This patch adds more precise side effects to the current ops with memory
effects, allowing us to determine which OpOperand/OpResult/BlockArgument
the
operation reads or writes, rather than just recording the reading and
writing
of values. This allows for convenient use of precise side effects to
achieve
analysis and optimization.
Related discussions:
https://discourse.llvm.org/t/rfc-add-operandindex-to-sideeffect-instance/79243
The `TilingInterface` methods have return values that allow the
interface implementation to return multiple operations, and also return
tiled values explicitly. This is to avoid the assumption that the
interface needs to return a single operation and this operations result
are the expected tiled values. Make the
`PartialReductionOpInterface::tileToPartialReduction` return
`TilingResult` as well for the same reason.
Similarly make the `PartialReductionOpInterface::mergeReductions` also
return a list of generated operations and values to use as replacements.
This is just a refactoring to allow for deprecation of
`linalg::tileReductionUsingForall` with `scf::tileReductionUsingSCF`
method.
This patch adds support for reducing operations with multiple results
using PartialReductionOpInterface. Also adds an implementation of
PartialReductionOpInterface for multiple results for linalg.generic.
This patch is a first pass at making consistent syntax across the
`LinalgTransformOp`s that use dynamic index lists for size parameters.
Previously, there were two different forms: inline types in the list, or
place them in the functional style tuple. This patch goes for the
latter.
In order to do this, the `printPackedOrDynamicIndexList`,
`printDynamicIndexList` and their `parse` counterparts were modified so
that the types can be optionally provided to the corresponding custom
directives.
All affected ops now use tablegen `assemblyFormat`, so custom
`parse`/`print` functions have been removed. There are a couple ops that
will likely add dynamic size support, and once that happens it should be
made sure that the assembly remains consistent with the changes in this
patch.
The affected ops are as follows: `pack`, `pack_greedily`,
`tile_using_forall`. The `tile_using_for` and `vectorize` ops already
used this syntax, but their custom assembly was removed.
---------
Co-authored-by: Oleksandr "Alex" Zinenko <ftynse@gmail.com>
This patch modifies the definition of `PadOp` to take transform params
and handles for the `pad_to_multiple_of` operand.
---------
Co-authored-by: Oleksandr "Alex" Zinenko <ftynse@gmail.com>
This adds patterns to convert from the Linalg matmul and batch_matmul
ops to the transposed variants. By default the LHS matrix is transposed.
Our work enabling a lowering path from linalg.matmul to ArmSME has
revealed the current lowering results in non-contiguous memory accesses
for the A matrix and very poor performance.
These patterns provide a simple option to fix this.
The previous implementation used a `notifyMatchFailure` to emit failure
message inappropriately and then used the
`emitDefaultSilenceableFailure`. This patch changes this to use the more
appropriate `emitSilenceableFailure` with error message. Additionally a
failure test has been added.
The previous implementation was doing an early successful return on
`rank <= 1` without adding the original op to transform results. This
resulted in errors about number of returns. This patch fixes this by
adding the original op to results. Additionally, we first check if op is
elementwise and return a slienceable failure early if not.
Transform interfaces are implemented, direction or via extensions, in
libraries belonging to multiple other dialects. Those dialects don't
need to depend on the non-interface part of the transform dialect, which
includes the growing number of ops and transitive dependency footprint.
Split out the interfaces into a separate library. This in turn requires
flipping the dependency from the interface on the dialect that has crept
in because both co-existed in one library. The interface shouldn't
depend on the transform dialect either.
As a consequence of splitting, the capability of the interpreter to
automatically walk the payload IR to identify payload ops of a certain
kind based on the type used for the entry point symbol argument is
disabled. This is a good move by itself as it simplifies the interpreter
logic. This functionality can be trivially replaced by a
`transform.structured.match` operation.
This lets `transform.structured.convert_to_loops` return handles to the
generated loops, making this transformation more useful to use for
(transformation-)nesting purposes. This is modelled after SCFs
`transform.loop.forall_to_for` which returns handles to loops.
Introduced in commit aa2a96a24ae3a8cc04635ab6ede474c5f2665053, with a
note that they might move out of the `Linalg`-Dialect, but no reason
given for the non-return of handles. As far as I can see, this transform
always returns loops.
A `transform.structured.flatten_elementwise` op is implemented for
flattening the iteration space and (applicable) operands/results to a
single dimension.
Added support to vectorized tensor.unpack. The unpack Op is split into a
`vector.transfer_read`, `vector.transpose`, `vector.shape_cast` and a
`vector.transfer_write`.
Rename listener callback names:
* `notifyOperationRemoved` -> `notifyOperationErased`
* `notifyBlockRemoved` -> `notifyBlockErased`
The current callback names are misnomers. The callbacks are triggered
when an operation/block is erased, not when it is removed (unlinked).
E.g.:
```c++
/// Notify the listener that the specified operation is about to be erased.
/// At this point, the operation has zero uses.
///
/// Note: This notification is not triggered when unlinking an operation.
virtual void notifyOperationErased(Operation *op) {}
```
This change is in preparation of adding listener support to the dialect
conversion. The dialect conversion internally unlinks IR before erasing
it at a later point of time. There is an important difference between
"remove" and "erase". Lister callback names should be accurate to avoid
confusion.
