llvm
/
torch-mlir
mirror of https://github.com/llvm/torch-mlir
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
torch-mlir/e2e_testing/xfail_sets.py

938 lines
38 KiB
Python
Raw Normal View History

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.
2021-09-30 00:03:40 +08:00
# Part of the LLVM Project, 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.
Add IREE support in TorchScript e2e tests. - Add support for "expected failures" in test reporting. The new error reports look like [this](https://gist.github.com/silvasean/6ffd95e1d55302b699673da201da210d). - We will now be able to put these tests into CI, since the harness understand which tests are expected to pass and fail. - Refactor RefBackendTestConfig to NpcompBackendTestConfig which supports both RefBackend and IREE. - Add instructions for installing IREE dependencies (both from packages and for local builds of IREE) - Add `tools/torchscript_e2e_test.sh` for invoking the e2e test harness (this makes invoking a bit easier, as it doesn't rely on a loose Python invocation).
2021-07-01 05:13:21 +08:00
# This file describes the sets of tests expected to fail for each config.
# This information is deliberately kept in a side table, rather than
# in-situ on the test, as a deliberate layering decision: tests should
# have unique keys to identify them and enable side tables of various kinds
# (this includes down into lower parts of the stack, where a side table
# might be used to keep more elaborate sets of testing configurations).
Move COMMON_TORCH_MLIR_LOWERING_XFAILS into test_suite That way, downstreams don't have to duplicate this list. Also, remove "external config" feature, since it is subsumed by just importing the test suite.
2022-04-20 03:35:56 +08:00
from torch_mlir_e2e_test.test_suite import COMMON_TORCH_MLIR_LOWERING_XFAILS
[e2e tests] Rename default config from "refbackend" to "linalg" This more accurately reflects what it is. The previous name was conflating the use of RefBackend (which `linalg`, `tosa`, and `mhlo` configs all use) with the use of the linalg backend (e.g. TorchToLinalg). This conflation was artifically giving the linalg backend a "privileged" position, which we want to avoid. We still keep it as the default backend, and it remains the most complete, but at least there's not artificial boosting.
2022-12-07 21:51:24 +08:00
LINALG_XFAIL_SET = COMMON_TORCH_MLIR_LOWERING_XFAILS
E2E framework: Add support for list/dict/scalar values Most of the change is in the reporting code to give error messages that are useful, and adjusting TraceItem to be semantically correct w.r.t. Python's modeling of return values. This allows writing a test like `ListLiteralModule_basic` for list functionality, which we will soon be hooking up to IREE. The IR for that test currently gets this far: ``` builtin.func @forward(%arg0: f64) -> !torch.list<!torch.float> { %0 = torch.from_f64 %arg0 %1 = torch.prim.ListConstruct %0, %0 : (!torch.float, !torch.float) -> !torch.list<!torch.float> return %1 : !torch.list<!torch.float> } ``` It should be sufficient to just add a conversion of `torch.prim.ListConstruct` (+ relevant type conversion) to necessary IREE primitives. For lists of *tensors* (rather than scalar floats), it gets more complicated, as we need to deal with changing their element type to ValueTensorType first (by default, they will all be NonValueTensorType). It seems that IREE might have a type we can lower into for non-value tensors as well, TBD.
2021-08-11 07:10:31 +08:00
[torchdynamo] Initial TorchDynamo support This adds a basic e2e Config for TorchDynamo using Linalg-on-Tensors/RefBackend. But TorchDynamo is pretty orthogonal to various other pieces, so it should compose nicely with variations like: - Switching out all the backends (Linalg-on-Tensors, TOSA, MHLO) - PyTorch functionalization and decompositions - Taking the example inputs and compiling with all dynamic or all static shapes without duplicating tests. This adds it to the CI, but there are still a lot of XFAIL's. This also adds a helper `from torch_mlir.dynamo import make_simple_dynamo_backend` which simplifies some of the steps for making a Torch-MLIR-based TorchDynamo backend. We include "simple" in the name because we are going to be exploring various things next from the long-term roadmap. The next steps are: - Burn down all the XFAIL's. - Start working on the pieces from the [long-term roadmap](https://github.com/llvm/torch-mlir/blob/main/docs/long_term_roadmap.md). - Add functionalization/decompositions into the TorchDynamo flow and remove reliance on the current Torch-MLIR "frontend". - Write a pure-Python direct FX->MLIR importer. - Hook up the new PyTorch symbolic shape stuff. - Explore PrimTorch decompositions for simplifying backends.
2022-11-18 20:21:19 +08:00
TORCHDYNAMO_XFAIL_SET = {
#### General TorchDynamo/PyTorch errors
# RecursionError: maximum recursion depth exceeded
# RuntimeError: Failed running call_function aten.lift_fresh_copy(...
[torchdynamo] Update XFAIL sets with upstream bug numbers.
2022-11-24 22:36:13 +08:00
# https://github.com/pytorch/pytorch/issues/89627
[torchdynamo] Initial TorchDynamo support This adds a basic e2e Config for TorchDynamo using Linalg-on-Tensors/RefBackend. But TorchDynamo is pretty orthogonal to various other pieces, so it should compose nicely with variations like: - Switching out all the backends (Linalg-on-Tensors, TOSA, MHLO) - PyTorch functionalization and decompositions - Taking the example inputs and compiling with all dynamic or all static shapes without duplicating tests. This adds it to the CI, but there are still a lot of XFAIL's. This also adds a helper `from torch_mlir.dynamo import make_simple_dynamo_backend` which simplifies some of the steps for making a Torch-MLIR-based TorchDynamo backend. We include "simple" in the name because we are going to be exploring various things next from the long-term roadmap. The next steps are: - Burn down all the XFAIL's. - Start working on the pieces from the [long-term roadmap](https://github.com/llvm/torch-mlir/blob/main/docs/long_term_roadmap.md). - Add functionalization/decompositions into the TorchDynamo flow and remove reliance on the current Torch-MLIR "frontend". - Write a pure-Python direct FX->MLIR importer. - Hook up the new PyTorch symbolic shape stuff. - Explore PrimTorch decompositions for simplifying backends.
