12-10 02:14:30 +00:00
Chris Lattner 3fbe73bef2 minor edits
llvm-svn: 44759
2007-12-10 02:05:32 +00:00
Chris Lattner cf7cb4bbdd make more positive.
llvm-svn: 44758
2007-12-10 01:52:24 +00:00
Chris Lattner 12f9855a42 remove some dead code.
llvm-svn: 44757
2007-12-10 01:51:38 +00:00
Chris Lattner 13daba07d9 fix some warnings.
llvm-svn: 44756
2007-12-10 01:51:22 +00:00
Chris Lattner d05f4ba524 Fix a big problem in the recent dtor refactoring work, now it passes 2007-11-19-InlineAsm.ll
llvm-svn: 44755
2007-12-10 01:48:29 +00:00
Chris Lattner 78eeea2ce9 Add a "comparing clang to other compilers" page, to help resolve some FAQ's.
llvm-svn: 44754
2007-12-10 01:44:24 +00:00
Chris Lattner 7f0ad21480 lots of this is done.
llvm-svn: 44753
2007-12-10 00:14:49 +00:00
Chris Lattner cb04ac9599 abort when we lower an initializer to the wrong type, as we currently do for:
char text[] = "string";

llvm-svn: 44752
2007-12-10 00:05:55 +00:00
Chris Lattner 686628e052 extend or truncate the initializer for a string initializer to match its type.
llvm-svn: 44751
2007-12-10 00:00:56 +00:00
Chris Lattner c25c42f3ca Implement codegen support for:
char text[8] = "string";

Big fixme remains.

llvm-svn: 44750
2007-12-09 23:49:42 +00:00