llvm-project/llvm/lib/CodeGen
Rafael Espindola 44bbe36de6 Second try at making direct object emission produce the same results
as llc + llvm-mc. This time ELF is not changed and I tested that llvm-gcc
bootstrap on darwin10 using darwin9's assembler and linker.

llvm-svn: 121006
2010-12-06 17:27:56 +00:00
..
AsmPrinter Second try at making direct object emission produce the same results 2010-12-06 17:27:56 +00:00
SelectionDAG Remove unneeded zero arrays. 2010-12-04 15:28:22 +00:00
AggressiveAntiDepBreaker.cpp Anti-dependency breaking needs to be careful not to use reserved regs 2010-09-02 17:12:55 +00:00
AggressiveAntiDepBreaker.h Use std::vector instead of TargetRegisterInfo::FirstVirtualRegister. 2010-07-15 18:43:09 +00:00
Analysis.cpp Enable sibling call optimization of libcalls which are expanded during 2010-11-30 23:55:39 +00:00
AntiDepBreaker.h Make BreakAntiDependencies' SUnits argument const, and make the Begin 2010-04-19 23:11:58 +00:00
BranchFolding.cpp Reapply r110396, with fixes to appease the Linux buildbot gods. 2010-08-06 18:33:48 +00:00
BranchFolding.h Tail merging pass shall not break up IT blocks. rdar://8115404 2010-06-22 01:18:16 +00:00
CMakeLists.txt Move the FindCopyInsertPoint method of PHIElimination to a new standalone 2010-12-05 19:51:05 +00:00
CalcSpillWeights.cpp Begin adding static dependence information to passes, which will allow us to 2010-10-12 19:48:12 +00:00
CallingConvLower.cpp In the calling convention logic, ValVT is always a legal type, 2010-11-04 10:49:57 +00:00
CodeGen.cpp Stub out a new LiveDebugVariables pass. 2010-11-30 02:17:10 +00:00
CodePlacementOpt.cpp Reapply r110396, with fixes to appease the Linux buildbot gods. 2010-08-06 18:33:48 +00:00
CriticalAntiDepBreaker.cpp Fixes <rdar://problem/8612856>: During postRAsched, the antidependence 2010-11-02 18:16:45 +00:00
CriticalAntiDepBreaker.h Fixes <rdar://problem/8612856>: During postRAsched, the antidependence 2010-11-02 18:16:45 +00:00
DeadMachineInstructionElim.cpp Get rid of static constructors for pass registration. Instead, every pass exposes an initializeMyPassFunction(), which 2010-10-19 17:21:58 +00:00
DwarfEHPrepare.cpp This may be an ARM target, so check for _Unwind_SjLj_Resume. 2010-10-29 07:46:01 +00:00
ELF.h Merge System into Support. 2010-11-29 18:16:10 +00:00
ELFCodeEmitter.cpp Get rid of a bunch of duplicated ELF enum values. 2010-07-16 07:53:29 +00:00
ELFCodeEmitter.h change EH related stuff (other than EH_LABEL) to use MCSymbol 2010-03-14 01:41:15 +00:00
ELFWriter.cpp Reapply r110396, with fixes to appease the Linux buildbot gods. 2010-08-06 18:33:48 +00:00
ELFWriter.h Tidy some #includes and forward-declarations, and move the C binding code 2010-08-07 00:43:20 +00:00
ExpandISelPseudos.cpp Rename ExpandPseudos to ExpandISelPseudos to help clarify its role. 2010-11-18 18:45:06 +00:00
GCMetadata.cpp Get rid of static constructors for pass registration. Instead, every pass exposes an initializeMyPassFunction(), which 2010-10-19 17:21:58 +00:00
GCMetadataPrinter.cpp mcize the gc metadata printing stuff. 2010-04-04 07:39:04 +00:00
GCStrategy.cpp Move some more hooks to TargetFrameInfo 2010-11-20 15:59:32 +00:00
IfConversion.cpp Prune includes. 2010-11-06 11:45:59 +00:00
InlineSpiller.cpp When spilling a register defined by an early clobber, make sure that the new 2010-11-15 20:55:49 +00:00
IntrinsicLowering.cpp Get rid of pop_macro warnings on MSVC. 2010-09-24 19:48:47 +00:00
LLVMTargetMachine.cpp Change some methods in MCDwarf.cpp to be able to handle an arbitrary 2010-11-19 02:26:16 +00:00
LatencyPriorityQueue.cpp Use `llvm::next' instead of `next' to make VC++ 2010 happy. 2010-05-30 13:14:21 +00:00
LiveDebugVariables.cpp Rename virtRegMap to avoid confusion with the VirtRegMap that it isn't. 2010-12-03 22:25:09 +00:00
LiveDebugVariables.h Emit DBG_VALUE instructions from LiveDebugVariables. 2010-12-03 21:47:10 +00:00
LiveInterval.cpp Teach ConnectedVNInfoEqClasses::Classify to deal with unused values. 2010-10-29 17:37:29 +00:00
LiveIntervalAnalysis.cpp Fix emergency spilling in LiveIntervals::spillPhysRegAroundRegDefsUses. 2010-11-16 19:55:14 +00:00
LiveIntervalUnion.cpp Comment typo. 2010-11-30 23:59:50 +00:00
LiveIntervalUnion.h Coding style. No significant functionality. Abandon linear scan style 2010-11-30 23:18:47 +00:00
