If the GEP instructions give us enough insights, model scalar accesses as
multi-dimensional (and generate the relevant run-time checks to ensure
correctness). This will allow us to simplify the dependence computation in
a subsequent commit.
llvm-svn: 247906
This will allow to generate non-wrap assumptions for integer expressions
that are part of the SCoP. We compare the common isl representation of
the expression with one computed with modulo semantic. For all parameter
combinations they are not equal we can have integer overflows.
The nsw flags are respected when the modulo representation is computed,
nuw and nw flags are ignored for now.
In order to not increase compile time to much, the non-wrap assumptions
are collected in a separate boundary context instead of the assumed
context. This helps compile time as the boundary context can become
complex and it is therefor not advised to use it in other operations
except runtime check generation. However, the assumed context is e.g.,
used to tighten dependences. While the boundary context might help to
tighten the assumed context it is doubtful that it will help in practice
(it does not effect lnt much) as the boundary (or no-wrap assumptions)
only restrict the very end of the possible value range of parameters.
PET uses a different approach to compute the no-wrap context, though lnt runs
have shown that this version performs slightly better for us.
llvm-svn: 247732
Due to the new domain generation, the SCoP keeps track of the domain
for all blocks, thus the SCEVAffinator can now work with blocks to avoid
duplication of the domains.
llvm-svn: 247731
At some point we build loop trip counts using this method. It was replaced by
a simpler trick that works only for affine (e.g., not modulo) constraints and
relies on the removal of unbounded parts. In order to allow modulo constrains
again we go back to the former, more accurate method.
llvm-svn: 247540
Summary:
TempScop is basically a holder for AccFuncMap, the dictionary from BasicBlocks to IRAccess lists. We move the list into polly::Scop and remove the polly::TempScop class.
There is one small change in behavior: If ScopInfo finds that its AssumedContext is impossible, it bails out by deleting the Scop object. The TempScop::print (invoked with opt -polly-scops -analyze) cannot print the AccFuncMap anymore as it would with a separate TempScop.
Differential Revision: http://reviews.llvm.org/D12803
llvm-svn: 247480
Hoist runtime checks in the loop nest if they guard an "error" like event.
Such events are recognized as blocks with an unreachable terminator or a call
to the ubsan function that deals with out of bound accesses. Other "error"
events can be added easily.
We will ignore these blocks when we detect/model/optmize and code generate SCoPs
but we will make sure that they would not have been executed using the assumption
framework.
llvm-svn: 247310
As we do not rely on ScalarEvolution any more we do not need to get
the backedge taken count. Additionally, our domain generation handles
everything that is affine and has one latch and our ScopDetection will
over-approximate everything else.
This change will therefor allow loops with:
- one latch
- exiting conditions that are affine
Additionally, it will not check for structured control flow anymore.
Hence, loops and conditionals are not necessarily single entry single
exit regions any more.
Differential Version: http://reviews.llvm.org/D12758
llvm-svn: 247289
The TempScopInfo (-polly-analyze-ir) pass is removed and its work taken
over by ScopInfo (-polly-scops). Several tests depend on
-polly-analyze-ir and use -polly-scops instead which for the moment
prints the output of both passes. This again is not expected by some
other tests, especially those with negative searches, which have been
adapted.
Differential Version: http://reviews.llvm.org/D12694
llvm-svn: 247288
This patch replaces the last legacy part of the domain generation, namely the
ScalarEvolution part that was used to obtain loop bounds. We now iterate over
the loops in the region and propagate the back edge condition to the header
blocks. Afterwards we propagate the new information once through the whole
region. In this process we simply ignore unbounded parts of the domain and
thereby assume the absence of infinite loops.
+ This patch already identified a couple of broken unit tests we had for
years.
+ We allow more loops already and the step to multiple exit and multiple back
edges is minimal.
+ It allows to model the overflow checks properly as we actually visit
every block in the SCoP and know where which condition is evaluated.
- It is currently not compatible with modulo constraints in the
domain.
Differential Revision: http://reviews.llvm.org/D12499
llvm-svn: 247279
The support for modulo expressions is not comlete and makes the new
domain generation harder. As the currently broken domain generation
needs to be replaced, we will first swap in the new, fixed domain
generation and make it compatible with the modulo expressions later.
llvm-svn: 247278
This prepares for a series of patches that merges TempScopInfo into ScopInfo to
reduce Polly's code complexity. Only ScopInfo.{cpp|h} will be left thereafter.
