Commit Graph

193475 Commits

Author SHA1 Message Date
Andrea Di Biagio b14ae8692d [CodeGenPrepare] Removed duplicate logic. SimplifyCFG already knows how to speculate calls to cttz/ctlz.
SimplifyCFG now knows how to speculate calls to intrinsic cttz/ctlz that are
'cheap' for the target. Therefore, some of the logic in CodeGenPrepare
that was originally added at revision 224899 can now be removed.

This patch is basically a no functional change. It removes the duplicated
logic in CodeGenPrepare and converts all the existing target specific tests
for cttz/ctlz into SimplifyCFG tests.

Differential Revision: http://reviews.llvm.org/D7608

llvm-svn: 229105
2015-02-13 14:15:48 +00:00
Tamas Berghammer f5f2ace211 Fix configure+make build broken by r228943 (part 2)
llvm-svn: 229104
2015-02-13 12:27:24 +00:00
Arnaud A. de Grandmaison a7c90d8487 [PBQP] Conservativelly allocatable nodes can be spilled and give a better solution
Although such nodes are allocatable, the cost of spilling may be less than
allocating to register, so spilling the node may provide a better solution.
The assert does not account for this case, so remove it for now.

llvm-svn: 229103
2015-02-13 12:04:42 +00:00
Hafiz Abid Qadeer 095b128671 Fix for http://llvm.org/bugs/show_bug.cgi?id=21744
GetVariableInfo () collected the values of the variable in a list. But it also
tried to generate the name/value pairs for children. This caused generation of
a wrong value string for may items. This function has been fixed to put value in
the list only.

The handling of --print-value related option has been moved to caller.

GetVariableInfo2 and MIResponseFormVariableInfo3 have been removed. They were
almost the duplicate of functions of similar names. I dont see any difference in
the output of -stack-list-locals and -stack-list-arguments. So these functions
just seemed unnecessary.

Char variable was being printed as a string which caused garbage output. This has
been fixed.

Some misc. cleanup.

Test cases have been added that check -stack-list-locals for struct, array and
pointers. Modified other tests which depended on hard coded line numbers.

Reviewed in http://reviews.llvm.org/D7589

llvm-svn: 229102
2015-02-13 11:53:50 +00:00
James Molloy 5eb75aced4 [SimplifyCFG] Add test for r229099
Add extra test that was accidentally not staged.

llvm-svn: 229101
2015-02-13 11:08:40 +00:00
Ilia K c9a475d447 Fix build after r229094: replace llvm/PassManager.h -> llvm/IR/LegacyPassManager.h
llvm-svn: 229100
2015-02-13 10:49:18 +00:00
James Molloy 1b6207e6eb [SimplifyCFG] Be more aggressive
Up the phi node folding threshold from a cheap "1" to a meagre "2".

Update tests for extra added selects and slight code churn.

llvm-svn: 229099
2015-02-13 10:48:30 +00:00
Tamas Berghammer e3c3135463 Fix configure+make build broken by r228943
llvm-svn: 229098
2015-02-13 10:39:23 +00:00
Toma Tabacu 16a74499af [mips] Improve support for the .set at/noat assembler directives.
Summary:
Made the following changes:
  Added calls to emitDirectiveSetNoAt() and emitDirectiveSetAt().
  Added special emit function for .set at=$reg, emitDirectiveSetAtWithArg(unsigned RegNo).
  Improved parsing error checks for .set at.
  Refactored parser code for .set at.
  Improved testing of both directives.
  Improved code readability and comments.

Reviewers: dsanders

Reviewed By: dsanders

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D7176

llvm-svn: 229097
2015-02-13 10:30:57 +00:00
Chandler Carruth 80b5f793e1 Disable a warning for the python modules as the python C API headers
trigger this warning. With this, 'ninja' succeeds without warnings for
me on Linux.

llvm-svn: 229096
2015-02-13 10:22:00 +00:00
Chandler Carruth 7ecd99163c [PM] Update the examples to reflect the removal of the
llvm/PassManager.h wrapper header and its using declarations. These now
directly use the legacy namespace.

