Commit Graph

71 Commits (2414bdb1f0fa17e7593ee60ab4af121aecbf0922)

Author SHA1 Message Date
Liam Fitzpatrick 2414bdb1f0 Linalg lowering for aten.conv2d(bias=True)
Previously aten.conv2d was only lowered if there was no bias.
Here lowering is extended to support bias.
2021-12-08 14:44:36 -08:00
Vivek Khandelwal 9958cf08b6 [MLIR][TORCH] Add E2E support for aten.zeros op
This commit adds lowering of `aten.zeros` op.

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2021-12-08 22:42:33 +05:30
Prashant Kumar 977b1b03ea Add aten::nll_loss_forward op lowering.
The op lowering has been added as a part of `torch-lower-to-linalg`
pass. This takes care of ignore_index but the weight and reduction
operand is still to be accounted for.

Signed-off-by: Prashant Kumar <prashant@nod-labs.com>
2021-12-07 17:11:08 +05:30
Daniel Garvey b0cb49ca93
Add scalar type promotion for mul and div (#454) 2021-12-03 13:51:25 -06:00
Yi Zhang 24bc06fc8d Fix compilation warnings. 2021-12-03 11:44:32 -05:00
Daniel Garvey a52aded0b9
Add lowering for slice and selectInt (#398) 2021-12-02 22:09:21 -06:00
Vivek Khandelwal 46a2189a41 [MLIR][TORCH] Add E2E support for aten.bitwise_and.tensor op
This commit adds lowering of `aten.bitwise_and.tensor` op.

Signed-Off By: Vivek Khandelwal vivek@nod-labs.com
2021-12-02 21:06:15 +05:30
Vivek Khandelwal 46a0668b3b [MLIR][TORCH] Add E2E support for aten.mean and aten.numel op.
This commit adds lowering of `aten.mean` and `aten.numel` op.

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2021-12-02 11:51:13 +05:30
Ramiro Leal-Cavazos e6675a50d3 Add support for dtype argument in reduction ops
Many reduction ops take as an argument an optional output dtype that
can change the type of the input tensor before the reduction is
performed. This commit adds support for the optional dtype flag that
had been previously ignored.

Test:
/tools/torchscript_e2e_test.sh -f 'ReduceSumDtype'
/tools/torchscript_e2e_test.sh -f 'ReduceSumDImIntListDtype'
2021-11-30 12:53:59 -05:00
Gaurav Shukla 73b27b32dc [MLIR][TORCH] Add E2E support for `aten.squeeze` op
This commit adds lowering of `aten.Squeeze` op into
`linalg.TensorCollapseShape` op. The size 1 dynamic dimensions are not
handled as a part of this commit.

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2021-11-30 23:00:28 +05:30
ds1231h 9ad5954e41 aten.abs and aten.reciprocal to linalg 2021-11-30 11:31:55 -05:00
Prashant Kumar 36afa4a4d3 Add aten.fill.Scalar op lowering
The lowering of aten.fill.Scalar has been added.
The changes have been made as a part of -torch-convert-to-linalg pass.

Signed-off-by: Prashant Kumar <prashant@nod-labs.com>
2021-11-30 21:12:15 +05:30
Daniel Garvey 539511c19b
Add dropout op (#436)
Co-authored-by: dan <dan@nod-labs.com>
2021-11-29 12:30:03 -06:00
Liam Fitzpatrick 7616d28ce1 Add leakyrelu support 2021-11-27 23:04:46 +05:30
Vivek Khandelwal 8d8d2c2fb8 [MLIR][TORCH] Add E2E support for aten.div.Scalar
This commit adds lowering of `aten.div.Scalar`.

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2021-11-24 11:17:40 +05:30
Gaurav Shukla 663fc1ef51 [MLIR][TORCH] Add E2E support for [`aten.mul.Scalar`|`aten.addmm`]
This commit adds lowering of `aten.mul.Scalar` and also adds
decomposition of `aten.addmm` to `aten.mul.Scalar`, `aten.add.Tensor`
and `aten.mm` ops.

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2021-11-18 22:26:41 +05:30
Prashant Kumar f8ff6d84f4 Support aten::linear with rank 3 inputs
Now, aten::linear supports rank 3 inputs. This is a fix
for upcoming bert-inference task. The correct way should be
to support broadcasting in `aten.matmul` op and decompose
`aten.linear` into right ops.
2021-11-18 22:15:04 +05:30
Prateek Gupta 146f109152 [NFC] Cleanup code for aten.gelu_backward operation.
This commit adds minor non functional changes to the aten.gelu_backward
operation.

Signed-Off-By: Prateek Gupta <prateek@nod-labs.com>
2021-11-18 11:24:04 -05:00
Prateek Gupta ecf78b9849
[TORCH][MLIR] Add E2E support for `aten.gelu_backward` operation. (#418)
This commit adds new operation `aten.gelu_backward` in the aten
dialect and adds lowering of this operation from aten to linalg.