2022-11-18 20:21:19 +08:00
"LiftFreshCopyModule_basic",
# TypeError: new_empty(): argument 'size' (position 1) must be tuple of ints, but found element of type NoneType at pos 0
# RuntimeError: Failed running call_function aten.convolution_backward(...
[torchdynamo] Update XFAIL sets with upstream bug numbers.
2022-11-24 22:36:13 +08:00
# https://github.com/pytorch/pytorch/issues/89629
[torchdynamo] Initial TorchDynamo support This adds a basic e2e Config for TorchDynamo using Linalg-on-Tensors/RefBackend. But TorchDynamo is pretty orthogonal to various other pieces, so it should compose nicely with variations like: - Switching out all the backends (Linalg-on-Tensors, TOSA, MHLO) - PyTorch functionalization and decompositions - Taking the example inputs and compiling with all dynamic or all static shapes without duplicating tests. This adds it to the CI, but there are still a lot of XFAIL's. This also adds a helper `from torch_mlir.dynamo import make_simple_dynamo_backend` which simplifies some of the steps for making a Torch-MLIR-based TorchDynamo backend. We include "simple" in the name because we are going to be exploring various things next from the long-term roadmap. The next steps are: - Burn down all the XFAIL's. - Start working on the pieces from the [long-term roadmap](https://github.com/llvm/torch-mlir/blob/main/docs/long_term_roadmap.md). - Add functionalization/decompositions into the TorchDynamo flow and remove reliance on the current Torch-MLIR "frontend". - Write a pure-Python direct FX->MLIR importer. - Hook up the new PyTorch symbolic shape stuff. - Explore PrimTorch decompositions for simplifying backends.
2022-11-18 20:21:19 +08:00
"ConvolutionBackwardModule2DPadded_basic",
"ConvolutionBackwardModule2D_basic",
build: update llvm tag to ba8b8a73f (#1856) * build: update llvm tag to ba8b8a73f * skip ConvolutionModule2DGroups_basic
2023-02-07 23:25:59 +08:00
[torchdynamo] Initial TorchDynamo support This adds a basic e2e Config for TorchDynamo using Linalg-on-Tensors/RefBackend. But TorchDynamo is pretty orthogonal to various other pieces, so it should compose nicely with variations like: - Switching out all the backends (Linalg-on-Tensors, TOSA, MHLO) - PyTorch functionalization and decompositions - Taking the example inputs and compiling with all dynamic or all static shapes without duplicating tests. This adds it to the CI, but there are still a lot of XFAIL's. This also adds a helper `from torch_mlir.dynamo import make_simple_dynamo_backend` which simplifies some of the steps for making a Torch-MLIR-based TorchDynamo backend. We include "simple" in the name because we are going to be exploring various things next from the long-term roadmap. The next steps are: - Burn down all the XFAIL's. - Start working on the pieces from the [long-term roadmap](https://github.com/llvm/torch-mlir/blob/main/docs/long_term_roadmap.md). - Add functionalization/decompositions into the TorchDynamo flow and remove reliance on the current Torch-MLIR "frontend". - Write a pure-Python direct FX->MLIR importer. - Hook up the new PyTorch symbolic shape stuff. - Explore PrimTorch decompositions for simplifying backends.
2022-11-18 20:21:19 +08:00
# RuntimeError: Index tensor must have the same number of dimensions as self tensor
# RuntimeError: Failed running call_function aten.nll_loss_backward(...
[torchdynamo] Update XFAIL sets with upstream bug numbers.
2022-11-24 22:36:13 +08:00
# https://github.com/pytorch/pytorch/issues/89630
[torchdynamo] Initial TorchDynamo support This adds a basic e2e Config for TorchDynamo using Linalg-on-Tensors/RefBackend. But TorchDynamo is pretty orthogonal to various other pieces, so it should compose nicely with variations like: - Switching out all the backends (Linalg-on-Tensors, TOSA, MHLO) - PyTorch functionalization and decompositions - Taking the example inputs and compiling with all dynamic or all static shapes without duplicating tests. This adds it to the CI, but there are still a lot of XFAIL's. This also adds a helper `from torch_mlir.dynamo import make_simple_dynamo_backend` which simplifies some of the steps for making a Torch-MLIR-based TorchDynamo backend. We include "simple" in the name because we are going to be exploring various things next from the long-term roadmap. The next steps are: - Burn down all the XFAIL's. - Start working on the pieces from the [long-term roadmap](https://github.com/llvm/torch-mlir/blob/main/docs/long_term_roadmap.md). - Add functionalization/decompositions into the TorchDynamo flow and remove reliance on the current Torch-MLIR "frontend". - Write a pure-Python direct FX->MLIR importer. - Hook up the new PyTorch symbolic shape stuff. - Explore PrimTorch decompositions for simplifying backends.
