multiplication
The following code modifies elements of the array D.
for (i = 0; i < _PB_NI; i++)
for (j = 0; j < _PB_NJ; j++)
{
for (k = 0; k < _PB_NK; k++)
{
double Mul = A[i][k] * B[k][j];
D[i][j][k] += Mul;
C[i][j] += Mul;
}
}
Nevertheless, the code is recognised as a matrix-matrix multiplication, since
the second and third dimensions of D are accessed with non-zero strides.
This fixes the typo, which was made during the translation to C++ bindings
(https://reviews.llvm.org/D35845).
Reviewed By: Michael Kruse <llvm@meinersbur.de>
Differential Revision: https://reviews.llvm.org/D110491
SplitBlockPredecessors is unable to insert an additional BasicBlock
between an indirectbr/callbr terminator and the successor blocks.
This is needed by Polly to normalize the control flow before emitting
its optimzed code.
This patches rejects regions entered by an indirectbr/callbr to not fail
later at code generation.
This fixes llvm.org/PR51964
Recommit with "REQUIRES: asserts" in test that uses statistics.
SplitBlockPredecessors is unable to insert an additional BasicBlock
between an indirectbr/callbr terminator and the successor blocks.
This is needed by Polly to normalize the control flow before emitting
its optimzed code.
This patches rejects regions entered by an indirectbr/callbr to not fail
later at code generation.
This fixes llvm.org/PR51964
Inline assembly was not handled at all and treated like a llvm::Value.
In particular, it tried to create a pointer it which is not allowed.
Fix by handling like a llvm::Constant such that it is just reused when
required, instead of trying to marshall it in memory.
Fixes llvm.org/PR51960
VirtualUse ensures consistency over different source of values with
Polly. In particular, this enables its use of instructions moved between
Statement. Before the patch, the code wrongly assumed that the BB's
instructions are also the ScopStmt's instructions. Reference are
determined for OpenMP outlining and GPGPU kernel extraction.
GPGPU CodeGen had some problems. For one, it generated GPU kernel
parameters for constants. Second, it emitted GPU-side invariant loads
which have already been loaded by the host. This has been partially
fixed, it still generates a store for the invariant load result, but
using the value that the host has already written.
WARNING: I did not test the generated PollyACC code on an actual GPU.
The improved consistency will be made use of in the next patch.
The function was intended to catch OpenMP functions such as
get_thread_id(). If matched, the call would be considered synthesizable.
There were a few problems with this:
* get_thread_id() is not 'const' in the sense of have the gcc manual
defines it: "do not examine any values except their arguments".
get_thread_id() reads OpenCL runtime libreary global state.
What was inteded was probably 'speculable'.
* isConstCall was implemented using mayReadOrWriteMemory(). 'const' is
stricter than that, mayReadOrWriteMemory is e.g. true for malloc(),
since it may only read/write addresses that are considered
inaccessible fro the application. However, malloc is certainly not
speculable.
* Values that are isConstCall were not handled consistently throughout
Polly. In particular, it was not considered for referenced values
(OpenMP outlining and PollyACC).
Fix by removing special handling for isConstCall entirely.
This is a simple version without the possibility to define distribute
points or followup-transformations. However, it is the first
transformation that has to check whether the transformation is correct.
It interprets the same metadata as the LoopDistribute pass.
Re-apply after revert in c7bcd72a38 with
fix: Take isBand out of #ifndef NDEBUG since it now is used
unconditionally.
The name of the option is misleading and has been renamed by isl to
"serialize-sccs". Instead of also renaming the option, remove it.
The option is still accessible using
-polly-isl-arg=--no-schedule-serialize-sccs
This is a simple version without the possibility to define distribute
points or followup-transformations. However, it is the first
transformation that has to check whether the transformation is correct.
It interprets the same metadata as the LoopDistribute pass.
This metadata was intended to mark all accesses within an iteration to be pairwise non-aliasing, in this case because every memory of a base pointer is touched (read or write) at most once. This is typical for 'sweeps' over all data. The stated motivation from D30606 is to ensure that unrolled iterations are considered non-aliasing.
Rhe implemention had multiple issues:
* The structure of the noalias metadata was malformed. D110026 added check in the verifier for this metadata, and the tests were failing since then.
* This is not true for the outer loops of the BLIS matrix multiplication, where it was being inserted. Each element of A, B, C is accessed multiple times, as often as the loop not used as an index is iterating.
