This revision adds enough support to allow InlineAsmOp to work properly with indirect memory constraints "*m".
These require an explicit "elementtype" TypeAttr on the operands to pass LLVM verification and need to be provided.
Reviewed By: bkramer
Differential Revision: https://reviews.llvm.org/D118006
Extract the division representation from equality constraints.
For example:
32*k == 16*i + j - 31 <-- k is the localVariable
expr = 16*i + j - 31, divisor = 32
k = (16*i + j - 32) floordiv 32
The dividend of the division is set to [16, 1, -32] and the divisor is set
to 32.
Reviewed By: Groverkss
Differential Revision: https://reviews.llvm.org/D117959
Following the discussion in D118318, mark `arith.addf/mulf` commutative.
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D118600
Part 2 of 3 of unifying the assembly formats of attributes/types and operations.The last patch that introduced attribute/type formats (D111594) factored out the format lexer entirely. This patch factors out most of the format parsers such that the attribute/type and op parsers only need to implement handling for specific elements.
Certain things could be factored better (element verification, 'seen' variables) but the primary goal of factoring is so that features can be used across both assembly formats.
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D117971
This matches the same API usage as attributes/ops/types. For example:
```c++
Dialect *dialect = ...;
// Instead of this:
if (auto *interface = dialect->getRegisteredInterface<DialectInlinerInterface>())
// You can do this:
if (auto *interface = dyn_cast<DialectInlinerInterface>(dialect))
```
Differential Revision: https://reviews.llvm.org/D117859
- Remove the `{Op,Attr,Type}Trait` TableGen classes and replace with `Trait`
- Rename `OpTraitList` to `TraitList` and use it in a few places
The bulk of this change is a mechanical s/OpTrait/Trait/ throughout the codebase.
Reviewed By: rriddle, jpienaar, herhut
Differential Revision: https://reviews.llvm.org/D118543
This reduces the dependencies of the MLIRVector target and makes the dialect consistent with other dialects.
Differential Revision: https://reviews.llvm.org/D118533
Support affine.load/store ops in fold-memref-subview ops pass. The
existing pass just "inlines" the subview operation on load/stores by
inserting affine.apply ops in front of the memref load/store ops: this
is by design always consistent with the semantics on affine.load/store
ops and the same would work even more naturally/intuitively with the
latter.
Differential Revision: https://reviews.llvm.org/D118565
Update SCF pass cmd line names to prefix `scf`. This is consistent with
guidelines/convention on how to name dialect passes. This also avoids
ambiguity on the context given the multiple `for` operations in the
tree.
NFC.
Differential Revision: https://reviews.llvm.org/D118564
There was a bug where some of the OpOperands needed in the replacement op were not in scope.
It does not matter where the replacement op is inserted. Any insertion point is OK as long as there are no dominance errors. In the worst case, the newly inserted op will bufferize out-of-place. This is no worse than not eliminating the InitTensorOp at all.
Differential Revision: https://reviews.llvm.org/D117685
Also reimplement `std-bufferize` in terms of BufferizableOpInterface-based bufferization. The old `std.select` bufferization pattern is no longer needed and deleted.
Differential Revision: https://reviews.llvm.org/D118559
The bufferization of arith.constant ops is also switched over to BufferizableOpInterface-based bufferization. The old implementation is deleted. Both implementations utilize GlobalCreator, now renamed to just `getGlobalFor`.
GlobalCreator no longer maintains a set of all created allocations to avoid duplicate allocations of the same constant. Instead, `getGlobalFor` scans the module to see if there is already a global allocation with the same constant value.
For compatibility reasons, it is still possible to create a pass that bufferizes only `arith.constant`. This pass (createConstantBufferizePass) could be deleted once all users were switched over to One-Shot bufferization.
Differential Revision: https://reviews.llvm.org/D118483
llvm/Support/Path.h was likely previously implicitly included, and a
refactoring removed that inclusion, breaking the pass.
Differential Revision: https://reviews.llvm.org/D118508
Type constraints such as BoolLike and SignlessIntegerLike appear to
have been defined by copy-paste and all share an underlying TypesLike
structure that can be factored out.
This also allows for defining additional constraints of a similar
form, such as F32Like.
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D118382
This patch adds the vector.scan op which computes the
scan for a given n-d vector. It requires specifying the operator,
the identity element and whether the scan is inclusive or
exclusive.