2022-11-18 20:21:19 +08:00
"NllLossModuleBackward1DMeanWeight_basic",
"NllLossModuleBackward1DMean_basic",
"NllLossModuleBackward1DSumWeight_basic",
"NllLossModuleBackward1DSum_basic",
"NllLossModuleBackward1DWeight_basic",
"NllLossModuleBackward1D_basic",
[torchdynamo] Use decompositions to support a few ops
2022-11-29 22:01:42 +08:00
# TypeError: uniform() missing 2 required keyword-only arguments: 'dtype' and 'device'
# RuntimeError: Failed running call_function aten.uniform(...
# https://github.com/pytorch/torchdynamo/issues/1954
"UniformNoCorrelationModule_basic",
[torchdynamo] Initial TorchDynamo support This adds a basic e2e Config for TorchDynamo using Linalg-on-Tensors/RefBackend. But TorchDynamo is pretty orthogonal to various other pieces, so it should compose nicely with variations like: - Switching out all the backends (Linalg-on-Tensors, TOSA, MHLO) - PyTorch functionalization and decompositions - Taking the example inputs and compiling with all dynamic or all static shapes without duplicating tests. This adds it to the CI, but there are still a lot of XFAIL's. This also adds a helper `from torch_mlir.dynamo import make_simple_dynamo_backend` which simplifies some of the steps for making a Torch-MLIR-based TorchDynamo backend. We include "simple" in the name because we are going to be exploring various things next from the long-term roadmap. The next steps are: - Burn down all the XFAIL's. - Start working on the pieces from the [long-term roadmap](https://github.com/llvm/torch-mlir/blob/main/docs/long_term_roadmap.md). - Add functionalization/decompositions into the TorchDynamo flow and remove reliance on the current Torch-MLIR "frontend". - Write a pure-Python direct FX->MLIR importer. - Hook up the new PyTorch symbolic shape stuff. - Explore PrimTorch decompositions for simplifying backends.
2022-11-18 20:21:19 +08:00
#### Torch-MLIR internal compiler errors
# These are probably due to slightly different ops being recorded by
# torchdynamo vs. torchscript.
[torchdynamo] Use decompositions to support a few ops
2022-11-29 22:01:42 +08:00
# No upstream decompositions.
[torchdynamo] Annotate the XFAIL's with more info
2022-11-25 20:33:34 +08:00
# %6:4 = torch.operator "aten._embedding_bag_forward_only"(%1, %3, %5, %false, %int0, %false, %none, %false, %int-1) : (!torch.tensor<*,f32>, !torch.tensor<*,si64>, !torch.tensor<*,si64>, !torch.bool, !torch.int, !torch.bool, !torch.none, !torch.bool, !torch.int) -> (!torch.tensor, !torch.tensor, !torch.tensor, !torch.tensor)
[torchdynamo] Use decompositions to support a few ops
2022-11-29 22:01:42 +08:00
# See also: https://github.com/pytorch/torchdynamo/issues/327
[torchdynamo] Initial TorchDynamo support This adds a basic e2e Config for TorchDynamo using Linalg-on-Tensors/RefBackend. But TorchDynamo is pretty orthogonal to various other pieces, so it should compose nicely with variations like: - Switching out all the backends (Linalg-on-Tensors, TOSA, MHLO) - PyTorch functionalization and decompositions - Taking the example inputs and compiling with all dynamic or all static shapes without duplicating tests. This adds it to the CI, but there are still a lot of XFAIL's. This also adds a helper `from torch_mlir.dynamo import make_simple_dynamo_backend` which simplifies some of the steps for making a Torch-MLIR-based TorchDynamo backend. We include "simple" in the name because we are going to be exploring various things next from the long-term roadmap. The next steps are: - Burn down all the XFAIL's. - Start working on the pieces from the [long-term roadmap](https://github.com/llvm/torch-mlir/blob/main/docs/long_term_roadmap.md). - Add functionalization/decompositions into the TorchDynamo flow and remove reliance on the current Torch-MLIR "frontend". - Write a pure-Python direct FX->MLIR importer. - Hook up the new PyTorch symbolic shape stuff. - Explore PrimTorch decompositions for simplifying backends.
2022-11-18 20:21:19 +08:00
"AtenEmbeddingBagSumExample_basic",
[torchdynamo] Annotate the XFAIL's with more info
2022-11-25 20:33:34 +08:00
# %1 = torch.operator "aten.scalar_tensor"(%float8.000000e00, %int6, %int0, %cpu, %none) : (!torch.float, !torch.int, !torch.int, !torch.Device, !torch.none) -> !torch.tensor
[torchdynamo] Initial TorchDynamo support This adds a basic e2e Config for TorchDynamo using Linalg-on-Tensors/RefBackend. But TorchDynamo is pretty orthogonal to various other pieces, so it should compose nicely with variations like: - Switching out all the backends (Linalg-on-Tensors, TOSA, MHLO) - PyTorch functionalization and decompositions - Taking the example inputs and compiling with all dynamic or all static shapes without duplicating tests. This adds it to the CI, but there are still a lot of XFAIL's. This also adds a helper `from torch_mlir.dynamo import make_simple_dynamo_backend` which simplifies some of the steps for making a Torch-MLIR-based TorchDynamo backend. We include "simple" in the name because we are going to be exploring various things next from the long-term roadmap. The next steps are: - Burn down all the XFAIL's. - Start working on the pieces from the [long-term roadmap](https://github.com/llvm/torch-mlir/blob/main/docs/long_term_roadmap.md). - Add functionalization/decompositions into the TorchDynamo flow and remove reliance on the current Torch-MLIR "frontend". - Write a pure-Python direct FX->MLIR importer. - Hook up the new PyTorch symbolic shape stuff. - Explore PrimTorch decompositions for simplifying backends.