* Scopes were added to SecondLevelOtherAliasScopeList (used for the !noalias scop list) on-the-fly when another SCEV was seen. This meant that previously visited instructions would not be updated with alias scopes that are only seen later, missing out those SCEVs they should not be aliasing with.
* Since the !noalias scope list would ideally consists of all other SCEV for this base pointer, we might run quickly into scalability issues. Especially after unrolling there would probably at least once SCEV per instruction and unroll instance.
* The inter-iteration noalias base pointer was not removed after leaving the loop marked with it, effectively marking everything after it to noalias as well.
A solution I considered was to mark each instruction as non-aliasing with its own scope. The instruction itself would obviously alias itself, but such construction might also be considered invalid. Duplicating the instruction (e.g. due to speculation) would mark the instruction non-aliasing with its clone. I don't want to go into this territory, especially since the original motivation of determining unrolled instances as noalias based on SCEV is the what scev-aa does as well.
This effectively reverts D30606 and D35761.
getMetadata() currently uses a weird API where it populates a
structure passed to it, and optionally merges into it. Instead,
we can return the AAMDNodes and provide a separate merge() API.
This makes usages more compact.
Differential Revision: https://reviews.llvm.org/D109852
Building a source distribution using autotools adds GPL-licenced
files into the the sources. Although redistribution of theses files is
explicitly allowed with an exception, these are not used by Polly
which uses a CMake replacement. Use the direct source checkout
instead (replacing the output of 'make dist').
Some m4 scripts with the same licence are also included in isl/ppcg
repository. Removing them renders the autotools-based build scipts
inoperable, so remove the autotools build system altogether.
As of 741fabc222f226d34d806056b804244b012853b, polly builders are
failing from this error. The signiature is slightly different and
accepts a ScalarEvolution reference instead. This should fix the polly
builders.
Polly does not use the count program itself, but somewhere in lit it is
expected to exists. Otherwise, the following error occurs:
llvm-lit: llvm-project/llvm/utils/lit/lit/llvm/subst.py:133: fatal: Did not find count in ./bin
With LLVM_LINK_LLVM_DYLIB and LLVM_POLLY_LINK_INTO_TOOLS, Polly is
already linked into libLLVM.so, linking libPolly.a as well into
unittests results in duplicate command line registration errors.
Code outside the SCoP will be executed recardless of the code versioning
runtime check introduced by CodeGeneration. Assumption made based on
that these are never executed in Polly-optimized code does not hold.
This fixes the miscompilation of MultiSource/Applications/lambda-0.1.3
The new pass manager does not allow adding module passes at the
-polly-position=before-vectorizer extension point. Introduce a
DumpFunctionPass that dumps only current function. In contrast to the
legacy pass manager's -polly-dump-before, each function will be dumped
into its own file. -polly-dump-before-file is still not supported.
The DumpFunctionPass uses llvm::CloneModule to copy the current function
into a new module and then write it into a file.
Compilation of the file insn-attrtab.c of the SPEC CPU 2017 502.gcc_r
benchmark takes excessive time (> 30min) with Polly enabled. Most time
is spent in the isErrorBlock function querying the DominatorTree.
The isErrorBlock is invoked redundantly over the course of ScopDetection
and ScopBuilder. This patch introduces a caching mechanism for its
result.
Instead of a free function, isErrorBlock is moved to ScopDetection where
its cache map resides. This also means that many functions directly or
indirectly calling isErrorBlock are not "const" anymore. The
DetectionContextMap was marked as "mutable", but IMHO it never should
have been since it stores the detection result.
502.gcc_r only takes excessive time with the new pass manager. The
reason seeams to be that it invalidates the ScopDetection analysis more
often than the legacy pass manager, for unknown reasons.
This is part of an effort to reduce the differences between the custom C++ bindings used right now by polly in `lib/External/isl/include/isl/isl-noxceptions.h` and the official isl C++ interface.
Changes made:
- Use `isl::val::sub` instead of `isl::val::sub_ui`
- `isl-noexceptions.h` has been generated by 355e84163a
Depends on D107225
Reviewed By: Meinersbur
Differential Revision: https://reviews.llvm.org/D107293
This is part of an effort to reduce the differences between the custom C++ bindings used right now by polly in `lib/External/isl/include/isl/isl-noxceptions.h` and the official isl C++ interface.
