This patch moves IntegerPolyhedron::reset to FlatAffineConstraints::reset. This
function is not required in IntegerPolyhedron and creates ambiguity while
shifting implementations to IntegerRelation.
This patch is part of a series of patches to introduce relations in Presburger
library.
Reviewed By: arjunp
Differential Revision: https://reviews.llvm.org/D120628
PDL currently doesn't support result values from constraints, meaning we need
to error out until this is actually supported to avoid crashes.
Differential Revision: https://reviews.llvm.org/D119782
This commits adds a C++ generator to PDLL that generates wrapper PDL patterns
directly usable in C++ code, and also generates the definitions of native constraints/rewrites
that have code bodies specified in PDLL. This generator is effectively the PDLL equivalent of
the current DRR generator, and will allow easy replacement of DRR patterns with PDLL patterns.
A followup will start to utilize this for end-to-end integration testing and show case how to
use this as a drop-in replacement for DRR tablegen usage.
Differential Revision: https://reviews.llvm.org/D119781
If the operand list or result list of an operation expression is not specified, we interpret
this as meaning that the operands/results are "unconstraint" (i.e. "could be anything").
We currently don't properly handle differentiating this case from the case of
"no operands/results". This commit adds the insertion of implicit value/type range
variables when these lists are unspecified. This allows for adding proper support
for when zero operands or results are expected.
Differential Revision: https://reviews.llvm.org/D119780
This commits starts to plumb PDLL down into MLIR and adds an initial
PDL generator. After this commit, we will have conceptually support
end-to-end execution of PDLL. Followups will add CPP generation to
match the current DRR setup, and begin to add various end-to-end
tests to test PDLL execution.
Differential Revision: https://reviews.llvm.org/D119779
This patch removes a redundant check in hasConsistentState which is always true
after introduction of PresburgerSpace.
Reviewed By: arjunp
Differential Revision: https://reviews.llvm.org/D120615
This patch moves identifier kind specific insert/append functions like
`insertDimId`, `appendSymbolId`, etc. from IntegerPolyhedron to
FlatAffineConstraints.
This change allows for a smoother transition to IntegerRelation.
This change is part of a series of patches to introduce Relations in Presburger
library.
Reviewed By: arjunp
Differential Revision: https://reviews.llvm.org/D120576
This patch factors out various checks for dimension compatibility to
PresburgerSpace::isEqual and PresburgerLocalSpace::isEqual (for local
identifiers).
Reviewed By: arjunp
Differential Revision: https://reviews.llvm.org/D120565
In the main-loop of the current coalesce implementation `i` was incremented
twice for some cases. This patch fixes this bug and adds a regression
testcase.
Reviewed By: arjunp
Differential Revision: https://reviews.llvm.org/D120613
The PyTACO DSL doesn't support reduction to scalars. This change
enhances the MLIR-PyTACO implementation to support reduction to scalars.
Extend an existing test to show the syntax of reduction to scalars and
two methods to retrieve the scalar values.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D120572
The AVX2 lowering for transpose operations is only applicable to f32 vector types.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D120427
The existing AVX2 lowering patterns for the transpose op only triggers if the
input vector is 2-D. This patch extends the patterns to trigger for n-D vectors
which are effectively 2-D vectors (e.g., vector<1x4x1x8x1). The main constraint
for the generalized AVX2 patterns to be applicable to these vectors is that the
dimensions that are greater than one must be transposed. Otherwise, the existing
patterns are not applicable.
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D119505
This change gives explicit order of verifier execution and adds
`hasRegionVerifier` and `verifyWithRegions` to increase the granularity
of verifier classification. The orders are as below,
1. InternalOpTrait will be verified first, they can be run independently.
2. `verifyInvariants` which is constructed by ODS, it verifies the type,
attributes, .etc.
3. Other Traits/Interfaces that have marked their verifier as
`verifyTrait` or `verifyWithRegions=0`.
4. Custom verifier which is defined in the op and has marked
`hasVerifier=1`
If an operation has regions, then it may have the second phase,
5. Traits/Interfaces that have marked their verifier as
`verifyRegionTrait` or
`verifyWithRegions=1`. This implies the verifier needs to access the
operations in its regions.
6. Custom verifier which is defined in the op and has marked
`hasRegionVerifier=1`
Note that the second phase will be run after the operations in the
region are verified. Based on the verification order, you will be able to
avoid verifying duplicate things.