2022-11-18 20:21:19 +08:00
"ElementwiseWhereScalarModule_basic",
"ElementwiseWhereScalarOtherModule_basic",
"ElementwiseWhereScalarSelfModule_basic",
[torchdynamo] Annotate the XFAIL's with more info
2022-11-25 20:33:34 +08:00
# %7 = torch.operator "aten._index_put_impl_.hacked_twin"(%1, %6, %5, %true, %false) : (!torch.tensor<*,f32>, !torch.list<tensor>, !torch.tensor<*,f32>, !torch.bool, !torch.bool) -> !torch.tensor
[torchdynamo] Initial TorchDynamo support This adds a basic e2e Config for TorchDynamo using Linalg-on-Tensors/RefBackend. But TorchDynamo is pretty orthogonal to various other pieces, so it should compose nicely with variations like: - Switching out all the backends (Linalg-on-Tensors, TOSA, MHLO) - PyTorch functionalization and decompositions - Taking the example inputs and compiling with all dynamic or all static shapes without duplicating tests. This adds it to the CI, but there are still a lot of XFAIL's. This also adds a helper `from torch_mlir.dynamo import make_simple_dynamo_backend` which simplifies some of the steps for making a Torch-MLIR-based TorchDynamo backend. We include "simple" in the name because we are going to be exploring various things next from the long-term roadmap. The next steps are: - Burn down all the XFAIL's. - Start working on the pieces from the [long-term roadmap](https://github.com/llvm/torch-mlir/blob/main/docs/long_term_roadmap.md). - Add functionalization/decompositions into the TorchDynamo flow and remove reliance on the current Torch-MLIR "frontend". - Write a pure-Python direct FX->MLIR importer. - Hook up the new PyTorch symbolic shape stuff. - Explore PrimTorch decompositions for simplifying backends.
2022-11-18 20:21:19 +08:00
"IndexPutImpl1DFloatAccumulateModule_basic",
"IndexPutImpl1DFloatNonAccumulateModule_basic",
"IndexPutImpl1DIntAccumulateModule_basic",
"IndexPutImpl1DIntNonAccumulateModule_basic",
"IndexPutImpl2DFloatAccumulateModule_basic",
"IndexPutImpl2DFloatNonAccumulateModule_basic",
[MLIR][TORCH] Extend implementation of aten._index_put_impl op. This commits adds the support for cases for index_put_op: 1.) where index is a 2-d tensor. 2.) where indices is a list of tensors and none, with exactly 2 non none tensors along the consecutive dimensions. This commit also adds a utility to compute the broadcast shape given the two input tensors. Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-12-08 13:46:54 +08:00
"IndexPutImpl2DIndexModule_basic",
[torchdynamo] Initial TorchDynamo support This adds a basic e2e Config for TorchDynamo using Linalg-on-Tensors/RefBackend. But TorchDynamo is pretty orthogonal to various other pieces, so it should compose nicely with variations like: - Switching out all the backends (Linalg-on-Tensors, TOSA, MHLO) - PyTorch functionalization and decompositions - Taking the example inputs and compiling with all dynamic or all static shapes without duplicating tests. This adds it to the CI, but there are still a lot of XFAIL's. This also adds a helper `from torch_mlir.dynamo import make_simple_dynamo_backend` which simplifies some of the steps for making a Torch-MLIR-based TorchDynamo backend. We include "simple" in the name because we are going to be exploring various things next from the long-term roadmap. The next steps are: - Burn down all the XFAIL's. - Start working on the pieces from the [long-term roadmap](https://github.com/llvm/torch-mlir/blob/main/docs/long_term_roadmap.md). - Add functionalization/decompositions into the TorchDynamo flow and remove reliance on the current Torch-MLIR "frontend". - Write a pure-Python direct FX->MLIR importer. - Hook up the new PyTorch symbolic shape stuff. - Explore PrimTorch decompositions for simplifying backends.
2022-11-18 20:21:19 +08:00
"IndexPutImpl3DFloatAccumulateModule_basic",
"IndexPutImpl3DFloatNonAccumulateModule_basic",
[torchdynamo] Use decompositions to support a few ops
2022-11-29 22:01:42 +08:00
[torchdynamo] Initial TorchDynamo support This adds a basic e2e Config for TorchDynamo using Linalg-on-Tensors/RefBackend. But TorchDynamo is pretty orthogonal to various other pieces, so it should compose nicely with variations like: - Switching out all the backends (Linalg-on-Tensors, TOSA, MHLO) - PyTorch functionalization and decompositions - Taking the example inputs and compiling with all dynamic or all static shapes without duplicating tests. This adds it to the CI, but there are still a lot of XFAIL's. This also adds a helper `from torch_mlir.dynamo import make_simple_dynamo_backend` which simplifies some of the steps for making a Torch-MLIR-based TorchDynamo backend. We include "simple" in the name because we are going to be exploring various things next from the long-term roadmap. The next steps are: - Burn down all the XFAIL's. - Start working on the pieces from the [long-term roadmap](https://github.com/llvm/torch-mlir/blob/main/docs/long_term_roadmap.md). - Add functionalization/decompositions into the TorchDynamo flow and remove reliance on the current Torch-MLIR "frontend". - Write a pure-Python direct FX->MLIR importer. - Hook up the new PyTorch symbolic shape stuff. - Explore PrimTorch decompositions for simplifying backends.
2022-11-18 20:21:19 +08:00
# https://github.com/llvm/torch-mlir/issues/1611
# error: 'tensor.cast' op operand type 'tensor<0xi64>' and result type 'tensor<18xi64>' are cast incompatible
"Aten_EmbeddingBagExample_basic",
# error: failed to legalize operation 'torch.valsem.aten.bernoulli.float' that was explicitly marked illegal
"BernoulliFloatModule_basic",
[MLIR][TORCH] Add decomposition for aten.bernoulli.p op (#1882) Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2023-02-16 01:06:29 +08:00
"BernoulliPModule_basic",
[torchdynamo] Initial TorchDynamo support This adds a basic e2e Config for TorchDynamo using Linalg-on-Tensors/RefBackend. But TorchDynamo is pretty orthogonal to various other pieces, so it should compose nicely with variations like: - Switching out all the backends (Linalg-on-Tensors, TOSA, MHLO) - PyTorch functionalization and decompositions - Taking the example inputs and compiling with all dynamic or all static shapes without duplicating tests. This adds it to the CI, but there are still a lot of XFAIL's. This also adds a helper `from torch_mlir.dynamo import make_simple_dynamo_backend` which simplifies some of the steps for making a Torch-MLIR-based TorchDynamo backend. We include "simple" in the name because we are going to be exploring various things next from the long-term roadmap. The next steps are: - Burn down all the XFAIL's. - Start working on the pieces from the [long-term roadmap](https://github.com/llvm/torch-mlir/blob/main/docs/long_term_roadmap.md). - Add functionalization/decompositions into the TorchDynamo flow and remove reliance on the current Torch-MLIR "frontend". - Write a pure-Python direct FX->MLIR importer. - Hook up the new PyTorch symbolic shape stuff. - Explore PrimTorch decompositions for simplifying backends.
