RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 11:42:57 +01:00
Code Issues Projects Releases Wiki Activity
40,871 Commits 4 Branches 5 Tags 704 MiB
8f4d612996
Commit Graph

40871 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Owen Anderson
821ddf6726 Use a combination of copyRegToReg and ISD::BIT_CONVERT when doing fast isel of bitcasts, 
allowing it to support the full range of conversions people might ask for in a correct manner.

llvm-svn: 55378
 2008-08-26 18:51:24 +00:00
Owen Anderson
fc7b8f3073 These assertions should be return false's instead, allowing the client to detect the failure. 
llvm-svn: 55377
 2008-08-26 18:50:40 +00:00
Owen Anderson
9e2381b77d We need to check that the return type is correct, even in cases where we don't 
have a return type that differs from the operand types.

llvm-svn: 55376
 2008-08-26 18:50:00 +00:00
Owen Anderson
5fef19facf Make TargetInstrInfo::copyRegToReg return a bool indicating whether the copy requested 
was inserted or not.  This allows bitcast in fast isel to properly handle the case
where an appropriate reg-to-reg copy is not available.

llvm-svn: 55375
 2008-08-26 18:03:31 +00:00
Devang Patel
211c05f7a3 If IV is used in a int-to-float cast inside the loop then try to eliminate the cast operation. 
llvm-svn: 55374
 2008-08-26 17:57:54 +00:00
Owen Anderson
76c3c73a7a Add support for fast isel of non-constant fptosi instructions. 
llvm-svn: 55373
 2008-08-26 17:44:42 +00:00
Gabor Greif
ee460cd197 fix doxygen comment 
llvm-svn: 55372
 2008-08-26 17:44:40 +00:00
Ted Kremenek
5f192023b2 Grammar fix. 
llvm-svn: 55371
 2008-08-26 16:41:15 +00:00
Ted Kremenek
909c1c36e2 Added "str()" method to raw_string_ostream. 
str() mirrors the same method in std::ostringstream.
str() flushes the buffered stream contents to string and returns a reference to the string.

llvm-svn: 55370
 2008-08-26 16:34:01 +00:00
Chris Lattner
1804f18b34 code simplification, no functionality change. 
llvm-svn: 55363
 2008-08-26 07:01:28 +00:00
Chris Lattner
006fc6636d stabilize more printing, this doesn't cause a problem 
in the example attached to PR2590, but is a problem in general.

llvm-svn: 55361
 2008-08-26 06:50:46 +00:00
Chris Lattner
6adb1b1b26 stablize SubRegsSet printing, part of PR2590 
llvm-svn: 55360
 2008-08-26 06:49:06 +00:00
Chris Lattner
e589d360a1 Stabilize 'getDwarfRegNumFull' output to not depend on random memory 
orders, part of PR2590

llvm-svn: 55359
 2008-08-26 06:43:25 +00:00
Chris Lattner
c5c00890e5 If an xmm register is referenced explicitly in an inline asm, make sure to 
assign it to a version of the xmm register with the regclass that matches its
type.  This fixes PR2715, a bug handling some crazy xpcom case in mozilla.

llvm-svn: 55358
 2008-08-26 06:19:02 +00:00
Chris Lattner
4367c5c58b typo fix. 
llvm-svn: 55355
 2008-08-26 06:07:47 +00:00
Dan Gohman
815d50b9e6 Actually recycle SDNode allocations. SelectionDAG is using 
RecyclingAllocator, but this change is needed for the nodes
to actually be recycled. This cuts SelectionDAG's memory
usage high-water-mark in half in some cases.