LiveRangeEdit.cpp Simplify the LiveRangeEdit::canRematerializeAt() interface a bit. 2010-11-10 01:05:12 +00:00
LiveRangeEdit.h Simplify the LiveRangeEdit::canRematerializeAt() interface a bit. 2010-11-10 01:05:12 +00:00
LiveStackAnalysis.cpp Make the spiller responsible for updating the LiveStacks analysis. 2010-10-26 00:11:33 +00:00
LiveVariables.cpp Begin adding static dependence information to passes, which will allow us to 2010-10-12 19:48:12 +00:00
LocalStackSlotAllocation.cpp Improve virtual frame base register allocation heuristics. 2010-08-31 17:58:19 +00:00
LowerSubregs.cpp Remove unused functions. 2010-08-16 17:18:20 +00:00
MachineBasicBlock.cpp Don't try to split weird critical edges that really aren't: 2010-11-02 00:58:37 +00:00
MachineCSE.cpp Teach machine cse to eliminate instructions with multiple physreg uses and defs. rdar://8610857. 2010-10-29 23:36:03 +00:00
MachineDominators.cpp Get rid of static constructors for pass registration. Instead, every pass exposes an initializeMyPassFunction(), which 2010-10-19 17:21:58 +00:00
MachineFunction.cpp move the pic base symbol stuff up to MachineFunction 2010-11-14 22:48:15 +00:00
MachineFunctionAnalysis.cpp Attach a GCModuleInfo to a MachineFunction. 2010-10-31 20:38:38 +00:00
MachineFunctionPass.cpp Ok, third time's the charm. No changes from last time except the CMake 2010-04-02 23:17:14 +00:00
MachineFunctionPrinterPass.cpp Reapply r110396, with fixes to appease the Linux buildbot gods. 2010-08-06 18:33:48 +00:00
MachineInstr.cpp Unbreak build. 2010-10-22 21:49:09 +00:00
MachineLICM.cpp Add a FIXME comment. 2010-11-11 18:08:43 +00:00
MachineLoopInfo.cpp Begin adding static dependence information to passes, which will allow us to 2010-10-12 19:48:12 +00:00
MachineModuleInfo.cpp CodeGen-Windows: Only emit _fltused if a VarArg function is called with floating point args. 2010-10-21 00:08:21 +00:00
MachineModuleInfoImpls.cpp Add a bit along with the MCSymbols stored in the MachineModuleInfo maps that 2010-03-10 22:34:10 +00:00
MachinePassRegistry.cpp
MachineRegisterInfo.cpp Add MachineRegisterInfo::constrainRegClass and use it in MachineCSE. 2010-10-06 23:54:39 +00:00
MachineSSAUpdater.cpp Fix PR7096. When a block containing multiple defs is tail duplicated, the 2010-05-10 17:14:26 +00:00
MachineSink.cpp Get rid of static constructors for pass registration. Instead, every pass exposes an initializeMyPassFunction(), which 2010-10-19 17:21:58 +00:00
MachineVerifier.cpp Only avoid the check if we're the last operand before the variable 2010-11-17 00:55:36 +00:00
Makefile make -fno-rtti the default unless a directory builds with REQUIRES_RTTI. 2010-01-24 20:43:08 +00:00
ObjectCodeEmitter.cpp
OcamlGC.cpp
OptimizePHIs.cpp Get rid of static constructors for pass registration. Instead, every pass exposes an initializeMyPassFunction(), which 2010-10-19 17:21:58 +00:00
PHIElimination.cpp Remove the PHIElimination.h header, as it is no longer needed. 2010-12-05 21:39:42 +00:00
PHIEliminationUtils.cpp Move the FindCopyInsertPoint method of PHIElimination to a new standalone 2010-12-05 19:51:05 +00:00
PHIEliminationUtils.h Move the FindCopyInsertPoint method of PHIElimination to a new standalone 2010-12-05 19:51:05 +00:00
Passes.cpp Use the fast register allocator by default for -O0 builds. 2010-06-03 00:39:06 +00:00
PeepholeOptimizer.cpp Remove ARM isel hacks that fold large immediates into a pair of add, sub, and, 2010-11-17 20:13:28 +00:00
PostRAHazardRecognizer.cpp Teach if-converter to be more careful with predicating instructions that would 2010-09-10 01:29:16 +00:00
PostRASchedulerList.cpp Teach if-converter to be more careful with predicating instructions that would 2010-09-10 01:29:16 +00:00
PreAllocSplitting.cpp Get rid of static constructors for pass registration. Instead, every pass exposes an initializeMyPassFunction(), which 2010-10-19 17:21:58 +00:00
ProcessImplicitDefs.cpp Begin adding static dependence information to passes, which will allow us to 2010-10-12 19:48:12 +00:00
PrologEpilogInserter.cpp Move more PEI-related hooks to TFI 2010-11-27 23:05:25 +00:00
PrologEpilogInserter.h Get rid of static constructors for pass registration. Instead, every pass exposes an initializeMyPassFunction(), which 2010-10-19 17:21:58 +00:00
PseudoSourceValue.cpp Merge System into Support. 2010-11-29 18:16:10 +00:00
README.txt
