2010-10-07 04:17:38 +00:00
|
|
|
//===- llvm/InitializePasses.h -------- Initialize All Passes ---*- C++ -*-===//
|
|
|
|
|
//
|
|
|
|
|
// The LLVM Compiler Infrastructure
|
|
|
|
|
//
|
|
|
|
|
// This file is distributed under the University of Illinois Open Source
|
|
|
|
|
// License. See LICENSE.TXT for details.
|
|
|
|
|
//
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
//
|
|
|
|
|
// This file contains the declarations for the pass initialization routines
|
|
|
|
|
// for the entire LLVM project.
|
|
|
|
|
//
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
|
|
|
|
#ifndef LLVM_INITIALIZEPASSES_H
|
|
|
|
|
#define LLVM_INITIALIZEPASSES_H
|
|
|
|
|
|
|
|
|
|
namespace llvm {
|
|
|
|
|
|
|
|
|
|
class PassRegistry;
|
|
|
|
|
|
2011-01-29 01:09:53 +00:00
|
|
|
/// initializeCore - Initialize all passes linked into the
|
2010-10-07 19:51:21 +00:00
|
|
|
/// TransformUtils library.
|
|
|
|
|
void initializeCore(PassRegistry&);
|
|
|
|
|
|
2011-01-29 01:09:53 +00:00
|
|
|
/// initializeTransformUtils - Initialize all passes linked into the
|
2010-10-07 17:55:47 +00:00
|
|
|
/// TransformUtils library.
|
|
|
|
|
void initializeTransformUtils(PassRegistry&);
|
|
|
|
|
|
2011-01-29 01:09:53 +00:00
|
|
|
/// initializeScalarOpts - Initialize all passes linked into the
|
2010-10-07 17:55:47 +00:00
|
|
|
/// ScalarOpts library.
|
|
|
|
|
void initializeScalarOpts(PassRegistry&);
|
|
|
|
|
|
2013-01-28 01:35:51 +00:00
|
|
|
/// initializeObjCARCOpts - Initialize all passes linked into the ObjCARCOpts
|
|
|
|
|
/// library.
|
|
|
|
|
void initializeObjCARCOpts(PassRegistry&);
|
|
|
|
|
|
2012-02-01 03:51:43 +00:00
|
|
|
/// initializeVectorization - Initialize all passes linked into the
|
|
|
|
|
/// Vectorize library.
|
|
|
|
|
void initializeVectorization(PassRegistry&);
|
|
|
|
|
|
2011-01-29 01:09:53 +00:00
|
|
|
/// initializeInstCombine - Initialize all passes linked into the
|
2015-01-20 22:44:35 +00:00
|
|
|
/// InstCombine library.
|
2010-10-07 20:04:55 +00:00
|
|
|
void initializeInstCombine(PassRegistry&);
|
|
|
|
|
|
2010-10-07 18:09:59 +00:00
|
|
|
/// initializeIPO - Initialize all passes linked into the IPO library.
|
|
|
|
|
void initializeIPO(PassRegistry&);
|
|
|
|
|
|
2010-10-07 20:17:24 +00:00
|
|
|
/// initializeInstrumentation - Initialize all passes linked into the
|
|
|
|
|
/// Instrumentation library.
|
|
|
|
|
void initializeInstrumentation(PassRegistry&);
|
|
|
|
|
|
2010-10-07 18:31:00 +00:00
|
|
|
/// initializeAnalysis - Initialize all passes linked into the Analysis library.
|
|
|
|
|
void initializeAnalysis(PassRegistry&);
|
|
|
|
|
|
|
|
|
|
/// initializeIPA - Initialize all passes linked into the IPA library.
|
|
|
|
|
void initializeIPA(PassRegistry&);
|
|
|
|
|
|
2010-10-07 18:41:20 +00:00
|
|
|
/// initializeCodeGen - Initialize all passes linked into the CodeGen library.
|
|
|
|
|
void initializeCodeGen(PassRegistry&);
|
|
|
|
|
|
2010-10-07 18:50:11 +00:00
|
|
|
/// initializeCodeGen - Initialize all passes linked into the CodeGen library.
|
|
|
|
|
void initializeTarget(PassRegistry&);
|
|
|
|
|
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeAAEvalPass(PassRegistry&);
|
2014-03-03 20:06:11 +00:00
|
|
|
void initializeAddDiscriminatorsPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeADCEPass(PassRegistry&);
|
|
|
|
|
void initializeAliasAnalysisAnalysisGroup(PassRegistry&);
|
|
|
|
|
void initializeAliasAnalysisCounterPass(PassRegistry&);
|
|
|
|
|
void initializeAliasDebuggerPass(PassRegistry&);
|
|
|
|
|
void initializeAliasSetPrinterPass(PassRegistry&);
|
|
|
|
|
void initializeAlwaysInlinerPass(PassRegistry&);
|
|
|
|
|
void initializeArgPromotionPass(PassRegistry&);
|
2014-08-21 21:50:01 +00:00
|
|
|
void initializeAtomicExpandPass(PassRegistry&);
|
SampleProfileLoader pass. Initial setup.
This adds a new scalar pass that reads a file with samples generated
by 'perf' during runtime. The samples read from the profile are
incorporated and emmited as IR metadata reflecting that profile.
