Commit Graph

611 Commits (ea2afce29a8b2070400a60de0be833bc713863a4)

Author SHA1 Message Date
Ashay Rane 340d8af28a
torch: handle `torch.prim.dtype` ops during type refinement (#1013)
The canonicalizer converts `torch.prim.dtype` ops into integer constants
for valid types, but the type may not be known until type refinement is
complete.  However, type refinement cannot make progress until
`torch.prim.dtype` ops have been resolved to their corresponding integer
constants, thus creating a circular dependency.

This patch creates a tight coupling between type refinement and the
lowering of `torch.prim.dtype` ops by handling such ops as they are
encountered during type refinement.  The unit test in this patch aims to
check whether the type refinement pass can now handle chains of
operations that alternate between type construction and type refinement.
2022-07-08 16:38:51 -07:00
Ramiro Leal-Cavazos 6a72ab4502
Add basic support for list of optional tensors in reduce-op-variants (#971)
This commit adds support for lists of type `list<optional<tensor>>`
where each element in the list is either a `!torch.tensor` or a
`!torch.none`.
2022-07-08 11:12:15 -07:00
Ashay Rane 6491c69539
torch: use ScalarType enum instead of raw constants (#1020)
This patch replaces the use of raw integers like 6, 4, etc. (that
represent PyTorch's scalar types) with named values from the ScalarType
enum (e.g. `ScalarType::Float`, `ScalarType::Long`, etc.) in code for
folding `prim.dtype` ops into numeric constants.

This patch isn't strictly a non-functional change, since its use of
`Torch::getScalarTypeForType()` implies that the input type has to be
one among the supported types, otherwise compilation will abort, whereas
previously, compilation proceeded without folding the unsupported data
type into a numeric constant.
2022-07-07 14:21:05 -07:00
Suraj Sudhir d38f2cae5b
[tosa] aten.transpose.int support (#1017)
Signed-off-by: Suraj Sudhir <suraj.sudhir@arm.com>
2022-07-07 13:05:33 -07:00
Quinn Dawkins f0c3b5a7ed
Add E2E support for aten.len.str (#969) 2022-07-07 10:41:55 -07:00
Ashay Rane 88316b3b4e
torch: fold prim.dtype(bf16) to integer constant 15 (#1012)
A prior patch (63538de2) that added support for bfloat16 type did not
add the canonicalization pattern to fold `torch.prim.dtype` operations
on bfloat16 tensors into the integer constant 15.  This patch fixes the
problem.
2022-07-06 18:21:43 -07:00
Andrew Cain 6885f1ed8a
fix: Broaden range of tosa.matmul outputs that don't need to be reshaped (#1015)
Co-authored-by: Andrew Cain <acain@d-matrix.ai>
2022-07-06 17:24:16 -07:00
Ramiro Leal-Cavazos bbb648410e
Fix compilation warning Wsign-compare (#1003) 2022-07-06 09:06:10 -07:00
Tanyo Kwok d4f1f41435
[MLIR][TORCH] Add decomposition of aten.repeat (#932)
* [MLIR][TORCH] Add decomposition of aten.repeat

* refine & rebase

* refine static shapes

* add e2e test

* Rebase and Refine naming style
2022-07-01 13:02:31 +08:00
Ramiro Leal-Cavazos f204210266
[LINALG] Fix handling of size-1 dims in `aten.view` again. (#992)
A previous fix to the handling of size-1 dims in
`aten.view` (https://github.com/llvm/torch-mlir/pull/962) resulted in
the wrong grouping of dimensions when size-1 dims where between two
dims of size greater than 1. This commit fixes that.
2022-06-30 16:39:25 -07:00
Suraj Sudhir bb576c2cb3
[tosa] aten.embedding op support (#991)
Enables BERT legalization.