2022-11-18 20:21:19 +08:00
# error: failed to legalize operation 'torch.aten.view' that was explicitly marked illegal
"ElementwiseFlattenBroadcastModule_basic",
"FlattenRank0Module_basic",
[torchdynamo] Use decompositions to support a few ops
2022-11-29 22:01:42 +08:00
"UniformModule_basic",
[torchdynamo] Initial TorchDynamo support This adds a basic e2e Config for TorchDynamo using Linalg-on-Tensors/RefBackend. But TorchDynamo is pretty orthogonal to various other pieces, so it should compose nicely with variations like: - Switching out all the backends (Linalg-on-Tensors, TOSA, MHLO) - PyTorch functionalization and decompositions - Taking the example inputs and compiling with all dynamic or all static shapes without duplicating tests. This adds it to the CI, but there are still a lot of XFAIL's. This also adds a helper `from torch_mlir.dynamo import make_simple_dynamo_backend` which simplifies some of the steps for making a Torch-MLIR-based TorchDynamo backend. We include "simple" in the name because we are going to be exploring various things next from the long-term roadmap. The next steps are: - Burn down all the XFAIL's. - Start working on the pieces from the [long-term roadmap](https://github.com/llvm/torch-mlir/blob/main/docs/long_term_roadmap.md). - Add functionalization/decompositions into the TorchDynamo flow and remove reliance on the current Torch-MLIR "frontend". - Write a pure-Python direct FX->MLIR importer. - Hook up the new PyTorch symbolic shape stuff. - Explore PrimTorch decompositions for simplifying backends.
2022-11-18 20:21:19 +08:00
# error: failed to materialize conversion for result #0 of operation 'torch.aten.t' that remained live after conversion
"TModuleRank1_basic",
xfail ElementwisePreluModule_basic in dynamo (#1763)
2023-01-01 05:54:25 +08:00
# error: unsupported by backend contract: tensor with unknown rank
# note: see current operation: %1 = "torch.tensor_static_info_cast"(%arg0) : (!torch.vtensor<[5,4,3,2,1],f32>) -> !torch.vtensor<*,f32>
"ElementwisePreluModule_basic",
build: manually update PyTorch version Set PyTorch and TorchVision version to nightly release 2023-02-06. Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2023-02-07 13:38:44 +08:00
#ERROR: value (Tensor with shape=[2, 3, 6, 10], dtype=torch.float32, min=-1.336e-32, max=+0.9152, mean=+0.4837) is not close to golden value (Tensor with shape=[2, 3, 6, 10], dtype=torch.float32, min=+0.02233, max=+0.9152, mean=+0.4777)
"UpSampleNearest2dDynamicFactor_basic",
[MLIR][TORCH] Add support for integer type input for max.dim op Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2023-02-06 19:52:04 +08:00
"ReduceMaxAlongDimUnsignedInt_basic",
build: manually update PyTorch version Set PyTorch and TorchVision version to nightly release 2023-02-20. Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2023-02-20 15:40:09 +08:00
#ERROR: value (-56) is not equal to golden value (200)
"AtenIntTensorByteDtypeModule_basic",
Fix handling of non-int tensors in `getScalarValue` (#1914) The current implementation of `getScalarValue` does not check that the input to a `ValueTensorLiteralOp` is an i64 before extracting the value, and it does not check that the result type of the `PrimNumToTensorScalarOp` is also an i64. This leads to crashes or invalid IR generated when the `input` is something other than an i64 tensor or `!torch.int`. This commit addresses those issues. In addition, the function `getScalarValue` is renamed to `getScalarIntValue` to make it clear that it *only* extracts scalar integers.
2023-03-07 02:12:58 +08:00
# ERROR: assert isinstance(e, FakeTensor)
"ElementwiseAddScalar_NumToTensorFloat_Module_basic",
[Torch Dialect] add RSub, ScalarImplicit canonicalize (#1899) * add rsub, scalarimplit canonicalizer * reformat * address comments * fix bug * fix test * Update elementwise.py * resolve merge conflict * change to 3 * change to 3 * real fix * fix name * add torchdynamo fail test --------- Co-authored-by: zhekun.zhang <zhekun.zhang@bytedance.com>
2023-03-07 09:38:27 +08:00
# ERROR: assert isinstance(e, FakeTensor)
"RsubInt0d_NumToTensor_Module_basic",
[MLIR][TORCH] Add decomposition for prims::squeeze op This commit adds the decomposition for the prims.squeeze op. Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-11-16 13:57:58 +08:00
# ERROR: RuntimeError: Found a custom (non-ATen) operator that either mutates or its inputs: prims::squeeze.. Getting these operators to work with functionalization requires some extra work. For mutable ops you need to register a corresponding out-of-place variant of the op, and you also need to register a Functionalization kernel that performs some boilerplate, telling functionalization to map from the mutable op to the out-of-place op. See a more complete example of how to do this at https://gist.github.com/bdhirsh/7dadbf6296f8f7d1abcf4c482f438aaa.
