This one required more changes than ideal due to overlapping generated name
with different return types. Changed getIndexingMaps to getIndexingMapsArray to
move it out of the way/highlight that it returns (more expensively) a
SmallVector and uses the prefixed name for the Attribute.
Differential Revision: https://reviews.llvm.org/D129919
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
The rules in the linalg file were very specific to sparse tensors so will
find a better home under sparse tensor dialect than linalg dialect. Also
moved some rewriting from sparsification into this new "pre-rewriting" file.
Reviewed By: springerm
Differential Revision: https://reviews.llvm.org/D129910
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
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
This is a followup to D128847. The `AffineMap::getPermutedPosition` method performs a linear scan of the map, thus the previous implementation had asymptotic complexity of `O(|topSort| * |m|)`. This change reduces that to `O(|topSort| + |m|)`.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D129011
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
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
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 aligns the SCF dialect file layout with the majority of the dialects.
Reviewed By: jpienaar
Differential Revision: https://reviews.llvm.org/D128049
Follow up from flipping dialects to both, flip accessor used to prefixed
variant ahead to flipping from _Both to _Prefixed. This just flips to
the accessors introduced in the preceding change which are just prefixed
forms of the existing accessor changed from.
Mechanical change using helper script
https://github.com/jpienaar/llvm-project/blob/main/clang-tools-extra/clang-tidy/misc/AddGetterCheck.cpp and clang-format.
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
The 'emit_c_wrappers' option in the FuncToLLVM conversion requests C interface
wrappers to be emitted for every builtin function in the module. While this has
been useful to bootstrap the interface, it is problematic in the longer term as
it may unintentionally affect the functions that should retain their existing
interface, e.g., libm functions obtained by lowering math operations (see
D126964 for an example). Since D77314, we have a finer-grain control over
interface generation via an attribute that avoids the problem entirely. Remove
the 'emit_c_wrappers' option. Introduce the '-llvm-request-c-wrappers' pass
that can be run in any pipeline that needs blanket emission of functions to
annotate all builtin functions with the attribute before performing the usual
lowering that accounts for the attribute.
Reviewed By: chelini
Differential Revision: https://reviews.llvm.org/D127952
The semi-ring blocks were simply "inlined" by the sparse compiler but
without any filtering or patching. This revision improves the analysis
(rejecting blocks that use non-invariant computations from outside
their blocks, except for linalg.index) and also improves the codegen
by properly patching up index computations (previous version crashed).
With a regression test. Also updated the documentation now that the
example code is properly working.
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D128000
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
By defining the `{primary,overhead}TypeFunctionSuffix` functions via the same x-macros used to generate the runtime library's functions themselves, this helps avoid bugs from typos or things getting out of sync.
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D126720
This is the first implementation of complex (f64 and f32) support
in the sparse compiler, with complex add/mul as first operations.
Note that various features are still TBD, such as other ops, and
reading in complex values from file. Also, note that the
std::complex<float> had a bit of an ABI issue when passed as
single argument. It is still TBD if better solutions are possible.
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D125596
Adding lowering for Unary and Binary required several changes due to
their unique nature of containing custom code for different "regions"
of the sparse structure being operated on. Along with a Kind, a pointer
to the Operation is passed along to be merged once the lattice
structure is figured out.
The original operation is maintained, as it is required for subsequent
lattice decisions. However, sparse_tensor.binary has some branches
are considered as fully handled and therefore are marked with as
kBinaryBranch to distinguish them.
A unique aspect of the custom code is that sometimes the desired result
is no result at all -- i.e. a user wants overlapping sparse entries to
become empty in the output. The solution to this is to return an
uninitialized Value(), which is checked and handled elsewhere in the
code and results in nothing being written to the output tensor for that
case.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D123057
Current index value generation uses fixed-length vector ops, this patch
adds an alterantive codegen path compatible with scalable vectors by
using `LLVM::StepVectorOp`.
Differential Revision: https://reviews.llvm.org/D124454
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
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
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
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 sets up the options and threads them through everywhere, but doesn't actually use them yet. The differential that finally makes use of them is D122061, which is the final differential in the chain that fixes bug 51652.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D122054
This removes any potential confusion with the `getType` accessors
which correspond to SSA results of an operation, and makes it
clear what the intent is (i.e. to represent the type of the function).
Differential Revision: https://reviews.llvm.org/D121762