Reviewed By: Mogball
Differential Revision: https://reviews.llvm.org/D116789
Fix MLIR-PyTACO and some tests to use np.array_equal to compare integer
values.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D120526
Split arithmetic function into unary and binary functions. The revision prepares the introduction of unary and binary function attributes that work similar to type function attributes.
Depends On D120108
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D120109
This change allows the use of scalar tensors with index 0 in tensor index
expressions. In this case, the scalar value is broadcast to match the
dimensions of other tensors in the same expression.
Using scalar tensors as a destination in tensor index expressions is not
supported in the PyTACO DSL.
Add a PyTACO test to show the use of scalar tensors.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D120524
Prepare the OpDSL function handling to introduce more function classes. A follow up commit will split ArithFn into UnaryFn and BinaryFn. This revision prepares the split by adding a function kind enum to handle different function types using a single class on the various levels of the stack (for example, there is now one TensorFn and one ScalarFn).
Depends On D119718
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D120108
This patch refactors the looping strategy of coalesce for future patches. The new strategy works in-place and uses IneqType to organize inequalities into vectors of the same type. Future coalesce cases will pattern match on this organization. E.g. the contained case needs all inequalities and equalities to be redundant, so this case becomes checking whether the respective vectors are empty. For other cases, the patterns consider the types of all inequalities of both sets making it wasteful to only consider whether a can be coalesced with b in one step, as inequalities would need to be typed again for the opposite case. Therefore, the new strategy tries to coalesce a with b and b with a in a single step.
Reviewed By: Groverkss, arjunp
Differential Revision: https://reviews.llvm.org/D120392
This patch replaces various functions over inequalities/equalities in
IntegerPolyhedron with Matrix functions already implementing them or refactors
them to a Matrix function.
Reviewed By: arjunp
Differential Revision: https://reviews.llvm.org/D120482
This patch moves the Presburger library to a new `presburger` namespace.
This allows to shorten some names, helps to avoid polluting the mlir namespace,
and also provides some structure.
Reviewed By: arjunp
Differential Revision: https://reviews.llvm.org/D120505
This patch removes redundant code from fourierMotzkinEliminate implementation
using existing functions in IntegerPolyhedron.
Reviewed By: arjunp
Differential Revision: https://reviews.llvm.org/D120502
Previously, OpDSL operation used hardcoded type conversion operations (cast or cast_unsigned). Supporting signed and unsigned casts thus meant implementing two different operations. Type function attributes allow us to define a single operation that has a cast type function attribute which at operation instantiation time may be set to cast or cast_unsigned. We may for example, defina a matmul operation with a cast argument:
```
@linalg_structured_op
def matmul(A=TensorDef(T1, S.M, S.K), B=TensorDef(T2, S.K, S.N), C=TensorDef(U, S.M, S.N, output=True),
cast=TypeFnAttrDef(default=TypeFn.cast)):
C[D.m, D.n] += cast(U, A[D.m, D.k]) * cast(U, B[D.k, D.n])
```
When instantiating the operation the attribute may be set to the desired cast function:
```
linalg.matmul(lhs, rhs, outs=[out], cast=TypeFn.cast_unsigned)
```
The revsion introduces a enum in the Linalg dialect that maps one-by-one to the type functions defined by OpDSL.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D119718
This patch removes the `const` from `usingBigM` to enable the implicit copy assignment operator for Simplex.
Reviewed By: Groverkss
Differential Revision: https://reviews.llvm.org/D120542
This transformation is useful to break dependency between consecutive loop
iterations by increasing the size of a temporary buffer. This is usually
combined with heavy software pipelining.
Differential Revision: https://reviews.llvm.org/D119406
This adds a variable op, emitted as C/C++ locale variable, which can be
used if the `emitc.constant` op is not sufficient.
As an example, the canonicalization pass would transform
```mlir
%0 = "emitc.constant"() {value = 0 : i32} : () -> i32
%1 = "emitc.constant"() {value = 0 : i32} : () -> i32
%2 = emitc.apply "&"(%0) : (i32) -> !emitc.ptr<i32>
%3 = emitc.apply "&"(%1) : (i32) -> !emitc.ptr<i32>
emitc.call "write"(%2, %3) : (!emitc.ptr<i32>, !emitc.ptr<i32>) -> ()
```
into
```mlir
%0 = "emitc.constant"() {value = 0 : i32} : () -> i32
%1 = emitc.apply "&"(%0) : (i32) -> !emitc.ptr<i32>
%2 = emitc.apply "&"(%0) : (i32) -> !emitc.ptr<i32>
emitc.call "write"(%1, %2) : (!emitc.ptr<i32>, !emitc.ptr<i32>) -> ()
```
resulting in pointer aliasing, as %1 and %2 point to the same address.
