have a return type that differs from the operand types.

llvm-svn: 55376

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

llvm-svn: 55374

llvm-svn: 55373

llvm-svn: 55372

llvm-svn: 55371

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

llvm-svn: 55363

in the example attached to PR2590, but is a problem in general.

llvm-svn: 55361

llvm-svn: 55360

orders, part of PR2590

llvm-svn: 55359

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

llvm-svn: 55355

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

llvm-svn: 55350

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

llvm-svn: 55348

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

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

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

binary primitives.

llvm-svn: 55343

llvm-svn: 55342

llvm-svn: 55341

Expand bitcast support in fast isel to support bitcasts of non-constant values by emitting reg-reg copies.

llvm-svn: 55340

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

generic stuff works fine.

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

llvm-svn: 55336

bitcast of constants in fast isel.

llvm-svn: 55325

llvm-svn: 55320

loads and stores but it's even more important for
it to store the right value.:(

llvm-svn: 55319

llvm-svn: 55318

instructions on having SSE2.

llvm-svn: 55317

llvm-svn: 55315

llvm-svn: 55301

llvm-svn: 55300

llvm-svn: 55296

/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

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 PseudoSourceValue.cpp from the llvm namespace.

llvm-svn: 55293

llvm-svn: 55292

llvm-svn: 55291