This op used to belong to the sparse dialect, but there are use cases for dense bufferization as well. (E.g., when a tensor alloc is returned from a function and should be deallocated at the call site.) This change moves the op to the bufferization dialect, which now has an `alloc_tensor` and a `dealloc_tensor` op.
Differential Revision: https://reviews.llvm.org/D129985
A new sparse_tensor operation allows for
custom reduction code to be injected during
linalg.generic lowering for sparse tensors.
An identity value is provided to indicate
the starting value of the reduction. A single
block region is required to contain the
custom reduce computation.
Reviewed by: aartbik
Differential Revision: https://reviews.llvm.org/D128004
This change removes the partial bufferization passes from the sparse compilation pipeline and replaces them with One-Shot Bufferize. One-Shot Analysis (and TensorCopyInsertion) is used to resolve all out-of-place bufferizations, dense and sparse. Dense ops are then bufferized with BufferizableOpInterface. Sparse ops are still bufferized in the Sparsification pass.
Details:
* Dense allocations are automatically deallocated, unless they are yielded from a block. (In that case the alloc would leak.) All test cases are modified accordingly. E.g., some funcs now have an "out" tensor argument that is returned from the function. (That way, the allocation happens at the call site.)
* Sparse allocations are *not* automatically deallocated. They must be "released" manually. (No change, this will be addressed in a future change.)
* Sparse tensor copies are not supported yet. (Future change)
* Sparsification no longer has to consider inplacability. If necessary, allocations and/or copies are inserted during TensorCopyInsertion. All tensors are inplaceable by the time Sparsification is running. Instead of marking a tensor as "not inplaceable", it can be marked as "not writable", which will trigger an allocation and/or copy during TensorCopyInsertion.
Differential Revision: https://reviews.llvm.org/D129356
A previous revision implemented expand/collapse reshaping between
dense and sparse tensors for sparse2dense and dense2sparse since those
could use the "cheap" view reshape on the already materialized
dense tensor (at either the input or output side), and do some
reshuffling from or to sparse. The dense2dense case, as always,
is handled with a "cheap" view change.
This revision implements the sparse2sparse cases. Lacking any "view"
support on sparse tensors this operation necessarily has to perform
data reshuffling on both ends.
Tracker for improving this:
https://github.com/llvm/llvm-project/issues/56477
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D129416
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
The revision makes a start with implementing expand/collapse reshaping
for sparse tensors. When either source or destination is sparse, but
other is dense, the "cheap" dense reshape can be used prior to converting
from or to a sparse tensor.
Note1
sparse to sparse reshaping is still TBD.
Note2
in the long run, we may want to implement a "view" into a sparse tensor so that the operation remains cheap and does not require data shuffling
Reviewed By: wrengr
Differential Revision: https://reviews.llvm.org/D129031
When the iteration graph is cyclic (even after several attempts using less and less constraints), the current sparse compiler bails out, and no rewriting hapens. However, this revision adds some new logic where the sparse compiler tries to find a single input sparse tensor that breaks the cycle, and then adds a proper sparse conversion operation. This way, more incoming kernels can be handled!
Note, the resulting code is not optimal (although it keeps more or less proper "sparse" complexity), and more improvements should be added (especially when the kernel directly yields without computation, such as the transpose example). However, handling is better than not handling ;-)
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D128847
Enforce the assumption made on tensor buffers explicitly. When in-place,
reuse the buffer, but fill with all zeroes for the non-update case, since
the kernel assumes all elements are written to. When not in-place, zero
out the new buffer when materializing or when no-updates occur. Copy the
original tensor value when updates occur. This prepares migrating to the
new bufferization strategy, where these assumptions must be made explicit.
Reviewed By: springerm
Differential Revision: https://reviews.llvm.org/D128691
Putting some direct use restrictions on tensor allocations in the
sparse case enables the use of simplifying assumptions in the
bufferization analysis.