The profile file is assumed to have been generated by an external
profile source. The profile information is converted into IR metadata,
which is later used by the analysis routines to estimate block
frequencies, edge weights and other related data.
External profile information files have no fixed format, each profiler
is free to define its own. This includes both the on-disk representation
of the profile and the kind of profile information stored in the file.
A common kind of profile is based on sampling (e.g., perf), which
essentially counts how many times each line of the program has been
executed during the run.
The SampleProfileLoader pass is organized as a scalar transformation.
On startup, it reads the file given in -sample-profile-file to
determine what kind of profile it contains. This file is assumed to
contain profile information for the whole application. The profile
data in the file is read and incorporated into the internal state of
the corresponding profiler.
To facilitate testing, I've organized the profilers to support two file
formats: text and native. The native format is whatever on-disk
representation the profiler wants to support, I think this will mostly
be bitcode files, but it could be anything the profiler wants to
support. To do this, every profiler must implement the
SampleProfile::loadNative() function.
The text format is mostly meant for debugging. Records are separated by
newlines, but each profiler is free to interpret records as it sees fit.
Profilers must implement the SampleProfile::loadText() function.
Finally, the pass will call SampleProfile::emitAnnotations() for each
function in the current translation unit. This function needs to
translate the loaded profile into IR metadata, which the analyzer will
later be able to use.
This patch implements the first steps towards the above design. I've
implemented a sample-based flat profiler. The format of the profile is
fairly simplistic. Each sampled function contains a list of relative
line locations (from the start of the function) together with a count
representing how many samples were collected at that line during
execution. I generate this profile using perf and a separate converter
tool.
Currently, I have only implemented a text format for these profiles. I
am interested in initial feedback to the whole approach before I send
the other parts of the implementation for review.
This patch implements:
- The SampleProfileLoader pass.
- The base ExternalProfile class with the core interface.
- A SampleProfile sub-class using the above interface. The profiler
generates branch weight metadata on every branch instructions that
matches the profiles.
- A text loader class to assist the implementation of
SampleProfile::loadText().
- Basic unit tests for the pass.
Additionally, the patch uses profile information to compute branch
weights based on instruction samples.
This patch converts instruction samples into branch weights. It
does a fairly simplistic conversion:
Given a multi-way branch instruction, it calculates the weight of
each branch based on the maximum sample count gathered from each
target basic block.
Note that this assignment of branch weights is somewhat lossy and can be
misleading. If a basic block has more than one incoming branch, all the
incoming branches will get the same weight. In reality, it may be that
only one of them is the most heavily taken branch.
I will adjust this assignment in subsequent patches.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194566 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-13 12:22:21 +00:00
|
|
|
void initializeSampleProfileLoaderPass(PassRegistry&);
|
2014-09-07 20:05:11 +00:00
|
|
|
void initializeAlignmentFromAssumptionsPass(PassRegistry&);
|
Introduce a BarrierNoop pass, a hack designed to allow *some* control
over the implicitly-formed-and-nesting CGSCC pass manager and function
pass managers, especially when using them on the opt commandline or
using extension points in the module builder. The '-barrier' opt flag
(or the pass itself) will create a no-op module pass in the pipeline,
resetting the pass manager stack, and allowing the creation of a new
pipeline of function passes or CGSCC passes to be created that is
independent from any previous pipelines.
For example, this can be used to test running two CGSCC passes in
independent CGSCC pass managers as opposed to in the same CGSCC pass
manager. It also allows us to introduce a further hack into the
PassManagerBuilder to separate the O0 pipeline extension passes from the
always-inliner's CGSCC pass manager, which they likely do not want to
participate in... At the very least none of the Sanitizer passes want
this behavior.
This fixes a bug with ASan at O0 currently, and I'll commit the ASan
test which covers this pass. I'm happy to add a test case that this pass
exists and works, but not sure how much time folks would like me to
spend adding test cases for the details of its behavior of partition
pass managers.... The whole thing is just vile, and mostly intended to
unblock ASan, so I'm hoping to rip this all out in a brave new pass
manager world.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166172 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-18 08:05:46 +00:00
|
|
|
void initializeBarrierNoopPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeBasicAliasAnalysisPass(PassRegistry&);
|
2013-11-26 04:19:30 +00:00
|
|
|
void initializeCallGraphWrapperPassPass(PassRegistry &);
|
Switch TargetTransformInfo from an immutable analysis pass that requires
a TargetMachine to construct (and thus isn't always available), to an
analysis group that supports layered implementations much like
AliasAnalysis does. This is a pretty massive change, with a few parts
that I was unable to easily separate (sorry), so I'll walk through it.
The first step of this conversion was to make TargetTransformInfo an
analysis group, and to sink the nonce implementations in
ScalarTargetTransformInfo and VectorTargetTranformInfo into
a NoTargetTransformInfo pass. This allows other passes to add a hard
requirement on TTI, and assume they will always get at least on
implementation.
The TargetTransformInfo analysis group leverages the delegation chaining
trick that AliasAnalysis uses, where the base class for the analysis
group delegates to the previous analysis *pass*, allowing all but tho
NoFoo analysis passes to only implement the parts of the interfaces they
support. It also introduces a new trick where each pass in the group
retains a pointer to the top-most pass that has been initialized. This
allows passes to implement one API in terms of another API and benefit
when some other pass above them in the stack has more precise results
for the second API.