This PR adds a direct vectorization lowering of `tensor.pack` into
`mask(vector.transfer_read)`->`vector.shape_cast`->`vector.transpose`->`vector.transfer_write`.
Using `LoopLikeOpInterface` as the basis for the implementation unifies
all the tiling logic for both `scf.for` and `scf.forall`. The only
difference is the actual loop generation. This is a follow up to
https://github.com/llvm/llvm-project/pull/72178
Instead of many entry points for each loop type, the loop type is now
passed as part of the options passed to the tiling method.
This is a breaking change with the following changes
1) The `scf::tileUsingSCFForOp` is renamed to `scf::tileUsingSCF`
2) The `scf::tileUsingSCFForallOp` is deprecated. The same
functionality is obtained by using `scf::tileUsingSCF` and setting
the loop type in `scf::SCFTilingOptions` passed into this method to
`scf::SCFTilingOptions::LoopType::ForallOp` (using the
`setLoopType` method).
3) The `scf::tileConsumerAndFusedProducerGreedilyUsingSCFForOp` is
renamed to `scf::tileConsumerAndFuseProducerUsingSCF`. The use of
the `controlFn` in `scf::SCFTileAndFuseOptions` allows implementing
any strategy with the default callback implemeting the greedy fusion.
4) The `scf::SCFTilingResult` and `scf::SCFTileAndFuseResult` now use
`SmallVector<LoopLikeOpInterface>`.
5) To make `scf::ForallOp` implement the parts of
`LoopLikeOpInterface` needed, the `getOutputBlockArguments()`
method is replaced with `getRegionIterArgs()`
These changes now bring the tiling and fusion capabilities using
`scf.forall` on par with what was already supported by `scf.for`
The pattern rewriter documentation states that "*all* IR mutations [...]
are required to be performed via the `PatternRewriter`." This commit
adds two functions that were missing from the rewriter API:
`moveOpBefore` and `moveOpAfter`.
After an operation was moved, the `notifyOperationInserted` callback is
triggered. This allows listeners such as the greedy pattern rewrite
driver to react to IR changes.
This commit narrows the discrepancy between the kind of IR modification
that can be performed and the kind of IR modifications that can be
listened to.
This commit renames 4 pattern rewriter API functions:
* `updateRootInPlace` -> `modifyOpInPlace`
* `startRootUpdate` -> `startOpModification`
* `finalizeRootUpdate` -> `finalizeOpModification`
* `cancelRootUpdate` -> `cancelOpModification`
The term "root" is a misnomer. The root is the op that a rewrite pattern
matches against
(https://mlir.llvm.org/docs/PatternRewriter/#root-operation-name-optional).
A rewriter must be notified of all in-place op modifications, not just
in-place modifications of the root
(https://mlir.llvm.org/docs/PatternRewriter/#pattern-rewriter). The old
function names were confusing and have contributed to various broken
rewrite patterns.
Note: The new function names use the term "modify" instead of "update"
for consistency with the `RewriterBase::Listener` terminology
(`notifyOperationModified`).
In the process a couple of test transform dialect ops are added just
for testing. These operations are not intended to use as full flushed
out of transformation ops, but are rather operations added for testing.
A separate operation is added to `LinalgTransformOps.td` to convert a
`TilingInterface` operation to loops using the
`generateScalarImplementation` method implemented by the
operation. Eventually this and other operations related to tiling
using the `TilingInterface` need to move to a better place (i.e. out
of `Linalg` dialect)
Adjust the silenceable failure message as we lower `tensor.unpack` as a
combination of `linalg.transpose` + `tensor.collapse_shape` and
`tensor.extract_slice`.
Test was failing due to a different transform sequence declaration (transform sequence were used, while now it should be named transform sequence). Test is now fixed.
The current vectorization of 1D depthwise convolutions in Linalg is
_sub-optimal_ for tensor with a low number of channel dimensions, e.g.:
```mlir
linalg.depthwise_conv_1d_nwc_wc
{dilations = dense<1> : vector<1xi64>,
strides = dense<1> : vector<1xi64>}
ins(%input, %filter : tensor<1x8x3xi8>, tensor<1x3xi8>)
outs(%output : tensor<1x8x3xi8>) -> tensor<1x8x3xi8>
```
That's due to the fact that ultimately (i.e. at LLVM level),
vectorization happens along the trailing dimension (i.e. the channel
dimension). In this case it leads to vectors with 3 elements (or worse,
if there's e.g. only 1 channel dimension). For comparison, a 128 bit
wide vector registers can hold 16 x i8.
