Commit Graph

372 Commits

Author SHA1 Message Date
Tobias Grosser 808cd69a92 Use schedule trees to represent execution order of statements
Instead of flat schedules, we now use so-called schedule trees to represent the
execution order of the statements in a SCoP. Schedule trees make it a lot easier
to analyze, understand and modify properties of a schedule, as specific nodes
in the tree can be choosen and possibly replaced.

This patch does not yet fully move our DependenceInfo pass to schedule trees,
as some additional performance analysis is needed here. (In general schedule
trees should be faster in compile-time, as the more structured representation
is generally easier to analyze and work with). We also can not yet perform the
reduction analysis on schedule trees.

For more information regarding schedule trees, please see Section 6 of
https://lirias.kuleuven.be/handle/123456789/497238

llvm-svn: 242130
2015-07-14 09:33:13 +00:00
Tobias Grosser ec46e5376d Print thread-identifiers in GPU debug output
This helps us to understand which thread prints which information.

llvm-svn: 241452
2015-07-06 15:36:16 +00:00
Tobias Grosser af4e809ca6 Remove code for scalar and PHI to array translation
This removes old code that has been disabled since several weeks and was hidden
behind the flags -disable-polly-intra-scop-scalar-to-array=false and
-polly-model-phi-nodes=false. Earlier, Polly used to translate scalars and
PHI nodes to single element arrays, as this avoided the need for their special
handling in Polly. With Johannes' patches adding native support for such scalar
references to Polly, this code is not needed any more. After this commit both
-polly-prepare and -polly-independent are now mostly no-ops. Only a couple of
simple transformations still remain, but they are scheduled for removal too.

Thanks again to Johannes Doerfert for his nice work in making all this code
obsolete.

llvm-svn: 240766
2015-06-26 07:31:18 +00:00
Tobias Grosser 967c1e0b93 Handle zero-element ArrayRefs in CUDA run-time debug builder
llvm-svn: 240312
2015-06-22 18:45:23 +00:00
Tobias Grosser e7e628cc07 Add NVIDIA vprintf printing to RuntimeDebugBuilder
2nd try, this time with the corresponding LLVM IRBuilder changes in place.

llvm-svn: 240119
2015-06-19 02:33:45 +00:00
Tobias Grosser 039955a44c Revert "Add NVIDIA vprintf printing to RuntimeDebugBuilder"
This reverts commit 239219 which requires some LLVM changes I forgot to commit.

Reported-by: Marshall Clow
llvm-svn: 239306
2015-06-08 16:24:49 +00:00
Tobias Grosser 6091417ebc Add NVIDIA vprintf printing to RuntimeDebugBuilder
llvm-svn: 239219
2015-06-06 08:43:22 +00:00
Tobias Grosser a5c092d844 Store ArrayShape in shared_ptr and MemAccs as actual objects
This fixes two more memory leaks.

llvm-svn: 239050
2015-06-04 16:03:16 +00:00
Tobias Grosser ff22e9e5f6 Store comparison objects as objects, not pointers
This fixes a memory leak. If we store the actual objects we can not forget to
free them.

llvm-svn: 239033
2015-06-04 11:44:09 +00:00
Tobias Grosser 7c3bad52dd Use value semantics for list of ScopStmt(s) instead of std::owningptr
David Blaike suggested this as an alternative to the use of owningptr(s) for our
memory management, as value semantics allow to avoid the additional interface
complexity caused by owningptr while still providing similar memory consistency
guarantees. We could also have used a std::vector, but the use of std::vector
would yield possibly changing pointers which currently causes problems as for
example the memory accesses carry pointers to their parent statements. Such
pointers should not change.

