The patch adds operations to `BlockAndValueMapping` and renames it to `IRMapping`. When operations are cloned, old operations are mapped to the cloned operations. This allows mapping from an operation to a cloned operation. Example:
```
Operation *opWithRegion = ...
Operation *opInsideRegion = &opWithRegion->front().front();
IRMapping map
Operation *newOpWithRegion = opWithRegion->clone(map);
Operation *newOpInsideRegion = map.lookupOrNull(opInsideRegion);
```
Migration instructions:
All includes to `mlir/IR/BlockAndValueMapping.h` should be replaced with `mlir/IR/IRMapping.h`. All uses of `BlockAndValueMapping` need to be renamed to `IRMapping`.
Reviewed By: rriddle, mehdi_amini
Differential Revision: https://reviews.llvm.org/D139665
Previously, we rely on the InsertOp to gradually increase the size of the
storage for all sparse tensors. We now allocate the full size values buffer
for annotated all dense tensors when we first allocate the tensor. This avoids
the cost of gradually increasing the buffer and allows accessing the values
buffer as if it were a dense tensor.
Reviewed By: Peiming
Differential Revision: https://reviews.llvm.org/D141516
Move the functionality to codegen utils for sharing with the codegen path.
Reviewed By: Peiming
Differential Revision: https://reviews.llvm.org/D141514
Previously, we generate AOS subviews for indices buffers when constructing an
immutable sparse tensor descriptor. We now only generate such subviews when
getIdxMemRefOrView is requested.
Reviewed By: Peiming
Differential Revision: https://reviews.llvm.org/D141325
Previously, we use a temporary tensor with identity ordering. We now use a
temporary tensor with the destination dimension ordering, to enable the use of
sort_coo for sorting the tensor.
Reviewed By: Peiming
Differential Revision: https://reviews.llvm.org/D141295
The template parameter is no longer needed after MutSparseTensorDescriptor
is implemented as a subclass of SparseTensorDescriptorImpl. The only purpose
for it was to enable SFINAE.
Reviewed By: bixia
Differential Revision: https://reviews.llvm.org/D141303
This patch fixes build failure due to -Wsign-compare in sparse2SparseRewrite(...) after https://reviews.llvm.org/D140871.
```
llvm-project/mlir/lib/Dialect/SparseTensor/Transforms/SparseTensorRewriting.cpp:842:32: error: comparison of integers of different signs: 'uint64_t' (aka 'unsigned long') and 'int64_t' (aka 'long') [-Werror,-Wsign-compare]
for (uint64_t i = 0; i < rank; i++) {
~ ^ ~~~~
1 error generated.
```
Reviewed By: MaskRay
Differential Revision: https://reviews.llvm.org/D141104
Use an array of structures to represent the indices for the tailing COO region
of a sparse tensor.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D140870
All members are now private and access is through delegate
or convenience methods only (except the loop emitter, which
is still under refactoring).
Reviewed By: Peiming
Differential Revision: https://reviews.llvm.org/D140519
Also, as a proof of concept, all functionality related to reductions
has been refactored into private fields and a clean public API. As a
result, some dead code was found as well. This approach also simplifies
asserting on a proper environment state for each call.
NOTE: making all other fields private and migrating more methods into
this new class is still TBD in yes another next revision!
Reviewed By: Peiming
Differential Revision: https://reviews.llvm.org/D140443
This cleans up a lot of parameter passing. It also prepares adding
proper "delegate" functions to the new environment and moving this
out into its own class with a better OO design.
Reviewed By: Peiming
Differential Revision: https://reviews.llvm.org/D140257
std::optional::value() has undesired exception checking semantics and is
unavailable in older Xcode (see _LIBCPP_AVAILABILITY_BAD_OPTIONAL_ACCESS). The
call sites block std::optional migration.
std::optional::value() has undesired exception checking semantics and is
unavailable in older Xcode (see _LIBCPP_AVAILABILITY_BAD_OPTIONAL_ACCESS). The
call sites block std::optional migration.
This is part of an effort to migrate from llvm::Optional to
std::optional. This patch changes the way mlir-tblgen generates .inc
files, and modifies tests and documentation appropriately. It is a "no
compromises" patch, and doesn't leave the user with an unpleasant mix of
llvm::Optional and std::optional.
A non-trivial change has been made to ControlFlowInterfaces to split one
constructor into two, relating to a build failure on Windows.
See also: https://discourse.llvm.org/t/deprecating-llvm-optional-x-hasvalue-getvalue-getvalueor/63716
Signed-off-by: Ramkumar Ramachandra <r@artagnon.com>
Differential Revision: https://reviews.llvm.org/D138934
When concat along dim 0, and all inputs/outputs are ordered with identity dimension ordering,
the concatenated coordinates will be yield in lexOrder, thus no need to sort.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D140228
This allows allocaBuffer to be used outside of SparseTensorConversion.cpp, which will be helpful for a some future commits.
Reviewed By: aartbik, Peiming
Differential Revision: https://reviews.llvm.org/D140047
Since STEA isa Attribute, and that's just (a wrapper around) a pointer, the extra `const` and `&` aren't necessary for function arguments.
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D139886
The op is not bufferizable but should be analyzable (for `EliminateEmptyTensors`, which uses the bufferization infrastructure).
Also improve debugging functionality and error messages.
Also adds a missing pass to the sparse pipeline. (tensor.empty should be replaced with bufferization.alloc_tensor, but it sometimes used to work without depending on how the tensor.empty is used. Now we always fail explicitly.)
This change cleans up the conversion pass re the "dim"-vs-"lvl" and "sizes"-vs-"shape" distinctions of the runtime. A quick synopsis includes:
* Adds new `SparseTensorStorageBase::getDimSize` method, with `sparseDimSize` wrapper in SparseTensorRuntime.h, and `genDimSizeCall` generator in SparseTensorConversion.cpp
* Changes `genLvlSizeCall` to perform no logic, just generate the function call.
* Adds `createOrFold{Dim,Lvl}Call` functions to handle the logic of replacing `gen{Dim,Lvl}SizeCall` with constants whenever possible. The `createOrFoldDimCall` function replaces the old `sizeFromPtrAtDim`.
* Adds `{get,fill}DimSizes` functions for iterating `createOrFoldDimCall` across the whole type. These functions replace the old `sizesFromPtr`.
* Adds `{get,fill}DimShape` functions for lowering a `ShapedType` into constants. These functions replace the old `sizesFromType`.
* Changes the `DimOp` rewrite to do the right thing.
* Changes the `ExpandOp` rewrite to compute the proper expansion size.
Depends On D138365
Reviewed By: aartbik
Differential Revision: https://reviews.llvm.org/D139165
