aboutsummaryrefslogtreecommitdiff
path: root/lib
AgeCommit message (Collapse)Author
2008-10-27For now, don't split live intervals around x87 stack register barriers. ↵Evan Cheng
FpGET_ST0_80 must be right after a call instruction (and ADJCALLSTACKUP) so we need to find a way to prevent reload of x87 registers between them. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58230 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-27Rewrite all the 'PromoteLocallyUsedAlloca[s]' logic. With the power ofChris Lattner
LargeBlockInfo, we can now dramatically simplify their implementation and speed them up at the same time. Now the code has time proportional to the number of uses of the alloca, not the size of the block. This also eliminates code that tried to batch up different allocas which are used in the same blocks, and eliminates the 'retry list' logic which was baroque and no unneccesary. In addition to being a speedup for crazy cases, this is also a nice cleanup: PromoteMemoryToRegister.cpp | 270 +++++++++++++++----------------------------- 1 file changed, 96 insertions(+), 174 deletions(-) git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58229 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-27Add a new LargeBlockInfo helper, which is just a wrapper aroundChris Lattner
a trivial dense map. Use this in RewriteSingleStoreAlloca to avoid aggressively rescanning blocks over and over again. This fixes PR2925, speeding up mem2reg on the testcase in that bug from 4.56s to 0.02s in a debug build on my machine. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58227 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-27Increase default setting of tail-merge-threshold toDale Johannesen
150, based on llvm-test measurements. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58225 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-26fix PR2953, an off-by-one error handling formatted i/o. Chris Lattner
Thanks to Török Edwin for the awesome reduced testcase. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58199 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-26Do not shrink wrap live interval in a mbb if it's livein any of its ↵Evan Cheng
successor blocks. The mbb can be revisited again after all of the successors are processed. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58184 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-26Fix type-o in ExprMapKeyType::operator ==(). The "&&" was missing.Bill Wendling
Patch by Frits van Bommel! git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58175 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-25Handle cases where there aren't uses in the barrier mbb.Evan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58174 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-25Make comments and code for QuietWarnings and QuietErrorsDan Gohman
actually correspond to what their names suggest. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58146 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-25SDNodes may have at most one Flag result. Update this commentDan Gohman
to reflect that. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58145 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-25Move the code that adds the DeadMachineInstructionElimPass fromDan Gohman
target-independent code to target-specific code. This prevents it from running on targets that aren't using fast-isel. In addition to saving compile time, this addresses the problem that not all targets are prepared for it. In order to use this pass, all instructions must declare all their fixed uses and defs of physical registers. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58144 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-25Related to PR2911, reject as invalid non-pointer GC roots.Gordon Henriksen
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58143 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-25Support for allocation of TLS variables in the JIT. Allocation of a globalNicolas Geoffray
variable is moved to the execution engine. The JIT calls the TargetJITInfo to allocate thread local storage. Currently, only linux/x86 knows how to allocate thread local global variables. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58142 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-25Generate code for TLS instructions.Nicolas Geoffray
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58141 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-25CMake: lib/Target/ARM/AsmPrinter/CMakeLists.txt added.Oscar Fuentes
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58133 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-25CMake: Cross-platform support for using pre-generated llvmAsmParser.cpp and ↵Oscar Fuentes
llvmAsmParser.h. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58130 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-25If val# def is ~0U, meaning it's defined by a PHI, and it's previously ↵Evan Cheng
split, spill before the barrier because it's impossible to determine if all the defs are spilled in the same spill slot. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58129 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-24Mark MFCR as reading all condition code registers.Dale Johannesen
Prevents some more overzealous deletions (mostly in AltiVec code). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58121 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-24Rewrite logic to figure out whether LR needs toDale Johannesen
be saved/restored in the prolog/epilog. We need to do this iff something in the function stores into it. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58116 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-24move the note to the correct READMETorok Edwin
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58104 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-24add note about va_arg code on x86 and x86-64Torok Edwin
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58103 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-24Fix a pasto.Evan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58102 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-24Fix translateX86CC: if SetCCOpcode is SETULE andDuncan Sands
LHS is a foldable load, then LHS and RHS are swapped and SetCCOpcode is changed to SETUGT. But the later code is expecting operands to be the wrong way round for SETUGT, but they are not in this case, resulting in an inverted compare. The solution is to move the load normalization before the correction for SETUGT. This bug was tickled by LegalizeTypes which happened to legalize the testcase slightly differently to LegalizeDAG. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58092 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-24Modify the cmake build system so that if it doesn't find bison, it will use ↵Cedric Venet
the pregenerated file in from the svn (.cvs). Work only for windows for the moment. Tested on Vista64 with MSVC2008express. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58090 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-24Don't try to create a mask when we don't need one. Fixes a crash.Nick Lewycky