TEST: Added test in ops.mlir
Reviewed By: ThomasRaoux
Differential Revision: https://reviews.llvm.org/D117171
The unit tests for PyTACO hasn't been upstreamed yet. A unit test for this
change will be added when we upstream all the unit tests for PyTACO.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D118417
mlir-cpu-runner has a dependency on ExecutionEngine which is only built for the native arch. So currently mlir-cpu-runner does not link correctly when the native arch is not targeted.
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D118422
This patch introduces a class LexSimplex that can currently be used to find the
lexicographically minimal rational point in an IntegerPolyhedron. This is a
series of patches leading to computing the lexicographically minimal integer
lattice point as well parametric lexicographic minimization.
Reviewed By: Groverkss
Differential Revision: https://reviews.llvm.org/D117437
With opaque pointers, we can no longer derive this from the pointer
type, so we need to explicitly provide the element type the atomic
operation should work with.
Differential Revision: https://reviews.llvm.org/D118359
This is is the start of the MLIR benchmarks. It sets up a command
line tool along with conventions to define and run benchmarks
using mlir's python bindings.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D115174
Although cmake should be platform-independent, we've observed
that some aspects of Python detection don't work on all platforms,
even with recent versions of cmake. This appears to be due to bugs
in the python detection logic, especially when the NumPy component
is required and not located within the python installation.
As a workaround, this patch first searches for "Development" before
searching for "Development.Module", which seems to workaround the
issue.
Differential Revision: https://reviews.llvm.org/D118148
This is in preparation of switching `-tensor-constant-bufferize` and `-arith-bufferize` to BufferizableOpInterface-based implementations.
Differential Revision: https://reviews.llvm.org/D118324
This commit switches the `tensor-bufferize` pass over to BufferizableOpInterface-based bufferization.
Differential Revision: https://reviews.llvm.org/D118246
The pass can currently not handle to_memref(to_tensor(x)) folding where a cast is necessary. This is required with the new unified bufferization. There is already a canonicalization pattern that handles such foldings and it should be used during this pass.
Differential Revision: https://reviews.llvm.org/D117988
Stop the Cpp target from emitting unused labels. The previosly generated
code generated warning if `-Wunused-label` is passed to a compiler.
Co-authored-by: Simon Camphausen <simon.camphausen@iml.fraunhofer.de>
Reviewed By: jpienaar
Differential Revision: https://reviews.llvm.org/D118154
Prefix "affine-" to affine transform passes that were missing it -- to
avoid ambiguity and for uniformity. There were only two needed this.
Move mispaced affine coalescing test case file.
NFC.
Differential Revision: https://reviews.llvm.org/D118314
OwningRewritePatternList has been deprecated for ~10 months now, we can remove
the leftover using directives at this point.
Differential Revision: https://reviews.llvm.org/D118287
These transformations already operate on memref operations (as part of
splitting up the standard dialect). Now that the operations have moved,
it's time for these transformations to move as well.
Differential Revision: https://reviews.llvm.org/D118285
We already convert to BitVector internally, and other APIs (namely Operation::eraseOperands)
already use BitVector as well. Switching over provides a common format between
API and also reduces the amount of format conversions necessary.
Fixes#53325
Differential Revision: https://reviews.llvm.org/D118083
The option parser currently does not properly handle nested options, meaning that
in some cases we can print pass pipelines that we can't actually parse back in. For example,
from #52885 we currently can't parse in inliner pipelines that have nested pipeline strings.
This commit adds handling for string values (e.g. "...") and nested options
(e.g. `foo{baz{bar=10 pizza=11}}`).
Fixes#52885
Differential Revision: https://reviews.llvm.org/D118078
Rationale:
Demonstrates the maximum tile size allowed for the f32 <= bf16 x bf16 op
Reviewed By: dcaballe
Differential Revision: https://reviews.llvm.org/D118277
This diff modifies the tablegen specification and code generation for
BitEnumAttr attributes in MLIR Operation Definition Specification (ODS) files.
Specifically:
- there is a new tablegen class for "none" values (i.e. no bits set)
- single-bit enum cases are specified via bit index (i.e. [0, 31]) instead of
the resulting enum integer value
- there is a new tablegen class to represent a "grouped" bitwise OR of other
enum values
This diff is intended as an initial step towards improving "fastmath"
optimization support in MLIR, to allow more precise control of whether certain
floating point optimizations are applied in MLIR passes. "Fast" math options
for floating point MLIR operations would (following subsequent RFC and
discussion) be specified by using the improved enum bit support in this diff.