I had updated the #include lines in my large commit but forgot that the
examples weren't being built and didn't update the code to use the
correct namespace. Sorry for the noise here.

llvm-svn: 229095
2015-02-13 10:21:05 +00:00
Chandler Carruth 30d69c2e36 [PM] Remove the old 'PassManager.h' header file at the top level of
LLVM's include tree and the use of using declarations to hide the
'legacy' namespace for the old pass manager.

This undoes the primary modules-hostile change I made to keep
out-of-tree targets building. I sent an email inquiring about whether
this would be reasonable to do at this phase and people seemed fine with
it, so making it a reality. This should allow us to start bootstrapping
with modules to a certain extent along with making it easier to mix and
match headers in general.

The updates to any code for users of LLVM are very mechanical. Switch
from including "llvm/PassManager.h" to "llvm/IR/LegacyPassManager.h".
Qualify the types which now produce compile errors with "legacy::". The
most common ones are "PassManager", "PassManagerBase", and
"FunctionPassManager".

llvm-svn: 229094
2015-02-13 10:01:29 +00:00
Chandler Carruth 24f59101b6 Remove a stray blank line that my sort_include.py script found.
llvm-svn: 229093
2015-02-13 09:57:05 +00:00
Chandler Carruth 9828e69a3f [PM] Fix #include order here that I forgot to update before changing it.
llvm-svn: 229092
2015-02-13 09:57:03 +00:00
Chandler Carruth d01918fa13 [PM] Convert Polly over to directly use the legacy pass manager
namespace and header rather than the top-level header and using
declarations. These helpers impede modular builds and are going away.
Migrating away from them will also be necessary to start mixing in any
usage of the new pass manager.

llvm-svn: 229091
2015-02-13 09:51:50 +00:00
Chandler Carruth 8f4f5090b4 [PM] Move away from the old llvm/PassManager.h header and its using
declarations and just use the legacy namespace qualifier in this file
and the permanent header name.

The old wrapper header is going away to make LLVM's build more modular,
and without updating Clang I can't easily start to add usage of the new
pass manager to Clang. This should make it more clear in the code which
set of types is doing what.

llvm-svn: 229090
2015-02-13 09:47:49 +00:00
Chandler Carruth 1f832f7c27 Re-sort the #include lines in bindings and examples which I managed to
miss previously.

llvm-svn: 229089
2015-02-13 09:14:30 +00:00
Chandler Carruth 71f308adb7 Re-sort #include lines using my handy dandy ./utils/sort_includes.py
script. This is in preparation for changes to lots of include lines.

llvm-svn: 229088
2015-02-13 09:09:03 +00:00
Chandler Carruth f766278204 Re-sort includes using the LLVM utils/sort_includes.py script.
llvm-svn: 229087
2015-02-13 09:07:58 +00:00
Chandler Carruth d066d3a7b4 Fix the last two warnings I see on Linx building 'lldb': mismatched
signed and unsigned types in comparisons.

For the text offset, use the addr_t type that is used elsewhere to get
these kinds of offsets, and which it is being compared against. This
seems to make things more consistent.

For the other, the numbers are clearly small and uninteresting, so just
cast them to the most boring 'int' type.

llvm-svn: 229085
2015-02-13 08:16:15 +00:00
Chandler Carruth 40927d0dcd Fix four missing 'override' specifiers found with the Clang
'-Winconsistent-missing-override' warning. I suggest folks use this to
ensure that override is consistently used to mark virtual function
overrides.

llvm-svn: 229084
2015-02-13 08:07:00 +00:00
Chandler Carruth f7888ab386 Remove an unused variable found with a Clang warning.
llvm-svn: 229083
2015-02-13 08:04:18 +00:00
David Majnemer abc482effc MS ABI: Implement /volatile:ms
The /volatile:ms semantics turn volatile loads and stores into atomic
acquire and release operations.  This distinction is important because
volatile memory operations do not form a happens-before relationship
with non-atomic memory.  This means that a volatile store is not
sufficient for implementing a mutex unlock routine.