Reviewed By: springerm
Differential Revision: https://reviews.llvm.org/D128463
Only the analysis part of the interface is implemented. The bufferization itself is performed by the SparseTensorConversion pass.
Differential Revision: https://reviews.llvm.org/D128138
This revision makes sure we accept sparse tensors as arguments
of the expand/collapse reshaping operations in the tensor dialect.
Note that the actual lowering to runnable IR is still TBD.
Reviewed By: springerm
Differential Revision: https://reviews.llvm.org/D128311
Marking bufferization allocation operation as invalid
during sparse lowering is too strict, since dense and
sparse allocation can co-exist. This revision refines
the lowering with a dynamic type check.
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D128305
This fixes all sorts of ABI issues due to passing by-value
(using by-reference with memref's exclusively).
Reviewed By: bkramer
Differential Revision: https://reviews.llvm.org/D128018
This is the first PR to add `F16` and `BF16` support to the sparse codegen. There are still problems in supporting these two data types, such as `BF16` is not quite working yet.
Add tests cases.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D127010
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
The trick of using an empty token in the `FOREVERY_O` x-macro relies on preprocessor behavior which is only standard since C99 6.10.3/4 and C++11 N3290 16.3/4 (whereas it was undefined behavior up through C++03 16.3/10). Since the `ExecutionEngine/SparseTensorUtils.cpp` file is required to be compile-able under C++98 compatibility mode (unlike the C++11 used elsewhere in MLIR), we shouldn't rely on that behavior.
Also, using a non-empty suffix helps improve uniformity of the API, since all other primary/overhead suffixes are also non-empty. I'm using the suffix `0` since that's the value used by the `SparseTensorEncoding` attribute for indicating the index overhead-type.
Depends On D126720
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D126724
This was leftover from when the standard dialect was destroyed, and
when FuncOp moved to the func dialect. Now that these transitions
have settled a bit we can drop these.
Most updates were handled using a simple regex: replace `^( *)func` with `$1func.func`
Differential Revision: https://reviews.llvm.org/D124146
Although we now have semi-rings to deal with arbitrary ops,
it is still good to convey zero-preserving semantics of
ops to the sparse compiler.
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D125043
The SparseTensor passes currently use opaque numbers for the CLI, despite using an enum internally. This patch exposes the enums instead of numbered items that are matched back to the enum.
Fixes GitHub issue #53389
Reviewed by: aartbik, mehdi_amini
Differential Revision: https://reviews.llvm.org/D123876
Reland Note: Adds a fix to properly mark a commutative operation as folded if we change the order
of its operands. This was uncovered by the fact that we no longer re-process constants.
This avoids accidentally reversing the order of constants during successive
application, e.g. when running the canonicalizer. This helps reduce the number
of iterations, and also avoids unnecessary changes to input IR.
Fixes#51892
Differential Revision: https://reviews.llvm.org/D122692
Rationale:
Allocating the temporary buffers for access pattern expansion on the stack
(using alloca) is a bit too agressive, since it easily runs out of stack space
for large enveloping tensor dimensions. This revision changes the dynamic
allocation of these buffers with explicit alloc/dealloc pairs.
Reviewed By: bixia, wrengr
Differential Revision: https://reviews.llvm.org/D123253
Prior to this change there were a number of places where the allocation and deallocation of SparseTensorCOO objects were not cleanly paired, leading to inconsistencies regarding whether each function released its tensor/coo arguments or not, as well as making it easy to run afoul of memory leaks, use-after-free, or double-free errors. This change cleans up the codegen vs runtime boundary to resolve those issues. Now, the only time the runtime library frees an object is either (a) because it's a function explicitly designed to do so, or (b) because the allocated object is entirely local to the function and would be a memory leak if not released. Thus, now the codegen takes complete responsibility for releasing any objects it caused to be allocated.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D122435
This reverts commit 59bbc7a085.
This exposes an issue breaking the contract of
`applyPatternsAndFoldGreedily` where we "converge" without applying
remaining patterns.