For example, a "fast" enum value would act as an alias for a group of other
cases (e.g. finite-math-only, no-signed-zeros, etc.), in a way that is similar
to support in C/C++ compilers (clang, gcc).
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D117029
This is part of splitting up the standard dialect. The move makes sense anyways,
given that the memref dialect already holds memref.atomic_rmw which is the non-region
sibling operation of std.generic_atomic_rmw (the relationship is even more clear given
they have nearly the same description % how they represent the inner computation).
Differential Revision: https://reviews.llvm.org/D118209
The GPU dialect currently contains an explicit reference to LLVMFuncOp
during verification to handle the situation where the kernel has already been
converted. This commit changes that reference to instead use FunctionOpInterface,
which has two main benefits:
* It allows for removing an otherwise unnecessary dependency on the LLVM dialect
* It removes hardcoded assumptions about the lowering path and use of the GPU dialect
Differential Revision: https://reviews.llvm.org/D118172
This reverts commit ef82063207.
- It conflicts with the existing llvm::size in STLExtras, which will now
never be called.
- Calling it without llvm:: breaks C++17 compat
This is for compatibility with existing bufferization passes. Also clean up memref type generation a bit.
Differential Revision: https://reviews.llvm.org/D118243
This revision adds enough support to allow InlineAsmOp to work properly with indirect memory constraints "*m".
These require an explicit "elementtype" TypeAttr on the operands to pass LLVM verification and need to be provided.
Reviewed By: bkramer
Differential Revision: https://reviews.llvm.org/D118006
The existing implementation called DenseMap::insert, which is a no-op if the map already contains an entry with the same key.
Differential Revision: https://reviews.llvm.org/D118165
If we are extracting it is more useful to push the index_cast past the
extraction. This increases the chance the tensor.extract can evaluated at
compile time.
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D118204
There is not much of a benefit to reshape a from element vs reloading it.
Updated to progagate shape manipulations into the output type of
tensor.from_elements.
Reviewed By: NatashaKnk
Differential Revision: https://reviews.llvm.org/D118201
Add methods to
- Get block argument that is tied with an opOperand
- Get the yield value that is tied with a output opOperand.
Differential Revision: https://reviews.llvm.org/D118085
Fusion of reshape ops by linearization incorrectly inverted the
indexing map before linearizing dimensions. This leads to incorrect
indexing maps used in the fused operation.
Differential Revision: https://reviews.llvm.org/D117908
This pattern is not written to handle operations with `linalg.index`
operations in its body, i.e. operations that have index semantics.
Differential Revision: https://reviews.llvm.org/D117856
This is mostly a copy of the existing tensor.from_elements bufferization. Once TensorInterfaceImpl.cpp is moved to the tensor dialect, the existing rewrite pattern can be deleted.
Differential Revision: https://reviews.llvm.org/D117775
This is mostly a copy of the existing tensor.generate bufferization. Once TensorInterfaceImpl.cpp is moved to the tensor dialect, the existing rewrite pattern can be deleted.
Differential Revision: https://reviews.llvm.org/D117770
This patch supports the atomic construct (capture) following section 2.17.7 of OpenMP 5.0 standard. Also added tests for the same.
Reviewed By: peixin, kiranchandramohan
Differential Revision: https://reviews.llvm.org/D115851
This is a pretty important debugging option to stay hidden. Also,
improve its cmd-line description; the current description gives no hint
that this is the one to use to have locations printed inline.
Out-of-line locations are also unproductive to work with in many cases
where the locations are actually compact, which is also why this option
should be more visible. This revision doesn't change the default on it
though.
Reviewed By: rriddle, jpienaar
Differential Revision: https://reviews.llvm.org/D117186
A lot of dialects have dependencies that are unnecessary, either because of copy/paste
of files when creating things or some other means. This commit cleans up a bunch of
the simple ones:
* Copy/Paste or missed during refactoring
Most of the dependencies cleaned up here look like copy/paste errors when creating
new dialects/transformations, or because the dependency wasn't removed during a
refactoring (e.g. when splitting the standard dialect).
* Unnecessary hard coding of constant operations in matchers
There are a few instances where a dialect had a dependency because it
was hardcoding checks for constant operations instead of using the better m_Constant
approach.
