This change adds support for promoting `linalg` operation operands that
are produced by rank-reducing `memref.subview` ops.
Differential Revision: https://reviews.llvm.org/D127086
The current vectorization logic implicitly expects "elementwise"
linalg ops to have projected permutations for indexing maps, but
the precondition logic misses this check. This can result in a
crash when executing the generic vectorization transform on an op
with a non-projected permutation input indexing map. This change
fixes the logic and adds a test (which crashes without this fix).
Differential Revision: https://reviews.llvm.org/D127000
This patch adds the knobs to use peeling in the codegen strategy
infrastructure.
Reviewed By: springerm
Differential Revision: https://reviews.llvm.org/D126842
These ops complement the tiling/padding transformations by transforming
higher-level named structured operations such as depthwise convolutions into
lower-level and/or generic equivalents that are better handled by some
downstream transformations.
Differential Revision: https://reviews.llvm.org/D126698
Now that we have an AllocTensorOp (previously InitTensorOp) in the bufferization dialect, the InitOp in the sparse dialect is no longer needed.
Differential Revision: https://reviews.llvm.org/D126180
No longer pass static dim sizes as an attribute. This was redundant and required extra checks in the verifier. This change also makes the op symmetrical to memref::AllocOp.
Differential Revision: https://reviews.llvm.org/D126178
This change adds a new op `alloc_tensor` to the bufferization dialect. During bufferization, this op is always lowered to a buffer allocation (unless it is "eliminated" by a pre-processing pass). It is useful to have such an op in tensor land, because it allows users to model tensor SSA use-def chains (which drive bufferization decisions) and because tensor SSA use-def chains can be analyzed by One-Shot Bufferize, while memref values cannot.
This change also replaces all uses of linalg.init_tensor in bufferization-related code with bufferization.alloc_tensor.
linalg.init_tensor and bufferization.alloc_tensor are similar, but the purpose of the former one is just to carry a shape. It does not indicate a memory allocation.
linalg.init_tensor is not suitable for modelling SSA use-def chains for bufferization purposes, because linalg.init_tensor is marked as not having side effects (in contrast to alloc_tensor). As such, it is legal to move linalg.init_tensor ops around/CSE them/etc. This is not desirable for alloc_tensor; it represents an explicit buffer allocation while still in tensor land and such allocations should not suddenly disappear or get moved around when running the canonicalizer/CSE/etc.
BEGIN_PUBLIC
No public commit message needed for presubmit.
END_PUBLIC
Differential Revision: https://reviews.llvm.org/D126003
It is very wrong if the ranges can't be infered. It's also checked in
verifyStructuredOpInterface, so we don't need the Optional return type.
Reviewed By: springerm
Differential Revision: https://reviews.llvm.org/D124596
Now that dialect constructors are generated in the .cpp file, we can
drop all of the dependent dialect includes from the .h file.
Differential Revision: https://reviews.llvm.org/D124298
The bubble up logic was written by assuming the slice operation is
always a normal slice that outputs a tensor with the same rank.
Differential Revision: https://reviews.llvm.org/D124283
This makes the API easier to use. Also allows us to check for incorrect API usage for easier debugging.
Differential Revision: https://reviews.llvm.org/D124265
* Move Module Bufferization to the bufferization dialect. The implementation is split into `OneShotModuleBufferize.cpp` and `FuncBufferizableOpInterfaceImpl.cpp`, so that the external model implementation can be easily moved to the func dialect in the future.
* Split and clean up test cases. A few test cases are still remaining in Linalg and will be updated separately.
* `linalg.inplaceable` is renamed to `bufferization.writable` to accurately reflect its current usage.
* Attributes and their verifiers are moved from the Linalg dialect to the Bufferization dialect.
* Expand documentation.
* Add a new flag to One-Shot Bufferize to allow for function boundary bufferization.