The second step of this conversion is to create a pass that implements
the TargetTransformInfo analysis using the target-independent
abstractions in the code generator. This replaces the
ScalarTargetTransformImpl and VectorTargetTransformImpl classes in
lib/Target with a single pass in lib/CodeGen called
BasicTargetTransformInfo. This class actually provides most of the TTI
functionality, basing it upon the TargetLowering abstraction and other
information in the target independent code generator.
The third step of the conversion adds support to all TargetMachines to
register custom analysis passes. This allows building those passes with
access to TargetLowering or other target-specific classes, and it also
allows each target to customize the set of analysis passes desired in
the pass manager. The baseline LLVMTargetMachine implements this
interface to add the BasicTTI pass to the pass manager, and all of the
tools that want to support target-aware TTI passes call this routine on
whatever target machine they end up with to add the appropriate passes.
The fourth step of the conversion created target-specific TTI analysis
passes for the X86 and ARM backends. These passes contain the custom
logic that was previously in their extensions of the
ScalarTargetTransformInfo and VectorTargetTransformInfo interfaces.
I separated them into their own file, as now all of the interface bits
are private and they just expose a function to create the pass itself.
Then I extended these target machines to set up a custom set of analysis
passes, first adding BasicTTI as a fallback, and then adding their
customized TTI implementations.
The fourth step required logic that was shared between the target
independent layer and the specific targets to move to a different
interface, as they no longer derive from each other. As a consequence,
a helper functions were added to TargetLowering representing the common
logic needed both in the target implementation and the codegen
implementation of the TTI pass. While technically this is the only
change that could have been committed separately, it would have been
a nightmare to extract.
The final step of the conversion was just to delete all the old
boilerplate. This got rid of the ScalarTargetTransformInfo and
VectorTargetTransformInfo classes, all of the support in all of the
targets for producing instances of them, and all of the support in the
tools for manually constructing a pass based around them.
Now that TTI is a relatively normal analysis group, two things become
straightforward. First, we can sink it into lib/Analysis which is a more
natural layer for it to live. Second, clients of this interface can
depend on it *always* being available which will simplify their code and
behavior. These (and other) simplifications will follow in subsequent
commits, this one is clearly big enough.
Finally, I'm very aware that much of the comments and documentation
needs to be updated. As soon as I had this working, and plausibly well
commented, I wanted to get it committed and in front of the build bots.
I'll be doing a few passes over documentation later if it sticks.
Commits to update DragonEgg and Clang will be made presently.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@171681 91177308-0d34-0410-b5e6-96231b3b80d8
2013-01-07 01:37:14 +00:00
|
|
|
void initializeBasicTTIPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeBlockExtractorPassPass(PassRegistry&);
|
2011-07-25 19:25:40 +00:00
|
|
|
void initializeBlockFrequencyInfoPass(PassRegistry&);
|
2012-05-22 17:19:09 +00:00
|
|
|
void initializeBoundsCheckingPass(PassRegistry&);
|
2012-02-08 21:22:48 +00:00
|
|
|
void initializeBranchFolderPassPass(PassRegistry&);
|
2011-06-04 01:16:30 +00:00
|
|
|
void initializeBranchProbabilityInfoPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeBreakCriticalEdgesPass(PassRegistry&);
|
2013-01-11 17:28:14 +00:00
|
|
|
void initializeCallGraphPrinterPass(PassRegistry&);
|
|
|
|
|
void initializeCallGraphViewerPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeCFGOnlyPrinterPass(PassRegistry&);
|
|
|
|
|
void initializeCFGOnlyViewerPass(PassRegistry&);
|
|
|
|
|
void initializeCFGPrinterPass(PassRegistry&);
|
2013-08-06 02:43:45 +00:00
|
|
|
void initializeCFGSimplifyPassPass(PassRegistry&);
|
2014-09-02 21:43:13 +00:00
|
|
|
void initializeCFLAliasAnalysisPass(PassRegistry&);
|
2014-11-11 21:08:02 +00:00
|
|
|
void initializeForwardControlFlowIntegrityPass(PassRegistry&);
|
2013-08-06 02:43:45 +00:00
|
|
|
void initializeFlattenCFGPassPass(PassRegistry&);
|
2013-06-19 20:18:24 +00:00
|
|
|
void initializeStructurizeCFGPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeCFGViewerPass(PassRegistry&);
|
2014-01-25 02:02:55 +00:00
|
|
|
void initializeConstantHoistingPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeCodeGenPreparePass(PassRegistry&);
|
|
|
|
|
void initializeConstantMergePass(PassRegistry&);
|
|
|
|
|
void initializeConstantPropagationPass(PassRegistry&);
|
2012-01-07 03:02:36 +00:00
|
|
|
void initializeMachineCopyPropagationPass(PassRegistry&);
|
2012-11-02 21:48:17 +00:00
|
|
|
void initializeCostModelAnalysisPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeCorrelatedValuePropagationPass(PassRegistry&);
|
|
|
|
|
void initializeDAEPass(PassRegistry&);
|
|
|
|
|
void initializeDAHPass(PassRegistry&);
|
|
|
|
|
void initializeDCEPass(PassRegistry&);
|
|
|
|
|
void initializeDSEPass(PassRegistry&);
|
2014-04-15 16:27:38 +00:00
|
|
|
void initializeDebugInfoVerifierLegacyPassPass(PassRegistry &);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeDeadInstEliminationPass(PassRegistry&);
|
|
|
|
|
void initializeDeadMachineInstructionElimPass(PassRegistry&);
|
2013-11-12 22:47:20 +00:00
|
|
|
void initializeDelinearizationPass(PassRegistry &);
|
dependence analysis
Patch from Preston Briggs <preston.briggs@gmail.com>.