This avoids accidentally reversing the order of constants during successive
application, e.g. when running the canonicalizer. This helps reduce the number
of iterations, and also avoids unnecessary changes to input IR.
Fixes#51892
Differential Revision: https://reviews.llvm.org/D122692
Use "enable-vla-vectorization=vla" to generate a vector length agnostic
loops during vectorization. This option works for vectorization strategy 2.
Differential Revision: https://reviews.llvm.org/D118379
This is work towards: https://github.com/llvm/llvm-project/issues/51652
This differential doesn't yet make use of the new kSparseToSparse, just introduces it. The differential that finally makes use of them is D122061, which is the final differential in the chain that fixes bug 51652.
Depends On D122054
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D122055
When the sparse_tensor dialect lowers linalg.generic,
it makes inferences about how the operations should
affect the looping logic. For example, multiplication
is an intersection while addition is a union of two
sparse tensors.
The new binary and unary op separate the looping logic
from the computation by nesting the computation code
inside a block which is merged at the appropriate level
in the lowered looping code.
The binary op can have custom computation code for the
overlap, left, and right sparse overlap regions. The
unary op can have custom computation code for the
present and absent values.
Reviewed by: aartbik
Differential Revision: https://reviews.llvm.org/D121018
The revision removes the linalg.fill operation and renames the OpDSL generated linalg.fill_tensor operation to replace it. After the change, all named structured operations are defined via OpDSL and there are no handwritten operations left.
A side-effect of the change is that the pretty printed form changes from:
```
%1 = linalg.fill(%cst, %0) : f32, tensor<?x?xf32> -> tensor<?x?xf32>
```
changes to
```
%1 = linalg.fill ins(%cst : f32) outs(%0 : tensor<?x?xf32>) -> tensor<?x?xf32>
```
Additionally, the builder signature now takes input and output value ranges as it is the case for all other OpDSL operations:
```
rewriter.create<linalg::FillOp>(loc, val, output)
```
changes to
```
rewriter.create<linalg::FillOp>(loc, ValueRange{val}, ValueRange{output})
```
All other changes remain minimal. In particular, the canonicalization patterns are the same and the `value()`, `output()`, and `result()` methods are now implemented by the FillOpInterface.
Depends On D120726
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D120728
This revision adds support for the linalg.index to the sparse compiler
pipeline. In essence, this adds the ability to refer to indices in
the tensor index expression, as illustrated below:
Y[i, j, k, l, m] = T[i, j, k, l, m] * i * j
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D121251
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
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
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
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
Depends On D115008
This change opens the way for D115012, and removes some corner cases in `CodegenUtils.cpp`. The `SparseTensorAttrDefs.td` already specifies that we allow `0` bitwidth for the two overhead types and that it is interpreted to mean the architecture's native width.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D115010
This revision implements sparse outputs (from scratch) in all cases where
the loops can be reordered with all but one parallel loops outer. If the
inner parallel loop appears inside one or more reductions loops, then an
access pattern expansion is required (aka. workspaces in TACO speak).
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D115091
Proper test for sparse tensor outputs is a single condition throughout
the whole tensor index expression (not a general conjunction, since this
may include other conditions that cause cancellation).
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D114810
Moves sparse tensor output support forward by generalizing from injective
insertions only to include reductions. This revision accepts the case with all
parallel outer and all reduction inner loops, since that can be handled with
an injective insertion still. Next revision will allow the inner parallel loop
to move inward (but that will require "access pattern expansion" aka "workspace").
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D114399
`vector::InsertElementOp` and `vector::ExtractElementOp` have had their `position`
operand changed to accept `AnySignlessIntegerOrIndex` for better operability with
operations that use `index`, such as affine loops.
LLVM's `extractelement` and `insertelement` can also accept `i64`, so lowering
directly to these operations without explicitly inserting casts is allowed. SPIRV's
equivalent ops can also accept `i64`.
Reviewed By: nicolasvasilache, jpienaar
Differential Revision: https://reviews.llvm.org/D114139