Differential Revision: https://reviews.llvm.org/D122229
This change generalizes the fusion of `tensor.expand_shape` ->
`linalg.generic` op by collapsing to handle cases where only a subset
of the reassociations specified in the `tensor.expand_shape` are valid
to be collapsed.
The method that does the collapsing is refactored to allow it to be a
generic utility when required.
Reviewed By: gysit
Differential Revision: https://reviews.llvm.org/D123153
The method to add elementwise ops fusion patterns pulls in many other
patterns by default. The patterns to pull in along with the
elementwise op fusion should be upto the caller. Split the method to
pull in just the elementwise ops fusion pattern. Other cleanup changes
include
- Move the pattern for constant folding of generic ops (currently only
constant folds transpose) into a separate file, cause it is not
related to fusion
- Drop the uber LinalgElementwiseFusionOptions. With the
populateElementwiseOpsFusionPatterns being split, this has no
utility now.
- Drop defaults for the control function.
- Fusion of splat constants with generic ops doesnt need a control
function. It is always good to do.
Differential Revision: https://reviews.llvm.org/D123236
Insert a buffer copy unless the dims are guaranteed to be collapsible. In the verifier, accept collapses unless they are guaranteed to be non-collapsible.
Differential Revision: https://reviews.llvm.org/D123316
This patch revamps the BranchOpInterface a bit and allows a proper implementation of what was previously `getMutableSuccessorOperands` for operations, which internally produce arguments to some of the block arguments. A motivating example for this would be an invoke op with a error handling path:
```
invoke %function(%0)
label ^success ^error(%1 : i32)
^error(%e: !error, %arg0 : i32):
...
```
The advantages of this are that any users of `BranchOpInterface` can still argue over remaining block argument operands (such as `%1` in the example above), as well as make use of the modifying capabilities to add more operands, erase an operand etc.
The way this patch implements that functionality is via a new class called `SuccessorOperands`, which is now returned by `getSuccessorOperands`. It basically contains an `unsigned` denoting how many operator produced operands exist, as well as a `MutableOperandRange`, which are the usual forwarded operands we are used to. The produced operands are assumed to the first few block arguments, followed by the forwarded operands afterwards. The role of `SuccessorOperands` is to provide various utility functions to modify and query the successor arguments from a `BranchOpInterface`.
Differential Revision: https://reviews.llvm.org/D123062
Bubble up extract_slice above Linalg operation.
A sequence of operations
%0 = linalg.<op> ... arg0, arg1, ...
%1 = tensor.extract_slice %0 ...
can be replaced with
%0 = tensor.extract_slice %arg0
%1 = tensor.extract_slice %arg1
%2 = linalg.<op> ... %0, %1, ...
This results in the reduce computation of the linalg operation.
The implementation uses the tiling utility functions. One difference
from the tiling process is that we don't need to insert the checking
code for the out-of-bound accesses. The use of the slice itself
represents that the code writer is sure about the boundary condition.
To avoid adding the boundary condtion check code, `omitPartialTileCheck`
is introduced for the tiling utility functions.
Differential Revision: https://reviews.llvm.org/D122437
This has been on _Both for a couple of weeks. Flip usages in core with
intention to flip flag to _Prefixed in follow up. Needed to add a couple
of helper methods in AffineOps and Linalg to facilitate a pure flag flip
in follow up as some of these classes are used in templates and so
sensitive to Vector dialect changes.
Differential Revision: https://reviews.llvm.org/D122151
- Adds default implementations of `isDefinedOutsideOfLoop` and `moveOutOfLoop` since 99% of all implementations of these functions were identical
- `moveOutOfLoop` takes one operation and doesn't return anything anymore. 100% of all implementations of this function would always return `success` and uses would either respond with a pass failure or an `llvm_unreachable`.
This revision supports padding only a subset of the iteration dimensions via an additional padding-dimensions parameter. This control allows us to pad an operation in multiple steps. For example, one may want to pad only the output dimensions of a producer matmul fused into a consumer loop nest, before tiling and padding its reduction dimension.