This is an updated version of the dependence-analysis patch, including an MIV
test based on Banerjee's inequalities.
It's a fairly complete implementation of the paper
Practical Dependence Testing
Gina Goff, Ken Kennedy, and Chau-Wen Tseng
PLDI 1991
It cannot yet propagate constraints between coupled RDIV subscripts (discussed
in Section 5.3.2 of the paper).
It's organized as a FunctionPass with a single entry point that supports testing
for dependence between two instructions in a function. If there's no dependence,
it returns null. If there's a dependence, it returns a pointer to a Dependence
which can be queried about details (what kind of dependence, is it loop
independent, direction and distance vector entries, etc). I haven't included
every imaginable feature, but there's a good selection that should be adequate
for supporting many loop transformations. Of course, it can be extended as
necessary.
Included in the patch file are many test cases, commented with C code showing
the loops and array references.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165708 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-11 07:32:34 +00:00
|
|
|
void initializeDependenceAnalysisPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeDomOnlyPrinterPass(PassRegistry&);
|
|
|
|
|
void initializeDomOnlyViewerPass(PassRegistry&);
|
|
|
|
|
void initializeDomPrinterPass(PassRegistry&);
|
|
|
|
|
void initializeDomViewerPass(PassRegistry&);
|
|
|
|
|
void initializeDominanceFrontierPass(PassRegistry&);
|
2014-01-13 13:07:17 +00:00
|
|
|
void initializeDominatorTreeWrapperPassPass(PassRegistry&);
|
2012-07-04 00:09:54 +00:00
|
|
|
void initializeEarlyIfConverterPass(PassRegistry&);
|
2011-01-04 21:10:05 +00:00
|
|
|
void initializeEdgeBundlesPass(PassRegistry&);
|
2012-02-08 21:23:13 +00:00
|
|
|
void initializeExpandPostRAPass(PassRegistry&);
|
2011-04-16 01:20:23 +00:00
|
|
|
void initializeGCOVProfilerPass(PassRegistry&);
|
2014-12-08 18:02:35 +00:00
|
|
|
void initializeInstrProfilingPass(PassRegistry&);
|
2011-11-16 01:35:23 +00:00
|
|
|
void initializeAddressSanitizerPass(PassRegistry&);
|
2012-11-28 10:31:36 +00:00
|
|
|
void initializeAddressSanitizerModulePass(PassRegistry&);
|
2012-11-29 09:57:20 +00:00
|
|
|
void initializeMemorySanitizerPass(PassRegistry&);
|
2012-02-13 22:50:51 +00:00
|
|
|
void initializeThreadSanitizerPass(PassRegistry&);
|
2014-11-11 22:14:37 +00:00
|
|
|
void initializeSanitizerCoverageModulePass(PassRegistry&);
|
2013-08-07 22:47:18 +00:00
|
|
|
void initializeDataFlowSanitizerPass(PassRegistry&);
|
2013-11-22 16:58:05 +00:00
|
|
|
void initializeScalarizerPass(PassRegistry&);
|
2015-01-27 01:34:14 +00:00
|
|
|
void initializeEarlyCSELegacyPassPass(PassRegistry &);
|
2010-11-18 18:45:06 +00:00
|
|
|
void initializeExpandISelPseudosPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeFunctionAttrsPass(PassRegistry&);
|
2012-02-08 21:23:13 +00:00
|
|
|
void initializeGCMachineCodeAnalysisPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeGCModuleInfoPass(PassRegistry&);
|
|
|
|
|
void initializeGVNPass(PassRegistry&);
|
|
|
|
|
void initializeGlobalDCEPass(PassRegistry&);
|
|
|
|
|
void initializeGlobalOptPass(PassRegistry&);
|
|
|
|
|
void initializeGlobalsModRefPass(PassRegistry&);
|
|
|
|
|
void initializeIPCPPass(PassRegistry&);
|
|
|
|
|
void initializeIPSCCPPass(PassRegistry&);
|
|
|
|
|
void initializeIVUsersPass(PassRegistry&);
|
|
|
|
|
void initializeIfConverterPass(PassRegistry&);
|
2015-01-16 01:03:22 +00:00
|
|
|
void initializeInductiveRangeCheckEliminationPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeIndVarSimplifyPass(PassRegistry&);
|
2013-01-21 11:39:18 +00:00
|
|
|
void initializeInlineCostAnalysisPass(PassRegistry&);
|
2015-01-20 22:44:35 +00:00
|
|
|
void initializeInstructionCombiningPassPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeInstCountPass(PassRegistry&);