Signed-Off-By: Prateek Gupta <prateek@nod-labs.com>
2021-11-17 14:59:38 +05:30
Yi Zhang 53733933a4 Update llvm upstream to 0b17336f793108a7b10c3fa913039144ef1d0f61
Update AsmPrinter/Parser and MatchAndRewrite
2021-11-16 13:04:51 -05:00
Ramiro Leal-Cavazos a2392a0f19 Fix bug in handling of pin_memory in AtenOnesOp conversion
This commit fixes a bug with the way ConvertAtenOnesOp was matching on
the pin_memory bool argument, which always resulted in a failed match.
2021-11-12 11:38:25 -05:00
George Petterson 2764e86f02 Add Rsqrt 2021-11-09 11:08:28 -05:00
Yi Zhang 05c4dd8e39 Add convertScalarToDtype helper.
This is to facilitate scalar type conversion in the TorchToLinalg. As
part of adding the helper, this PR also:
- Updated `AtenAddTensorOp`, `AtenSubTensorOp` to use the helpers to
support more type variants.
- Added e2e type promotion testing.
- Added i32 memref return/arg type to support e2e testing.
2021-11-08 17:50:52 -05:00
George Petterson e23cabf3a9 Add log2 2021-11-08 16:19:59 -05:00
George Petterson f41958037a Add NumToTensor 2021-11-08 15:56:52 -05:00
Prateek Gupta 18e8806b14 [TORCH][MLIR] Add E2E support for aten::to.dtype.
This commit adds end to end support for AtenToDtypeOp from aten
to linalg.

Signed-Off-By: Prateek Gupta <prateek@nod-labs.com>
2021-11-08 12:56:03 -05:00
Wang Kangyu 4bb9b44775 Add lowering of "aten.pow.Tensor_Scalar" op
Add e2e support for torch.pow(Tensor, Float)
2021-11-08 09:19:50 -08:00
Wang Kangyu b33543af85 Add lowering of aten.floor op 2021-11-06 17:31:44 -04:00
nodlabs 5ff823ace9 lowerd Sqrt to linalg
reused clang-format, as changes got deleted
2021-11-06 11:29:46 -04:00
Prashant Kumar 127c7d8e27 Add lowering of `torch.log` op
The lowering of `torch.log` op has been added.

Signed-off-by: Prashant Kumar <prashant@nod-labs.com>
2021-11-02 21:18:00 +05:30
George Petterson 6dde5b347e Add rsub 2021-11-02 09:56:48 -04:00
Prashant Kumar 53b4275ef5 Add lowering of `aten.Int.Tensor` op.
The lowering of `aten.Int.Tensor` op has been added.
The changes has been made as a part of `convert-torch-to-linalg` pass.

Signed-off-by: Prashant Kumar <prashant@nod-labs.com>
2021-11-01 21:58:08 +05:30
Gaurav Shukla 69eaf9a154 [MLIR][TORCH] Add E2E support for `torch.aten.view`
- This commit adds lowering of `aten.View` to `linalg.TensorExpandShape`.
- This lowering will be successful only when one or more static
  dimensions are expanded.
- It also fixes a typo in `ConvertAtenFlattenUsingIntsOp` conversion
  pattern.

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2021-10-29 22:33:10 +05:30
Yi Zhang 752abc8d01 Add type promotion code to refine types.
The types have different levels of categories: where
complex > floating > integral > boolean (> means left hand
side has higher category).

The operands have different levels of priorities where:
dimensioned tensor > 0-dim tensor > scalar == wrapped 0-dim tensor.
This is represented by the `ResultTypeState.dimResult`,
`ResultTypeState.zeroResult` and `ResultTypeState..wrappedResult` in
the source code.

For operands of the same priorities, the result type should be the
highest categories with sufficient width to hold all operands.

By default, only the highest priority operands participate in the type
promotion logic. Lower priority operands participate if they are in
a higher category than any higher priority operands.

For example, <[],f32> (lower priority) and <[1], si64> tensor would
result in <[?],f32> tensor because floating > integeral. Another example
<[],f64> (lower priority) and <[1], f32> tensor would result in
<[?], f32> tensor because f32 and f64 are the same category.

The ScalarType enum definition, type promotion table, ResultTypeState
struct definition and some helpers are copied from
aten/src/ATen/native/TypeProperties.*
Other references:
- https://pytorch.org/docs/stable/tensor_attributes.html#type-promotion-doc
- https://github.com/pytorch/pytorch/issues/9515

Other minor changes:
1. Fix `visitExpandLikeOp` to consider cases where the given sizes list
size is larger than the input rank.
2. Add back the somehow deleted `torch.aten.softmax.int` tests in
decompose-complex-ops.mlir.
2021-10-29 11:17:39 -04:00
George Petterson 2ea2ab518b Add contiguous 2021-10-29 11:11:50 -04:00
Prateek Gupta c33a2ca952 [TORCH][MLIR] Add E2E support for aten.permute.
This commit adds lowering of aten.permute to linalg.generic operation.