With this commit we are moving from the `polly-generator` branch to the `new-polly-generator` branch that is more mantainable and is based on the official C++ interface `cpp-checked.h`.
Changes made:
- There are now many sublcasses for `isl::ast_node` representing different isl types. Use `isl::ast_node_for`, `isl::ast_node_user`, `isl::ast_node_block` and `isl::ast_node_mark` where needed.
- There are now many sublcasses for `isl::schedule_node` representing different isl types. Use `isl::schedule_node_mark`, `isl::schedule_node_extension`, `isl::schedule_node_band` and `isl::schedule_node_filter` where needed.
- Replace the `isl::*::dump` with `dumpIslObj` since the isl dump method is not exposed in the C++ interface.
- `isl::schedule_node::get_child` has been renamed to `isl::schedule_node::child`
- `isl::pw_multi_aff::get_pw_aff` has been renamed to `isl::pw_multi_aff::at`
- The constructor `isl::union_map(isl::union_pw_multi_aff)` has been replaced with the static method `isl::union_map::from()`
- Replace usages of `isl::val::add_ui` with `isl::val::add`
- `isl::union_set_list::alloc` is now a constructor
- All the `isl_size` values are now wrapped inside the class `isl::size` use `isl::size::release` to get the internal `isl_size` value where needed.
- `isl-noexceptions.h` has been generated by 73f5ed1f4d
No functional change intended.
Reviewed By: Meinersbur
Differential Revision: https://reviews.llvm.org/D107225
Avoid doing the detection work inside the constructor. In addition to
polymorphism being unintuitive in constructors and other design problems
such as if an exception is thrown, the ScopDetection class is usable
without detection in the sense of "no Scop found" or "function skipped".
The compilation of the file
526.blender_r/src/blender/source/blender/editors/space_logic/logic_ops.c
from the SPEC CPU 2017 benchmarks took excessive time to compute
InvalidDomain.gist_params(Ctx)
Simplifying beforehand, specifically using isl_set_detect_equalities,
reduces the computation time to a negible level again.
Add unittests for IslMaxOperationsGuard and the behaviour of the isl-noexception.h wrapper under exceeded max_operations.
Reviewed By: patacca
Differential Revision: https://reviews.llvm.org/D107401
The foreach callback wrappers tests check the return values of isl::stat:ok() and isl::stat::error() separately. However, due to the the container they are iterating over containing just one element, they are actually not testing the difference between them.
This patch changes to set to be iterated over to contain 2 element to make returning sl::stat:ok (continue iterating the next element) and isl::stat::error (break after current element) have different effects other than the return value of the foreach itself.
Reviewed By: patacca
Differential Revision: https://reviews.llvm.org/D107395
Pulled out the OptimizationLevel class from PassBuilder in order to be able to access it from within the PassManager and avoid include conflicts.
Reviewed By: mtrofin
Differential Revision: https://reviews.llvm.org/D107025
This is needed for having the functions isl_{set,map}_n_basic_{set,map}
exported to the C++ interface.
Some tests have been modified to reflect the isl changes.
This is part of an effort to reduce the differences between the custom C++ bindings used right now by polly in `lib/External/isl/include/isl/isl-noxceptions.h` and the official isl C++ interface.
Changes made:
- Stop using `isl::set::lex_le_set`. The official way to do this is to use `isl::map::lex_le_at`
- Removed `isl::set::lex_le_set` from `isl-noexceptions.h`
- `isl-noexceptions.h` has been generated by this 266fea1d3d
Reviewed By: Meinersbur
Differential Revision: https://reviews.llvm.org/D106269
This is part of an effort to reduce the differences between the custom C++ bindings used right now by polly in `lib/External/isl/include/isl/isl-noxceptions.h` and the official isl C++ interface.
Note that not all the usages of `isl::set::dim` were replaced
This is part of an effort to reduce the differences between the custom C++ bindings used right now by polly in `lib/External/isl/include/isl/isl-noxceptions.h` and the official isl C++ interface.
Changes made:
- Use `isl::union_map::unite()` instead of `isl::union_map::add_map()`
- `isl-noexceptions.h` has been generated by this 3f43ae29fa
Depends on D106059
Reviewed By: Meinersbur
Differential Revision: https://reviews.llvm.org/D106061
Roman Gareev