"PrimsSqueezeModule_basic",
"PrimsSqueezeEmptyDimensionsModule_basic",
[TorchDynamo] Add aten.squeeze op to the decomposition list Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2023-04-05 19:32:52 +08:00
[MLIR][TORCH] Add support for prims::view_of op This op does nothing and just returns the input operand as the result of the op. Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2023-04-10 11:50:26 +08:00
# ERROR: RuntimeError: Found a custom (non-ATen) operator that either mutates or its inputs: prims::view_of.. Getting these operators to work with functionalization requires some extra work. For mutable ops you need to register a corresponding out-of-place variant of the op, and you also need to register a Functionalization kernel that performs some boilerplate, telling functionalization to map from the mutable op to the out-of-place op. See a more complete example of how to do this at https://gist.github.com/bdhirsh/7dadbf6296f8f7d1abcf4c482f438aaa.
"PrimsViewOfModule_basic",
"PrimsViewOfZeroRankModule_basic",
[torchdynamo] Initial TorchDynamo support This adds a basic e2e Config for TorchDynamo using Linalg-on-Tensors/RefBackend. But TorchDynamo is pretty orthogonal to various other pieces, so it should compose nicely with variations like: - Switching out all the backends (Linalg-on-Tensors, TOSA, MHLO) - PyTorch functionalization and decompositions - Taking the example inputs and compiling with all dynamic or all static shapes without duplicating tests. This adds it to the CI, but there are still a lot of XFAIL's. This also adds a helper `from torch_mlir.dynamo import make_simple_dynamo_backend` which simplifies some of the steps for making a Torch-MLIR-based TorchDynamo backend. We include "simple" in the name because we are going to be exploring various things next from the long-term roadmap. The next steps are: - Burn down all the XFAIL's. - Start working on the pieces from the [long-term roadmap](https://github.com/llvm/torch-mlir/blob/main/docs/long_term_roadmap.md). - Add functionalization/decompositions into the TorchDynamo flow and remove reliance on the current Torch-MLIR "frontend". - Write a pure-Python direct FX->MLIR importer. - Hook up the new PyTorch symbolic shape stuff. - Explore PrimTorch decompositions for simplifying backends.
2022-11-18 20:21:19 +08:00
}
mhlo: migrate conversion to stablehlo (#1840) This patch replaces all MHLO operations with their StableHLO counterparts and adds a validation pass to ensure that no MHLO operations remain before translating all Stablehlo operations to the MHLO dialect for further lowering to the Linalg dialect. This patch also updates all lit tests so that they refer to the `convert-torch-to-stablehlo` pass and so that they check for StableHLO operations.
2023-02-02 21:29:47 +08:00
STABLEHLO_PASS_SET = {
[MHLO] Support AtenMaskedFillScalar (#1839) * [MHLO] Support MaskedFillScalar. * Update. * Update. * Update. --------- Co-authored-by: Ziheng Jiang <ziheng.jiang@bytedance.com>
2023-02-11 05:58:39 +08:00
"MaskedFillScalarIntValueStaticModule_basic",
"MaskedFillScalarFloatValueStaticModule_basic",
[MHLO] Evaluate RuntimeAssertOp at compile time (#1732)
2022-12-22 17:12:52 +08:00
"AdaptiveAvgPool2dNonUnitOutputSizeStaticModule_basic",
mhlo: migrate conversion to stablehlo (#1840) This patch replaces all MHLO operations with their StableHLO counterparts and adds a validation pass to ensure that no MHLO operations remain before translating all Stablehlo operations to the MHLO dialect for further lowering to the Linalg dialect. This patch also updates all lit tests so that they refer to the `convert-torch-to-stablehlo` pass and so that they check for StableHLO operations.
2023-02-02 21:29:47 +08:00
"AddSizeIntModule_basic",
"AddSizeIntNegDimModule_basic",
Add torch-to-mhlo e2e support for AtenArangeStartStepOp (#1385) Co-authored-by: Vremold <xremold@gamil.com>
2022-09-20 22:31:24 +08:00
"ArangeDtypeFloatModule_basic",
"ArangeDtypeIntModule_basic",
"ArangeFalsePinMemoryModule_basic",
"ArangeFloatModule_basic",
"ArangeIntModule_basic",
"ArangeNegativeStartFloatModule_basic",
"ArangeNegativeStartIntModule_basic",
"ArangeStartFloatModule_basic",
"ArangeStartIntModule_basic",
"ArangeStartNegativeStepFloatModule_basic",
"ArangeStartNegativeStepIntModule_basic",
"ArangeStartStepFloatModule_basic",
"ArangeStartStepIntModule_basic",
"ArangeZeroElementOutputModule_basic",
mhlo: migrate conversion to stablehlo (#1840) This patch replaces all MHLO operations with their StableHLO counterparts and adds a validation pass to ensure that no MHLO operations remain before translating all Stablehlo operations to the MHLO dialect for further lowering to the Linalg dialect. This patch also updates all lit tests so that they refer to the `convert-torch-to-stablehlo` pass and so that they check for StableHLO operations.