|
|
|
|
|
void initializeInstNamerPass(PassRegistry&);
|
|
|
|
|
void initializeInternalizePassPass(PassRegistry&);
|
|
|
|
|
void initializeIntervalPartitionPass(PassRegistry&);
|
2014-06-05 19:29:43 +00:00
|
|
|
void initializeJumpInstrTableInfoPass(PassRegistry&);
|
|
|
|
|
void initializeJumpInstrTablesPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeJumpThreadingPass(PassRegistry&);
|
|
|
|
|
void initializeLCSSAPass(PassRegistry&);
|
|
|
|
|
void initializeLICMPass(PassRegistry&);
|
|
|
|
|
void initializeLazyValueInfoPass(PassRegistry&);
|
|
|
|
|
void initializeLibCallAliasAnalysisPass(PassRegistry&);
|
|
|
|
|
void initializeLintPass(PassRegistry&);
|
2010-11-30 02:17:10 +00:00
|
|
|
void initializeLiveDebugVariablesPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeLiveIntervalsPass(PassRegistry&);
|
2012-06-09 02:13:10 +00:00
|
|
|
void initializeLiveRegMatrixPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeLiveStacksPass(PassRegistry&);
|
|
|
|
|
void initializeLiveVariablesPass(PassRegistry&);
|
|
|
|
|
void initializeLoaderPassPass(PassRegistry&);
|
2012-02-08 21:23:13 +00:00
|
|
|
void initializeLocalStackSlotPassPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeLoopDeletionPass(PassRegistry&);
|
|
|
|
|
void initializeLoopExtractorPass(PassRegistry&);
|
2015-01-17 14:16:18 +00:00
|
|
|
void initializeLoopInfoWrapperPassPass(PassRegistry&);
|
2011-01-03 00:25:16 +00:00
|
|
|
void initializeLoopInstSimplifyPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeLoopRotatePass(PassRegistry&);
|
|
|
|
|
void initializeLoopSimplifyPass(PassRegistry&);
|
|
|
|
|
void initializeLoopStrengthReducePass(PassRegistry&);
|
2011-10-17 17:17:43 +00:00
|
|
|
void initializeGlobalMergePass(PassRegistry&);
|
2013-11-16 23:59:05 +00:00
|
|
|
void initializeLoopRerollPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeLoopUnrollPass(PassRegistry&);
|
|
|
|
|
void initializeLoopUnswitchPass(PassRegistry&);
|
2010-12-26 19:32:44 +00:00
|
|
|
void initializeLoopIdiomRecognizePass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeLowerAtomicPass(PassRegistry&);
|
2011-07-06 18:22:43 +00:00
|
|
|
void initializeLowerExpectIntrinsicPass(PassRegistry&);
|
2010-10-19 17:21:58 +00:00
|
|
|
void initializeLowerIntrinsicsPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeLowerInvokePass(PassRegistry&);
|
|
|
|
|
void initializeLowerSwitchPass(PassRegistry&);
|
2011-07-25 19:25:40 +00:00
|
|
|
void initializeMachineBlockFrequencyInfoPass(PassRegistry&);
|
Implement a block placement pass based on the branch probability and
block frequency analyses. This differs substantially from the existing
block-placement pass in LLVM:
1) It operates on the Machine-IR in the CodeGen layer. This exposes much
more (and more precise) information and opportunities. Also, the
results are more stable due to fewer transforms ocurring after the
pass runs.
2) It uses the generalized probability and frequency analyses. These can
model static heuristics, code annotation derived heuristics as well
as eventual profile loading. By basing the optimization on the
analysis interface it can work from any (or a combination) of these
inputs.
3) It uses a more aggressive algorithm, both building chains from tho
bottom up to maximize benefit, and using an SCC-based walk to layout
chains of blocks in a profitable ordering without O(N^2) iterations
which the old pass involves.
The pass is currently gated behind a flag, and not enabled by default
because it still needs to grow some important features. Most notably, it
needs to support loop aligning and careful layout of loop structures
much as done by hand currently in CodePlacementOpt. Once it supports
these, and has sufficient testing and quality tuning, it should replace
both of these passes.