RegAllocBase.h Coding style. No significant functionality. Abandon linear scan style 2010-11-30 23:18:47 +00:00
RegAllocBasic.cpp Coding style. No significant functionality. Abandon linear scan style 2010-11-30 23:18:47 +00:00
RegAllocFast.cpp Get rid of static constructors for pass registration. Instead, every pass exposes an initializeMyPassFunction(), which 2010-10-19 17:21:58 +00:00
RegAllocLinearScan.cpp Emit DBG_VALUE instructions from LiveDebugVariables. 2010-12-03 21:47:10 +00:00
RegAllocPBQP.cpp Fix some style issues in PBQP. Patch by David Blaikie. 2010-11-12 05:47:21 +00:00
RegisterCoalescer.cpp Analysis groups need to initialize their default implementations. 2010-10-13 21:49:58 +00:00
RegisterScavenging.cpp The scavenger should just use getAllocatableSet() rather than reinventing it 2010-09-02 18:29:04 +00:00
RenderMachineFunction.cpp The variable liTRC is not used for anything useful, zap it 2010-10-21 16:04:43 +00:00
RenderMachineFunction.h Get rid of static constructors for pass registration. Instead, every pass exposes an initializeMyPassFunction(), which 2010-10-19 17:21:58 +00:00
ScheduleDAG.cpp Remove trailing whitespace, no functionality changes. 2010-06-30 03:40:54 +00:00
ScheduleDAGEmit.cpp Emit COPY instructions instead of using copyRegToReg in InstrEmitter, 2010-07-10 19:08:25 +00:00
ScheduleDAGInstrs.cpp Two sets of changes. Sorry they are intermingled. 2010-11-03 00:45:17 +00:00
ScheduleDAGInstrs.h Properly model the latency of register defs which are 1) function returns or 2010-10-23 02:10:46 +00:00
ScheduleDAGPrinter.cpp Remove ShortNames from getNodeLabel in DOTGraphTraits 2009-11-30 12:38:47 +00:00
ShadowStackGC.cpp use ArgOperand API and CallSite to access arguments of CallInst 2010-06-25 08:48:19 +00:00
ShrinkWrapping.cpp Change errs() to dbgs(). 2010-01-05 01:25:39 +00:00
SimpleRegisterCoalescing.cpp Update LiveDebugVariables during coalescing. 2010-12-02 18:15:44 +00:00
SimpleRegisterCoalescing.h Implement the first half of LiveDebugVariables. 2010-12-02 00:37:37 +00:00
SjLjEHPrepare.cpp Prune includes. 2010-11-06 11:45:59 +00:00
SlotIndexes.cpp Insert two blank SlotIndexes between basic blocks instead of just one. 2010-11-11 00:19:20 +00:00
Spiller.cpp Delete SplittingSpiller. It was not being used by anyone, and it is being 2010-11-11 00:52:44 +00:00
Spiller.h RABasic is nearly functionally complete. There are a few remaining 2010-11-10 19:18:47 +00:00
SplitKit.cpp No need to add liveness that's already there. 2010-11-10 23:56:00 +00:00
SplitKit.h Basic rematerialization during splitting. 2010-11-10 19:31:50 +00:00
Splitter.cpp Begin adding static dependence information to passes, which will allow us to 2010-10-12 19:48:12 +00:00
Splitter.h Get rid of static constructors for pass registration. Instead, every pass exposes an initializeMyPassFunction(), which 2010-10-19 17:21:58 +00:00
StackProtector.cpp Get rid of static constructors for pass registration. Instead, every pass exposes an initializeMyPassFunction(), which 2010-10-19 17:21:58 +00:00
StackSlotColoring.cpp Get rid of static constructors for pass registration. Instead, every pass exposes an initializeMyPassFunction(), which 2010-10-19 17:21:58 +00:00
StrongPHIElimination.cpp Some cleanup before I start committing some incremental progress on 2010-12-05 22:34:08 +00:00
TailDuplication.cpp Reapply r110396, with fixes to appease the Linux buildbot gods. 2010-08-06 18:33:48 +00:00
TargetInstrInfoImpl.cpp force clients of MachineFunction::getMachineMemOperand to provide a 2010-09-21 04:46:39 +00:00
TargetLoweringObjectFileImpl.cpp Fixed version of 118639 with an extra assert to catch similar problems 2010-11-09 23:42:07 +00:00
TwoAddressInstructionPass.cpp Remove some variables that are never really used 2010-10-21 16:03:28 +00:00
UnreachableBlockElim.cpp Get rid of static constructors for pass registration. Instead, every pass exposes an initializeMyPassFunction(), which 2010-10-19 17:21:58 +00:00
VirtRegMap.cpp Remember to resize SpillSlotToUsesMap when allocating an emergency spill slot. 2010-11-16 00:41:01 +00:00
VirtRegMap.h Remember to resize SpillSlotToUsesMap when allocating an emergency spill slot. 2010-11-16 00:41:01 +00:00
VirtRegRewriter.cpp Prune includes. 2010-11-06 11:45:59 +00:00
VirtRegRewriter.h Code clean up. Move includes from VirtRegRewriter.h to VirtRegRewriter.cpp. 2010-04-06 17:19:55 +00:00