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58075 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-24Fix a end() dereference; remove an abort() that wasn't meant to be left in.Evan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58072 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-24Add value range analyzing of Add and Sub.Nick Lewycky
Understand that mul %x, 1 = %x. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58069 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-24Avoid splitting an interval multiple times; avoid splitting ↵Evan Cheng
re-materializable val# (for now). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58068 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-24Fix constant-offset emission for x86-64 absolute addresses. ThisDan Gohman
fixes a bunch of test-suite JIT failures on x86-64 in -relocation-model=static mode. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58066 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-24Initialize uninitialized variable.Dale Johannesen
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58057 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-23Added raw_fd_ostream::close().Ted Kremenek
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58052 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-23Committing a good chunk of the pre-register allocation live interval ↵Evan Cheng
splitting pass. It's handling simple cases and appear to do good things. Next: avoid splitting an interval multiple times; renumber registers when possible; record stack slot live intervals for coloring; rematerialize defs when possible. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58044 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-23Mark defs and uses of CTR and LR correctly.Dale Johannesen
Prevents DeadMachineInstructionElim from thinking things like MTCTR are dead (fixes massive testsuite breakage at -O0). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58043 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-23Make sure to set stdout to binary when writing bitcode files viaDaniel Dunbar
std::ostream API. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58042 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-23Fix thinko - the operand number has nothing to doDuncan Sands
with the result number. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58041 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-22Change create*Pass factory functions to return Pass* instead ofDaniel Dunbar
LoopPass*. - Although less precise, this means they can be used in clients without RTTI (who would otherwise need to include LoopPass.h, which eventually includes things using dynamic_cast). This was the simplest solution that presented itself, but I am happy to use a better one if available. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58010 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-22remove extraneous #ifdef'sJim Grosbach
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58006 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-22Add raw_ostream versions of WriteBitcodeToFile and BitcodeWriterPass.Daniel Dunbar
- The old versions are still hanging around, but should be migrated away from. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57989 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-22Remove allocation of unused stack slot.Dale Johannesen
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57987 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-22Fix for PR2881: fix a small leak exposed by valgrind, using a ManagedStatic.Julien Lerouge
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57984 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-22LegalizeTypes soft-float support for fpow.Duncan Sands
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57973 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-22Get this working with LegalizeTypes: (1) don'tDuncan Sands
assume that i64 has been turned into a BUILD_PAIR node (when called from LegalizeTypes this hasn't happened yet) and don't use a vector shuffle mask with an illegal element type. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57972 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-22Be nice to CellSPU: for this target getSetCCResultTypeDuncan Sands
may return i8, which can result in SELECT nodes for which the type of the condition is i8, but there are no patterns for select with i8 condition. Tweak the LegalizeTypes logic to avoid this as much as possible. This isn't a real fix because it is still perfectly possible to end up with such select nodes - CellSPU needs to be fixed IMHO. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57968 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-22Port from LegalizeDAG the logic to only generateDuncan Sands
ADDC/ADDE/SUBC/SUBE if the target supports it. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57967 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-22Add some comments explaining the meaning of a booleanDuncan Sands
that is not of type MVT::i1 in SELECT and SETCC nodes. Relax the LegalizeTypes SELECT condition promotion sanity checks to allow other condition types than i1. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57966 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-22Temporarily allow the operands of a BUILD_VECTORDuncan Sands
to have a different type to the vector element type. This should be fairly harmless because in the past guys like this were being built all over the place (and were cleaned up when I added this check). The reason for relaxing this check is that it helps LegalizeTypes legalize vector shuffles: the mask is a BUILD_VECTOR that it is *not always possible* to legalize while keeping it a BUILD_VECTOR (vector_shuffle requires the mask to be a BUILD_VECTOR, as opposed to a vector with the right vector type). With this check it is even harder to legalize the mask - turning the check off means that LegalizeTypes manages to legalize almost all vector shuffles encountered in practice. The correct solution is to change vector_shuffle to be a variadic node with the mask built into it as operands. While waiting for that change, this hack stops the problem with vector_shuffle from blocking the turning on of LegalizeTypes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57965 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-22Fix PR2907 by digging through constant expressions to find FP constants thatChris Lattner
are their operands. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57956 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-22Move Print*Pass to use raw_ostream.Daniel Dunbar
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57946 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-22CMake: Turned some libraries into partially linked objects. CorrectedOscar Fuentes
names of LLVMCore and ARMCodeGen. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57943 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-22Adjust comments for pedantic satisfaction.Dale Johannesen
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57940 91177308-0d34-0410-b5e6-96231b3b80d8