Signed-off-by: Suraj Sudhir <suraj.sudhir@arm.com>
2022-06-30 13:13:52 -07:00
Sean Silva 227dea7b2e Add support for ScalarType::QUInt8
I ran into this while poking around at
https://github.com/llvm/torch-mlir/issues/959
2022-06-29 15:33:28 -07:00
JakopinA 5888c4f7dc Added E2E support for torch::aten.__contains__int_list 2022-06-27 19:30:00 +05:30
Ashay Rane 163fa57cde
torch: allow torch dialect ops after running drop-shape pass (#979)
In the `pyhpc_turbulent_kinetic_energy` TorchBench benchmark, the shape
calculation occurs inside loops, but because `DropShapeCalculationsPass`
does not explicitly mark the Torch dialect as legal, the pass execution
fails.

This patch adds Torch to the list of legal dialects, and adds a test to
validate the translation.
2022-06-25 07:27:47 -07:00
Gaurav Shukla 1be604bfd3 [LINALG] Lower `aten.Matmul` to `linalg.BatchMatmul`
This commit lowers `aten.matmul` to `linalg.BatchMatmul` under the
following conditions:
1. The result of matrix multiplication must have batch dimensions,
   i.e., rank greater than 2.
2. The resultant matrix must have at most 1 dynamic batch dimension.

It also handles broadcasting of batch dimensions when batch dimensions
of the matrices are broadcastable.

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2022-06-25 10:58:06 +05:30
Ramiro Leal-Cavazos 400fecc1e5
[LINALG] Fix shape function of index.Tensor + support N-rank inputs (#972)
This commit fixes the shape function for `index.Tensor`, adding
support for multiple index tensors and `None`s in the indices
list. This commit also adds support for input tensors of rank greater
than 1. The lowering for `index.Tensor` still has the the limitation
that only a single index tensor along the first dimension of the input
tensor is supported.
2022-06-24 09:45:44 -07:00
Ashay Rane 234fc7fe0c
linalg: lower `aten.triu` op to `linalg.generic` (#965)
Prior to this patch, the torch dialect included `AtenTriuOp` for
computing the upper triangular part of the input matrix, but there was
no code for lowering the op to the linalg dialect.

This patch adds code to generate a `linalg.generic` operation that
compares indices (computed using `linalg.index`) to choose between zero
or the original value (using `arith.select`).  The lowering fails if the
number of dimensions are less than two.  This patch also adds a few
end-to-end tests.
2022-06-23 22:45:48 -07:00
Tanyo Kwok 143a7bcb76
[MLIR][TORCH] Add folder for torch_c.from_i64 & torch_c.to_i64 (#933)
* [MLIR][TORCH] Add folder for torch_c.from_i64 & torch_c.to_i64

* add unit tests for each individual fold

* fix failure of NumelZeroRankModule & TestMultipleTensorAndPrimitiveTypesReturn
2022-06-24 09:34:39 +08:00
Ramiro Leal-Cavazos 189afa82c5
Update shape library with LLVM bump changes (#973) 2022-06-23 18:13:03 -07:00
erman-gurses 5cff40c88a Add canonicalization for aten.add.tensor op 2022-06-23 17:24:59 -04:00
Maksim Levental 829717c96e
Bump LLVM (#958) 2022-06-22 22:23:46 -05:00
Ramiro Leal-Cavazos 8b94759303
[LINALG] Fix handling of size-1 dims in `aten.view` (#962)
This commit adds support for several size-1 dims in a row in an
expansion using `aten.view`.
2022-06-22 15:58:40 -07:00
Maksim Levental a34dad2e07
Fix `verifyLinalgCompatibleTypes` which currently doesn't successfully catch `torch.tensor`. (#947) 2022-06-15 18:21:36 -05:00
Vivek Khandelwal 77ab31641f [MLIR][TORCH] Add decomposition of aten.numpy_T op
This commit adds the decomposition of `aten.numpy_T` op into
`aten.t` or `aten.permute` op.