In such a case, the `emitc.variable` operation can be used instead.
Reviewed By: jpienaar
Differential Revision: https://reviews.llvm.org/D120098
This patch removes binary operator enum which was introduced with `omp.atomic.update`. Now the update operation handles update in a region so this is no longer required.
Reviewed By: kiranchandramohan
Differential Revision: https://reviews.llvm.org/D120458
Documentation exists about the details of the API but is missing a
description of the overall structure per dialect.
Reviewed By: shabalin
Differential Revision: https://reviews.llvm.org/D117002
The current implementation of ShuffleVectorOp assumes all vectors are
scalable. LLVM IR allows shufflevector operations on scalable vectors,
and the current translation between LLVM Dialect and LLVM IR does the
rigth thing when the shuffle mask is all zeroes. This is required to
do a splat operation on a scalable vector, but it doesn't make sense
for scalable vectors outside of that operation, i.e.: with non-all zero
masks.
Differential Revision: https://reviews.llvm.org/D118371
In D115022, we introduced an optimization where OpResults of a `linalg.generic` may bufferize in-place with an "in" OpOperand if the corresponding "out" OpOperand is not used in the computation.
This optimization can lead to unexpected behavior if the newly chosen OpOperand is in the same alias set as another OpOperand (that is used in the computation). In that case, the newly chosen OpOperand must bufferize out-of-place. This can be confusing to users, as always choosing the "out" OpOperand (regardless of whether it is used) would be expected when having the notion of "destination-passing style" in mind.
With this change, we go back to always bufferizing in-place with "out" OpOperands by default, but letting users override the behavior with a bufferization option.
Differential Revision: https://reviews.llvm.org/D120182
Previously only accessing values for `index` and signless int types
would work; signed and unsigned ints would hit an assert in
`IntegerAttr::getInt`. This exposes `IntegerAttr::get{S,U}Int` to the C
API and calls the appropriate function from the python bindings.
Reviewed By: ftynse
Differential Revision: https://reviews.llvm.org/D120194
Previously, we only support float64. We now support float32 and float64. When
constructing a tensor without providing a data type, the default is float32.
Fix the tests to data type consistency. All PyTACO application tests now use
float32 to match the default data type of TACO. Other tests may use float32 or
float64.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D120356
Now that sparse tensor types are first-class citizens and the sparse compiler
is taking shape, it is time to make sure other compiler optimizations compose
well with sparse tensors. Mostly, this should be completely transparent (i.e.,
dense and sparse take the same path). However, in some cases, optimizations
only make sense in the context of sparse tensors. This is a first example of
such an optimization, where fusing a sampled elt-wise multiplication only makes
sense when the resulting kernel has a potential lower asymptotic complexity due
to the sparsity.
As an extreme example, running SDDMM with 1024x1024 matrices and a sparse
sampling matrix with only two elements runs in 463.55ms in the unfused
case but just 0.032ms in the fused case, with a speedup of 14485x that
is only possible in the exciting world of sparse computations!
Reviewed By: mravishankar
Differential Revision: https://reviews.llvm.org/D120429
By specifying a sectionMemoryMapper, users can control how
memory for JIT code is allocated.
In particular, I need this in order to use a named memory
region so that profilers such as perf(1) can correctly label
execution cycles coming from JIT'ed code.
Reviewed-by: ezhulenev
Differential Revision: https://reviews.llvm.org/D120415
Given a cmpf of either uitofp or sitofp and a constant, attempt to canonicalize it to a cmpi.
This PR rewrites equivalent code within LLVM to now apply to MLIR arith.
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D117257
+ compare block size with the unrollable inner dimension
+ reduce nesting in the code and simplify a bit IR building
Reviewed By: cota
Differential Revision: https://reviews.llvm.org/D120075
This eliminates the requirement that pass-related strings outlive pass
instances, which will facilitate future work enabling dynamic passes
written in other languages.
Differential Revision: https://reviews.llvm.org/D120341
Its number of optional parameters has grown too large,
which makes adding new optional parameters quite a chore.
Fix this by using an options struct.
