Commit Graph

31 Commits (88c216da13dbce32e9d122b5c962a584925c1400)

Author SHA1 Message Date
max fe8ac57e6d This PR implements an eager mode backend for PyTorch through the torch-mlir framework. This is accomplished by overriding the `__torch_dispatch__` class method on wrapper subclass `TorchMLIRTensor(torch.Tensor)`.
Effectively, this mode works by compiling op by op as the NN is eagerly executed by PyTorch. Entailed in that compilation is building a representation of the op that can be `torch.jit.script`ed, importing using `ModuleBuilder`, and then executing (e.g., with `RefBackendLinalgOnTensorsBackend`). This mode includes a fallback to conventional PyTorch if anything in the torch-mlir compilation process fails (e.g., unsupported op).

Currently, all e2e tests pass execpt for two that involve an upstream PyTorch bug (https://github.com/pytorch/pytorch/issues/74400).

High priority next steps:

1. A compile cache in order to speed up reruns of the same NN.
2. Integration with IREE (though not in this repo).
3. Integration with `torch.distributed`.
2022-03-22 14:42:57 -07:00
Vivek Khandelwal 3d95c3d6c9 [MLIR][TORCH] Add value tensor variant to aten::_index_put_impl_
This commit adds the op `ValsemVariantAtenIndexPutImplOp` that represents
`Aten_IndexPutImpl_Op` without the underscore. This is needed to
make sure that the `ReduceOpVariants` pass turns the in-place op
into an op that takes value tensors as inputs, otherwise the
`MaximizeValueSemantics` pass will not be able to add value
semantics correctly.

This commit also adds the lowering of `ValsemVariantAtenIndexPutImplOp` op.

This commit also updates the `torch.bincount` op test cases.
2022-03-16 22:02:02 +05:30
Gaurav Shukla 41acde599b [LINALG] Add E2E support for `aten.[le|ge].Scalar` ops
- This commit adds lowering of `aten.le.Scalar` and `aten.ge.Scalar` ops
  as a part of `convert-torch-to-linalg` pass.
- It also creates a new test script `elementwise_comparison.py` for all
  element-wise comparison ops.

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2022-02-15 12:21:09 +05:30
Gaurav Shukla 78c7844c6c [LINALG] Add E2E support for `aten.eq.int` op
- This commit adds lowering of `aten.eq.int` op as a part of
  `convert-torch-to-std` pass.
- It also refactors the code for binary comparison ops lowering.

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2022-02-15 01:37:35 +05:30
Gaurav Shukla f00d1686c8 [LINALG] Add E2E support for `aten.[Bool.Tensor|Float.Tensor]` op
- This commit adds lowering of `aten.Bool.Tensor` and
  `aten.Float.Tensor` op as a part of `convert-torch-to-linalg` pass.
- It also adds support for returning bool types.
- It also fixes lowering of the `aten.Int.Tensor` op for non-zero rank
  input tensors.
- If a scalar number is converted to a 0-d tensor and passed on to the
  `aten.Float.Tensor` op, it folds to the scalar number.

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2022-02-14 23:09:20 +05:30
Gaurav Shukla 2fefe68ffd [TORCH][MLIR] Add E2E support for `aten.native_batch_norm` op
- This commit adds support for `aten.native_batch_norm` operation.
- The current implementation only supports inference mode of
  `aten.native_batch_norm` op.

Signed-Off-By: Gaurav Shukla <gaurav@nod-labs.com>
2022-02-08 02:54:03 +05:30
Gaurav Shukla 0079901039 [TORCH][MLIR] Add E2E support for `aten.reshape` op
This commit decomposes `aten.reshape` into `aten.view` op in the case of
value tensor type operand.

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2022-02-02 20:41:47 +05:30
Yi Zhang 0cb216a1ad [Torch][Linalg] Add basic support for RNG
This PR include the following pieces:
- Add torch `Generator` type. `Generator` type is converted to i64 in
refbackend type converter.
- Add seed managment support for the default global generator.
`torch_c.getNextSeed` op is used to get the seed. On refbackend, the
`torch_c.getNextSeed` is lowered to load/store from [0] of global
variable `default_generator` memref<i64> in `InsertRngGlobals` pass.
- Add `aten.uniform_` and testing as an example op for RNG ops. Add
`torch.pseudo.aten.uniform` op. It has the same operands and return as
the `aten.uniform_` from the op registry except for value semantics.
2022-01-31 18:56:42 -05:00
Gaurav Shukla 13b9fd62c6 [TBE] Add a test module for table batch embedding
This commit adds a test module specifically for table batch embedding
algorithm. This test case is in reference to the FBGEMM table batch
embedding:
https://github.com/pytorch/FBGEMM/blob/main/fbgemm_gpu/bench/split_table_batched_embeddings_benchmark.py#L270