Moving the code of TempScopInfo in one commit makes the mains diffs simpler to
understand.
In detail, merging the following classes is planned:
TempScopInfo into ScopInfo
TempScop into Scop
IRAccess into MemoryAccess
Only moving code, no functional changes intended.
Differential Version: http://reviews.llvm.org/D12693
llvm-svn: 247274
The support for pointer expressions is broken as it can only handle
some patterns in the IslExprBuilder. We should to treat pointers in
expressions the same as integers at some point and revert this patch.
llvm-svn: 247147
Add a custom makefile rule to generate lib/External/isl/gitversion.h
from GIT_HEAD_ID and trigger it using BULIT_SOURCES to ensure the file
exists before compilation starts.
The latest ISL creates gitversion.h from Makefile.am only, instead also
from configure.ac in previous version. While the Polly build invokes
configure, it does not invoke ISL's make such that the file was missing.
Invoking ISL's make would come with additional problems such as
triggering automake because of not preserved file time stamps.
Re-running automake might not be successful on other system
configurations for instance because it was preconfigured without
--with-clang option.
llvm-svn: 247142
Not all users of our IslNodeBuilder will attach scheduling information to the
AST in the same way IslAstInfo is doing it today. By going through a virtual
function when extracting the schedule of an AST node other users can provide
their own functions for extract scheduling information in case they attach
scheduling information in a different way to the AST nodes.
No functional change for Polly itself intended.
llvm-svn: 247126
While we do not need to model PHI nodes in the region exit (as it is not part
of the SCoP), we need to prepare for the case that the exit block is split in
code generation to create a single exiting block. If this will happen, hence
if the region did not have a single exiting block before, we will model the
operands of the PHI nodes as escaping scalars in the SCoP.
Differential Revision: http://reviews.llvm.org/D12051
llvm-svn: 247078
Instead of having two separate options
-polly-detect-scops-in-functions-without-loops and
-polly-detect-scops-in-regions-without-loops we now just use
-polly-detect-unprofitable to force the detection of scops ignoring any compile
time saving bailout heuristics.
llvm-svn: 247057
Certain backends, e.g. NVPTX, do not support '.' in function names. Hence,
we ensure all '.' are replaced by '_' when generating function names for
subfunctions. For the current OpenMP code generation, this is not strictly
necessary, but future uses cases (e.g. GPU offloading) need this issue to be
fixed.
llvm-svn: 246980
When this option is enabled, Polly will emit printf calls for each scalar
load/and store which dump the scalar value loaded/stored at run time.
This patch also refactors the RuntimeDebugBuilder to use variadic templates
when generating CPU printfs. As result, it now becomes easier to print
strings that consist of a set of arguments. Also, as a single printf
call is emitted, it is more likely for such strings to be emitted atomically
if executed multi-threaded.
llvm-svn: 246941
Some of the structures are renamed, subfunction introduced to clarify the
individual steps and comments are added describing their functionality.
llvm-svn: 246929
In the common case, the access functions are not modified, hence there is no
need to obtain the IslAstBuild context at all. This should not only be minimally
faster, but this also allows the IslNodeBuilder to work on asts that are not
annotated with isl_ast_builds as long as the memory accesses are not modified.
llvm-svn: 246928
By inspection the update of the GlobalMaps in the RegionGenerator seems unneed,
and is removed as also no test cases fail when dropping this. Johannes Doerfert
confirmed that this is indeed save:
"I think that code was needed when we did not use the scalar codegen by default.
Now everything defined in a non-affine region should be communicated via memory
and reloaded in the user block. Hence, we should be good removing this code."
llvm-svn: 246926
When computing the index expressions for new, multi-dimensional memory accesses
these new index expressions may reference original llvm::Values that are not
transfered into the OpenMP subfunction. Using GlobalMap we now replace
references to such values with the rewritten values that have e.g. been passed
to the OpenMP subfunction.
llvm-svn: 246923
The GlobalMap variable used in BlockGenerator should always reference the same
list througout the entire code generation, hence we can make it a member
variable to avoid passing it around through every function call.
History: Before we switched to the SCEV based code generation the GlobalMap
also contained a mapping form old to new induction variables, hence it was
different for each ScopStmt, which is why we passed it as function argument
to copyStmt. The new SCEV based code generation now uses a separate mapping
called LTS -> LoopToSCEV that maps each original loop to a new loop iteration
variable provided as a SCEVExpr. The GlobalMap is currently mostly used for
OpenMP code generation, where references to parameters in the original function
need to be rewritten to the locations of these variables after they have been
passed to the subfunction.
