summaryrefslogtreecommitdiffstats
path: root/llvm
Commit message (Collapse)AuthorAgeFilesLines
* Deepen the map structure tablegen uses to compute FastISel patterns, in ↵Owen Anderson2008-08-251-54/+61
| | | | | | | | preparation for having patterns with return types that differ from their input types. This is not yet used. llvm-svn: 55344
* Implement 32 & 64 bit versions of PPC atomicDale Johannesen2008-08-255-48/+230
| | | | | | binary primitives. llvm-svn: 55343
* Unbreak build.Evan Cheng2008-08-251-2/+2
| | | | llvm-svn: 55342
* 80 col. violations.Evan Cheng2008-08-251-3/+4
| | | | llvm-svn: 55341
* Expand bitcast support in fast isel to support bitcasts of non-constant ↵Owen Anderson2008-08-251-1/+29
| | | | | | values by emitting reg-reg copies. llvm-svn: 55340
* Try approach to moving call address load inside of callseq_start. Now it's ↵Evan Cheng2008-08-253-36/+108
| | | | | | 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
* Remove PPC-specific lowering for atomics; theDale Johannesen2008-08-254-108/+12
| | | | | | | | generic stuff works fine. Mark rewritten cmp-and-swap as not using CR1. llvm-svn: 55336
* Add support for fast isel of (integer) immediate materialization pattens, ↵Owen Anderson2008-08-254-10/+53
| | | | | | | | and use them to support bitcast of constants in fast isel. llvm-svn: 55325
* Adjust grep's for new code sequence.Dale Johannesen2008-08-252-2/+2
| | | | llvm-svn: 55320
* It's important for the cmp-and-swap to balanceDale Johannesen2008-08-251-13/+31
| | | | | | | loads and stores but it's even more important for it to store the right value.:( llvm-svn: 55319
* Nevermind. This broke the bootstrap (?!).Bill Wendling2008-08-252-11/+7
| | | | llvm-svn: 55318
* MOVQ2DQ and MOVQ2DQ use SSE2. We should conditionalize the use of theseBill Wendling2008-08-252-7/+11
| | | | | | instructions on having SSE2. llvm-svn: 55317
* Fix pasto (values -> types) noticed by Josh ConnerChris Lattner2008-08-251-5/+3
| | | | llvm-svn: 55315
* flush stream after dumping.Chris Lattner2008-08-251-3/+3
| | | | llvm-svn: 55301
* Fix asm printing of MOVSDto64mr and MOV64toSDrm.Evan Cheng2008-08-252-2/+60
| | | | llvm-svn: 55300
* Fix this test. Don't null out the file, just XFAIL it until patch can be fixed.Bill Wendling2008-08-241-0/+11
| | | | llvm-svn: 55296
* Temporarily reverting r55292. It's causing a bootstraping failure:Bill Wendling2008-08-242-17/+2
| | | | | | | | | | | | | | | | | /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
* remove the type checking logic already done by tblgen, just keep theChris Lattner2008-08-241-36/+10
| | | | | | | parts tblgen doesn't do (checking for constant, alloca, enclosing function has gc marker). This passes dj! :) llvm-svn: 55294
* simplify PseudoSourceValue printing a bit. Unnest all of ↵Chris Lattner2008-08-243-59/+47
| | | | | | PseudoSourceValue.cpp from the llvm namespace. llvm-svn: 55293
* Move callseq_start above the call address load to allow load to be folded ↵Evan Cheng2008-08-242-2/+17
| | | | | | into the call node. llvm-svn: 55292
* Print PseudoSourceValue.Evan Cheng2008-08-243-2/+21
| | | | llvm-svn: 55291
* we should use 'class' for non-pod types instead of 'struct' toChris Lattner2008-08-242-2/+3
| | | | | | make it easier to deal with the VC++ struct/class bug. llvm-svn: 55290
* add a hack to temporarily allow pseudo source values.Chris Lattner2008-08-241-1/+2
| | | | llvm-svn: 55289
* make sure to flush the stream after dumping, to make sure it goes out ↵Chris Lattner2008-08-241-0/+1
| | | | | | immediately. llvm-svn: 55288
* Use additionnal include directory instead of ../ in #include.Cedric Venet2008-08-244-15/+15
| | | | | | Suggested by aKor. llvm-svn: 55282
* Updating VC++ project.Cedric Venet2008-08-245-26/+43
| | | | | | Adding one include file and correct one declaration from class to struct in order to make llvm compile on VC2005. llvm-svn: 55279
* Update GC docs for clarified naming and AsmWriter refactoring.Gordon Henriksen2008-08-241-66/+93
| | | | llvm-svn: 55275
* improve encapsulation of the BBExecutable set.Chris Lattner2008-08-231-8/+4
| | | | llvm-svn: 55271
* Switch an assortment of maps, sets and vectors to more efficient versions,Chris Lattner2008-08-231-28/+25
| | | | | | patch contributed by m-s! llvm-svn: 55270
* get MachineConstantPool off std::ostream, onto raw_ostream. It would beChris Lattner2008-08-233-34/+26
| | | | | | really nice if someone converted MachineFunction::print to raw_ostream. llvm-svn: 55268
* minor cleanups.Chris Lattner2008-08-231-6/+9
| | | | llvm-svn: 55267
* remove dead method.Chris Lattner2008-08-231-1/+0
| | | | llvm-svn: 55266
* Add raw_stream adaptors that write into an std::string and ↵Chris Lattner2008-08-232-1/+66
| | | | | | SmallVector/SmallString. llvm-svn: 55265
* Switch the asmprinter (.ll) and all the stuff it requires over toChris Lattner2008-08-2336-250/+269
