This new option is set to `false` by default. It should be set only in Canonicalizer tests to detect faulty canonicalization patterns. I.e., patterns that prevent the canonicalizer from converging. The canonicalizer should always convergence on such small unit tests that we have in `canonicalize.mlir`.
Two faulty canonicalization patterns were detected and fixed with this change.
Differential Revision: https://reviews.llvm.org/D140873
External functions have no body, so they cannot be analyzed. Assume conservatively that each tensor bbArg may be aliasing with each tensor result. Furthermore, assume that each function arg is read and written-to after bufferization. This default behavior can be controlled with `bufferization.access` (similar to `bufferization.memory_layout`) in test cases.
Also fix a bug in the dialect attribute verifier, which did not run for region argument attributes.
Differential Revision: https://reviews.llvm.org/D139517
TensorCopyInsertion should not have been exposed as a pass. This was a flaw in the original design. It is a preparation step for bufferization and certain transforms (that would otherwise be legal) are illegal between TensorCopyInsertion and actual rewrite to MemRef ops. Therefore, even if broken down as two separate steps internally, they should be exposed as a single pass.
This change affects the sparse compiler, which uses `TensorCopyInsertionPass`. A new `SparsificationAndBufferizationPass` is added to replace all passes in the sparse tensor pipeline from `TensorCopyInsertionPass` until the actual bufferization (rewrite to memref/non-tensor). It is generally unsafe to run arbitrary passes in-between, in particular passes that hoist tensor ops out of loops or change SSA use-def chains along tensor ops.
Differential Revision: https://reviews.llvm.org/D138915
This patch consolidates the two transform ops from the affine dialect
and the scf dialect to avoid code duplication.
This is to address the review comments from
https://reviews.llvm.org/D137997.
The transform ops directory / file structure for the affine dialect is
kept for the purpose of forth-coming transform ops
for affine, but get_parent_for and unroll are removed.
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D138980
This is generated by running
```
sed --in-place 's/[[:space:]]\+$//' mlir/**/*.td
sed --in-place 's/[[:space:]]\+$//' mlir/**/*.mlir
```
Reviewed By: rriddle, dcaballe
Differential Revision: https://reviews.llvm.org/D138866
Dim sizes of `scf.foreach_thread` op results match the dim sizes of their respective tied shared_outs operands.
Differential Revision: https://reviews.llvm.org/D138484
MemRef has been accepting a general Attribute as memory space for
a long time. This commits updates bufferization side to catch up,
which allows downstream users to plugin customized symbolic memory
space. This also eliminates quite a few `getMemorySpaceAsInt`
calls, which is deprecated.
Reviewed By: springerm
Differential Revision: https://reviews.llvm.org/D138330
Previously, the need for a dense permutation leaked into the thread_dim_mapping specification.
This revision allows to use a sparse specification of the thread_dim_mapping and the proper completion / sorting is applied automatically.
In the process, the sematics of scf.foreach_thread is tightened to require a matching number of thread dimensions and mappings.
The relevant negative test is added.
Differential Revision: https://reviews.llvm.org/D137906
`scf.foreach_thread` defines mapping its loops to processors via an integer array, see an example below. A lowering can use this mapping. However, expressing mapping as an integer array is very confusing, especially when there are multiple levels of parallelism. In addition, the op does not verify the integer array. This change introduces device mapping attribute to make mapping descriptive and verifiable. Then it makes GPU transform dialect use it.
```
scf.foreach_thread (%i, %j) in (%c1, %c2) {
scf.foreach_thread (%i2, %j2) in (%c1, %c2)
{...} { thread_dim_mapping = [0, 1]}
} { thread_dim_mapping = [0, 1]}
```
It first introduces a `DeviceMappingInterface` which is an attribute interface. `scf.foreach_thread` defines its mapping via this interface. A lowering must define its attributes and implement this interface as well. This way gives us a clear validation.