Suggested-by: Johannes Doerfert <doerfert@cs.uni-saarland.de>
llvm-svn: 246920
Originally, we disallowed the import of multi-dimensional access functions due
to our code generation not supporting the generation of new address expressions
for multi-dimensional memory accesses. When building our run-time alias check
infrastructure we added code generation support for multi-dimensional address
calculations. Hence, we can now savely allow the import of new
multi-dimensional access functions.
llvm-svn: 246917
By just removing dimensions (and the constraints they are involved in) we
may loose information about the dimensions we do not remove. By instead
using project_out, we are sure all constraints on the outer dimensions are
preserved.
No test case, as this error condition is very unlikely to be triggered by
isl's current code. We still 'fix' this, as isl gives little guarantees
regarding the behavior of remove_divs.
llvm-svn: 246567
Code generation currently does not expect unbounded loops. When
using ISL to compute the loop trip count, if we find that the
iteration domain remains unbounded, we invalidate the Scop by
creating an infeasible context.
Contributed-by: Matthew Simpson <mssimpso@codeaurora.org>
This fixes PR24634.
Differential Revision: http://reviews.llvm.org/D12493
llvm-svn: 246477
Instead of building domains with MaxLoopDepth dimensions, we now build
the domains such that they have the right amount of dimensions all the
time.
llvm-svn: 246443
Before this commit we did this only for Arguments or Constants, but indeed
an instruction may define a value a lot higher up in the dominance tree, but
the actual write generally needs to happen right before branching to the
PHI node. Otherwise, the writes of different branches into PHI nodes may get
intermixed if they lay higher up in the dominance tree.
llvm-svn: 246441
There is no reason the loops in a region need to touch either entry or exit
block. Hence, we need to look through all loops that may touch the region as
well as their children to understand if our region has at least two loops.
llvm-svn: 246433
While ignoring read-only scalar dependences it was not necessary to consider
store instructins, but as store instructions can be the target of a scalar
read-only dependency we need to consider them for the construction of scalar
read-only dependences.
llvm-svn: 246429
Our OpenMP code generation generated part of its launching code directly into
the start basic block and without this change the scalar initialization was
run _after_ the OpenMP threads have been launched. This resulted in
uninitialized scalar values to be used.
llvm-svn: 246427
Even though these are not strictly necessary for sequential code generation,
we still model both for sequential and parallel code generation to reduce
the set of configurations that needs to be tested. If this turns out, against
what we currently see, to be significant overhead, we can decide to limit this
feature again to parallel code-generation use cases only.
llvm-svn: 246420
Scalar dependences between scop statements have caused troubles during parallel
code generation as we did not pass on the new stack allocation created for such
scalars to the parallel subfunctions. This change now detects all scalar
reads/writes in parallel subfunctions, creates the allocas for these scalar
objects, passes the resulting memory locations to the subfunctions and ensures
that within the subfunction requests for these memory locations will return the
rewritten values.
Johannes suggested as a future optimization to privatizing some of the scalars
in the subfunction.
llvm-svn: 246414
In order to compute domain conditions for conditionals we will now
traverse the region in the ScopInfo once and build the domains for
each block in the region. The SCoP statements can then use these
constraints when they build their domain.
The reason behind this change is twofold:
1) This removes a big chunk of preprocessing logic from the
TempScopInfo, namely the Conditionals we used to build there.
Additionally to moving this logic it is also simplified. Instead
of walking the dominance tree up for each basic block in the
region (as we did before), we now traverse the region only
once in order to collect the domain conditions.
2) This is the first step towards the isl based domain creation.
The second step will traverse the region similar to this step,
however it will propagate back edge conditions. Once both are in
place this conditional handling will allow multiple exit loops
additional logic.
Reviewers: grosser
Differential Revision: http://reviews.llvm.org/D12428
llvm-svn: 246398
We already modeled read-only dependences to scalar values defined outside the
scop as memory reads and also generated read accesses from the corresponding
alloca instructions that have been used to pass these scalar values around
during code generation. However, besides for PHI nodes that have already been
handled, we failed to store the orignal read-only scalar values into these
alloc. This commit extends the initialization of scalar values to all read-only
scalar values used within the scop.
llvm-svn: 246394
The current code really tries hard to use getNewScalarValue(), which checks if
not the original value, but a possible copy or demoted value needs to be stored.