Thanks to Nick Lewycky and Richard Smith for help authoring & debugging
this, and to Jakob, Andy, Eric, Jim, and probably a few others I'm
forgetting for reviewing and answering all my questions. Writing
a backend pass is *sooo* much better now than it used to be. =D
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@142641 91177308-0d34-0410-b5e6-96231b3b80d8
2011-10-21 06:46:38 +00:00
|
|
|
void initializeMachineBlockPlacementPass(PassRegistry&);
|
2011-11-02 07:17:12 +00:00
|
|
|
void initializeMachineBlockPlacementStatsPass(PassRegistry&);
|
2011-06-16 20:22:37 +00:00
|
|
|
void initializeMachineBranchProbabilityInfoPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeMachineCSEPass(PassRegistry&);
|
|
|
|
|
void initializeMachineDominatorTreePass(PassRegistry&);
|
2014-07-12 21:59:52 +00:00
|
|
|
void initializeMachineDominanceFrontierPass(PassRegistry&);
|
2012-09-17 14:08:37 +00:00
|
|
|
void initializeMachinePostDominatorTreePass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeMachineLICMPass(PassRegistry&);
|
|
|
|
|
void initializeMachineLoopInfoPass(PassRegistry&);
|
|
|
|
|
void initializeMachineModuleInfoPass(PassRegistry&);
|
2014-07-19 18:29:29 +00:00
|
|
|
void initializeMachineRegionInfoPassPass(PassRegistry&);
|
2012-01-17 06:55:03 +00:00
|
|
|
void initializeMachineSchedulerPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeMachineSinkingPass(PassRegistry&);
|
2012-07-26 18:38:11 +00:00
|
|
|
void initializeMachineTraceMetricsPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeMachineVerifierPassPass(PassRegistry&);
|
|
|
|
|
void initializeMemCpyOptPass(PassRegistry&);
|
|
|
|
|
void initializeMemDepPrinterPass(PassRegistry&);
|
|
|
|
|
void initializeMemoryDependenceAnalysisPass(PassRegistry&);
|
2014-07-18 19:13:09 +00:00
|
|
|
void initializeMergedLoadStoreMotionPass(PassRegistry &);
|
2012-09-11 02:46:18 +00:00
|
|
|
void initializeMetaRenamerPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeMergeFunctionsPass(PassRegistry&);
|
|
|
|
|
void initializeModuleDebugInfoPrinterPass(PassRegistry&);
|
|
|
|
|
void initializeNoAAPass(PassRegistry&);
|
2011-06-15 23:37:01 +00:00
|
|
|
void initializeObjCARCAliasAnalysisPass(PassRegistry&);
|
2012-01-17 20:52:24 +00:00
|
|
|
void initializeObjCARCAPElimPass(PassRegistry&);
|
2011-06-15 23:37:01 +00:00
|
|
|
void initializeObjCARCExpandPass(PassRegistry&);
|
|
|
|
|
void initializeObjCARCContractPass(PassRegistry&);
|
|
|
|
|
void initializeObjCARCOptPass(PassRegistry&);
|
2014-11-17 02:28:27 +00:00
|
|
|
void initializePAEvalPass(PassRegistry &);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeOptimizePHIsPass(PassRegistry&);
|
2013-08-23 10:27:02 +00:00
|
|
|
void initializePartiallyInlineLibCallsPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializePEIPass(PassRegistry&);
|
|
|
|
|
void initializePHIEliminationPass(PassRegistry&);
|
|
|
|
|
void initializePartialInlinerPass(PassRegistry&);
|
|
|
|
|
void initializePeepholeOptimizerPass(PassRegistry&);
|
|
|
|
|
void initializePostDomOnlyPrinterPass(PassRegistry&);
|
|
|
|
|
void initializePostDomOnlyViewerPass(PassRegistry&);
|
|
|
|
|
void initializePostDomPrinterPass(PassRegistry&);
|
|
|
|
|
void initializePostDomViewerPass(PassRegistry&);
|
|
|
|
|
void initializePostDominatorTreePass(PassRegistry&);
|
2012-02-08 21:23:13 +00:00
|
|
|
void initializePostRASchedulerPass(PassRegistry&);
|
2013-12-28 21:56:51 +00:00
|
|
|
void initializePostMachineSchedulerPass(PassRegistry&);
|
2014-01-12 12:15:39 +00:00
|
|
|
void initializePrintFunctionPassWrapperPass(PassRegistry&);
|
|
|
|
|
void initializePrintModulePassWrapperPass(PassRegistry&);
|
2013-02-08 23:37:41 +00:00
|
|
|
void initializePrintBasicBlockPassPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeProcessImplicitDefsPass(PassRegistry&);
|
|
|
|
|
void initializePromotePassPass(PassRegistry&);
|
|
|
|
|
void initializePruneEHPass(PassRegistry&);
|
|
|
|
|
void initializeReassociatePass(PassRegistry&);
|
|
|
|
|
void initializeRegToMemPass(PassRegistry&);
|
2014-07-19 18:29:29 +00:00
|
|
|
void initializeRegionInfoPassPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeRegionOnlyPrinterPass(PassRegistry&);
|
|
|
|
|
void initializeRegionOnlyViewerPass(PassRegistry&);
|
|
|
|
|
void initializeRegionPrinterPass(PassRegistry&);
|
|
|
|
|
void initializeRegionViewerPass(PassRegistry&);
|
|
|
|
|
void initializeSCCPPass(PassRegistry&);
|
Introduce a new SROA implementation.
This is essentially a ground up re-think of the SROA pass in LLVM. It
was initially inspired by a few problems with the existing pass:
- It is subject to the bane of my existence in optimizations: arbitrary
thresholds.
- It is overly conservative about which constructs can be split and
promoted.
- The vector value replacement aspect is separated from the splitting
logic, missing many opportunities where splitting and vector value
formation can work together.
- The splitting is entirely based around the underlying type of the
alloca, despite this type often having little to do with the reality
of how that memory is used. This is especially prevelant with unions
and base classes where we tail-pack derived members.
- When splitting fails (often due to the thresholds), the vector value
replacement (again because it is separate) can kick in for
preposterous cases where we simply should have split the value. This
results in forming i1024 and i2048 integer "bit vectors" that
tremendously slow down subsequnet IR optimizations (due to large
APInts) and impede the backend's lowering.