The change also introduces two new attributes (`#gpu.thread<x/y/z>` and `#gpu.block<x,y,z>` ). After this change, the above code prints as below, as seen here, this way clarifies the loop mappings. The change also implements consuming of these two new attribute by the transform dialect. Transform dialect binds the outermost loops to the thread blocks and innermost loops to threads.
```
scf.foreach_thread (%i, %j) in (%c1, %c2) {
scf.foreach_thread (%i2, %j2) in (%c1, %c2)
{...} { thread_dim_mapping = [#gpu.thread<x>, #gpu.thread<y>]}
} { thread_dim_mapping = [#gpu.block<x>, #gpu.block<y>]}
```
Reviewed By: ftynse, nicolasvasilache
Differential Revision: https://reviews.llvm.org/D137413
The KeyTy of attribute/type storage classes provide enough information for
automatically implementing the necessary sub element interface methods. This
removes the need for derived classes to do it themselves, which is both much
nicer and easier to handle certain invariants (e.g. null handling). In cases where
explicitly handling for parameter types is necessary, they can provide an implementation
of `AttrTypeSubElementHandler` to opt-in to support.
This tickles a few things alias wise, which annoyingly messes with tests that hard
code specific affine map numbers.
Differential Revision: https://reviews.llvm.org/D137374
In D134622 the printed form of a pass manager is changed to include the
name of the op that the pass manager is anchored on. This updates the
`-pass-pipeline` argument format to include the anchor op as well, so
that the printed form of a pipeline can be directly passed to
`-pass-pipeline`. In most cases this requires updating
`-pass-pipeline='pipeline'` to
`-pass-pipeline='builtin.module(pipeline)'`.
This also fixes an outdated assert that prevented running a
`PassManager` anchored on `'any'`.
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D134900
There was a bug in scf.for loop bufferization that could lead to a missing buffer copy (alloc was there, but not the copy).
Differential Revision: https://reviews.llvm.org/D135053
We currently only support one level of aliases, which isn't great
in situations where an attribute/type can have multiple duplicated
components nested within it(e.g. debuginfo metadata). This commit
refactors alias generation to support nested aliases, which requires
changing alias grouping to take into account the depth of child
aliases, to ensure that attributes/types aren't printed before the
aliases they use.
The only real user facing change here was that we no longer print
0 as an alias suffix, which would be unnecessarily expensive to keep
in the new alias generation method (and isn't that valuable of a
behavior to preserve).
Differential Revision: https://reviews.llvm.org/D136541
The `scf.index_switch` is a control-flow operation that branches to one of the
given regions based on the values of the argument and the cases. The
argument is always of type `index`.
Example:
```mlir
%0 = scf.index_switch %arg0 -> i32
case 2 {
%1 = arith.constant 10 : i32
scf.yield %1 : i32
}
case 5 {
%2 = arith.constant 20 : i32
scf.yield %2 : i32
}
default {
%3 = arith.constant 30 : i32
scf.yield %3 : i32
}
```
Reviewed By: jpienaar
Differential Revision: https://reviews.llvm.org/D136003
Many tests wrap the piece of the IR related to the transform dialect
into `transform.with_pdl_patterns` without actually using PDL patterns
inside. Some of these are leftovers from migration to `structured.match`
and some others are cargo cult, both are useless and pollute the tests.
Reviewed By: guraypp
Differential Revision: https://reviews.llvm.org/D135661
Use the recently introduced TransformTypeInterface instead of hardcoding
the PDLOperationType. This will allow the operations to use more
specific transform types to express pre/post-conditions in the future.
It requires the syntax and Python op construction API to be updated.
Dialect extensions will be switched separately.
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D135584
This fixes a bug where a required buffer copy was not inserted.
Not only written aliases, but also read aliases should be taken into account when computing common enclosing repetitive regions. Furthermore, for writing ops, it does not matter where the destination tensor is defined, but where the op itself is located.
Differential Revision: https://reviews.llvm.org/D135420
This function must be implemented for all ops, where the result memref type is different from the input memref type.