llvm-svn: 55351
 2008-08-26 01:44:34 +00:00
Dan Gohman
5438048f54 Avoid a warning about isTargetNullPtr being unused in release builds. 
llvm-svn: 55350
 2008-08-26 01:38:29 +00:00
Owen Anderson
9c207563a1 Throw the switch to allow FastISel to emit instructions whose return types different from their inputs. Next step: adding lowering pattens in FastISel that actually use these newly available opcodes. 
llvm-svn: 55349
 2008-08-26 01:22:59 +00:00
Evan Cheng
65d29b2553 This is done. 
llvm-svn: 55348
 2008-08-26 01:13:44 +00:00
Owen Anderson
7e677167d6 Enhance TableGen to emit code for FastISel of opcodes with variadic return types without slowing down opcodes that are not variadic. No such opcodes are currently generated, but in theory it should be a matter of just hitting the switch. 
llvm-svn: 55347
 2008-08-26 00:42:26 +00:00
Owen Anderson
9264f41ef2 Add a RetVT parameter to emitted FastISel methods, so that we will be able to pass the desired return 
type down.  This is not currently used.

llvm-svn: 55345
 2008-08-25 23:58:18 +00:00
Owen Anderson
19b73e58e8 Deepen the map structure tablegen uses to compute FastISel patterns, in preparation for having patterns 
with return types that differ from their input types.  This is not yet used.

llvm-svn: 55344
 2008-08-25 23:43:09 +00:00
Dale Johannesen
f201a3aaf3 Implement 32 & 64 bit versions of PPC atomic 
binary primitives.

llvm-svn: 55343
 2008-08-25 22:34:37 +00:00
Evan Cheng
45e24233c7 Unbreak build. 
llvm-svn: 55342
 2008-08-25 22:20:39 +00:00
Evan Cheng
19738e3956 80 col. violations. 
llvm-svn: 55341
 2008-08-25 21:58:43 +00:00
Owen Anderson
1532aad9a8 Expand bitcast support in fast isel to support bitcasts of non-constant values by emitting reg-reg copies. 
llvm-svn: 55340
 2008-08-25 21:32:34 +00:00
Evan Cheng
569b489cf5 Try approach to moving call address load inside of callseq_start. Now it's done during the preprocess of x86 isel. callseq_start's chain is changed to load's chain node; while load's chain is the last of callseq_start or the loads or copytoreg nodes inserted to move arguments to the right spot. 
llvm-svn: 55338
 2008-08-25 21:27:18 +00:00
Dale Johannesen
fbb408de74 Remove PPC-specific lowering for atomics; the 
generic stuff works fine.

Mark rewritten cmp-and-swap as not using CR1.

llvm-svn: 55336
 2008-08-25 21:09:52 +00:00
Owen Anderson
27491bbf2c Add support for fast isel of (integer) immediate materialization pattens, and use them to support 
bitcast of constants in fast isel.

llvm-svn: 55325
 2008-08-25 20:20:32 +00:00
Dale Johannesen
6431c39237 Adjust grep's for new code sequence. 
llvm-svn: 55320
 2008-08-25 18:53:58 +00:00
Dale Johannesen
39bd83dbc0 It's important for the cmp-and-swap to balance 
loads and stores but it's even more important for
it to store the right value.:(

llvm-svn: 55319
 2008-08-25 18:53:26 +00:00
Bill Wendling
7f52506926 Nevermind. This broke the bootstrap (?!). 
llvm-svn: 55318
 2008-08-25 18:32:39 +00:00
Bill Wendling
f86b246fdb MOVQ2DQ and MOVQ2DQ use SSE2. We should conditionalize the use of these 
instructions on having SSE2.

