maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
49,594 Commits 23 Branches 0 Tags 2.2 GiB
Commit Graph

42261 Commits

Author SHA1 Message Date
Evan Cheng 972fd1a1e0 Improve JIT debugging outputs format consistency. 
llvm-svn: 58807
 2008-11-06 17:46:04 +00:00
Nuno Lopes 2817338558 plug leakage of mutex data. pthread_mutex_destroy() doesnt free our malloc'ed memory. 
llvm-svn: 58805
 2008-11-06 16:21:49 +00:00
Duncan Sands f178f8300d Formating/comment changes - no functionality change. 
llvm-svn: 58801
 2008-11-06 08:51:32 +00:00
Evan Cheng 47b546d75f Remove opcode from instruction TS flags; add MOVCC support; fix addrmode3 encoding bug. 
llvm-svn: 58800
 2008-11-06 08:47:38 +00:00
Bill Wendling b3f7a39877 - Rename stackprotector_{prologue,epilogue} to stackprotector_{create,check}. 
- Get rid of "HasStackProtector" in MachineFrameInfo.
- Modify intrinsics to tell which are doing what with memory.

llvm-svn: 58799
 2008-11-06 07:23:03 +00:00
Steve Naroff ef625263ef Update VC++ projects. 
llvm-svn: 58798
 2008-11-06 06:24:59 +00:00
Mon P Wang 9a8d60a7c0 Widening cleanup 
llvm-svn: 58796
 2008-11-06 05:31:54 +00:00
Evan Cheng 36ae40342f Handle smul<x><y>, smulw<y>, smla<x><y>, smlaw<y>. 
llvm-svn: 58793
 2008-11-06 03:35:07 +00:00
Bill Wendling 43de293d75 Adjust the stack protector heuristic to care about only arrays or calls to 
"alloca".

llvm-svn: 58792
 2008-11-06 02:38:58 +00:00
Bill Wendling d970ea3eac Implement the stack protector stack accesses via intrinsics: 
- stackprotector_prologue creates a stack object and stores the guard there.

- stackprotector_epilogue reads the stack guard from the stack position created
  by stackprotector_prologue.

- The PrologEpilogInserter was changed to make sure that the stack guard is
  first on the stack frame.

llvm-svn: 58791
 2008-11-06 02:29:10 +00:00
Evan Cheng b870fd8874 Fix so_imm encoding bug; add support for MOVi2pieces. 
llvm-svn: 58790
 2008-11-06 02:25:39 +00:00
Evan Cheng 2686c8fb34 Fix encoding of multiple instructions with 3 src operands; also handle smmul, smmla, and smmls. 
llvm-svn: 58789
 2008-11-06 01:21:28 +00:00
Evan Cheng 3aeeb3a47c Need a \n. 
llvm-svn: 58788
 2008-11-06 01:18:29 +00:00
Devang Patel 5a5ab730e0 InstructionNamer preserves everything. 
llvm-svn: 58787
 2008-11-06 01:00:16 +00:00
Devang Patel 9e3e776e28 Emit label for llvm.dbg.func.start of the inlined function. 
llvm-svn: 58786
 2008-11-06 00:30:09 +00:00
Steve Naroff 0b0c99610c Add post-build event for clangDriver (to copy clang.exe into "dstroot"). 
llvm-svn: 58783
 2008-11-06 00:11:31 +00:00
Evan Cheng d1c5c7f499 Undo 58778 but makes the binary dump prettier. 
llvm-svn: 58782
 2008-11-05 23:44:08 +00:00
Bill Wendling f5f6f74c16 Add comments to function. 
llvm-svn: 58781
 2008-11-05 23:42:27 +00:00
Evan Cheng fd2adbfa28 Encode pic load / store instructions; fix some encoding bugs. 
llvm-svn: 58780
 2008-11-05 23:22:34 +00:00
Evan Cheng 6158254d1d Add command line option -entry-funcion to override entry function (default is main). 
llvm-svn: 58779
 2008-11-05 23:21:52 +00:00
Evan Cheng 51b9b9f6e2 Remove debug output that's not really useful. 
llvm-svn: 58778
 2008-11-05 23:21:11 +00:00
Dan Gohman 3777ed765f Make ISel ignore dead nodes. The DAGCombiner normally eliminates 
dead nodes, but in this case its missing one. Fixing the DAGCombiner
is desirable, but it's somewhat involved.

llvm-svn: 58777
 2008-11-05 22:56:47 +00:00
Andrew Lenharth 912e7131a4 opt was not exporting the Mangler symbols 
llvm-svn: 58775
 2008-11-05 22:42:50 +00:00
Devang Patel f53d7ff870 Add PR number. 
llvm-svn: 58765
 2008-11-05 18:41:15 +00:00
Evan Cheng 81889d010c Restructure ARM code emitter to use instruction formats instead of addressing modes to determine how to encode instructions. 
llvm-svn: 58764
 2008-11-05 18:35:52 +00:00
Dan Gohman ce2417f4e1 Use an assert to check that SelectCode isn't called on 
nodes that are already selected.