In this calling context it seems, that we _always_ use the ScalarValue that
comes from the incoming PHI node, but never any other value. As also no test
cases fail, it seems right to just drop this call to getNewScalarValue and
remove the parameters that are not needed any more.
Johannes suggested that code like this might be needed for parallel code
generation with offloading, but it was still unclear if/what exactly would
be needed. As the parallel code generation does currently not support scalars
at all, we will remove this code for now and add relevant code back when
complitng the support of scalars in the parallel code generation.
Reviewers: jdoerfert
Subscribers: pollydev, llvm-commits
Differential Revision: http://reviews.llvm.org/D12470
llvm-svn: 246389
Our code generation currently does not support scalar references to metadata
values. Hence, it would crash if we try to model scalar dependences to metadata
values. Fortunately, for one of the common uses, debug information, we can
for now just ignore the relevant intrinsics and consequently the issue of how
to model scalar dependences to metadata.
llvm-svn: 246388
This commit drops some dead code. Specifically, there is no need to initialize
the virtual memory locations of scalars in BlockGenerator::handleOutsideUsers,
the function that initalizes the escape map that keeps track of out-of-scope
uses of scalar values. We already model instructions inside the scop that
are used outside the scope (escaping instructions) as scalar memory writes at
the position of the instruction. As a result, the virtual memory location of
this instructions is already initialized when code-generating the corresponding
virtual scalar write and consequently does not need to be initialized later on
when generating the set of escaping values.
Code references:
In TempScopInfo::buildScalarDependences we detect scalar cross-statement
dependences for all instructions (including PHIs) that have uses outside of the
scop's region:
// Check whether or not the use is in the SCoP.
if (!R->contains(UseParent)) {
AnyCrossStmtUse = true;
continue;
}
We use this information in TempScopInfo::buildAccessFunctions were we build
scalar write memory accesses for all these instructions:
if (!isa<StoreInst>(Inst) &&
buildScalarDependences(Inst, &R, NonAffineSubRegion)) {
// If the Instruction is used outside the statement, we need to build the
// write access.
IRAccess ScalarAccess(IRAccess::MUST_WRITE, Inst, ZeroOffset, 1, true,
Inst);
Functions.push_back(std::make_pair(ScalarAccess, Inst));
}
Reviewers: jdoerfert
Subscribers: pollydev, llvm-commits
Differential Revision: http://reviews.llvm.org/D12472
llvm-svn: 246383
For external users, the memory locations into which we generate scalar values
may be of interest. This change introduces two functions that allow to obtain
(or create) the AllocInsts for a given BasePointer.
We use this change to simplify the code in BlockGenerators.
llvm-svn: 246285
If a region does not have more than one loop, we do not identify it as
a Scop in ScopDetection. The main optimizations Polly is currently performing
(tiling, preparation for outer-loop vectorization and loop fusion) are unlikely
to have a positive impact on individual loops. In some cases, Polly's run-time
alias checks or conditional hoisting may still have a positive impact, but those
are mostly enabling transformations which LLVM already performs for individual
loops. As we do not focus on individual loops, we leave them untouched to not
introduce compile time regressions and execution time noise. This results in
good compile time reduction (oourafft: -73.99%, smg2000: -56.25%).
Contributed-by: Pratik Bhatu <cs12b1010@iith.ac.in>
Reviewers: grosser
Differential Revision: http://reviews.llvm.org/D12268
llvm-svn: 246161
This change allows the BlockGenerator to be reused in contexts where we want to
provide different/modified isl_ast_expressions, which are not only changed to
a different access relation than the original statement, but which may indeed
be different for each code-generated instance of the statement.
We ensure testing of this feature by moving Polly's support to import changed
access functions through a jscop file to use the BlockGenerators support for
generating arbitary access functions if provided.
This commit should not change the behavior of Polly for now. The diff is rather
large, but most changes are due to us passing the NewAccesses hash table through
functions. This style, even though rather verbose, matches what is done
throughout the BlockGenerator with other per-statement properties.
llvm-svn: 246144
Use ISL to compute the loop trip count when scalar evolution is unable to do
so.
Contributed-by: Matthew Simpson <mssimpso@codeaurora.org>
Differential Revision: http://reviews.llvm.org/D9444
llvm-svn: 246142
Other passes which perform different optimizations might be interested in
also applying data-locality transformations as part of their overall
transformation.
llvm-svn: 245824
Originally, we intersected the iteration space with the AssumedContext before
computing the minimal/maximal memory offset in our run-time alias checks. With
this patch we drop this intersection as the AssumedContext can - for larger or
more complex scops - become very complicated (contain many disjuncts). When
intersecting an object with many disjuncts with other objects, the number of
disjuncts in these other objects also increases quickly. As a result, the
compile time is unnecessarily increased. This patch now drops the intersection
with the assumed context to ensure we do not pay unnecessary compile time
costs.