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2022-01-28 02:24:28 +05:30
Nirvedh 17a4843cf7 Adding an e2e test for histogram binning calibration 2022-01-25 18:27:20 -05:00
Vivek Khandelwal ca662dc9cc [MLIR][TORCH] Add E2E support for aten.threshold, aten.threshold_backward op
This commit adds lowering of `aten.threshold` op
This commit adds lowering of `aten.threshold_backward` op

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-01-10 11:56:56 +05:30
Gaurav Shukla 3c40539b34 [TORCH][MLIR] Add E2E support for `aten.[ones_like|zeros_like]`
- This commit adds E2E support for `aten.ones_like` and
  `aten.zeros_like` ops.
- Adds support for non-None `dtype` argument of `aten.empty_like` op.
- All the unit test cases related to constant tensor allocation like ops
  are moved to a different file named `constant_alloc.py`.

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2022-01-06 20:24:40 +05:30
Vivek Khandelwal 4486de5ef3 [MLIR][TORCH] Add E2E support for torch.arange op
This commit adds lowering of `aten.arange.start_step` op.
This commit decomposes `aten.arange` and `aten.arange.start` into
`aten.arange.start_step` op.

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2021-12-27 22:45:48 +05:30
Vivek Khandelwal 8130354c09 [MLIR][TORCH] Add E2E support for aten.index_select op
This commit adds lowering of `aten.index_select` op.

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2021-12-09 23:13:36 +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 a52aded0b9
Add lowering for slice and selectInt (#398) 2021-12-02 22:09:21 -06:00
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
dan 03fdf56f21 add aten.add.int lowering in TorchToStd 2021-11-29 13:22:50 -05:00
Yi Zhang 3bd9d2a4c7 Add e2e support for aten._softmax_backward_data.
Decompose aten._softmax_backward_data into aten math ops. Also decompose
`aten.size` to facilitate decomposing _softmax_backward_data.
2021-11-09 13:09:30 +05:30
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
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
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
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
Sean Silva f69630255a Add --external-config option to tools/torchscript_e2e_test.sh
This is a simple way for externals to plug their backends into the test
suite. They just implement the `TestConfig` class for their backend and
write a small script that exposes it.

I have a pending PR for iree-samples that successfully integrates this.
2021-10-04 11:48:16 -07:00
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 4fad753073 Move external/torch-mlir to the root of the repo. 2021-09-27 17:11:08 -07:00
Sean Silva 404bd74ddf Port the bulk of the remaining code to torch-mlir
This leaves no real code outside torch-mlir.

This also renames the "npcomp backend contract" to "linalg on tensors
backend contract" as the name of the abstraction layer that RefBackend
(IREE too) accepts.
2021-09-27 12:48:33 -07:00
Sean Silva 1a0b953ea7 Eliminate almost all mentions of IREE.
A few remain in examples/docs that will be naturally be updated in due
time.

This regresses the list support and the general direction of more widely
supported control flow, lists/dicts/globals that we were going for with
the TorchScript path. The idea is that we are deferring that work to
make torch-mlir a very clean standalone thing. We will reboot it,
probably using some of the tools of iree_pydm to make it simpler, and in
a more natural place (such as an iree-torch repo that depends on IREE and
torch-mlir to build a working PyTorch frontend solution for IREE -- it
was really weird that npcomp depended on IREE).
2021-09-22 16:06:38 -07:00
Sean Silva 8779d920b2 Remove "refjit" terminology.
We now use RefBackend/refbackend consistently.
2021-09-22 15:41:23 -07:00
Sean Silva 0eb767ea45 Remove frontends/pytorch directory.
It just contained the e2e testing framework. We now fold it into the
main project to reduce complexity.

- `frontends/pytorch/python/` -> `python/torch_support`
- `frontends/pytorch/e2e_testing -> e2e_testing`
- `frontends/pytorch/examples -> examples`
- `frontends/pytorch/test` -> `python/test`
- `torch_mlir_torchscript` python module -> `npcomp_torchscript`
- `torch_mlir_torchscript_e2e_test_configs` python module ->
  `npcomp_torchscript_e2e_test_configs`

This also changes the license of a handful of files from the
"pytorch-style" license to the regular LLVM/npcomp license. The only
people who committed to those files were myself and Yi.
2021-09-17 09:27:49 -07:00