RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 19:23:23 +01:00
Code Issues Projects Releases Wiki Activity
42,401 Commits 4 Branches 5 Tags 704 MiB
69b9f9f3f1
Commit Graph

42401 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Dale Johannesen
e51c5296a6 Allow SROA of vectors. Removing this caused a 
huge performance regression in something we care
about.  This may not be final fix.

llvm-svn: 58718
 2008-11-04 20:54:03 +00:00
Dale Johannesen
eee3a8a2e0 80 columns 
llvm-svn: 58717
 2008-11-04 20:52:49 +00:00
Evan Cheng
45496b349f Custom lower bit_convert i64 -> f64 into FMDRR. This is now happening with legalizetypes. 
llvm-svn: 58714
 2008-11-04 19:57:48 +00:00
Tanya Lattner
775d919c49 Add note about cmake. Patch by Oscar Fuentes. 
llvm-svn: 58712
 2008-11-04 18:40:27 +00:00
Dan Gohman
171432bfe1 Give tablegen's Type a destructor, to suppress spurious 
"Type has virtual functions but non-virtual destructor"
warnings.

llvm-svn: 58710
 2008-11-04 18:09:07 +00:00
Duncan Sands
aed2dfe3f6 Fix typo. Patch by nlewycky. 
llvm-svn: 58709
 2008-11-04 18:05:30 +00:00
Evan Cheng
d63b7563b7 Debug output tweak. 
llvm-svn: 58708
 2008-11-04 17:58:53 +00:00
Evan Cheng
088f7c51a4 LDM_RET restores pc, do not set 's' bit which would restore CPSR from SPSR. 
llvm-svn: 58707
 2008-11-04 17:57:07 +00:00
Duncan Sands
58ebf09772 Fix PR3011: LegalizeTypes support for scalarizing 
SELECT_CC.

llvm-svn: 58706
 2008-11-04 17:31:08 +00:00
Dan Gohman
50183113b9 Duncan pointed out that the Extended case in getTypeForMVT could 
be considerably simplified.

llvm-svn: 58703
 2008-11-04 16:19:44 +00:00
Dan Gohman
13237dda2d Add a return statement to suppress warnings in NDEBUG builds. 
llvm-svn: 58702
 2008-11-04 16:08:57 +00:00
Dan Gohman
2dff90b025 Add some asserts to verify MVT invariant assumptions. 
llvm-svn: 58701
 2008-11-04 16:03:56 +00:00
Nuno Lopes
b16d9bd0c3 regenerate 
llvm-svn: 58697
 2008-11-04 14:43:20 +00:00
Nuno Lopes
064bb29c9d fix leakage of APFloats in getExistingVal() 
llvm-svn: 58696
 2008-11-04 14:42:19 +00:00
Nuno Lopes
8499bc5e1d regenerate 
llvm-svn: 58694
 2008-11-04 14:28:33 +00:00
Nuno Lopes
5caf466051 fix leakage of APSInt in getVal() 
llvm-svn: 58693
 2008-11-04 14:26:58 +00:00
Nuno Lopes
0995eae6b8 fix leakage of IfcvtTokens 
llvm-svn: 58690
 2008-11-04 13:02:59 +00:00
Evan Cheng
28e234a959 For some targets, it's not possible to place GVs in the same memory buffer as the MachineCodeEmitter allocated memory. Code and data has different read / write / execution privilege requirements. 
This is a short term workaround. The current solution is for the JIT memory manager to manage code and data memory separately.

llvm-svn: 58688
 2008-11-04 09:30:48 +00:00
Nick Lewycky
1fc44bd56f Don't "shell out" to resolve paths. Using pure perl makes llvm-config 
friendlier to non-Unixes that happen to have perl. Patch from Sascha Othman!

llvm-svn: 58687
 2008-11-04 08:05:21 +00:00
Evan Cheng
7847f4f030 80 col violation. 
llvm-svn: 58684
 2008-11-04 06:10:31 +00:00
Evan Cheng
f15a9cfb31 Stylistic change. 
llvm-svn: 58683
 2008-11-04 06:10:06 +00:00
Evan Cheng
0369860450 hasDisassembler should return false if disassembler isn't available. 
llvm-svn: 58682
 2008-11-04 06:09:38 +00:00
Oscar Fuentes
582a9fcc48 CMakeLists: removed asmprinter component from 
tools/llc/CMakeLists.txt.

llvm-svn: 58678
 2008-11-04 03:28:37 +00:00
Oscar Fuentes
8e964f2e6f CMake: Support for building 32 bit mode libs and binaries on 
Linux/x86-64.

llvm-svn: 58677
 2008-11-04 03:27:24 +00:00
Oscar Fuentes
9f6d4e7fb0 CMake: Updated list of source files. 
llvm-svn: 58676
 2008-11-04 03:24:04 +00:00
Bill Wendling
0f3f36688b Initial checkin for stack protectors. Here's what it does: 
* The prologue is modified to read the __stack_chk_guard global and insert it
  onto the stack.

* The epilogue is modified to read the stored guard from the stack and compare
  it to the original __stack_chk_guard value. If they differ, then the
  __stack_chk_fail() function is called.

* The stack protector needs to be first on the stack (after the parameters) to
  catch any stack-smashing activities.