Differential Revision: http://reviews.llvm.org/D7580

llvm-svn: 229082
2015-02-13 07:55:47 +00:00
Zachary Turner 2a903b900d Fix the windows build *again*. Grrr, MSVC.
llvm-svn: 229081
2015-02-13 07:55:29 +00:00
Chandler Carruth d99f427e31 Revert a series of commits starting at r228886 which is triggering some
regressions for LLDB on Linux. Rafael indicated on lldb-dev that we
should just go ahead and revert these but that he wasn't at a computer.
The patches backed out are as follows:

r228980: Add support for having multiple sections with the name and ...
r228889: Invert the section relocation map.
r228888: Use the existing SymbolTableIndex intsead of doing a lookup.
r228886: Create the Section -> Rel Section map when it is first needed.

These patches look pretty nice to me, so hoping its not too hard to get
them re-instated. =D

llvm-svn: 229080
2015-02-13 07:52:39 +00:00
Zachary Turner 191b57478e Fix non-windows builds unhappy about a missing header.
llvm-svn: 229079
2015-02-13 07:45:49 +00:00
Craig Topper 916708f152 [X86] Add support for parsing and printing the mnemonic aliases for the XOP VPCOM instructions.
llvm-svn: 229078
2015-02-13 07:42:25 +00:00
Craig Topper e32546dd29 [X86] Fix XOP vpcom intrinsic autoupgrade to map 'true' and 'false' to the correct immediates. Seems they were swapped.
llvm-svn: 229077
2015-02-13 07:42:15 +00:00
Zachary Turner a952c49c20 llvm-pdbdump: Add more comprehensive dumping of symbol types.
In particular this patch adds the ability to dump complete
function signature information including argument types as
correctly formatted strings.  A side effect of this is that
almost all symbol and meta types are now formatted.

llvm-svn: 229076
2015-02-13 07:40:03 +00:00
Mehdi Amini 383d7ae0bd InstCombine: cleanup redundant dyn_cast<> (NFC)
From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 229075
2015-02-13 07:38:04 +00:00
Ed Schouten 12dc2c4f3b Don't use bzero() and strcpy().
Instead of bzero(), we can simply use memset(). The strcpy() calls are
unneeded, as we can simply keep track of a pointer to the constant
strings we are copying.

Reviewed by:	Jonathan Roelofs

llvm-svn: 229074
2015-02-13 07:18:22 +00:00
Craig Topper 4fb4581716 [X86] Fix test cases that I foolishly copied and modified from another file that had optimizations on. This caused the check patterns to not quite match.
llvm-svn: 229073
2015-02-13 06:27:39 +00:00
Will Newton 6b3f59b6a9 ELF/AArch64: Add support for checking for ABS32 overflow
Add support for checking overflow when applying a R_AARCH64_ABS32
relocation and add a test to ensure it behaves correctly.

llvm-svn: 229072
2015-02-13 06:22:31 +00:00
Craig Topper 007a713ebf Fix a typo in a comment. NFC
llvm-svn: 229071
2015-02-13 06:07:29 +00:00
Craig Topper d1e1bf5d78 Fix probable typo in test.
llvm-svn: 229070
2015-02-13 06:07:27 +00:00
Craig Topper 4e0700f365 [X86] Remove int_x86_sse2_psll_dq_bs and int_x86_sse2_psrl_dq_bs intrinsics. The builtins aren't used by clang.
llvm-svn: 229069
2015-02-13 06:07:24 +00:00
Craig Topper 65e2cb5676 [X86] Remove references to builtin names that have been removed from clang. Hope to remove the intrinsics themselves soon.
llvm-svn: 229068
2015-02-13 06:07:14 +00:00
Craig Topper 8dd7d0d9c1 [X86] Add range checking on immediate arguments on XOP vpcom builtins.
llvm-svn: 229067
2015-02-13 06:04:48 +00:00
Craig Topper a462482d98 [X86] Add _mm_bslli_si128 and _mm_bsrli_si128 as aliases of _mm_slli_si128 and _mm_srli_si128. This matches Intel documentation and gcc.
llvm-svn: 229066
2015-02-13 06:04:45 +00:00
Craig Topper 51e47418d4 [X86] Simplify some code and remove some -Wshadow disables from intrinsic header.
llvm-svn: 229065
2015-02-13 06:04:43 +00:00
Chandler Carruth 1fbc316534 [unroll] Concede defeat and disable the unroll analyzer for now.
The issues with the new unroll analyzer are more fundamental than code
cleanup, algorithm, or data structure changes. I've sent an email to the
original commit thread with details and a proposal for how to redesign
things. I'm disabling this for now so that we don't spend time
debugging issues with it in its current state.