Reviewer: jblaikie, jdoerfert

Differential Revision: http://reviews.llvm.org/D10041

llvm-svn: 238290
2015-05-27 05:16:57 +00:00
Tobias Grosser ab6714464a Use unique_ptr to clarify ownershop of ScopArrayInfoMap
llvm-svn: 238091
2015-05-23 05:58:27 +00:00
Tobias Grosser 679dfafd33 Use unique_ptr to clarify ownership of ScopStmt
llvm-svn: 238090
2015-05-23 05:14:09 +00:00
Johannes Doerfert ecff11dcfb Add scalar and phi code generation
To reduce compile time and to allow more and better quality SCoPs in
  the long run we introduced scalar dependences and PHI-modeling. This
  patch will now allow us to generate code if one or both of those
  options are set. While the principle of demoting scalars as well as
  PHIs to memory in order to communicate their value stays the same,
  this allows to delay the demotion till the very end (the actual code
  generation). Consequently:
    - We __almost__ do not modify the code if we do not generate code
      for an optimized SCoP in the end. Thus, the early exit as well as
      the unprofitable option will now actually preven us from
      introducing regressions in case we will probably not get better
      code.
    - Polly can be used as a "pure" analyzer tool as long as the code
      generator is set to none.
    - The original SCoP is almost not touched when the optimized version
      is placed next to it. Runtime regressions if the runtime checks
      chooses the original are not to be expected and later
      optimizations do not need to revert the demotion for that part.
    - We will generate direct accesses to the demoted values, thus there
      are no "trivial GEPs" that select the first element of a scalar we
      demoted and treated as an array.

Differential Revision: http://reviews.llvm.org/D7513

llvm-svn: 238070
2015-05-22 23:43:58 +00:00
Tobias Grosser a8512b1784 Add diagnostic for unsigned integer comparisions
llvm-svn: 237800
2015-05-20 15:37:11 +00:00
Tobias Grosser 49ad36ca16 Add printing and testing to ScopArrayInfo
Being here, we extend the interface to return the element type and not a pointer
to the element type. We also provide a function to get the size (in bytes) of
the elements stored in this array.

We currently still store the element size as an innermost dimension in
ScopArrayInfo, which is somehow inconsistent and should be addressed in future
patches.

llvm-svn: 237779
2015-05-20 08:05:31 +00:00
Tobias Grosser b80def51e1 Drop unused PTX generator file
This code has been part of Polly's GPGPU backend, which has been remove together
with the code generation backend. Development now continues in an out-of-tree
branch.

llvm-svn: 237450
2015-05-15 15:41:14 +00:00
Tobias Grosser 6f48e0fd2b Give each memory access a reference ID
This reference ID is handy for use cases where we need to identify individual
memory accesses (e.g. to modify their access functions).

This is a reworked version of a patch originally developed by Yabin Hu as part
of his summer of code project.

llvm-svn: 237431
2015-05-15 09:58:32 +00:00
Tobias Grosser 09d3069740 Rename IslCodeGeneration to CodeGeneration
Besides class, function and file names, we also change the command line option
from -polly-codegen-isl to just -polly-codegen. The isl postfix is a leftover
from the times when we still had the CLooG based -polly-codegen. Today it is
just redundant and we drop it.

llvm-svn: 237099
2015-05-12 07:45:52 +00:00
Tobias Grosser cd524dc51d Add explicit #includes for used isl features
llvm-svn: 236931
2015-05-09 09:36:38 +00:00
Tobias Grosser ba0d09227c Sort include directives
Upcoming revisions of isl require us to include header files explicitly, which
have previously been already transitively included. Before we add them, we sort
the existing includes.

Thanks to Chandler for sort_includes.py. A simple, but very convenient script.

llvm-svn: 236930
2015-05-09 09:13:42 +00:00
Tobias Grosser e71ed19841 Add iterators for the ArrayInfo objects of the scop
This patch also changes the implementation of the ArrayInfoMap to a MapVector
which will ensure that iterating over the list of ArrayInfo objects gives
predictable results. The single loop that currently enumerates the ArrayInfo
objects only frees the individual objectes, hence a possibly changing
iteration order does not affect the outcome. The added robustness is for
future users of this interface.

llvm-svn: 236583
2015-05-06 10:05:20 +00:00
Tobias Grosser a63b7cee66 Adding debug location information to Polly's JSCOP and dot exports
This change adds location information for the detected regions in Polly when the
required debug information is available.

The JSCOP output format is extended with a "location" field which contains the
information in the format "source.c:start-end"

The dot output is extended to contain the location information for each nested
region in the analyzed function.

As part of this change, the existing getDebugLocation function has been moved
into lib/Support/ScopLocation.cpp to avoid having to include
polly/ScopDetectionDiagnostics.h.