Instead, this patch adds an option to flatten/collapse the channel
dimension into the width dimension of the input/filter/output using
`vector.shape_cast` operation:
```mlir
%sc_input = vector.shape_cast %input : vector<1x8x3xi8> to vector<1x24xi8>
%sc_output = vector.shape_cast %output : vector<1x8x3xi8> to vector<1x24xi8>
%b_filter = vector.broadcast %filter : vector<3xi8> to vector<1x8x3xi8>
%sc_filter = vector.shape_cast %b_filter : vector<1x8x3xi8> to vector<1x24xi8>
```
This new vectorization mode is implemented in `depthwiseConv` by
inserting `vector.shape_cast` Ops before and after
`depthwiseConv1dSliceAsMulAcc` is invoked. It can be selected through
e.g. a transform dialect attribute:
```mlir
transform.structured.vectorize_children_and_apply_patterns %conv {flatten_1d_depthwise_conv}
```
A forthcoming patch will implement a strategy to automatically switch
between the two implementations, depending on the shape of the input
tensors.
Co-authored by: Bradley Smith <bradley.smith@arm.com>
`TileUsingForOp` has an optional Attribute `interchange` which was given
in curly braces like this: `{interchange = [...]}`. The way this was
parsed meant that no `attr-dict` could be attached to the Op.
This patch adds printing / parsing of an `attr-dict` to the Op and
prints/parses the `interchange` Attribute separate from the
discardable Attributes.
* Add a LinAlg pass to convert 2D convolutions and quantized 2D
convolutions that have the `FHWC` filter channel ordering into a
transpose followed by 2D convolutions that have the `HWCF` channel
ordering.
* Add a lit test to check the semantics of the transformation are
correct for both quantized and unquantized variants.
Signed-off-by: Jack Frankland <jack.frankland@arm.com>
`TileUsingForOp` has an optional Attribute `interchange` which was given
in curly braces like this: `{interchange = [...]}`. The way this was
parsed meant that no normal `attr-dict` could be attached to the Op.
This patch adds printing / parsing of an `attr-dict` to the Op and treats
the `interchange` Attribute as part of that dictionary for now.
`bufferization.materialize_in_destination` should be used instead. Both
ops bufferize to a memcpy. This change also conceptually cleans up the
memref dialect a bit: the memref dialect no longer contains ops that
operate on tensor values.
Introduce an operation to specialize linalg.generics, for example,
detecting a linalg.generic that is semantically equivalent to a
linalg.copy and replacing the former with the latter. After code
generation, it is helpful to lower named operations to vendor-optimized
libraries.
Adds the Img2Col transformation for the fhwc channel ordering in a
Conv2D. Because of how the channel ordering affects the matrix
dimensions in the flattened filter this results in a slightly different
implementation of the actual "matrix multiplication". Instead of doing a
regular row-column dot-product this arrangement requires a row-row dot
product, otherwise the filter matrix would first need to be transposed.
Adds a lit test to the transform dialect to check the semantics of the
optimization are correct.
Signed-off-by: Jack Frankland <jack.frankland@arm.com>
Rename and restructure tiling-related transform ops from the structured
extension to be more homogeneous. In particular, all ops now follow a
consistent naming scheme:
- `transform.structured.tile_using_for`;
- `transform.structured.tile_using_forall`;
- `transform.structured.tile_reduction_using_for`;
- `transform.structured.tile_reduction_using_forall`.
This drops the "_op" naming artifact from `tile_to_forall_op` that
shouldn't have been included in the first place, consistently specifies
the name of the control flow op to be produced for loops (instead of
`tile_reduction_using_scf` since `scf.forall` also belongs to `scf`),
and opts for the `using` connector to avoid ambiguity.
The loops produced by tiling are now systematically placed as *trailing*
results of the transform op. While this required changing 3 out of 4 ops
(except for `tile_using_for`), this is the only choice that makes sense
when producing multiple `scf.for` ops that can be associated with a
variadic number of handles. This choice is also most consistent with
*other* transform ops from the structured extension, in particular with
fusion ops, that produce the structured op as the leading result and the
loop as the trailing result.
The implementation doesn't emit any diagnostics as it is shared with the
pattern-based implementation. Check preconditions early and emit
diagnostics from the transform op instead. Without this change, the op
would produce a definite failure and no error message.
This PR renames the vectorization transform ops as follows:
* `structured.masked_vectorize` => `structured.vectorize`. This reflects
the fact that since [recently](https://reviews.llvm.org/D157774) the op
can also handle the unmasked case.
* `structured.vectorize` =>
`structured.vectorize_children_and_applies_patterns`. This reflects the
fact that the op does not just vectorize the given payload op but all
vectorizable children contained in it, and applies patterns before and
after for preparation and clean-up.
This rename was discussed first
[here](https://reviews.llvm.org/D157774).
The PR also adapts and cleans ups the tablegen description of the
`VectorizeChildrenAndApplyPatternsOp` (formerly `VectorizeOp`).
This commit removes the deallocation capabilities of
one-shot-bufferization. One-shot-bufferization should never deallocate
any memrefs as this should be entirely handled by the
ownership-based-buffer-deallocation pass going forward. This means the
`allow-return-allocs` pass option will default to true now,
`create-deallocs` defaults to false and they, as well as the escape
attribute indicating whether a memref escapes the current region, will
be removed. A new `allow-return-allocs-from-loops` option is added as a
temporary workaround for some bufferization limitations.
This reverts commit 6a91dfedeb956dfa092a6a3f411e8b02f0d5d289.
This caused problems in downstream projects. We are reverting to give
them more time for integration.