With this patch we see -3.17% reduction in compile time for 3mm with default
flags and -17.87% when compiling 3mm with -DPOLYBENCH_USE_C99_PROTO flag. We
did not observe any regressions in LNT.
Contributed-by: Pratik Bhatu <cs12b1010@iith.ac.in>
Reviewers: grosser
Differential Revision: http://reviews.llvm.org/D12198
llvm-svn: 245617
To avoid multiple exits and the resulting complicated conditions when
creating a SCoP we now use the single hasFeasibleRuntimeContext()
check to decide if a SCoP should be dismissed right after
construction. If building runtime checks failed the assumed context is
made infeasible, hence the optimized version will never be executed
and the SCoP can be dismissed.
llvm-svn: 245593
If nothing is executed we can bail out early. Otherwise we can use the
constraints that ensure at least one statement is executed for
simplification.
llvm-svn: 245585
We will record if a SAI is the base of another SAI or derived from it.
This will allow to reason about indirect base pointers later on and
allows a clearer picture of indirection also in the SCoP dump.
llvm-svn: 245584
Register tiling in Polly is for now just an additional level of tiling which
is fully unrolled. It is disabled by default. To make this useful for more than
experiments, we still need a cost function as well as possibly further
optimizations that teach LLVM to actually put some of the values we got into
scalar registers.
llvm-svn: 245564
By default we only use one level of tiling for loops, but in general tiling
for multiple levels is trivial for us. Hence, we add a set of options that
allow people to play with a second level of tiling. If this is profitable for
some cases we can work on heuristics that allow us to identify these cases
and use two-level tiling for them.
llvm-svn: 245563
Instead of generating code for an empty assumed context we bail out
early. As the number of assumptions we generate increases this becomes
more and more important. Additionally, this change will allow us to
hide internal contexts that are only used in runtime checks e.g., a
boundary context with constraints not suited for simplifications.
llvm-svn: 245540
To make alias scope metadata generation work in OpenMP mode we now provide
the ScopAnnotator with information about the base pointer rewrite that happens
when passing arrays into the OpenMP subfunction.
llvm-svn: 245451
Polly uses 'prevectorization' to enable outer loop vectorization. When
vectorizing an outer loop, we strip-mine <number-of-prevec-dims> loop
iterations which are than interchanged to the innermost level such that LLVM's
inner loop vectorizer (or Polly's simple vectorizer) can easily vectorize this
loop. The number of loop iterations to strip-mine is now configurable with the
option -polly-prevect-width=<number-of-prevec-dims>.
This is mostly a debugging option. We should probably add a heuristic that
derives the number of prevectorization dimensions from the target data and
the data types used.
llvm-svn: 245424
This patch changes Polly to compute the data-dependences on the schedule tree
instead of a flat schedule representation. Calculating dependences directly on
the schedule tree results in some good compile-time improvements (adi : -23.35%,
3mm : -9.57%), as the structure of the schedule can be exploited for increased
efficiency.
Earlier experiments with schedule tree based dependence analysis in Polly showed
some compile-time regressions. These regressions arose due to the schedule tree
based dependence analysis not taking into account the domain constraints of the
schedule tree. As a result, the computed dependences were different and this
difference caused in some cases the schedule optimizer to take a very long time.
Since isl version fe865996 the schedule tree based dependence analysis takes
domain constraints into account, which fixes the earlier compile-time issues.
Contributed-by: Pratik Bhatu <cs12b1010@iith.ac.in>
llvm-svn: 245300
executeScopConditionally would destroy a predecessor region if it the
scop's entry was the region's exit block by forking it to polly.start
and thus creating a secnd exit out of the region. This patch "shrinks"
the predecessor region s.t. polly.split_new_and_old is not the
region's exit anymore.
llvm-svn: 245294
The SCEVExpander cannot deal with all SCEVs Polly allows in all kinds
of expressions. To this end we introduce a ScopExpander that handles
the additional expressions separatly and falls back to the
SCEVExpander for everything else.
Reviewers: grosser, Meinersbur
Subscribers: #polly
Differential Revision: http://reviews.llvm.org/D12066
llvm-svn: 245288
Tobias Grosser