The new design takes an approach that fundamentally is not susceptible
to many of these problems. It is the result of a discusison between
myself and Duncan Sands over IRC about how to premptively avoid these
types of problems and how to do SROA in a more principled way. Since
then, it has evolved and grown, but this remains an important aspect: it
fixes real world problems with the SROA process today.
First, the transform of SROA actually has little to do with replacement.
It has more to do with splitting. The goal is to take an aggregate
alloca and form a composition of scalar allocas which can replace it and
will be most suitable to the eventual replacement by scalar SSA values.
The actual replacement is performed by mem2reg (and in the future
SSAUpdater).
The splitting is divided into four phases. The first phase is an
analysis of the uses of the alloca. This phase recursively walks uses,
building up a dense datastructure representing the ranges of the
alloca's memory actually used and checking for uses which inhibit any
aspects of the transform such as the escape of a pointer.
Once we have a mapping of the ranges of the alloca used by individual
operations, we compute a partitioning of the used ranges. Some uses are
inherently splittable (such as memcpy and memset), while scalar uses are
not splittable. The goal is to build a partitioning that has the minimum
number of splits while placing each unsplittable use in its own
partition. Overlapping unsplittable uses belong to the same partition.
This is the target split of the aggregate alloca, and it maximizes the
number of scalar accesses which become accesses to their own alloca and
candidates for promotion.
Third, we re-walk the uses of the alloca and assign each specific memory
access to all the partitions touched so that we have dense use-lists for
each partition.
Finally, we build a new, smaller alloca for each partition and rewrite
each use of that partition to use the new alloca. During this phase the
pass will also work very hard to transform uses of an alloca into a form
suitable for promotion, including forming vector operations, speculating
loads throguh PHI nodes and selects, etc.
After splitting is complete, each newly refined alloca that is
a candidate for promotion to a scalar SSA value is run through mem2reg.
There are lots of reasonably detailed comments in the source code about
the design and algorithms, and I'm going to be trying to improve them in
subsequent commits to ensure this is well documented, as the new pass is
in many ways more complex than the old one.
Some of this is still a WIP, but the current state is reasonbly stable.
It has passed bootstrap, the nightly test suite, and Duncan has run it
successfully through the ACATS and DragonEgg test suites. That said, it
remains behind a default-off flag until the last few pieces are in
place, and full testing can be done.
Specific areas I'm looking at next:
- Improved comments and some code cleanup from reviews.
- SSAUpdater and enabling this pass inside the CGSCC pass manager.
- Some datastructure tuning and compile-time measurements.
- More aggressive FCA splitting and vector formation.
Many thanks to Duncan Sands for the thorough final review, as well as
Benjamin Kramer for lots of review during the process of writing this
pass, and Daniel Berlin for reviewing the data structures and algorithms
and general theory of the pass. Also, several other people on IRC, over
lunch tables, etc for lots of feedback and advice.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@163883 91177308-0d34-0410-b5e6-96231b3b80d8
2012-09-14 09:22:59 +00:00
|
|
|
void initializeSROAPass(PassRegistry&);
|
2011-01-18 03:53:26 +00:00
|
|
|
void initializeSROA_DTPass(PassRegistry&);
|
2011-01-14 08:13:00 +00:00
|
|
|
void initializeSROA_SSAUpPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeScalarEvolutionAliasAnalysisPass(PassRegistry&);
|
|
|
|
|
void initializeScalarEvolutionPass(PassRegistry&);
|
|
|
|
|
void initializeSimpleInlinerPass(PassRegistry&);
|
2011-06-26 22:34:10 +00:00
|
|
|
void initializeRegisterCoalescerPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeSingleLoopExtractorPass(PassRegistry&);
|
|
|
|
|
void initializeSinkingPass(PassRegistry&);
|
2014-05-01 18:38:36 +00:00
|
|
|
void initializeSeparateConstOffsetFromGEPPass(PassRegistry &);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeSlotIndexesPass(PassRegistry&);
|
2011-01-06 01:21:53 +00:00
|
|
|
void initializeSpillPlacementPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeStackProtectorPass(PassRegistry&);
|
2012-09-06 09:17:37 +00:00
|
|
|
void initializeStackColoringPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeStackSlotColoringPass(PassRegistry&);
|
|
|
|
|
void initializeStripDeadDebugInfoPass(PassRegistry&);
|
|
|
|
|
void initializeStripDeadPrototypesPassPass(PassRegistry&);
|
|
|
|
|
void initializeStripDebugDeclarePass(PassRegistry&);
|
|
|
|
|
void initializeStripNonDebugSymbolsPass(PassRegistry&);
|
|
|
|
|
void initializeStripSymbolsPass(PassRegistry&);
|
|
|
|
|
void initializeTailCallElimPass(PassRegistry&);
|
2012-02-08 21:23:13 +00:00
|
|
|
void initializeTailDuplicatePassPass(PassRegistry&);
|
2012-02-04 02:56:45 +00:00
|
|
|
void initializeTargetPassConfigPass(PassRegistry&);
|
2014-02-25 17:30:31 +00:00
|
|
|
void initializeDataLayoutPassPass(PassRegistry &);
|
2013-01-05 11:43:11 +00:00
|
|
|
void initializeTargetTransformInfoAnalysisGroup(PassRegistry&);
|
2014-09-18 00:34:14 +00:00
|
|
|
void initializeFunctionTargetTransformInfoPass(PassRegistry &);
|
2013-01-05 11:43:11 +00:00
|
|
|
void initializeNoTTIPass(PassRegistry&);
|
2015-01-15 10:41:28 +00:00
|
|
|
void initializeTargetLibraryInfoWrapperPassPass(PassRegistry &);
|
2015-01-04 12:03:27 +00:00
|
|
|
void initializeAssumptionCacheTrackerPass(PassRegistry &);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeTwoAddressInstructionPassPass(PassRegistry&);
|
|
|
|
|
void initializeTypeBasedAliasAnalysisPass(PassRegistry&);
|
Add scoped-noalias metadata
This commit adds scoped noalias metadata. The primary motivations for this
feature are:
1. To preserve noalias function attribute information when inlining
2. To provide the ability to model block-scope C99 restrict pointers
Neither of these two abilities are added here, only the necessary
infrastructure. In fact, there should be no change to existing functionality,
only the addition of new features. The logic that converts noalias function
parameters into this metadata during inlining will come in a follow-up commit.