llvm-svn: 229064
2015-02-13 05:31:46 +00:00
Michael Liao d266b928ae [InstCombine] Fix a bug when combining `icmp` from `ptrtoint`
- First, there's a crash when we try to combine that pointers into `icmp`
  directly by creating a `bitcast`, which is invalid if that two pointers are
  from different address spaces.

- It's not always appropriate to cast one pointer to another if they are from
  different address spaces as that is not no-op cast. Instead, we only combine
  `icmp` from `ptrtoint` if that two pointers are of the same address space.

llvm-svn: 229063
2015-02-13 04:51:26 +00:00
Chandler Carruth 6c03dff7cc [unroll] Merge the simplification and DCE estimation methods on the
UnrollAnalyzer.

Now they share a single worklist and have less implicit state between
them. There was no real benefit to separating these two things out.

I'm going to subsequently refactor things to share even more code.

llvm-svn: 229062
2015-02-13 04:39:05 +00:00
Chandler Carruth d9591d8922 [unroll] Remove pointless dyn_cast<>s to Instruction - the users of an
instruction must by definition be instructions.

llvm-svn: 229061
2015-02-13 04:33:21 +00:00
Chandler Carruth 5457e20d27 [unroll] Don't check the loop set for whether an instruction is
contained in it each time we try to add it to the worklist, just check
this when pulling it off the worklist. That way we do it at most once
per instruction with the cost of the worklist set we would need to pay
anyways.

llvm-svn: 229060
2015-02-13 04:30:44 +00:00
Chandler Carruth e5c30e4e10 [unroll] Change the other worklist in the unroll analyzer to be a set
vector.

In addition to dramatically reducing the work required for contrived
example loops, this also has to correct some serious latent bugs in the
cost computation. Previously, we might add an instruction onto the
worklist once for every load which it used and was simplified. Then we
would visit it many times and accumulate "savings" each time.

I mean, fortunately this couldn't matter for things like calls with 100s
of operands, but even for binary operators this code seems like it must
be double counting the savings.

I just noticed this by inspection and due to the runtime problems it can
introduce, I don't have any test cases for cases where the cost produced
by this routine is unacceptable.

llvm-svn: 229059
2015-02-13 04:27:50 +00:00
Chandler Carruth 7824bc9241 [unroll] Replace a boolean, for loop, condition, and break with
std::all_of and a lambda. Much cleaner, no functionality
changed.

llvm-svn: 229058
2015-02-13 04:18:14 +00:00
Chandler Carruth 06d537cdd6 [unroll] Directly query for dead instructions.
In the unroll analyzer, it is checking each user to see if that user
will become dead. However, it first checked if that user was missing
from the simplified values map, and then if was also missing from the
dead instructions set. We add everything from the simplified values map
to the dead instructions set, so the first step is completely subsumed
by the second. Moreover, the first step requires *inserting* something
into the simplified value map which isn't what we want at all.

This also replaces a dyn_cast with a cast as an instruction cannot be
used by a non-instruction.

llvm-svn: 229057
2015-02-13 04:14:05 +00:00
Chandler Carruth 82cb30f10c [unroll] Replace a linear time check for no uses with a constant time
check.

Also hoist this into the enqueue process as it is faster even than
testing the worklist set, we should just directly filter these out much
like we filter out constants and such.

llvm-svn: 229056
2015-02-13 04:06:08 +00:00
Rui Ueyama d9cb620330 Remove unused parameters.
llvm-svn: 229055
2015-02-13 04:02:55 +00:00