IRCE eliminates range checks of the form
0 <= A * I + B < Length
by splitting a loop's iteration space into three segments in a way
that the check is completely redundant in the middle segment. As an
example, IRCE will convert
len = < known positive >
for (i = 0; i < n; i++) {
if (0 <= i && i < len) {
do_something();
} else {
throw_out_of_bounds();
}
}
to
len = < known positive >
limit = smin(n, len)
// no first segment
for (i = 0; i < limit; i++) {
if (0 <= i && i < len) { // this check is fully redundant
do_something();
} else {
throw_out_of_bounds();
}
}
for (i = limit; i < n; i++) {
if (0 <= i && i < len) {
do_something();
} else {
throw_out_of_bounds();
}
}
IRCE can deal with multiple range checks in the same loop (it takes
the intersection of the ranges that will make each of them redundant
individually).
Currently IRCE does not do any profitability analysis. That is a
TODO.
Please note that the status of this pass is *experimental*, and it is
not part of any default pass pipeline. Having said that, I will love
to get feedback and general input from people interested in trying
this out.
This pass was originally r226201. It was reverted because it used C++
features not supported by MSVC 2012.
Differential Revision: http://reviews.llvm.org/D6693
llvm-svn: 226238
The change used C++11 features not supported by MSVC 2012. I will fix
the change to use things supported MSVC 2012 and recommit shortly.
llvm-svn: 226216
IRCE eliminates range checks of the form
0 <= A * I + B < Length
by splitting a loop's iteration space into three segments in a way
that the check is completely redundant in the middle segment. As an
example, IRCE will convert
len = < known positive >
for (i = 0; i < n; i++) {
if (0 <= i && i < len) {
do_something();
} else {
throw_out_of_bounds();
}
}
to
len = < known positive >
limit = smin(n, len)
// no first segment
for (i = 0; i < limit; i++) {
if (0 <= i && i < len) { // this check is fully redundant
do_something();
} else {
throw_out_of_bounds();
}
}
for (i = limit; i < n; i++) {
if (0 <= i && i < len) {
do_something();
} else {
throw_out_of_bounds();
}
}
IRCE can deal with multiple range checks in the same loop (it takes
the intersection of the ranges that will make each of them redundant
individually).
Currently IRCE does not do any profitability analysis. That is a
TODO.
Please note that the status of this pass is *experimental*, and it is
not part of any default pass pipeline. Having said that, I will love
to get feedback and general input from people interested in trying
this out.
Differential Revision: http://reviews.llvm.org/D6693
llvm-svn: 226201
This adds a ScalarEvolution-powered transformation that updates load, store and
memory intrinsic pointer alignments based on invariant((a+q) & b == 0)
expressions. Many of the simple cases we can get with ValueTracking, but we
still need something like this for the more complicated cases (such as those
with an offset) that require some algebra. Note that gcc's
__builtin_assume_aligned's optional third argument provides exactly for this
kind of 'misalignment' offset for which this kind of logic is necessary.
The primary motivation is to fixup alignments for vector loads/stores after
vectorization (and unrolling). This pass is added to the optimization pipeline
just after the SLP vectorizer runs (which, admittedly, does not preserve SE,
although I imagine it could). Regardless, I actually don't think that the
preservation matters too much in this case: SE computes lazily, and this pass
won't issue any SE queries unless there are any assume intrinsics, so there
should be no real additional cost in the common case (SLP does preserve DT and
LoopInfo).
llvm-svn: 217344
Merges equivalent loads on both sides of a hammock/diamond
and hoists into into the header.
Merges equivalent stores on both sides of a hammock/diamond
and sinks it to the footer.
Can enable if conversion and tolerate better load misses
and store operand latencies.
llvm-svn: 213396
This patch is to move GlobalMerge pass from Transform/Scalar
to CodeGen, because GlobalMerge depends on TargetMachine.
In the mean time, the macro INITIALIZE_TM_PASS is also moved
to CodeGen/Passes.h. With this fix we can avoid making
libScalarOpts depend on libCodeGen.
llvm-svn: 210951
CodeGenPrepare uses extensively TargetLowering which is part of libLLVMCodeGen.
This is a layer violation which would introduce eventually a dependence on
CodeGen in ScalarOpts.
Move CodeGenPrepare into libLLVMCodeGen to avoid that.
Follow-up of <rdar://problem/15519855>
llvm-svn: 201912
This commit caused -Woverloaded-virtual warnings. The two new
TargetTransformInfo::getIntImmCost functions were only added to the superclass,
and to the X86 subclass. The other targets were not updated, and the
warning highlighted this by pointing out that e.g. ARMTTI::getIntImmCost was
hiding the two new getIntImmCost variants.
We could pacify the warning by adding "using TargetTransformInfo::getIntImmCost"
to the various subclasses, or turning it off, but I suspect that it's wrong to
leave the functions unimplemnted in those targets. The default implementations
return TCC_Free, which I don't think is right e.g. for ARM.
llvm-svn: 200058
Retry commit r200022 with a fix for the build bot errors. Constant expressions
have (unlike instructions) module scope use lists and therefore may have users
in different functions. The fix is to simply ignore these out-of-function uses.
llvm-svn: 200034
This pass identifies expensive constants to hoist and coalesces them to
better prepare it for SelectionDAG-based code generation. This works around the
limitations of the basic-block-at-a-time approach.