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-06-16 00:01:22 +05:30
Vivek Khandelwal 4605dc9c99 [MLIR][TORCH] Add support for bool type in convertScalarToDtype utility
Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-06-16 00:00:47 +05:30
Albert Sandru 708a51ae2e Add E2E support for aten.is_floating_point 2022-06-15 11:54:00 -05:00
Ramiro Leal-Cavazos 246c2df65a
[LINALG] Fix typo in conversion pattern of `aten.embedding` (#942) 2022-06-15 09:45:10 -07:00
Vivek Khandelwal aed5517fda [MLIR][TORCH] Add integer dtype support for aten.rsub.Scalar op
Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-06-15 16:46:28 +05:30
Bob Adolf b90837ee24
Temporarily revert support for custom op extensions. (#944)
The MacOS builders are having linking trouble with the extension library.
Until it's fixed, all support for op extensions is disabled. It should be
easy to restore once the issue is resolved.
2022-06-14 18:24:40 -07:00
Ramiro Leal-Cavazos 93f6d8e776
[LINALG] Add 0-rank case for `aten.permute` (#940)
The function `AffineMap::inferFromExprList` does not work if the first
vector of expressions is empty, because it uses these expressions to
obtain the context. This prevented `aten.permute` from working for
inputs of 0-rank. This commit adds support for 0-rank inputs.
2022-06-14 12:50:46 -07:00
Vivek Khandelwal 33fa8e7761 [MLIR][TORCH] Add decomposition of aten.floor_divide op
This commit adds the decomposition of `aten.floor_divide` op into
`aten.div.Tensor_mode` op.

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-06-14 08:56:25 +05:30
Bob Adolf 0a7ba62438
Allow torch-mlir to support PyTorch extensions. (#895)
PyTorch allows new operators to be registered dynamically in modules.
Torch-mlir already makes it fairly straightforward to add support for
new operators, and this commit just extends that support to allow new
PyTorch ops to come from a external module.

This does *not* allow ops to be dynamically loaded into torch-mlir.
Torch-mlir must still be compiled with support built-in.

Add a `_torch_mlir_custom_op_example` subpackage to `torch_mlir` which
registers an demonstration op. It will not be imported by default when
importing torch_mlir. It's strictly for testing and documentation.

Adds an end-to-end test for the `torch_mlir_custom_op_example::identity` op.

With all these changes, we should now be actively testing PyTorch extension
support with all future patches.
2022-06-13 14:51:30 -07:00
Maksim Levental 5c85ac3100
Handle `nn.Linear(..., bias=False)` case for TorchToLinalg (#919) 2022-06-08 21:13:43 -05:00
Sean Silva e1b38e74dd Use upstream shape functions directly.
Now that upstream exposes them nicely, we can use them.

I noticed that we had added stuff into the upstream_shape_helpers.py
file (which was supposed to stay pristine), so some more shape functions
need to be upstreamed.

Going forward, all shape functions should be upstreamed similar to
https://github.com/pytorch/pytorch/pull/76889 instead of added in this
file.
2022-06-07 11:15:03 -07:00
Vivek Khandelwal b95b3d844d [MLIR][TORCH] Add E2E support for aten.div.Tensor_mode op
This commit adds lowering of `aten.div.Tensor_mode` op.
This commit also fixes formatting for the test file elementwise.py.

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-06-07 22:26:44 +05:30
Vivek Khandelwal a11ef674a7 [MLIR][TORCH] Add E2E support for aten.baddbmm op
This commit decomposes `aten.baddbmm` op into `aten.bmm`,
`aten.mul.Scalar`, and `aten.add.Tensor` op.

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-06-07 22:26:28 +05:30
Vivek Khandelwal 2718b4d838 [MLIR][TORCH] Add E2E support for aten.clamp_[min|max] op
This commit decomposes `aten.clamp_min` and `aten.clamp_max` op
into `aten.clamp` op.