| | | | | | | | | | | | | | | | | | | | | | | | use raw_ostream instead of std::ostream. Among other goodness, this speeds up llvm-dis of kc++ with a release build from 0.85s to 0.49s (88% faster). Other interesting changes: 1) This makes Value::print be non-virtual. 2) AP[S]Int and ConstantRange can no longer print to ostream directly, use raw_ostream instead. 3) This fixes a bug in raw_os_ostream where it didn't flush itself when destroyed. 4) This adds a new SDNode::print method, instead of only allowing "dump". A lot of APIs have both std::ostream and raw_ostream versions, it would be useful to go through and systematically anihilate the std::ostream versions. This passes dejagnu, but there may be minor fallout, plz let me know if so and I'll fix it. llvm-svn: 55263
* use proper namespace qualificationsChris Lattner2008-08-232-9/+8
| | | | llvm-svn: 55259
* Add #includeChris Lattner2008-08-231-0/+1
| | | | llvm-svn: 55258
* add #includeChris Lattner2008-08-231-0/+1
| | | | llvm-svn: 55257
* add #includeChris Lattner2008-08-231-0/+1
| | | | llvm-svn: 55252
* Split format() out to its own file, add support for formattingChris Lattner2008-08-232-59/+156
| | | | | | up to three values in one call. llvm-svn: 55251
* conditionalize this to work on windows, untested but it should workChris Lattner2008-08-231-0/+5
| | | | | | according to the intarnetz llvm-svn: 55248
* add a simple mechanism for formatted output. This gives raw_ostream's Chris Lattner2008-08-232-5/+116
| | | | | | | | all the power and risk of fprintf format strings. Use them like this: OS << format("%10.4f", 42.0) << "\n" << format("%x", 42) << '\n'; llvm-svn: 55246
* Testcase for 64bit maskmovqAnton Korobeynikov2008-08-231-0/+27
| | | | llvm-svn: 55239
* Provide a 64 bit variant of mmx.maskmovq intrinsic lowering.Anton Korobeynikov2008-08-232-0/+7
| | | | | | Is there way to avoid explicit target check? llvm-svn: 55238
* Reverting r55227. This was causing the following failures in the regressionBill Wendling2008-08-231-0/+39
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | tests: Running /Volumes/Sandbox/Buildbot/llvm/full-llvm/build/llvm.HEAD.src/test/Verifier/dg.exp ... FAIL: /Volumes/Sandbox/Buildbot/llvm/full-llvm/build/llvm.HEAD.src/test/Verifier/gcread-ptrptr.ll for PR1633 Failed with exit(1) at line 1 while running: not llvm-as < /Volumes/Sandbox/Buildbot/llvm/full-llvm/build/llvm.HEAD.src/test/Verifier/gcread-ptrptr.ll >& /dev/null child process exited abnormally FAIL: /Volumes/Sandbox/Buildbot/llvm/full-llvm/build/llvm.HEAD.src/test/Verifier/gcroot-alloca.ll for PR1633 Failed with exit(1) at line 1 while running: not llvm-as < /Volumes/Sandbox/Buildbot/llvm/full-llvm/build/llvm.HEAD.src/test/Verifier/gcroot-alloca.ll >& /dev/null child process exited abnormally FAIL: /Volumes/Sandbox/Buildbot/llvm/full-llvm/build/llvm.HEAD.src/test/Verifier/gcroot-meta.ll for PR1633 Failed with exit(1) at line 1 while running: not llvm-as < /Volumes/Sandbox/Buildbot/llvm/full-llvm/build/llvm.HEAD.src/test/Verifier/gcroot-meta.ll >& /dev/null child process exited abnormally FAIL: ndbox/Buildbot/llvm/full-llvm/build/llvm.HEAD.src/test/Verifier/gcroot-ptrptr.ll for PR1633 Failed with exit(1) at line 1 while running: not llvm-as < /Volumes/Sandbox/Buildbot/llvm/full-llvm/build/llvm.HEAD.src/test/Verifier/gcroot-ptrptr.ll >& /dev/null child process exited abnormally FAIL: /Volumes/Sandbox/Buildbot/llvm/full-llvm/build/llvm.HEAD.src/test/Verifier/gcwrite-ptrptr.ll for PR1633 Failed with exit(1) at line 1 while running: not llvm-as < /Volumes/Sandbox/Buildbot/llvm/full-llvm/build/llvm.HEAD.src/test/Verifier/gcwrite-ptrptr.ll >& /dev/null child process exited abnormally === Summary === # of expected passes 3021 # of unexpected failures 6 # of expected failures 16 make[1]: *** [check-local] Error 1 make: *** [check] Error 2 llvm-svn: 55233
* Add a new trivial -inst-namer pass which makes it possible to diff theChris Lattner2008-08-233-0/+57
| | | | | | before/after effects of a pass, crazy! llvm-svn: 55230
* Verify that the alignment argument to llvm.memcpy is a constantChris Lattner2008-08-232-0/+21
| | | | | | integer, PR2318. llvm-svn: 55228
* remove verification for gc intrinsic argument types. it was indented wrongChris Lattner2008-08-231-39/+0
| | | | | | and tblgen now knows intrinsic prototypes. llvm-svn: 55227
* Fix PR2423 by checking all indices for out of range access, not only Chris Lattner2008-08-232-35/+53
| | | | | | | indices that start with an array subscript. x->field[10000] is just as bad as (*X)[14][10000]. llvm-svn: 55226
* the bug was apparently fixed long ago, reenable the assertionChris Lattner2008-08-231-2/+1
| | | | llvm-svn: 55224
* Make MBBMap a DenseMap instead of a std::map.Dan Gohman2008-08-233-6/+5
| | | | llvm-svn: 55220
OpenPOWER on IntegriCloud