Signed-Off-By: Prateek Gupta <prateek@nod-labs.com>
2021-10-28 10:25:26 -04:00
Sean Silva 30df2ec71b Add min/max/clamp support.
Part of #380

Also
- BoolType is not considered as Scalar
- e2e framework fixes for nan handling
- `tu.rand(..., low=, high=)` support
- delete unused variable (fix warning)
- Add IouOfModule from #380 to e2e test suite (this is a common
  calculation in vision models)

 Your branch is ahead of 'origin/main' by 1 commit.
2021-10-27 13:29:21 -07:00
Prashant Kumar 5009cbf55c Add lowering of aten.matmul op.
Lowering of `aten.matmul` op is added from torch to linalg dialect.
The different cases correspond to
https://pytorch.org/docs/stable/generated/torch.matmul.html.
TODO: Broadcasting in case of batch-matmul is yet to be taken care of.

Signed-off-by: Prashant Kumar <prashant@nod-labs.com>
2021-10-26 12:45:09 -04:00
Boian Petkantchin e276dbbaa6
Add aten::gelu lowering (#374)
* Print more exception info on error during test execution

* Fix formatting

* Add aten::gelu lowering

Co-authored-by: Boian Petkantchin <boian@nod-labs.com>
2021-10-25 16:16:01 -07:00
Ramiro Leal-Cavazos 8bfb819d35 Fix bug with transpose of negative dims
Summary:
This commit fixes an off-by-one error in how negative dimensiosn were
being handled in the lowering of transpose. This commit also adds
tests to transpose and unsqueeze to test negative dimensions.
2021-10-25 15:50:55 -04:00
George Petterson 22aeb967c5 Add ones 2021-10-21 14:46:59 -04:00
George Petterson 8853dfbc74 Add broadcast 2021-10-19 13:33:31 -04:00
Yi Zhang a459e09ab7 E2e support for aten.softmax.int and aten.embedding
- Added a DecomposeComplexOps pass to decompose complex torchOps.
- Refactored `visitAtenArgmaxOp` and `visitAtenAnyDimOp` to
`visitReductionAlongDimIntOp`.
- Moved some helper functions into
torch-mlir/Dialect/Torch/Utils/Utils.h to be shared by multiple files.
- Added support for f64 tensor as argument and return types.
2021-10-18 17:57:45 -04:00
Yi Zhang 0902438882 Update llvm-project to a54f4eae0e1d0ef5adccdcf9f6c2b518dc1101aa
This brings in https://reviews.llvm.org/D110797. PRs that are in
progress will need to use scripts provided by
https://llvm.discourse.group/t/psa-removed-arithmetic-ops-from-standard/4455.
2021-10-18 13:36:42 -04:00
dan 7750d2173a add argmax lowering
Add argmax lowering from torch to linalg
2021-10-13 14:31:16 -04:00
Sean Silva 0c5c84d63d Add a basic TOSA E2E backend.
We lower through linalg-on-tensors and use RefBackend to run it.
This adds enough support for a "tanh" op. Adding more ops should be
fairly mechanical now that things are wired up. Run with:
```
./tools/torchscript_e2e_test.sh -c tosa
```

The backend structure is very similar to linalg-on-tensors based E2E
backends and is a nice parallel (see `tosa_backend.py`). Actually, this
forced a nice refactoring to the layering here. We removed
`torchscript-module-to-linalg-on-tensors-backend-pipeline` and instead
require separately running
```
torchscript-function-to-torch-backend-pipeline,torch-backend-to-linalg-on-tensors-backend-pipeline
```
This highlights the step that lowers to the "torch backend contract"
of cleaned up `torch` dialect ops is a critical step in the lowering.
Going forward, that is the key load-bearing contract of the torch-mlir
project, not the linalg-on-tensors backend contract.

Recommended review order:
- `TorchToTosa.cpp` / `TorchToTosa/basic.mlir`
- `python/torch_mlir_e2e_test/torchscript/configs/tosa_backend.py` and
  the new `utils.py` file there.
- `python/torch_mlir_e2e_test/tosa_backends/linalg_on_tensors.py` and
  `abc.py` in that directory for the TOSA backend e2e interface.
- other misc mechanical changes
2021-10-08 09:59:45 -07:00
Yi Zhang 98ba255288 E2e support for layernorm. 2021-10-04 14:15:13 -04:00
Sean Silva 5b6902e31c Dual license the torch-mlir project.
This commit (with approval from all contributors) dual licenses
the torch-mlir project under both the standard LLVM license and the
standard PyTorch license. This will facilitate moving code between
torch-mlir and the two upstream projects.

The standard file comment is now:

```
// This file is licensed under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
// Also available under a BSD-style license. See LICENSE.
```

See `LICENSE` in the project root for the terms of both licenses.
2021-10-01 10:46:08 -07:00
Sean Silva 8b2c099914 Update llvm-project to 204d301bb1921431a853c0bfba32007c018df1d5
This brings in the fix for the obscure RefBackend bug we were hitting.
2021-09-28 17:38:10 -07:00
Sean Silva 4fad753073 Move external/torch-mlir to the root of the repo. 2021-09-27 17:11:08 -07:00