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-06-06 11:52:29 +05:30
Vidush Singhal fc419b1e7d
Add E2E support for AtenLogicalOrOp. (#883) 2022-06-03 16:21:03 -07:00
Henry Tu abf5c94a1b
Replace valsem.aten.zero with aten.zero.functional (#893) 2022-06-03 16:27:31 -04:00
Vidush Singhal 0a913bc904
Add E2E support for AtenAllBoolOp (#874) 2022-06-01 18:20:25 -07:00
Ashay Rane 7fdc1cff02
build: remove manual changes to ShapeLibrary.cpp (#894)
The patch bumped up the LLVM tag made manual fixes to the code in
`ShapeLibrary.cpp`.  However, since that file is generated by the
`update_shape_lib.sh` script, its contents were reverted each time the
script was run.  This patch fixes the problem by removing the manual
changes to that file.
2022-06-01 14:11:29 -07:00
Vivek Khandelwal 06750815d1 [tosa] Support for AtenAvgPool2d op
Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-05-27 07:56:37 +05:30
Vivek Khandelwal 6f548fc3ad [MLIR][TORCH] Add decomposition of aten.adaptive_avg_pool2d op
This commit adds the decomposition of `aten.adaptive_avg_pool2d` op into
`aten.avg_pool2d` op. The current decomposition only supports cases where
input size is equal to the output size.

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-05-27 07:56:37 +05:30
Ashay Rane 029cd54327
build: fix code so that the compiler does not emit warnings (#871)
When compiling without assertions (i.e. in `NDEBUG` mode), a handful of
statements turn to NOPs, which results in warnings such as missing
return statement or unused variables and function. This patch replaces
such statements with `llvm_unreachable()`, which informs the compiler
about program termination regardless of the `NDEBUG` mode. This also
enables torch-mlir to be compiled using the flags `-Wall`, `-Wextra`,
`-Wpedantic`, and `-Werror`.
2022-05-25 14:04:59 -07:00
Vivek Khandelwal 56e77d4213 [MLIR][TORCH] Add E2E support for aten.Bool.[float|int] op
This commit adds lowering of `aten.Bool.float` and `aten.Bool.int` op.

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-05-24 21:18:34 +05:30
Vivek Khandelwal 014a6d16c7 [MLIR][TORCH] Add E2E support for aten.any.bool op
This commit adds lowering of `aten.any.bool` op.

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-05-24 17:24:28 +05:30
Vivek Khandelwal bc9b2156e3 [MLIR][TORCH] Add E2E support for aten.sqrt.int op
This commit adds lowering of `aten.sqrt.int` op.

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-05-24 16:50:39 +05:30
Ashay Rane f18b2be911
torch,linalg: add support for translating aten.linalg.vector_norm (#839)
This patch adds support for the torch.linalg.vector_norm op to the torch
dialect, including the necessary shape function.  It also extends the
conversion of reduction operators to support lowering of
AtenLinalgVectorNormOp, in addition to adding a handful of end-to-end
tests to validate the lowering.

There exist several opportunities to make this lowering optimal and
robust.  For instance, in its current form, the translation does not
support ord = 0, +inf, or -inf.  For L1 norms, we don't need to raise
each element to the power 1.0.  Similarly, L2 norms could benefit from
strength reduction.  Since the canonicalization pass is not able to
apply these optimizations, we should consider applying them during the
linalg lowering itself.
2022-05-19 15:48:15 -07:00
Sean Silva 3fb54cba4c torch.prim.TupleIndex: Adjust tensor types when folding.
In cases where a refinement/derefinement was needed, we didn't fold.

Fixes https://github.com/llvm/torch-mlir/issues/863
2022-05-19 09:36:27 -07:00
Ashay Rane bb52a460cb
mlir: bump llvm tag to 5380e3 (#856)
In addition to updating the llvm-project submodule, this patch also:

1. updates shape functions and tests so that `func` and `call`
   operations refer to the `func` dialect
2. avoid duplicate registration of dialects
2022-05-16 12:54:35 -07:00