README.txt

//===---------------------------------------------------------------------===//

Common register allocation / spilling problem:

        mul lr, r4, lr
        str lr, [sp, #+52]
        ldr lr, [r1, #+32]
        sxth r3, r3
        ldr r4, [sp, #+52]
        mla r4, r3, lr, r4

can be:

        mul lr, r4, lr
        mov r4, lr
        str lr, [sp, #+52]
        ldr lr, [r1, #+32]
        sxth r3, r3
        mla r4, r3, lr, r4

and then "merge" mul and mov:

        mul r4, r4, lr
        str lr, [sp, #+52]
        ldr lr, [r1, #+32]
        sxth r3, r3
        mla r4, r3, lr, r4

It also increase the likelyhood the store may become dead.

//===---------------------------------------------------------------------===//

bb27 ...
        ...
        %reg1037 = ADDri %reg1039, 1
        %reg1038 = ADDrs %reg1032, %reg1039, %NOREG, 10
    Successors according to CFG: 0x8b03bf0 (#5)

bb76 (0x8b03bf0, LLVM BB @0x8b032d0, ID#5):
    Predecessors according to CFG: 0x8b0c5f0 (#3) 0x8b0a7c0 (#4)
        %reg1039 = PHI %reg1070, mbb<bb76.outer,0x8b0c5f0>, %reg1037, mbb<bb27,0x8b0a7c0>

Note ADDri is not a two-address instruction. However, its result %reg1037 is an
operand of the PHI node in bb76 and its operand %reg1039 is the result of the
PHI node. We should treat it as a two-address code and make sure the ADDri is
scheduled after any node that reads %reg1039.