2023-02-02 21:29:47 +08:00
"BatchMlpLayerModule_basic",
fix mhlo e2e ci crashes (#1620) * fix mhlo e2e ci crashes * add passed tests * calc dynamic positive dim
2022-11-21 21:50:35 +08:00
"BmmModule_basic",
"BroadcastToModule_basic",
"BroadcastToSameRankStaticModule_basic",
"BroadcastZeroRankInputStaticModule_basic",
Add aten.bucketize op and its decomposition (#1834)
2023-02-03 10:20:47 +08:00
"BucketizeTensorStaticFloatModule_basic",
"BucketizeTensorStaticModule_basic",
[MHLO] Support aten.cumsum op in mhlo backend (#1825)
2023-01-30 13:38:27 +08:00
"CumsumStaticModule_basic",
"CumsumStaticNegativeDimModule_basic",
Add e2e support for aten logical or/and/xor/not ops (#1761)
2023-01-04 10:11:25 +08:00
"ElementwiseAtenLogicalAndOpPromoteBroadcastStaticShapeModule_basic",
"ElementwiseAtenLogicalNotOpModule_basic",
"ElementwiseAtenLogicalNotOpPromoteModule_basic",
"ElementwiseAtenLogicalOrOpPromoteBroadcastStaticShapeModule_basic",
"ElementwiseAtenLogicalXorOpPromoteBroadcastStaticShapeModule_basic",
Add more mhlo basic converters (#1628) * Add more mhlo basic converters * remove unused pinnedMemory constraints * refine naming
2022-11-24 14:28:34 +08:00
"ElementwiseAtenWhereSelfModule_basic",
[LINALG][TOSA][MHLO] Add e2e support for aten bitwise ops (#1753)
2023-01-12 06:40:03 +08:00
"ElementwiseBitwiseAndStaticShapeModule_basic",
"ElementwiseBitwiseNotInt64Module_basic",
"ElementwiseBitwiseNotInt32Module_basic",
"ElementwiseBitwiseOrStaticShapeModule_basic",
"ElementwiseBitwiseXorStaticShapeModule_basic",
Add AtenClampOp conversion pattern to MHLO (#1356) Add AtenClampOp conversion pattern to MHLO
2022-09-16 15:09:21 +08:00
"ElementwiseClampModule_basic",
"ElementwiseClampMinModule_basic",
"ElementwiseClampMaxModule_basic",
[StableHLO] Add support for AtenPowTensorScalar. (#1883) * [MHLO] Add support for AtenPowTensorScalar. * Update. --------- Co-authored-by: Ziheng Jiang <ziheng.jiang@bytedance.com>
2023-02-17 12:26:46 +08:00
"ElementwisePowModule_basic",
[MLIR][MHLO] Add AtenFrobeniusNormDimOp and add its conversion pattern to MHLO and linalg (#1306) * Add aten.frobenius_norm.dim op and init its conversion pattern to linalg and MHLO, * run symbolic-shape-optimization before hlo-legalize-to-linalg to fit more mhlo e2e tests.
2022-09-08 10:15:36 +08:00
"ElementwiseExpModule_basic",
mhlo: migrate conversion to stablehlo (#1840) This patch replaces all MHLO operations with their StableHLO counterparts and adds a validation pass to ensure that no MHLO operations remain before translating all Stablehlo operations to the MHLO dialect for further lowering to the Linalg dialect. This patch also updates all lit tests so that they refer to the `convert-torch-to-stablehlo` pass and so that they check for StableHLO operations.
2023-02-02 21:29:47 +08:00
"ElementwiseFlattenBroadcastModule_basic",
"ElementwiseLeakyReluModule_basic",
[MLIR][MHLO] Add AtenFrobeniusNormDimOp and add its conversion pattern to MHLO and linalg (#1306) * Add aten.frobenius_norm.dim op and init its conversion pattern to linalg and MHLO, * run symbolic-shape-optimization before hlo-legalize-to-linalg to fit more mhlo e2e tests.
2022-09-08 10:15:36 +08:00
"ElementwiseLogModule_basic",
"ElementwiseNegModule_basic",
[Torch][MHLO] Decompose aten.copy op. Lower aten.rsqrt & sigmoid to mhlo. (#1734)
2022-12-22 10:13:59 +08:00
"ElementwiseRsqrtModule_basic",
"ElementwiseSigmoidModule_basic",
[MLIR][MHLO] Add AtenFrobeniusNormDimOp and add its conversion pattern to MHLO and linalg (#1306) * Add aten.frobenius_norm.dim op and init its conversion pattern to linalg and MHLO, * run symbolic-shape-optimization before hlo-legalize-to-linalg to fit more mhlo e2e tests.
2022-09-08 10:15:36 +08:00
"ElementwiseSqrtModule_basic",
[MHLO] move AtenTanhOp to ConvertAtenUnaryFPOnlyPatten and add sin/cos/ceil/floor pattern (#1847)
2023-02-07 03:14:26 +08:00
"ElementwiseSinModule_basic",
"ElementwiseCosModule_basic",
"ElementwiseCeilModule_basic",
"ElementwiseFloorModule_basic",
[MLIR][MHLO] Add AtenFrobeniusNormDimOp and add its conversion pattern to MHLO and linalg (#1306) * Add aten.frobenius_norm.dim op and init its conversion pattern to linalg and MHLO, * run symbolic-shape-optimization before hlo-legalize-to-linalg to fit more mhlo e2e tests.
2022-09-08 10:15:36 +08:00
"ElementwiseUnaryModule_basic",
mhlo: migrate conversion to stablehlo (#1840) This patch replaces all MHLO operations with their StableHLO counterparts and adds a validation pass to ensure that no MHLO operations remain before translating all Stablehlo operations to the MHLO dialect for further lowering to the Linalg dialect. This patch also updates all lit tests so that they refer to the `convert-torch-to-stablehlo` pass and so that they check for StableHLO operations.
2023-02-02 21:29:47 +08:00
"ElementwiseUnsqueezeBroadcastModule_basic",
[MLIR][MHLO] Add AtenFrobeniusNormDimOp and add its conversion pattern to MHLO and linalg (#1306) * Add aten.frobenius_norm.dim op and init its conversion pattern to linalg and MHLO, * run symbolic-shape-optimization before hlo-legalize-to-linalg to fit more mhlo e2e tests.