Differential Revision: https://reviews.llvm.org/D118062
This has been a major TODO for a very long time, and is necessary for establishing a proper
dialect-free dependency layering for the Transforms library. Code was moved to effectively
two main locations:
* Affine/
There was quite a bit of affine dialect related code in Transforms/ do to historical reasons
(of a time way into MLIR's past). The following headers were moved to:
Transforms/LoopFusionUtils.h -> Dialect/Affine/LoopFusionUtils.h
Transforms/LoopUtils.h -> Dialect/Affine/LoopUtils.h
Transforms/Utils.h -> Dialect/Affine/Utils.h
The following transforms were also moved:
AffineLoopFusion, AffinePipelineDataTransfer, LoopCoalescing
* SCF/
Only one SCF pass was in Transforms/ (likely accidentally placed here): ParallelLoopCollapsing
The SCF specific utilities in LoopUtils have been moved to SCF/Utils.h
* Misc:
mlir::moveLoopInvariantCode was also moved to LoopLikeInterface.h given
that it is a simple utility defined in terms of LoopLikeOpInterface.
Differential Revision: https://reviews.llvm.org/D117848
Transforms/ should only contain transformations that are dialect-independent and
this pass interacts with MemRef operations (making it a better fit for living in that
dialect).
Differential Revision: https://reviews.llvm.org/D117841
Transforms/ should only contain dialect-independent transformations,
and these files are a much better fit for the bufferization dialect anyways.
Differential Revision: https://reviews.llvm.org/D117839
The current lowering from GPU to NVVM does
not correctly handle the following cases when
lowering the gpu shuffle op.
1. When the active width is set to 32 (all lanes),
then the current approach computes (1 << 32) -1 which
results in poison values in the LLVM IR. We fix this by
defining the active mask as (-1) >> (32 - width).
2. In the case of shuffle up, the computation of the third
operand c has to be different from the other 3 modes due to
the op definition in the ISA reference.
(https://docs.nvidia.com/cuda/parallel-thread-execution/index.html)
Specifically, the predicate value is computed as j >= maxLane
for up and j <= maxLane for all other modes. We fix this by
computing maskAndClamp as 32 - width for this mode.
TEST: We modify the existing test and add more checks for the up mode.
Reviewed By: ThomasRaoux
Differential Revision: https://reviews.llvm.org/D118086
Adding a similar decomposition for exponential minus one to the SPIRV
backends along with the necessary tests.
Reviewed By: antiagainst
Differential Revision: https://reviews.llvm.org/D118081
Control-Flow Sink moves operations whose only uses are in conditionally-executed regions into those regions so that paths in which their results are not needed do not perform unnecessary computation.
Depends on D115087
Reviewed By: jpienaar, rriddle, bondhugula
Differential Revision: https://reviews.llvm.org/D115088
Add a transpose option to hoist padding to transpose the padded tensor before storing it into the packed tensor. The early transpose improves the memory access patterns of the actual compute kernel. The patch introduces a transpose right after the hoisted pad tensor and a second transpose inside the compute loop. The second transpose can either be fused into the compute operation or will canonicalize away when lowering to vector instructions.
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D117893
No longer go through an external model. Also put BufferizableOpInterface into the same build target as the BufferizationDialect. This allows for some code reuse between BufferizationOps canonicalizers and BufferizableOpInterface implementations.
Differential Revision: https://reviews.llvm.org/D117987
Both insertion points are valid. This is to make BufferizableOpInteface-based bufferization compatible with existing partial bufferization test cases. (So less changes are necessary to unit tests.)
Differential Revision: https://reviews.llvm.org/D117986
This is the only op that is not supported via BufferizableOpInterfaceImpl bufferization. Once this op is supported we can switch `tensor-bufferize` over to the new unified bufferization.
Differential Revision: https://reviews.llvm.org/D117985
This is in preparation of unifying the existing bufferization with One-Shot bufferization.
A subsequent commit will replace `tensor-bufferize`'s implementation with the BufferizableOpInterface-based implementation and move over missing test cases.
Differential Revision: https://reviews.llvm.org/D117984
Only using that change in StringRef already decreases the number of
preoprocessed lines from 7837621 to 7776151 for LLVMSupport
Perhaps more interestingly, it shows that many files were relying on the
inclusion of StringRef.h to have the declaration from STLExtras.h. This
patch tries hard to patch relevant part of llvm-project impacted by this
hidden dependency removal.