//===---------------------------------------------------------------------===//

Use local info (i.e. register scavenger) to assign it a free register to allow
reuse:
        ldr r3, [sp, #+4]
        add r3, r3, #3
        ldr r2, [sp, #+8]
        add r2, r2, #2
        ldr r1, [sp, #+4]  <==
        add r1, r1, #1
        ldr r0, [sp, #+4]
        add r0, r0, #2

//===---------------------------------------------------------------------===//

LLVM aggressively lift CSE out of loop. Sometimes this can be negative side-
effects:

R1 = X + 4
R2 = X + 7
R3 = X + 15

loop:
load [i + R1]
...
load [i + R2]
...
load [i + R3]

Suppose there is high register pressure, R1, R2, R3, can be spilled. We need
to implement proper re-materialization to handle this:

R1 = X + 4
R2 = X + 7
R3 = X + 15

loop:
R1 = X + 4  @ re-materialized
load [i + R1]
...
R2 = X + 7 @ re-materialized
load [i + R2]
...
R3 = X + 15 @ re-materialized
load [i + R3]

Furthermore, with re-association, we can enable sharing:

R1 = X + 4
R2 = X + 7
R3 = X + 15

loop:
T = i + X
load [T + 4]
...
load [T + 7]
...
load [T + 15]
//===---------------------------------------------------------------------===//

It's not always a good idea to choose rematerialization over spilling. If all
the load / store instructions would be folded then spilling is cheaper because
it won't require new live intervals / registers. See 2003-05-31-LongShifts for
an example.

//===---------------------------------------------------------------------===//

With a copying garbage collector, derived pointers must not be retained across
collector safe points; the collector could move the objects and invalidate the
derived pointer. This is bad enough in the first place, but safe points can
crop up unpredictably. Consider:

        %array = load { i32, [0 x %obj] }** %array_addr
        %nth_el = getelementptr { i32, [0 x %obj] }* %array, i32 0, i32 %n
        %old = load %obj** %nth_el
        %z = div i64 %x, %y
        store %obj* %new, %obj** %nth_el

If the i64 division is lowered to a libcall, then a safe point will (must)
appear for the call site. If a collection occurs, %array and %nth_el no longer
point into the correct object.

The fix for this is to copy address calculations so that dependent pointers
are never live across safe point boundaries. But the loads cannot be copied
like this if there was an intervening store, so may be hard to get right.

Only a concurrent mutator can trigger a collection at the libcall safe point.
So single-threaded programs do not have this requirement, even with a copying
collector. Still, LLVM optimizations would probably undo a front-end's careful
work.

//===---------------------------------------------------------------------===//

The ocaml frametable structure supports liveness information. It would be good
to support it.

//===---------------------------------------------------------------------===//

The FIXME in ComputeCommonTailLength in BranchFolding.cpp needs to be
revisited. The check is there to work around a misuse of directives in inline
assembly.

//===---------------------------------------------------------------------===//

It would be good to detect collector/target compatibility instead of silently
doing the wrong thing.

//===---------------------------------------------------------------------===//

It would be really nice to be able to write patterns in .td files for copies,
which would eliminate a bunch of explicit predicates on them (e.g. no side 
effects).  Once this is in place, it would be even better to have tblgen 
synthesize the various copy insertion/inspection methods in TargetInstrInfo.

//===---------------------------------------------------------------------===//

Stack coloring improvments:

1. Do proper LiveStackAnalysis on all stack objects including those which are
   not spill slots.
2. Reorder objects to fill in gaps between objects.
   e.g. 4, 1, <gap>, 4, 1, 1, 1, <gap>, 4 => 4, 1, 1, 1, 1, 4, 4

//===---------------------------------------------------------------------===//

The scheduler should be able to sort nearby instructions by their address. For
example, in an expanded memset sequence it's not uncommon to see code like this:

  movl $0, 4(%rdi)
  movl $0, 8(%rdi)
  movl $0, 12(%rdi)
  movl $0, 0(%rdi)

Each of the stores is independent, and the scheduler is currently making an
arbitrary decision about the order.

//===---------------------------------------------------------------------===//

Another opportunitiy in this code is that the $0 could be moved to a register:

  movl $0, 4(%rdi)
  movl $0, 8(%rdi)
  movl $0, 12(%rdi)
  movl $0, 0(%rdi)

This would save substantial code size, especially for longer sequences like
this. It would be easy to have a rule telling isel to avoid matching MOV32mi
if the immediate has more than some fixed number of uses. It's more involved
to teach the register allocator how to do late folding to recover from
excessive register pressure.