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D120380
Use an `MLIRContext` declared in a single place in the `parsePoly` function that almost all Presburger unit tests use for parsing sets. This function is only used in tests.
This saves us from having to declare and pass a new `MLIRContext` in every test.
Reviewed By: bondhugula, mehdi_amini
Differential Revision: https://reviews.llvm.org/D119251
This trait results in PDL ops being erroneously CSE'd. These ops are side-effect free in the rewriter but not in the matcher (where unused values aren't allowed anyways). These ops should have a more nuanced side-effect modeling, this is fixing a bug introduced by a previous change.
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D120222
Header class in SPIR-V HTML spec has changed. Update script to reflect that.
Reviewed By: antiagainst
Differential Revision: https://reviews.llvm.org/D120179
The related functionality is moved over to the bufferization dialect. Test cases are cleaned up a bit.
Differential Revision: https://reviews.llvm.org/D120191
This patch adds a class to represent a relation in Presburger Library.
This patch only adds the skeleton class. Functionality from IntegerPolyhedron
will be moved to IntegerRelation in later patches to make it easier to review.
This patch is a part of a series of patches adding support for relations in
Presburger Library.
Reviewed By: arjunp
Differential Revision: https://reviews.llvm.org/D120156
The `.def` and `.def_property_readonly` functions in PybindAdaptors.h should
construct the functions as method of the current class rather than as method of
pybind11:none(), which is an object and not even a class.
Depends On D117658
Reviewed By: gysit
Differential Revision: https://reviews.llvm.org/D117659
This commit adds canonicalization pattern in `linalg.generic` op
for static shape inference. If any of the inputs or outputs have
static shape or is casted from a tensor of static shape, then
shapes of all the inputs and outputs can be inferred by using the
affine map of the static shape input/output.
Signed-Off-By: Prateek Gupta <prateek@nod-labs.com>
Reviewed By: mravishankar
Differential Revision: https://reviews.llvm.org/D118929
This patch adds assemblyFormat for omp.sections operation.
Some existing functions have been altered to fit the custom directive
in assemblyFormat. This has led to their callsites to get modified too,
but those will be removed in later patches, when other operations get
their assemblyFormat. All operations were not changed in one patch for
ease of review.
Reviewed By: Mogball
Differential Revision: https://reviews.llvm.org/D120176
This patch adds typing of inequalities to the simplex. This is a cental part of the coalesce algorithm and will be heavily used in later coalesce patches. Currently, only the three most basic types are supported with more to be introduced when they are needed.
Reviewed By: arjunp
Differential Revision: https://reviews.llvm.org/D119925
This allows to differentiate between the cases where the optimum does not
exist due to being unbounded and due to the polytope being empty.
Reviewed By: Groverkss
Differential Revision: https://reviews.llvm.org/D120127
Add `BufferizableOpInterface::verifyAnalysis`. Ops can implement this method to check for expected invariants and limitations.
The purpose of this change is to introduce a modular way of checking assertions such as `assertScfForAliasingProperties`.
Differential Revision: https://reviews.llvm.org/D120189
This patch adds assemblyFormat for omp.parallel operation.
Some existing functions have been altered to fit the custom directive
in assemblyFormat. This has led to their callsites to get modified too,
but those will be removed in later patches, when other operations get
their assemblyFormat. All operations were not changed in one patch for
ease of review.
Reviewed By: Mogball
Differential Revision: https://reviews.llvm.org/D120157
These routines will need to be specialized a lot more based on value types,
index types, pointer types, and permutation/dimension ordering. This is a
careful first step, providing some functionality needed in PyTACO bridge.
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D120154
This patch removes the following clauses from OpenMP Dialect:
- private
- firstprivate
- lastprivate
- shared
- default
- copyin
- copyprivate
The privatization clauses are being handled in the flang frontend. The
data copying clauses are not being handled anywhere for now. Once
we have a better picture of how to handle these clauses in OpenMP
Dialect, we can add these. For the time being, removing unneeded
clauses.
For detailed discussion about this refer to [[ https://discourse.llvm.org/t/rfc-privatisation-in-openmp-dialect/3526 | Privatisation in OpenMP dialect ]]
Reviewed By: kiranchandramohan, clementval
Differential Revision: https://reviews.llvm.org/D120029
This patch introducing seperating dimensions into two types: Domain and Range.
This allows building relations over PresburgerSpace.
This patch is part of a series of patches to introduce relations in Presburger
library.
