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>
Linalg operations can include `complex` types in the src/target types.
This should include conversion between `arith` and `complex` types when
constructing `linalg` operations.
Reviewed By: kuhar
Differential Revision: https://reviews.llvm.org/D154740
The old code used to materialize constants as ops, immediately folded them into the resulting affine map and then deleted the constant ops again. Instead, directly fold the attributes into the affine map. Furthermore, all helpers accept `OpFoldResult` instead of `Value` now. This makes the code at call sites more efficient, because it is no longer necessary to materialize a `Value`, just to be able to use these helper functions.
Note: The API has changed (accepts OpFoldResult instead of Value), otherwise this change is NFC.
Differential Revision: https://reviews.llvm.org/D153324
The MLIR classes Type/Attribute/Operation/Op/Value support
cast/dyn_cast/isa/dyn_cast_or_null functionality through llvm's doCast
functionality in addition to defining methods with the same name.
This change begins the migration of uses of the method to the
corresponding function call as has been decided as more consistent.
Note that there still exist classes that only define methods directly,
such as AffineExpr, and this does not include work currently to support
a functional cast/isa call.
Caveats include:
- This clang-tidy script probably has more problems.
- This only touches C++ code, so nothing that is being generated.
Context:
- https://mlir.llvm.org/deprecation/ at "Use the free function variants
for dyn_cast/cast/isa/…"
- Original discussion at https://discourse.llvm.org/t/preferred-casting-style-going-forward/68443
Implementation:
This first patch was created with the following steps. The intention is
to only do automated changes at first, so I waste less time if it's
reverted, and so the first mass change is more clear as an example to
other teams that will need to follow similar steps.
Steps are described per line, as comments are removed by git:
0. Retrieve the change from the following to build clang-tidy with an
additional check:
https://github.com/llvm/llvm-project/compare/main...tpopp:llvm-project:tidy-cast-check
1. Build clang-tidy
2. Run clang-tidy over your entire codebase while disabling all checks
and enabling the one relevant one. Run on all header files also.
3. Delete .inc files that were also modified, so the next build rebuilds
them to a pure state.
4. Some changes have been deleted for the following reasons:
- Some files had a variable also named cast
- Some files had not included a header file that defines the cast
functions
- Some files are definitions of the classes that have the casting
methods, so the code still refers to the method instead of the
function without adding a prefix or removing the method declaration
at the same time.
```
ninja -C $BUILD_DIR clang-tidy
run-clang-tidy -clang-tidy-binary=$BUILD_DIR/bin/clang-tidy -checks='-*,misc-cast-functions'\
-header-filter=mlir/ mlir/* -fix
rm -rf $BUILD_DIR/tools/mlir/**/*.inc
git restore mlir/lib/IR mlir/lib/Dialect/DLTI/DLTI.cpp\
mlir/lib/Dialect/Complex/IR/ComplexDialect.cpp\
mlir/lib/**/IR/\
mlir/lib/Dialect/SparseTensor/Transforms/SparseVectorization.cpp\
mlir/lib/Dialect/Vector/Transforms/LowerVectorMultiReduction.cpp\
mlir/test/lib/Dialect/Test/TestTypes.cpp\
mlir/test/lib/Dialect/Transform/TestTransformDialectExtension.cpp\
mlir/test/lib/Dialect/Test/TestAttributes.cpp\
mlir/unittests/TableGen/EnumsGenTest.cpp\
mlir/test/python/lib/PythonTestCAPI.cpp\
mlir/include/mlir/IR/
```
Differential Revision: https://reviews.llvm.org/D150123
When the input types don't match the accumulator type in named
convolution ops there is supposed to be a conversion to the accumulator
type before the multiply and accumulate.
Differential Revision: https://reviews.llvm.org/D146824
Following up on the comments in https://reviews.llvm.org/D144108 this
patch refactors the im2col conversion patterns for `linalg.conv_2d_nhwc_hwcf`
and `linalg.conv_2d_nchw_fchw` convolutions to use gather semantics for the im2col
packing `linalg.generic`.
Follow up work can include a similar pattern for depthwise convolutions
and a generalization of the patterns here to work with any `LinalgOp` as
well.
Differential Revision: https://reviews.llvm.org/D144678
This patch adds patterns to convert `linalg.conv_2d_xxx` operations
into `linalg.generic` (for img2col packing) and `linalg.matmul`.
The meat of the patch comes straight from IREE
(https://github.com/iree-org/iree).
(To the original authors are you okay with that?)
What this patch adds is proper plumbing of the im2col patterns into the
transform dialect.
PS: Feel free to add more reviewers. I wanted to cover the original contributors of im2col in IREE but I'm not sure I got all of them.
Reviewed By: nicolasvasilache, ThomasRaoux
Differential Revision: https://reviews.llvm.org/D144108