Depends On D122309
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D122560
Pass the padding options using arrays instead of lambdas. In particular pass the padding value as string and use the argument parser to create the padding value. Arrays are a more natural choice that matches the current use cases and avoids converting arrays to lambdas.
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D122309
This transformation allow to break up a reduction dimension in a
parallel and a reduction dimension. This is followed by a separate
reduction op. This allows to generate tree reduction which is beneficial
on target allowing to take advantage parallelism.
Differential Revision: https://reviews.llvm.org/D122045
Previously, only LinalgOps whose operands are defined by an ExtractSliceOp could be padded. The revision supports walking a use-def chain of LinalgOps to find an ExtractSliceOp.
Reviewed By: hanchung
Differential Revision: https://reviews.llvm.org/D122116
This revision introduces a heuristic to stop fusion for shape-only tensors. A shape-only tensor only defines the shape of the consumer computation while the data is not used. Pure producer consumer fusion thus shall not fuse the producer of a shape-only tensor. In particular, since the shape-only tensor will have other uses that actually consume the data.
The revision enables fusion for consumers that have two uses of the same tensor. One as input operand and one as shape-only output operand. In these cases, we want to fuse only the input operand and avoid output fusion via iteration argument.
Reviewed By: hanchung
Differential Revision: https://reviews.llvm.org/D120981
This provides a way to create an operation without manipulating
OperationState directly. This is useful for creating unregistered ops.
Reviewed By: rriddle, mehdi_amini
Differential Revision: https://reviews.llvm.org/D120787
ExpandShapeOp builder cannot infer the result type since it doesn't know
how the dimension needs to be split. Remove this builder so that it
doesn't get used accidently. Also remove one potential path using it in
generic fusion.
Differential Revision: https://reviews.llvm.org/D122019
The current dialect registry allows for attaching delayed interfaces, that are added to attrs/dialects/ops/etc.
when the owning dialect gets loaded. This is clunky for quite a few reasons, e.g. each interface type has a
separate tracking structure, and is also quite limiting. This commit refactors this delayed mutation of
dialect constructs into a more general DialectExtension mechanism. This mechanism is essentially a registration
callback that is invoked when a set of dialects have been loaded. This allows for attaching interfaces directly
on the loaded constructs, and also allows for loading new dependent dialects. The latter of which is
extremely useful as it will now enable dependent dialects to only apply in the contexts in which they
are necessary. For example, a dialect dependency can now be conditional on if a user actually needs the
interface that relies on it.
Differential Revision: https://reviews.llvm.org/D120367
This commit moves FuncOp out of the builtin dialect, and into the Func
dialect. This move has been planned in some capacity from the moment
we made FuncOp an operation (years ago). This commit handles the
functional aspects of the move, but various aspects are left untouched
to ease migration: func::FuncOp is re-exported into mlir to reduce
the actual API churn, the assembly format still accepts the unqualified
`func`. These temporary measures will remain for a little while to
simplify migration before being removed.
Differential Revision: https://reviews.llvm.org/D121266
New buffer allocations can now be returned/yielded from blocks with `allow-return-allocs`. One-Shot Bufferize deallocates all buffers at the end of the block. If this is not possible (because the buffer escapes the block), this is now done by the existing BufferDeallocation pass.
Differential Revision: https://reviews.llvm.org/D121527
This improves the modularity of the bufferization.
From now on, all ops that do not implement BufferizableOpInterface are considered hoisting barriers. Previously, all ops that do not implement the interface were not considered barriers and such ops had to be marked as barriers explicitly. This was unsafe because we could've hoisted across unknown ops where it was not safe to hoist.
As a side effect, this allows for cleaning up AffineBufferizableOpInterfaceImpl. This build unit no longer needed and can be deleted.
Differential Revision: https://reviews.llvm.org/D121519