Reviewed By: arjunp
Differential Revision: https://reviews.llvm.org/D119709
MLIR has the notion of allocation scopes which specify that stack allocations (e.g. memref.alloca, llvm.alloca) should be freed or equivalently aren't available at the end of the corresponding region.
Currently neither OpenMP parallel nor SCF parallel regions have the notion of such a scope.
This clearly makes sense for an OpenMP parallel as this is implemented in with a new function which outlines the region, and clearly any allocations in that newly outlined function have a lifetime that ends at the return of the function, by definition.
While SCF.parallel doesn't have a guaranteed runtime which it is implemented with, this similarly makes sense for SCF.parallel since otherwise an allocation within an SCF.parallel will needlessly continue to allocate stack memory that isn't cleaned up until the function (or other allocation scope op) which contains the SCF.parallel returns. This means that it is impossible to represent thread or iteration-local memory without causing a stack blow-up. In the case that this stack-blow-up behavior is intended, this can be equivalently represented with an allocation outside of the SCF.parallel with a size equal to the number of iterations.
Reviewed By: ftynse
Differential Revision: https://reviews.llvm.org/D119743
insert is soft deprecated, so remove all references so it's less likely
to be used and can be easily removed in the future.
Differential Revision: https://reviews.llvm.org/D120021
This is a bit awkward since ExtractOp allows both `f32` and
`vector<1xf32>` results for a scalar extraction. Allow both, but make
inference return the scalar to make this as NFC as possible.
This change changes the handling of trailing dimensions with unknown
extent. Users of the changessociationIndicesForReshape helper should
see benefits when transforming reshape like operations into
expand/collapse pairs if the higher-rank type has trailing unknown
dimensions.
The motivating example is a reshape from tensor<16x1x?xi32> to
tensor<16xi32> that can be modeled as collapsing the three dimensions.
Differential Revision: https://reviews.llvm.org/D119730
Previously, NaNs would be dropped in favor of bounded values which was
strictly incorrect. Now the min/max operation propagate this
information. Not all uses of min/max need this, but the given change
will help protect future additions, and this prevents the need for an
additional cmpf and select operation to handle NaNs.
Differential Revision: https://reviews.llvm.org/D120020
This op is added to allow MLIR code running on multi-GPU systems to
select the GPU they want to execute operations on when no GPU is
otherwise specified.
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D119883
NamedAttrList.append(StringAttr, StringAttr) fails to compile because it is
matched to the IteratorT append. Fixes the method to only match if the type is
an iterator.
It is time to compose Linalg related optimizations with SparseTensor
related optimizations. This is a careful first start by adding some
general Linalg optimizations "upstream" of the sparse compiler in the
full sparse compiler pipeline. Some minor changes were needed to make
those optimizations aware of sparsity.
Note that after this, we will add a sparse specific fusion rule,
just to demonstrate the power of the new composition.
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D119971
In SPIR-V, resources are represented as global variables that
are bound to certain descriptor. SPIR-V requires those global
variables to be declared as aliased if multiple ones are bound
to the same slot. Such aliased decorations can cause issues
for transcompilers like SPIRV-Cross when converting to source
shading languages like MSL.
So this commit adds a pass to perform analysis of aliased
resources and see if we can unify them into one.
Reviewed By: ThomasRaoux
Differential Revision: https://reviews.llvm.org/D119872
This would create a double free when a memref is passed twice to the
same op. This wasn't a problem at the time the pass was written but is
common since the introduction of scf.while.
There's a latent non-determinism that's triggered by the test, but this
change is messy enough as-is so I'll leave that for later.
Differential Revision: https://reviews.llvm.org/D120044
The MLIR parser allows regions to have an unnamed entry block.
Make this explicit in the language grammar.
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D119950
During dialect conversion, target materialization is triggered to create
cast-like operations when a type mismatch occurs between the value that
replaces a rewritten operation and the type that another operations expects as
operands processed by the type conversion. First, a dummy cast is inserted to
make sure the pattern application can proceed. The decision to trigger the
user-provided materialization hook is taken later based on the result of the
dummy cast having uses. However, it only has uses if other patterns constructed
new operations using the casted value as operand. If existing (legal)
operations use the replaced value, they may have not been updated to use the
casted value yet. The conversion infra would then delete the dummy cast first,
and then would replace the uses with now-invalid (null in the bast case) value.