llvm-svn: 55317
 2008-08-25 18:20:52 +00:00
Chris Lattner
df2af1f4c5 Fix pasto (values -> types) noticed by Josh Conner 
llvm-svn: 55315
 2008-08-25 17:03:15 +00:00
Chris Lattner
0efa9e9d2e flush stream after dumping. 
llvm-svn: 55301
 2008-08-25 04:55:46 +00:00
Evan Cheng
2b9f879a99 Fix asm printing of MOVSDto64mr and MOV64toSDrm. 
llvm-svn: 55300
 2008-08-25 04:11:42 +00:00
Bill Wendling
05e1910595 Fix this test. Don't null out the file, just XFAIL it until patch can be fixed. 
llvm-svn: 55296
 2008-08-24 21:48:46 +00:00
Bill Wendling
5728cf59fd Temporarily reverting r55292. It's causing a bootstraping failure: 
/Volumes/Sandbox/Buildbot/llvm/full-llvm/build/llvm-gcc.obj/./gcc/xgcc ... src/libiberty/make-temp-file.c -o make-temp-file.o
Assertion failed: (Node2Index[SU->NodeNum] > Node2Index[I->Dep->NodeNum] && "Wrong topological sorting"), function InitDAGTopologicalSorting, file /Volumes/Sandbox/Buildbot/llvm/full-llvm/build/llvm.src/lib/CodeGen/SelectionDAG/ScheduleDAGRRList.cpp, line 508.
../../../../llvm-gcc.src/libiberty/hashtab.c:955: internal compiler error: Abort trap
Please submit a full bug report,
with preprocessed source if appropriate.
See <URL:http://developer.apple.com/bugreporter> for instructions.
make[4]: *** [hashtab.o] Error 1
make[4]: *** Waiting for unfinished jobs....
make[3]: *** [multi-do] Error 1
make[2]: *** [all] Error 2
make[1]: *** [all-target-libiberty] Error 2
make: *** [all] Error 2

llvm-svn: 55295
 2008-08-24 21:45:30 +00:00
Chris Lattner
5a8d6a20e6 remove the type checking logic already done by tblgen, just keep the 
parts tblgen doesn't do (checking for constant, alloca, enclosing 
function has gc marker).  This passes dj! :)

llvm-svn: 55294
 2008-08-24 20:46:13 +00:00
Chris Lattner
e5073632e2 simplify PseudoSourceValue printing a bit. Unnest all of PseudoSourceValue.cpp from the llvm namespace. 
llvm-svn: 55293
 2008-08-24 20:37:32 +00:00
Evan Cheng
a600778748 Move callseq_start above the call address load to allow load to be folded into the call node. 
llvm-svn: 55292
 2008-08-24 19:19:55 +00:00
Evan Cheng
19c915aa0e Print PseudoSourceValue. 
llvm-svn: 55291
 2008-08-24 18:51:20 +00:00
Chris Lattner
af40013b25 we should use 'class' for non-pod types instead of 'struct' to 
make it easier to deal with the VC++ struct/class bug.

llvm-svn: 55290
 2008-08-24 18:38:56 +00:00
Chris Lattner
f6e98a0f30 add a hack to temporarily allow pseudo source values. 
llvm-svn: 55289
 2008-08-24 18:33:17 +00:00
Chris Lattner
2147640791 make sure to flush the stream after dumping, to make sure it goes out immediately. 
llvm-svn: 55288
 2008-08-24 18:28:30 +00:00
Cedric Venet
6c99b53fda Use additionnal include directory instead of ../ in #include. 
Suggested by aKor.

llvm-svn: 55282
 2008-08-24 12:30:46 +00:00
Cedric Venet
d1b22a76d2 Updating VC++ project. 
Adding one include file and correct one declaration from class to struct in order to make llvm compile on VC2005.

llvm-svn: 55279
 2008-08-24 11:56:40 +00:00
Gordon Henriksen
587b7ac051 Update GC docs for clarified naming and AsmWriter refactoring. 
llvm-svn: 55275
 2008-08-24 03:18:23 +00:00
Chris Lattner
9f10b57760 improve encapsulation of the BBExecutable set. 
llvm-svn: 55271
 2008-08-23 23:39:31 +00:00
Chris Lattner
15f29cad83 Switch an assortment of maps, sets and vectors to more efficient versions, 
patch contributed by m-s!

llvm-svn: 55270
 2008-08-23 23:36:38 +00:00