First it scans all instructions for integer constants and calculates its
cost. If the constant can be folded into the instruction (the cost is
TCC_Free) or the cost is just a simple operation (TCC_BASIC), then we don't
consider it expensive and leave it alone. This is the default behavior and
the default implementation of getIntImmCost will always return TCC_Free.
If the cost is more than TCC_BASIC, then the integer constant can't be folded
into the instruction and it might be beneficial to hoist the constant.
Similar constants are coalesced to reduce register pressure and
materialization code.
When a constant is hoisted, it is also hidden behind a bitcast to force it to
be live-out of the basic block. Otherwise the constant would be just
duplicated and each basic block would have its own copy in the SelectionDAG.
The SelectionDAG recognizes such constants as opaque and doesn't perform
certain transformations on them, which would create a new expensive constant.
This optimization is only applied to integer constants in instructions and
simple (this means not nested) constant cast experessions. For example:
%0 = load i64* inttoptr (i64 big_constant to i64*)
Reviewed by Eric
llvm-svn: 200022
This adds a loop rerolling pass: the opposite of (partial) loop unrolling. The
transformation aims to take loops like this:
for (int i = 0; i < 3200; i += 5) {
a[i] += alpha * b[i];
a[i + 1] += alpha * b[i + 1];
a[i + 2] += alpha * b[i + 2];
a[i + 3] += alpha * b[i + 3];
a[i + 4] += alpha * b[i + 4];
}
and turn them into this:
for (int i = 0; i < 3200; ++i) {
a[i] += alpha * b[i];
}
and loops like this:
for (int i = 0; i < 500; ++i) {
x[3*i] = foo(0);
x[3*i+1] = foo(0);
x[3*i+2] = foo(0);
}
and turn them into this:
for (int i = 0; i < 1500; ++i) {
x[i] = foo(0);
}
There are two motivations for this transformation:
1. Code-size reduction (especially relevant, obviously, when compiling for
code size).
2. Providing greater choice to the loop vectorizer (and generic unroller) to
choose the unrolling factor (and a better ability to vectorize). The loop
vectorizer can take vector lengths and register pressure into account when
choosing an unrolling factor, for example, and a pre-unrolled loop limits that
choice. This is especially problematic if the manual unrolling was optimized
for a machine different from the current target.
The current implementation is limited to single basic-block loops only. The
rerolling recognition should work regardless of how the loop iterations are
intermixed within the loop body (subject to dependency and side-effect
constraints), but the significant restriction is that the order of the
instructions in each iteration must be identical. This seems sufficient to
capture all current use cases.
This pass is not currently enabled by default at any optimization level.
llvm-svn: 194939
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.
llvm-svn: 194566
This pass was based on the previous (essentially unused) profiling
infrastructure and the assumption that by ordering the basic blocks at
the IR level in a particular way, the correct layout would happen in the
end. This sometimes worked, and mostly didn't. It also was a really
naive implementation of the classical paper that dates from when branch
predictors were primarily directional and when loop structure wasn't
commonly available. It also didn't factor into the equation
non-fallthrough branches and other machine level details.
Anyways, for all of these reasons and more, I wrote
MachineBlockPlacement, which completely supercedes this pass. It both
uses modern profile information infrastructure, and actually works. =]
llvm-svn: 190748
...so that it can be used for z too. Most of the code is the same.
The only real change is to use TargetTransformInfo to test when a sqrt
instruction is available.
The pass is opt-in because at the moment it only handles sqrt.
llvm-svn: 189097
This commit completely removes what is left of the simplify-libcalls
pass. All of the functionality has now been migrated to the instcombine
and functionattrs passes. The following C API functions are now NOPs:
1. LLVMAddSimplifyLibCallsPass
2. LLVMPassManagerBuilderSetDisableSimplifyLibCalls
llvm-svn: 184459
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.
llvm-svn: 163883
specified in the same file that the library itself is created. This is
more idiomatic for CMake builds, and also allows us to correctly specify
dependencies that are missed due to bugs in the GenLibDeps perl script,
or change from compiler to compiler. On Linux, this returns CMake to
a place where it can relably rebuild several targets of LLVM.
I have tried not to change the dependencies from the ones in the current
auto-generated file. The only places I've really diverged are in places
where I was seeing link failures, and added a dependency. The goal of
this patch is not to start changing the dependencies, merely to move
them into the correct location, and an explicit form that we can control
and change when necessary.
This also removes a serialization point in the build because we don't
have to scan all the libraries before we begin building various tools.
We no longer have a step of the build that regenerates a file inside the
source tree. A few other associated cleanups fall out of this.
This isn't really finished yet though. After talking to dgregor he urged
switching to a single CMake macro to construct libraries with both
sources and dependencies in the arguments. Migrating from the two macros
to that style will be a follow-up patch.
Also, llvm-config is still generated with GenLibDeps.pl, which means it
still has slightly buggy dependencies. The internal CMake
'llvm-config-like' macro uses the correct explicitly specified
dependencies however. A future patch will switch llvm-config generation
(when using CMake) to be based on these deps as well.
This may well break Windows. I'm getting a machine set up now to dig
into any failures there. If anyone can chime in with problems they see
or ideas of how to solve them for Windows, much appreciated.
llvm-svn: 136433
of instcombine that is currently in the middle of the loop pass pipeline. This
commit only checks in the pass; it will hopefully be enabled by default later.
llvm-svn: 122719