Differential Revision: http://reviews.llvm.org/D9431

Contributed-by: Roal Jordans <r.jordans@tue.nl>
llvm-svn: 236393
2015-05-03 05:21:36 +00:00
Tobias Grosser 0c55cb6071 Extract IslNodeBuilder into its own file
The IslNodeBuilder is a generic class that may be useful in other contexts
as well. Hence, we extract it into its own .h/.cpp file.

llvm-svn: 235873
2015-04-27 12:32:24 +00:00
Tobias Grosser 8fd2390053 Do not expose code generator choice in the header
There is no need for other passes to access the code-generator command-line
option. Hence, drop it from the header to simplify the interface.

llvm-svn: 235866
2015-04-27 12:02:33 +00:00
Tobias Grosser 6325cd2fcd Remove flag '-polly-annotate-alias-scopes'
This option is enabled since a long time and there does not seem to be a
situation in which we would not want to print alias scopes. Remove this option
to reduce the set of command-line option combinations that may expose bugs.

llvm-svn: 235861
2015-04-27 10:43:10 +00:00
Tobias Grosser b68068bf62 Remove implementation of getNumberOfIterations from header [NFC]
We moved this implementation into the header file to share it between
the CLooG and isl code generator. As the CLooG code generator was dropped,
the implementation can be folded back into the .cpp file.

No functional change intended.

llvm-svn: 235860
2015-04-27 10:38:45 +00:00
Tobias Grosser 5483931117 Rename 'scattering' to 'schedule'
In Polly we used both the term 'scattering' and the term 'schedule' to describe
the execution order of a statement without actually distinguishing between them.
We now uniformly use the term 'schedule' for the execution order.  This
corresponds to the terminology of isl.

History: CLooG introduced the term scattering as the generated code can be used
as a sequential execution order (schedule) or as a parallel dimension
enumerating different threads of execution (placement). In Polly and/or isl the
term placement was never used, but we uniformly refer to an execution order as a
schedule and only later introduce parallelism. When doing so we do not talk
about about specific placement dimensions.

llvm-svn: 235380
2015-04-21 11:37:25 +00:00
Tobias Grosser 5a475e7936 Drop unused extern declaration
llvm-svn: 235256
2015-04-18 15:57:56 +00:00
Tobias Grosser adfd1b730c Fix typo
llvm-svn: 235252
2015-04-18 09:40:01 +00:00
Johannes Doerfert f8206cf6d4 Allow loops in non-affine subregions -- SCoP Modeling
This will allow the ScopInfo to build the polyhedral representation for
  non-affine regions that contain loops. Such loops are basically not visible
  in the SCoP representation. Accesses that are variant in such loops are
  therefor represented as non-affine accesses.

Differential Revision: http://reviews.llvm.org/D8153

llvm-svn: 234713
2015-04-12 22:58:40 +00:00
Johannes Doerfert f3e98f44e3 Allow loops in non-affine subregions -- SCoP Detection
This will allow the ScopDetection to detect non-affine regions that
  contain loops. All loops contained will be collected and are
  accessible to later passes in order to adjust the access functions.
  As the loops are non-affine and will not be part of the polyhedral
  representation later, all accesses that are variant in these loops
  have to be over approximated as non-affine accesses. They are
  therefore handled the same way as other non-affine accesses.
  Additionally, we do not count non-affine loops for the profitability
  heuristic, thus a region with only a non-affine loop will only be
  detected if the general detection of loop free regions is enabled.

Differential Revision: http://reviews.llvm.org/D8152

llvm-svn: 234711
2015-04-12 22:52:20 +00:00
David Blaikie f0e3d50d52 [opaque pointer type] More GEP API migrations
llvm-svn: 234131
2015-04-05 22:51:12 +00:00
Tobias Grosser d654eeb862 Drop some CLooG leftovers
llvm-svn: 233572
2015-03-30 17:56:50 +00:00
Tobias Grosser 18b03e606e Delete some leftovers from scoplib
llvm-svn: 233571
2015-03-30 17:55:40 +00:00
Tobias Grosser 378e003748 Drop libpluto support
We do not have buildbots or anything that tests this functionality, hence it
most likely bitrots. People interested to use this functionality can always
recover it from svn history.

llvm-svn: 233570
2015-03-30 17:54:01 +00:00
Tobias Grosser 619190d5a7 Delinearization of expressions that contain array size parameters
This allows us to delinerize code such as:

  A[][n]

  for (i
    for (j
      A[i][n-j-1] = ...

which would previously have been delinearize to an access A[i+1][-j-1].