Differential Revision: https://reviews.llvm.org/D134331
This change allows the SCF LoopPipelining transform to handle ops with
nested regions within the pipelined `scf.for` body. The op and nested
regions are treated as a single unit from the transform's perspective.
This change also makes explicit the requirement that only ops whose
parent Block is the loop body Block are allowed to be scheduled by the
caller.
Reviewed By: ThomasRaoux, nicolasvasilache
Differential Revision: https://reviews.llvm.org/D133965
Bufferization already makes the assumption that buffers pass function
boundaries in the strided form and uses the corresponding affine map layouts.
Switch it to use the recently introduced strided layout instead to avoid
unnecessary casts when bufferizing further operations to the memref dialect
counterparts that now largely rely on the strided layout attribute.
Depends On D133947
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D133951
Memref subview operation has been initially designed to work on memrefs with
strided layouts only and has never supported anything else. Port it to use the
recently added StridedLayoutAttr instead of extracting the strided from
implicitly from affine maps.
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D133938
Currently, if the `before` and `after` regions of a while op have
tensor args in different indices, this leads to a crash.
This moves the pass-through check for args to the handling of the
condition block, since that is where the results are produced, so
it's also where copies must be made.
Reviewed By: springerm
Differential Revision: https://reviews.llvm.org/D133477
Currently, one-shot-bufferize crashes as soon as there's
a mixture of tensor and non-tensor arguments. This seems
to happen for no good reason.
Reviewed By: springerm
Differential Revision: https://reviews.llvm.org/D133419
This change refines the semantics of scf.foreach_thread. Tensors that are inserted into in the terminator must now be passed to the region explicitly via `shared_outs`. Inside of the body of the op, those tensors are then accessed via block arguments.
The body of a scf.foreach_thread is now treated as a repetitive region. I.e., op dominance can no longer be used in conflict detection when using a value that is defined outside of the body. Such uses may now be considered as conflicts (if there is at least one read and one write in the body), effectively privatizing the tensor. Shared outputs are not privatized when they are used via their corresponding block arguments.
As part of this change, it was also necessary to update the "tiling to scf.foreach_thread", such that the generated tensor.extract_slice ops use the scf.foreach_thread's block arguments. This is implemented by cloning the TilingInterface op inside the scf.foreach_thread, rewriting all of its outputs with block arguments and then calling the tiling implementation. Afterwards, the cloned op is deleted again.
Differential Revision: https://reviews.llvm.org/D133114
Introduce a new attribute to represent the strided memref layout. Strided
layouts are omnipresent in code generation flows and are the only kind of
layouts produced and supported by a half of operation in the memref dialect
(view-related, shape-related). However, they are internally represented as
affine maps that require a somewhat fragile extraction of the strides from the
linear form that also comes with an overhead. Furthermore, textual
representation of strided layouts as affine maps is difficult to read: compare
`affine_map<(d0, d1, d2)[s0, s1] -> (d0*32 + d1*s0 + s1 + d2)>` with
`strides: [32, ?, 1], offset: ?`. While a rudimentary support for parsing a
syntactically sugared version of the strided layout has existed in the codebase
for a long time, it does not go as far as this commit to make the strided
layout a first-class attribute in the IR.
This introduces the attribute and updates the tests that using the pre-existing
sugared form to use the new attribute instead. Most memref created
programmatically, e.g., in passes, still use the affine form with further
extraction of strides and will be updated separately.
Update and clean-up the memref type documentation that has gotten stale and has
been referring to the details of affine map composition that are long gone.
See https://discourse.llvm.org/t/rfc-materialize-strided-memref-layout-as-an-attribute/64211.
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D132864
A part of the functionality of `bufferize` is extracted into `getBufferType`. Also, bufferized scf.yields inside scf.if are now created with the correct bufferized type from the get-to.
Differential Revision: https://reviews.llvm.org/D132862
Even though iter_arg and init_arg of an scf.for loop may have the same tensor type, their bufferized memref types are not necessarily equal. It is sometimes necessary to insert a cast in case of differing layout maps.
