This uses a indexed linalg.generic, which is rather awkward standalone but
allows fusing into the output of the concatenate and avoid to ever materialize
it in memory. I think this is the only way to get that with the current linalg
stack, fusion across a concatenate would require more infrastructure.
PiperOrigin-RevId: 369677652
The pattern does not support ops with non-zero padding config. Add a check to
prevent unexpected lowering.
It is not easy to add tests because other patterns will convert body ops, and
it causes issues like invalid IRs.
PiperOrigin-RevId: 367202450
We only need the memref_reinterpret_cast if we don't know whether a dimension
gets expanded or not. With static shapes we know that a dimension can only be
expanded if it's a static 1, so lower it in the same way we lower fully
static broadcasts.
PiperOrigin-RevId: 363859181
This is the same as iota, but instead of taking the dimensions from the result
tensor we use the supplied shape extents tensor.
PiperOrigin-RevId: 362298548
This is an annoying edge case because the collapse->expand lowering expects at
least R1 or it will produce invalid linalg reshapes. Using the direct lowering
works fine.
PiperOrigin-RevId: 362269199
Imported from GitHub PR https://github.com/tensorflow/tensorflow/pull/46723
Reduces some warnings about comparison of integers of different signs.
Copybara import of the project:
--
311f436f77b334f5462127d8cf179cce067969ca by Marius Brehler <marius.brehler@iml.fraunhofer.de>:
Adjust types of loop counters
Reduces some warnings about comparison of integers of different signs.
PiperOrigin-RevId: 360912203
The linalg named ops are now type polymorphic, so the type-monomorphic
varieties are redundant (and will be deleted soon).
PiperOrigin-RevId: 360509010
This pattern only works for normal convolutions. It does not work for depthwise
convolutions. The Linalg conv ops are defined with static rank, so it only
supports 1d/2d/3d cases, which are the most typical cases.
This also refactors out the same check in lmhlo.conv lowering.
PiperOrigin-RevId: 359503527
In IREE, we use indexed generic op to handle the initial value. However, we
lower it to a generic op that carries an init_tensor here, and leave the handle
of initialization problem to later passes.
PiperOrigin-RevId: 354294807
If mhlo.reshape is not purely collapsing some consecutive operand
dimensions into result dimensions, we will generate two linalg
reshape op for it: the first one collapses all operand dimensions
into one dimension, and the second one expands it to all result
dimensions. For this case, the number of collapsed/expanded dimensions
should be coming strictly from the operand/result. It is different
from the case where we can generate one linalg reshape. For that case,
the reassociation map should have rank equal to the largest among
operand/result shape.
PiperOrigin-RevId: 354293826
We prototyped the lowering from mhlo.dot to linalg.matmul in IREE. Since Linalg
now supports matmul in tensors world, we can move the lowering logic to tensors
world, and upstream to legalize_to_linalg.cc. The patch lowers the mhlo.dot to
the linalg.matmul/matvec/dot in tensors world.
PiperOrigin-RevId: 351184911
For floating point operations, this uses std.pow.
For integer operations, this lowers to a loop.
This adds a dependency on scf.
PiperOrigin-RevId: 348537232
It can happen that a lowering for a certain type is not implemented yet.
We should not segfault in such a case, but instead return a failure().
PiperOrigin-RevId: 347801106
- Add this attribute to match the corresponding XLA HLO attribute on convolution
operations.
- A true value indicates a reversal of the corresponding kernel spatial dimension.
- Since XLA builder does not support this attribute, use a custom HLO converted to map
from mlir::mhlo::ConvOp to XLA.
PiperOrigin-RevId: 346891737
Hanhan Wang
Benjamin Kramer
Rahul Joshi
A. Unique TensorFlower
Adrian Kuegel
Stella Laurenzo
Marius Brehler
Geoffrey Martin-Noble
Mahesh Ravishankar
Lei Zhang
Alexander Belyaev
Tres Popp
River Riddle