Front-end support will follow after a round of beta testing.

llvm-svn: 58673
 2008-11-04 02:10:20 +00:00
Evan Cheng
f117632c3f Handle ARM machine constantpool entries. 
llvm-svn: 58671
 2008-11-04 00:50:32 +00:00
Dan Gohman
0ba8aad1af The ANDMask node folds to a constant, and isn't the node that needs to 
have its node id set. The new and and shift nodes are the nodes that need
the IDs. This fixes PR2982.

llvm-svn: 58655
 2008-11-03 23:43:55 +00:00
Devang Patel
09aea7e93e Fix unused variable warnings. 
llvm-svn: 58653
 2008-11-03 23:20:04 +00:00
Devang Patel
40cfcf7ce2 Fix unused variable warnings. 
llvm-svn: 58651
 2008-11-03 23:14:09 +00:00
Dan Gohman
3258c45d0f Add C bindings for extractvalue and insertvalue. Patch by Frits van Bommel! 
llvm-svn: 58650
 2008-11-03 22:55:43 +00:00
Evan Cheng
999398c004 Remove a dead switch statement. 
llvm-svn: 58644
 2008-11-03 21:26:52 +00:00
Evan Cheng
b3fd30ed7c Minor code restructuring. No functionality change. 
llvm-svn: 58643
 2008-11-03 21:02:39 +00:00
Dale Johannesen
d9906b90d0 Fix some ppcf128 regressions: make ExpandFloatRes_LOAD 
work correctly, and bring over a late change to ppcf128
SetCC handling.

llvm-svn: 58642
 2008-11-03 20:47:45 +00:00
Duncan Sands
8a94be8c5b Make VAARG promotion work correctly with large funky 
sized integers like i129, and also reduce the number
of assumptions made about how vaarg is implemented.
This still doesn't work correctly for small integers
like (eg) i1 on x86, since x86 passes each of them
(essentially an i8) in a 4 byte stack slot, so the
pointer needs to be advanced by 4 bytes not by 1 byte
as now.  But this is no longer a LegalizeTypes problem
(it was also wrong in LT before): it is a bug in the
operation expansion in LegalizeDAG: now LegalizeTypes
turns an i1 vaarg into an i8 vaarg which would work
fine if only the i8 vaarg was turned into correct code
later.

llvm-svn: 58635
 2008-11-03 20:22:12 +00:00
Dan Gohman
1532a1621c Overload AddInteger on int/long/long long instead of on int/int64_t, 
to avoid overload ambiguities. This fixes build errors introduced
by r58623.

llvm-svn: 58632
 2008-11-03 19:40:18 +00:00
Devang Patel
c959b4dbd3 Ignore conditions that are outside the loop. 
llvm-svn: 58631
 2008-11-03 19:38:07 +00:00
Andrew Lenharth
97343f0e8b add a period at the end of the comment, ignoring the fact that the comment would be hard pressed to be considered a sentence, but if it makes Bill happy... 
llvm-svn: 58630
 2008-11-03 19:29:29 +00:00
Jim Grosbach
5262898365 Add binary encoding support for multiply instructions. Some blanks left to fill in, but the basics are there. 
llvm-svn: 58626
 2008-11-03 18:38:31 +00:00
Devang Patel
78b7de25d1 Turn floating point IVs into integer IVs where possible. 
This allows SCEV users to effectively calculate trip count.
LSR later on transforms back integer IVs to floating point IVs
later on to avoid int-to-float casts inside the loop.

llvm-svn: 58625
 2008-11-03 18:32:19 +00:00
Dan Gohman
155df8a79e Refactor various TargetAsmInfo subclasses' TargetMachine members away 
adding a TargetMachine member to the base TargetAsmInfo class instead.

llvm-svn: 58624
 2008-11-03 18:22:42 +00:00
Dan Gohman
edf3dc97c2 Change how extended types are represented in MVTs. Instead of fiddling 
bits, use a union of a SimpleValueType enum and a regular Type*.

This increases the size of MVT on 64-bit hosts from 32 bits to 64 bits.
In most cases, this doesn't add significant overhead. There are places
in codegen that use arrays of MVTs, so these are now larger, but
they're small in common cases.

This eliminates restrictions on the size of integer types and vector
types that can be represented in codegen. As the included testcase
demonstrates, it's now possible to codegen very large add operations.
There are still some complications with using very large types. PR2880
is still open so they can't be used as return values on normal targets,
there are no libcalls defined for very large integers so operations
like multiply and divide aren't supported.

This also introduces a minimal tablgen Type library, capable of
handling IntegerType and VectorType. This will allow parts of
TableGen that don't depend on using SimpleValueType values to handle
arbitrary integer and vector types.

llvm-svn: 58623
 2008-11-03 17:56:27 +00:00
Daniel Dunbar
cd663da6ec Comment fix. 
llvm-svn: 58621
 2008-11-03 17:33:36 +00:00
Dan Gohman
2c6be1710e Remove redundant inline keywords from functions defined within 
class definitions.

llvm-svn: 58620
 2008-11-03 17:10:24 +00:00
Andrew Lenharth
312c00cdd4 Ensure that we are checking only calls to the function we are interested in specializing 
llvm-svn: 58615
 2008-11-03 16:05:35 +00:00
Anton Korobeynikov
4b194f9aac Testcase for recent llvm-gcc fix 
llvm-svn: 58611
 2008-11-03 14:43:31 +00:00
Duncan Sands
a9047944bc Make VAARG work with x86 long double (which is 
10 bytes long, but is passed in 12/16 bytes).

llvm-svn: 58608
 2008-11-03 11:51:11 +00:00
Matthijs Kooijman
a91b759ccf Make MachineFrameInfo::print not crash when no TargetFrameInfo is available. 
llvm-svn: 58606
 2008-11-03 11:16:43 +00:00
Evan Cheng
45516a94c1 Silence a compiler warning. 
llvm-svn: 58598
 2008-11-03 07:14:02 +00:00
Nick Lewycky
3315ae6e08 Typo 
llvm-svn: 58594
 2008-11-03 03:50:40 +00:00