What is added here is the ability to generally specify noalias memory-access
sets. Regarding the metadata, alias-analysis scopes are defined similar to TBAA
nodes:
!scope0 = metadata !{ metadata !"scope of foo()" }
!scope1 = metadata !{ metadata !"scope 1", metadata !scope0 }
!scope2 = metadata !{ metadata !"scope 2", metadata !scope0 }
!scope3 = metadata !{ metadata !"scope 2.1", metadata !scope2 }
!scope4 = metadata !{ metadata !"scope 2.2", metadata !scope2 }
Loads and stores can be tagged with an alias-analysis scope, and also, with a
noalias tag for a specific scope:
... = load %ptr1, !alias.scope !{ !scope1 }
... = load %ptr2, !alias.scope !{ !scope1, !scope2 }, !noalias !{ !scope1 }
When evaluating an aliasing query, if one of the instructions is associated
with an alias.scope id that is identical to the noalias scope associated with
the other instruction, or is a descendant (in the scope hierarchy) of the
noalias scope associated with the other instruction, then the two memory
accesses are assumed not to alias.
Note that is the first element of the scope metadata is a string, then it can
be combined accross functions and translation units. The string can be replaced
by a self-reference to create globally unqiue scope identifiers.
[Note: This overview is slightly stylized, since the metadata nodes really need
to just be numbers (!0 instead of !scope0), and the scope lists are also global
unnamed metadata.]
Existing noalias metadata in a callee is "cloned" for use by the inlined code.
This is necessary because the aliasing scopes are unique to each call site
(because of possible control dependencies on the aliasing properties). For
example, consider a function: foo(noalias a, noalias b) { *a = *b; } that gets
inlined into bar() { ... if (...) foo(a1, b1); ... if (...) foo(a2, b2); } --
now just because we know that a1 does not alias with b1 at the first call site,
and a2 does not alias with b2 at the second call site, we cannot let inlining
these functons have the metadata imply that a1 does not alias with b2.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213864 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-24 14:25:39 +00:00
|
|
|
void initializeScopedNoAliasAAPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeUnifyFunctionExitNodesPass(PassRegistry&);
|
|
|
|
|
void initializeUnreachableBlockElimPass(PassRegistry&);
|
|
|
|
|
void initializeUnreachableMachineBlockElimPass(PassRegistry&);
|
2014-01-20 11:34:08 +00:00
|
|
|
void initializeVerifierLegacyPassPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
void initializeVirtRegMapPass(PassRegistry&);
|
2012-06-08 23:44:45 +00:00
|
|
|
void initializeVirtRegRewriterPass(PassRegistry&);
|
2010-12-20 20:54:37 +00:00
|
|
|
void initializeInstSimplifierPass(PassRegistry&);
|
2011-12-14 02:11:42 +00:00
|
|
|
void initializeUnpackMachineBundlesPass(PassRegistry&);
|
2012-01-19 07:47:03 +00:00
|
|
|
void initializeFinalizeMachineBundlesPass(PassRegistry&);
|
2012-10-17 18:25:06 +00:00
|
|
|
void initializeLoopVectorizePass(PassRegistry&);
|
2013-04-09 19:44:35 +00:00
|
|
|
void initializeSLPVectorizerPass(PassRegistry&);
|
2012-02-01 03:51:43 +00:00
|
|
|
void initializeBBVectorizePass(PassRegistry&);
|
2012-05-30 00:17:12 +00:00
|
|
|
void initializeMachineFunctionPrinterPassPass(PassRegistry&);
|
2013-12-14 06:53:06 +00:00
|
|
|
void initializeStackMapLivenessPass(PassRegistry&);
|
2014-08-03 21:35:39 +00:00
|
|
|
void initializeMachineCombinerPass(PassRegistry &);
|
2014-05-29 01:55:07 +00:00
|
|
|
void initializeLoadCombinePass(PassRegistry&);
|
2014-11-07 21:32:08 +00:00
|
|
|
void initializeRewriteSymbolsPass(PassRegistry&);
|
2010-10-07 04:17:38 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#endif
|