Differential Revision: https://reviews.llvm.org/D132860
Add an option (cleanUpUnroll) to unroll cleanup loop even if the trip count is smaller the unroll factor.
Differential Revision: https://reviews.llvm.org/D129171
This fixes a bug in SCF/AffineCanonicalizationUtils.cpp. Loop lb/ub were previously considered dimensions, which caused a crash when a (non-optimizable) affine.min / affine.max expression was processed (due to multiplication of two dims). Lb/ub are now considered symbols and symbols may be multiplied. (The scope of the analysis is "within the loop body", at which point lb/ub are constants.)
Differential Revision: https://reviews.llvm.org/D132021
This reland includes changes to the Python bindings.
Switch variadic operand and result segment size attributes to use the
dense i32 array. Dense integer arrays were introduced primarily to
represent index lists. They are a better fit for segment sizes than
dense elements attrs.
Depends on D131801
Reviewed By: rriddle
Differential Revision: https://reviews.llvm.org/D131803
Introduce two different failure propagation mode in the Transform
dialect's Sequence operation. These modes specify whether silenceable
errors produced by nested ops are immediately propagated, thus stopping
the sequence, or suppressed. The latter is useful in end-to-end
transform application scenarios where the user cannot correct the
transformation, but it is robust enough to silenceable failures. It
can be combined with the "alternatives" operation. There is
intentionally no default value to avoid favoring one mode over the
other.
Downstreams can update their tests using:
S='s/sequence \(%.*\) {/sequence \1 failures(propagate) {/'
T='s/sequence {/sequence failures(propagate) {/'
git grep -l transform.sequence | xargs sed -i -e "$S"
git grep -l transform.sequence | xargs sed -i -e "$T"
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D131774
Using a loop init_arg inside of the loop is not supported. This change adds a pre-processing pass that resolves such IR with copies.
Differential Revision: https://reviews.llvm.org/D131689
Switch variadic operand and result segment size attributes to use the
dense i32 array. Dense integer arrays were introduced primarily to
represent index lists. They are a better fit for segment sizes than
dense elements attrs.
Depends on D131738
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D131702
This operation is a NavigationOp that simplifies the writing of transform IR.
Since there is no way of refering to an interface by name, the current implementation uses
an EnumAttr and depends on the interfaces it supports.
In the future, it would be worthwhile to remove this dependence and generalize.
Differential Revision: https://reviews.llvm.org/D130267
bufferization.writable is used in most cases instead. All remaining test cases are updated. Some code that is no longer needed is deleted.
Differential Revision: https://reviews.llvm.org/D129739
This is a partial revert of D128615.
to_memref(to_tensor(x)) always be folded to x. But to_tensor(to_memref(x)) cannot be folded in the general case because writes to the intermediary memref may go unnoticed.
Differential Revision: https://reviews.llvm.org/D129354
This is moslty NFC and will allow tensor.parallel_insert_slice to gain
rank-reducing semantics by reusing the vast majority of the tensor.insert_slice impl.
Depends on D128857
Differential Revision: https://reviews.llvm.org/D128920
This change updates all remaining bufferization patterns (except for scf.while) and the remaining bufferization infrastructure to infer the memory space whenever possible instead of falling back to "0". (If a default memory space is set in the bufferization options, we still fall back to that value if the memory space could not be inferred.)
Differential Revision: https://reviews.llvm.org/D128423
An optional thread_dim_mapping index array attribute specifies for each
virtual thread dimension, how it remaps 1-1 to a set of concrete processing
element resources (e.g. a CUDA grid dimension or a level of concrete nested
async parallelism). At this time, the specification is backend-dependent and
is not verified by the op, beyond being an index array attribute.
It is the reponsibility of the lowering to interpret the index array in the
context of the concrete target the op is lowered to, or to ignore it when
the specification is ill-formed or unsupported for a particular target.
Differential Revision: https://reviews.llvm.org/D128633
This allows for better type inference during bufferization and is in preparation of supporting memory spaces.
Differential Revision: https://reviews.llvm.org/D128581