When deciding whether to trigger cast materialization, check for liveness the
uses not only of the casted value, but also of all the values that it replaces.
This was discovered in the finalizing bufferize pass that cleans up
mutually-cancelling casts without touching other operations. It is not
impossible that there are other scenarios where the dialect converison infra
could produce invalid operand uses because of dummy casts erased too eagerly.
Reviewed By: springerm
Differential Revision: https://reviews.llvm.org/D119937
Previously `gpu-kernel-outlining` pass was also doing index computation sinking into gpu.launch before actual outlining.
Split ops sinking from `gpu-kernel-outlining` pass into separate pass, so users can use theirs own sinking pass before outlining.
To achieve old behavior users will need to call both passes: `-gpu-launch-sink-index-computations -gpu-kernel-outlining`.
Differential Revision: https://reviews.llvm.org/D119932
Currently some of the nested IR building inconsistently uses `nb` and `b`, it's very easy to call wrong builder outside of the current scope, so for simplicity all builders are always called `b`, and in nested IR building regions they just shadow the "parent" builder.
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D120003
A very small refactoring, but a big impact on tests that expect an exact order.
This revision fixes the tests, but also makes them less brittle for similar
minor changes in the future!
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D119992
This commit adds a pattern to wrap a tensor.pad op with
an scf.if op to separate the cases where we don't need padding
(all pad sizes are actually zeros) and where we indeed need
padding.
This pattern is meant to handle padding inside tiled loops.
Under such cases the padding sizes typically depend on the
loop induction variables. Splitting them would allow treating
perfect tiles and edge tiles separately.
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D117018
The pad-slice swap pattern generates `scf.if` and `tensor.generate`
to guard against zero-sized slices if it cannot prove the slice is
always non-zero. This is safe but quite conservative. It can be
unnecessary for cases where we know by problem definition such cases
does not exist, even if with dynamic shaped ops or unknown tile/slice
sizes, e.g., convolution padding size = 1 with kernel dim size = 3.
So this commit introduces a control to the pattern to specify
whether to generate the if constructs to handle such cases better,
given that once the if constructs is materialized, it's very hard
to analyze and simplify.
Reviewed By: mravishankar
Differential Revision: https://reviews.llvm.org/D117017
Fusion of `linalg.generic` with
`tensor.expand_shape/tensor.collapse_shape` currently handles fusion
with reshape by expanding the dimensionality of the `linalg.generic`
operation. This helps fuse elementwise operations better since they
are fused at the highest dimensionality while keeping all indexing
maps involved projected permutations. The intent of these is to push
the reshape to the boundaries of functions.
The presence of named ops (or other ops across which the reshape
cannot be propagated) stops the propagation to the edges of the
function. At this stage, the converse patterns that fold the reshapes
with generic ops by collapsing the dimensions of the generic op can
push the reshape towards edges. In particular it helps the case where
reshapes exist in between named ops and generic ops.
`linalg.named_op` -> `tensor.expand_shape` -> `linalg.generic`
Pushing the reshape down will help fusion of `linalg.named_op` ->
`linalg.generic` using tile + fuse transformations.
This pattern is intended to replace the following patterns
1) FoldReshapeByLinearization : These patterns create indexing maps
that are not projected permutations that affect future
transformations. They are only useful for folding unit-dimensions.
2) PushReshapeByExpansion : This pattern has the same functionality
but has some restrictions
a) It tries to avoid creating new reshapes that limits its
applicability. The pattern added here can achieve the same
functionality through use of the `controlFn` that allows clients
of the pattern freedom to make this decision.
b) It does not work for ops with indexing semantics.
These patterns will be deprecated in a future patch.
Differential Revision: https://reviews.llvm.org/D119365
This change exposes printer flags in AsmState and AsmStateImpl. All functions
receiving AsmState as a parameter now use the flags from the AsmState instead of
taking an additional OpPrintingFlags parameter.
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D119870
This allow user to register a callback that can annotate operations
during software pipelining. This allows user potential annotate op to
know what part of the pipeline they correspond to.
Differential Revision: https://reviews.llvm.org/D119866
Without results, there is no getType injected and so generating one in prefixed form doesn't result in any failures during C++ compilation.
Differential Revision: https://reviews.llvm.org/D119871
This test shows that when access patterns do not match (e.g. transposing
a row-wise sparse matrix into another row-wise sparse matrix), a conversion
operation in between can enable codegen (i.e. avoid cycle in iteration graph).