Potential impact:
- "llvm/ADT/StringRef.h" no longer includes <memory>,
"llvm/ADT/Optional.h" nor "llvm/ADT/STLExtras.h"
Related Discourse thread:
https://llvm.discourse.group/t/include-what-you-use-include-cleanup/5831
This patch moves merging of duplicate divisions to presburger utility
functions. This is required to support division merging in structures other
than IntegerPolyhedron.
Reviewed By: arjunp
Differential Revision: https://reviews.llvm.org/D118001
Pass a ValueRange instead of an ArrayRef<Value> for better compatibility. Also provide an additional function overload that automatically deallocates the buffer if specified.
Differential Revision: https://reviews.llvm.org/D118025
This patch changes names of identifiers and their corresponding getters in
PresburgerSet to match those of IntegerPolyhedron.
Reviewed By: arjunp
Differential Revision: https://reviews.llvm.org/D117998
When the coefficients of dividend are negative, the gcd may be negative
which will change the sign of dividend and overflow denominator.
Reviewed By: Groverkss
Differential Revision: https://reviews.llvm.org/D117911
When 2 clamp ops are in a row, they can be canonicalized into a single clamp
that uses the most constrained range
Reviewed By: rsuderman
Differential Revision: https://reviews.llvm.org/D117934
Rationale:
Although file I/O is a bit alien to MLIR itself, we provide two convenient ways
for sparse tensor I/O. The input part was already there (behind the swiss army
knife sparse_tensor.new). Now we have a sparse_tensor.out to write out data. As
before, the ops are kept vague and may change in the future. For now this
allows us to compare TACO vs MLIR very easily.
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D117850
Implement a taylor series approximation for atan and add an atan2 lowering
that uses atan's appromation. This includes tests for edge cases and tests
for each quadrant.
Reviewed By: NatashaKnk
Differential Revision: https://reviews.llvm.org/D115682
Add TACO tests to test/Integration/Dialect/SparseTensor/taco. Add the MLIR
PyTACO implementation as tools under the directory.
Reviewed By: aartbik, mehdi_amini
Differential Revision: https://reviews.llvm.org/D117260
The cleanup was manual, but assisted by "include-what-you-use". It consists in
1. Removing unused forward declaration. No impact expected.
2. Removing unused headers in .cpp files. No impact expected.
3. Removing unused headers in .h files. This removes implicit dependencies and
is generally considered a good thing, but this may break downstream builds.
I've updated llvm, clang, lld, lldb and mlir deps, and included a list of the
modification in the second part of the commit.
4. Replacing header inclusion by forward declaration. This has the same impact
as 3.
Notable changes:
- llvm/Support/TargetParser.h no longer includes llvm/Support/AArch64TargetParser.h nor llvm/Support/ARMTargetParser.h
- llvm/Support/TypeSize.h no longer includes llvm/Support/WithColor.h
- llvm/Support/YAMLTraits.h no longer includes llvm/Support/Regex.h
- llvm/ADT/SmallVector.h no longer includes llvm/Support/MemAlloc.h nor llvm/Support/ErrorHandling.h
You may need to add some of these headers in your compilation units, if needs be.
As an hint to the impact of the cleanup, running
clang++ -E -Iinclude -I../llvm/include ../llvm/lib/Support/*.cpp -std=c++14 -fno-rtti -fno-exceptions | wc -l
before: 8000919 lines
after: 7917500 lines
Reduced dependencies also helps incremental rebuilds and is more ccache
friendly, something not shown by the above metric :-)
Discourse thread on the topic: https://llvm.discourse.group/t/include-what-you-use-include-cleanup/5831
The LangRef currently lacks a top-level production, leaving the productions attribute-alias-def and type-alias-defunused. Clarify the situation by declaring what is to be parsed by an MLIR parser at the toplevel.
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D117668
In some cases, fusion can produce illegal operations if after fusion
the range of some of the loops cannot be computed from shapes of its
operands. Check for this case and abort the fusion if this happens.
Differential Revision: https://reviews.llvm.org/D117602
This is superseded by the same method on OpAsmOpInterface, which is
available on the Dialect through the Fallback mechanism,
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D117750
This extends dense attribute element access to support 8b and 16b ints.
Also extends the corresponding parts of the C api.
Reviewed By: ftynse
Differential Revision: https://reviews.llvm.org/D117731
This allows to pipe sequences of `mlir-opt -split-input-file | mlir-opt -split-input-file`.
Depends On D117750
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D117756
Benjamin Kramer