To recover the correct access we apply the piecewise expression:

  { A[i][j] -> A[i-1][i+N]: i < 0; A[i][j] -> A[i][i]: i >= 0}

This approach generalizes to higher dimensions.

llvm-svn: 233566
2015-03-30 17:22:28 +00:00
Tobias Grosser 4f663aae09 Add some missing isl prefixes
llvm-svn: 233533
2015-03-30 11:52:59 +00:00
Johannes Doerfert be40996cfe Strip constant factors from SCoP parameters
This will strip the constant factor of a parameter befor we add it to
  the SCoP. As a result the access functions are simplified, e.g., for
  the attached test case.

llvm-svn: 233501
2015-03-29 20:45:09 +00:00
Tobias Grosser 2873645c51 Drop -polly-vectorizer-unroll-only option
This options was earlier used for experiments with the vectorizer, but to my
knowledge is not really used anymore. If anybody needs this, we can always
reintroduce this feature.

llvm-svn: 232934
2015-03-23 07:00:36 +00:00
Tobias Grosser f2716ea7d5 Add -polly-vectorizer=stripmine
By strip-mining outer loops to the innermost level we can enable LLVM's loop
vectorizer to vectorize outer loops.

llvm-svn: 232100
2015-03-12 20:48:07 +00:00
Tobias Grosser bb4126470a Drop option to prepare code for the BB vectorizer
The BB vectorizer is deprecated and there is no point in generating code for it
any more. This option was introduced when there was not yet any loop vectorizer
in sight. Now being matured, Polly should target the loop vectorizer.

llvm-svn: 232099
2015-03-12 20:47:58 +00:00
Johannes Doerfert 6a4d81c1f6 Add end user report message for unprofitable regions [NFC]
llvm-svn: 231593
2015-03-08 15:11:50 +00:00
Tobias Grosser 1fa434992b Fix leftover Dependences.cpp -> DependenceInfo.cpp
llvm-svn: 231355
2015-03-05 06:52:42 +00:00
Johannes Doerfert 7e6424ba5a Create a dependence struct to hold dependence information for a SCoP.
The new Dependences struct in the DependenceInfo holds all information
  that was formerly part of the DependenceInfo. It also provides the
  same interface for the user to access this information.

  This is another step to a more general ScopPass interface that does
  allow multiple SCoPs to be "in flight".

llvm-svn: 231327
2015-03-05 00:43:48 +00:00
Johannes Doerfert 6745822fd1 Add missing forward declaration [NFC]
llvm-svn: 231326
2015-03-05 00:40:07 +00:00
Johannes Doerfert f6557f98a2 Rename the Dependences pass to DependenceInfo [NFC]
We rename the Dependences pass to DependenceInfo as a first step to a
  caching pass policy. The new DependenceInfo pass will later provide
  "Dependences" for a SCoP.

  To keep consistency the test folder is renamed too.

llvm-svn: 231308
2015-03-04 22:43:40 +00:00
Tobias Grosser b021a4faad Add support for conditional 'and' and 'or' expressions
No test cases unfortunately as we do not yet generate isl_ast_op_and_then or
isl_ast_op_or_else. Those will be added in a later commit.

llvm-svn: 231268
2015-03-04 18:14:59 +00:00
Johannes Doerfert d239aac2ee Do not model scalar accesses in non-affine subregions
If a scalar was defined and used only in a non-affine subregion we do
  not need to model the accesses. However, if the scalar was defined
  inside the region and escapes the region we have to model the access.
  The same is true if the scalar was defined outside and used inside the
  region.

llvm-svn: 230960
2015-03-02 14:06:01 +00:00
Johannes Doerfert 2495cfe01d [Refactor] Simplify ScopPass interface
llvm-svn: 230899
2015-03-01 18:43:50 +00:00
Johannes Doerfert 909a3bf21d [Refactor] Use virtual and override appropriately
+ Add override for overwritten methods.
  + Remove virtual for methods we do not want to be overwritten.

llvm-svn: 230898
2015-03-01 18:42:08 +00:00