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D119864
Optional parameters with `defaultValue` set will be populated with that value if they aren't encountered during parsing. Moreover, parameters equal to their default values are elided when printing.
Depends on D118210
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D118544
This change is needed when lowering alloca()-using code on targets
such as ROCDL that represent private scratch space as a separate
address space.
Reviewed By: ftynse
Differential Revision: https://reviews.llvm.org/D119775
Casting between scalable vectors and fixed-length vectors doesn't make
sense. If one of the operands is scalable, the other has to be scalable
to be able to guarantee they have the same shape at runtime.
Differential Revision: https://reviews.llvm.org/D119568
This patch changes the syntax of omp.atomic.update to allow the other
dialects to modify the variable with appropriate operations in the
region.
Reviewed By: ftynse
Differential Revision: https://reviews.llvm.org/D119522
Add verifier for gpu.alloc op to verify if the dimension operand counts
and symbol operand counts are same as their memref counterparts.
Differential Revision: https://reviews.llvm.org/D117427
Support ALLOW filters and DENY filters. This is needed for compatibility with existing code that specifies more complex op filters.
Differential Revision: https://reviews.llvm.org/D119820
Also, it seems Khronos has changed html spec format so small adjustment to script was needed.
Base op parsing is also probably broken.
Differential Revision: https://reviews.llvm.org/D119678
The only method to create a true dense tensor (i.e un-annotated) in MLIR-PyTACO
is through the from_array method. However, the annotated all dense tensors are
also implemented as true dense tensor currently. The PR fixes the
implementation to support annotated all dense sparse tensors.
Extend the tensor init method to support the construction of a tensor without
any sparsity annotation.
Change the tensor to_file method to only support writing unpacked sparse
tensors to file through the MLIR sparse tensor dialect.
Add unit tests for true dense tensors and all dense sparse tensors.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D119500
This patch changes the argument from template-IRBuilder to IRBuilderBase
thus allowing us to write less code while getting the location from a
builder.
Reviewed By: ftynse
Differential Revision: https://reviews.llvm.org/D119717
* While annoying, this is the only way to get C++ exception handling out of the happy path for normal iteration.
* Implements sq_length and sq_item for the sequence protocol (used for iteration, including list() construction).
* Implements mp_subscript for general use (i.e. foo[1] and foo[1:1]).
* For constructing a `list(op.results)`, this reduces the time from ~4-5us to ~1.5us on my machine (give or take measurement overhead) and eliminates C++ exceptions, which is a worthy goal in itself.
* Compared to a baseline of similar construction of a three-integer list, which takes 450ns (might just be measuring function call overhead).
* See issue discussed on the pybind side: https://github.com/pybind/pybind11/issues/2842
Differential Revision: https://reviews.llvm.org/D119691
Rationale:
empty line between main include for this file
moved include that actually defines code into right section
Note that this revision started as breaking up ops/attrs even more
(for bug https://github.com/llvm/llvm-project/issues/52748), but due
the the connection in Dialect.initalize(), this cannot be split further).
All heavy lifting refactoring was already done by River in previous cleanup.
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D119617
Adds a pointer type to EmitC. The emission of pointers is so far only
possible by using the `emitc.opaque` type
Co-authored-by: Simon Camphausen <simon.camphausen@iml.fraunhofer.de>
Reviewed By: jpienaar
Differential Revision: https://reviews.llvm.org/D119337
Adapt the region builder signature to hand in the attributes of the created ops. The revision is a preparation step the support named ops that need access to the operation attributes during op creation.
Depends On D119692
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D119693
Group and reorder the classed defined by comprehension.py and add type annotations.
Depends On D119126
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D119692
Index attributes had no default value, which means the attribute values had to be set on the operation. This revision adds a default parameter to `IndexAttrDef`. After the change, every index attribute has to define a default value. For example, we may define the following strides attribute:
```
```
When using the operation the default stride is used if the strides attribute is not set. The mechanism is implemented using `DefaultValuedAttr`.
Additionally, the revision uses the naming index attribute instead of attribute more consistently, which is a preparation for follow up revisions that will introduce function attributes.
Depends On D119125
Reviewed By: stellaraccident
Differential Revision: https://reviews.llvm.org/D119126
This pass doesn't have any limitations specific to FuncOp and it will be useful to be able to run it on other ops (e.g. gpu.func).
Differential Revision: https://reviews.llvm.org/D119662
Mehdi Amini