llvm-svn: 58763
 2008-11-05 18:30:52 +00:00
Dan Gohman 87002dbea1 The HadDelete field is no longer used. 
llvm-svn: 58761
 2008-11-05 17:35:14 +00:00
Dan Gohman 7a638a8c7e Reintroduce a comment that was removed with the AddToISelQueue 
changes.

llvm-svn: 58760
 2008-11-05 17:16:24 +00:00
Dan Gohman 22079067e1 Update some comments to reflect the new code. 
llvm-svn: 58759
 2008-11-05 17:13:57 +00:00
Richard Osborne bfd58d87f3 Test commit, add Makefile for XCore target, more to follow. 
llvm-svn: 58755
 2008-11-05 09:53:58 +00:00
Duncan Sands 68035d4076 Fix thinko in ppcf128 expansion of truncating store. 
llvm-svn: 58753
 2008-11-05 07:17:27 +00:00
Evan Cheng 27889ab29f Add more vector move low and zero-extend patterns. 
llvm-svn: 58752
 2008-11-05 06:04:51 +00:00
Evan Cheng c7b04a12bb Type of shuffle mask has changed. 
llvm-svn: 58751
 2008-11-05 06:04:18 +00:00
Evan Cheng 3cd5e8c97b Indentation. 
llvm-svn: 58750
 2008-11-05 06:03:38 +00:00
Dan Gohman f14b77ebf1 Eliminate the ISel priority queue, which used the topological order for a 
priority function. Instead, just iterate over the AllNodes list, which is
already in topological order. This eliminates a fair amount of bookkeeping,
and speeds up the isel phase by about 15% on many testcases.

The impact on most targets is that AddToISelQueue calls can be simply removed.

In the x86 target, there are two additional notable changes.

The rule-bending AND+SHIFT optimization in MatchAddress that creates new
pre-isel nodes during isel is now a little more verbose, but more robust.
Instead of either creating an invalid DAG or creating an invalid topological
sort, as it has historically done, it can now just insert the new nodes into
the node list at a position where they will be consistent with the topological
ordering.

Also, the address-matching code has logic that checked to see if a node was
"already selected". However, when a node is selected, it has all its uses
taken away via ReplaceAllUsesWith or equivalent, so it won't recieve any
further visits from MatchAddress. This code is now removed.

llvm-svn: 58748
 2008-11-05 04:14:16 +00:00
Dan Gohman fd820528ab Use getTargetConstant instead of getConstant for nodes that should not be visited 
by isel and potentially forced into registers.

llvm-svn: 58747
 2008-11-05 02:06:09 +00:00
Evan Cheng 132de1983f Rename isGVLazyPtr to isGVNonLazyPtr relocation. This represents Mac OS X 
indirect gv reference. Please don't call it lazy.

llvm-svn: 58746
 2008-11-05 01:50:32 +00:00
Devang Patel f04bfc6989 New test case. 
llvm-svn: 58745
 2008-11-05 01:40:30 +00:00
Devang Patel f0ef35738c Do now allow InlineAlways pass to remove dead functions. 
llvm-svn: 58744
 2008-11-05 01:39:16 +00:00
Devang Patel e94321305f Silence unused variable warnings. 
llvm-svn: 58743
 2008-11-05 01:37:40 +00:00
Devang Patel 7a848b0ee3 Check Attribute::NoInline. 
llvm-svn: 58742
 2008-11-05 01:37:05 +00:00
Bill Wendling db045a3048 Remove dead variable. 
llvm-svn: 58741
 2008-11-05 00:56:35 +00:00
Bill Wendling f1b4e2626b Simplify the allocated size calculation. 
llvm-svn: 58740
 2008-11-05 00:54:27 +00:00
Bill Wendling 75e38fedc8 Fix comment 
llvm-svn: 58739
 2008-11-05 00:46:15 +00:00
Owen Anderson 26c10f1b4a Use the new predicate to control when we do prealloc splitting. Fix a small bug. 
llvm-svn: 58738
 2008-11-05 00:32:13 +00:00
Evan Cheng 33ba5e78d2 Debugging output tweak. 
llvm-svn: 58737
 2008-11-05 00:22:28 +00:00
Oscar Fuentes 076e048cf7 CMake: updated list of source files. 
llvm-svn: 58736
 2008-11-05 00:11:22 +00:00
Bill Wendling 782e8346a5 Some code simplification. It now doesn't generate a prologue if the epilogue 
isn't going to be generated.

llvm-svn: 58734
 2008-11-05 00:00:21 +00:00
Dan Gohman 8cdea717a3 Add a new pass to simplify specific half_powr function calls. This is 
a specialized pass that it not likely to be generally useful.

llvm-svn: 58732
 2008-11-04 23:41:45 +00:00
Devang Patel db9d785338 On darwin, 32-bit x86 target is i386-apple-darwin... 
llvm-svn: 58731
 2008-11-04 23:13:50 +00:00