2022-09-08 10:15:36 +08:00
"ElementwiseUnsqueezeNegDimsModule_basic",
Replace empty_like && empty_memory_format with full/full_like (#1398) * Replace empty_like && empty_memory_format with full/full_like * fix broadcast rank0 tensor
2022-09-23 10:24:36 +08:00
"ElementwiseToDtypeF32ToI64Module_basic",
Add relu6 and binary broadcasts (#1408) * Add relu6 and binary broadcasts
2022-09-23 20:39:15 +08:00
"ElementwiseAddModule_basic",
"ElementwiseAddScalarFloatModule_basic",
"ElementwiseAddScalarInt64Module_basic",
"ElementwiseAddScalarIntModule_basic",
Fix handling of non-int tensors in `getScalarValue` (#1914) The current implementation of `getScalarValue` does not check that the input to a `ValueTensorLiteralOp` is an i64 before extracting the value, and it does not check that the result type of the `PrimNumToTensorScalarOp` is also an i64. This leads to crashes or invalid IR generated when the `input` is something other than an i64 tensor or `!torch.int`. This commit addresses those issues. In addition, the function `getScalarValue` is renamed to `getScalarIntValue` to make it clear that it *only* extracts scalar integers.
2023-03-07 02:12:58 +08:00
"ElementwiseAddScalar_NumToTensorFloat_Module_basic",
"ElementwiseAddScalar_TensorLiteralInt32_Module_basic",
Add relu6 and binary broadcasts (#1408) * Add relu6 and binary broadcasts
2022-09-23 20:39:15 +08:00
"ElementwiseDivScalarModule_basic",
"ElementwiseEqDiffWidthScalarModule_basic",
"ElementwiseEqFloatScalarModule_basic",
"ElementwiseEqIntScalarModule_basic",
"ElementwiseErfModule_basic",
"ElementwiseGeluModule_basic",
"ElementwiseGtFloatScalarModule_basic",
"ElementwiseGtIntScalarModule_basic",
"ElementwiseGtMixed2ScalarModule_basic",
Add more mhlo basic converters (#1628) * Add more mhlo basic converters * remove unused pinnedMemory constraints * refine naming
2022-11-24 14:28:34 +08:00
"ElementwiseGeFloatIntScalarModule_basic",
"ElementwiseGeFloatScalarModule_basic",
"ElementwiseGeIntScalarModule_basic",
"ElementwiseGeMixedIntScalarModule_basic",
Add E2E support for LeakyRelu and LeakyReluBackward ops (#1733) Co-authored-by: srirammaswamy <srirammaswamy@gmail.com>
2023-01-04 00:30:16 +08:00
"ElementwiseLeakyReluStaticModule_basic",
Add more mhlo basic converters (#1628) * Add more mhlo basic converters * remove unused pinnedMemory constraints * refine naming
2022-11-24 14:28:34 +08:00
"ElementwiseLeFloatIntScalarModule_basic",
"ElementwiseLeFloatScalarModule_basic",
"ElementwiseLeIntScalarModule_basic",
"ElementwiseLeMixedIntScalarModule_basic",
Add relu6 and binary broadcasts (#1408) * Add relu6 and binary broadcasts
2022-09-23 20:39:15 +08:00
"ElementwiseLtDiffWidthScalarModule_basic",
"ElementwiseLtFloatScalarModule_basic",
"ElementwiseLtIntScalarModule_basic",
"ElementwiseMulScalarModule_basic",
"ElementwiseMulScalarModule_float",
"ElementwiseMulScalarModule_int",
"ElementwiseNeFloatTensorModule_basic",
"ElementwiseNeIntScalarModule_basic",
"ElementwiseReciprocalModule_basic",
"ElementwiseRelu6Module_basic",
"ElementwiseReluModule_basic",
Add more mhlo basic converters (#1628) * Add more mhlo basic converters * remove unused pinnedMemory constraints * refine naming
2022-11-24 14:28:34 +08:00
"ElementwiseRemainderScalarModule_Bool_basic",
"ElementwiseRemainderScalarModule_Float_basic",
"ElementwiseRemainderScalarModule_Int_Float_basic",
"ElementwiseRemainderScalarModule_Int_basic",
Add relu6 and binary broadcasts (#1408) * Add relu6 and binary broadcasts
2022-09-23 20:39:15 +08:00
"ElementwiseSubScalarFloatModule_basic",
"ElementwiseSubScalarIntModule_basic",
Add more mhlo basic converters (#1628) * Add more mhlo basic converters * remove unused pinnedMemory constraints * refine naming
2022-11-24 14:28:34 +08:00
"ElementwiseWhereScalarModule_basic",
fix mhlo e2e ci crashes (#1620) * fix mhlo e2e ci crashes * add passed tests * calc dynamic positive dim
2022-11-21 21:50:35 +08:00
"EmbeddingModule1DIndices_basic",
"EmbeddingModuleI32Static_basic",
"EmbeddingModuleI32_basic",
"EmbeddingModuleI64_basic",
[RefineTypes] Fix knowledge dtype for `aten.embedding` op -- The dtype of the result of `aten.embedding` should match that of the `weight` operand's (operand[0]) instead of hardcoding to f32. -- This commit aims to provide a fix for the same. Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
2022-11-30 19:14:48 +08:00
"EmbeddingModuleF16_basic",
Replace empty_like && empty_memory_format with full/full_like (#1398) * Replace empty_like && empty_memory_format with full/full_like * fix broadcast rank0 tensor
2022-09-23 10:24:36 +08:00
"ExpandAsIntModule_basic",
[MLIR][MHLO] Add AtenFrobeniusNormDimOp and add its conversion pattern to MHLO and linalg (#1306) * Add aten.frobenius_norm.dim op and init its conversion pattern to linalg and MHLO, * run symbolic-shape-optimization before hlo-legalize-to-linalg to fit more mhlo e2e tests.
2022-09-08 10:15:36 +08:00
"ExpandModule_basic",
Replace empty_like && empty_memory_format with full/full_like (#1398) * Replace empty_like && empty_memory_format with full/full_like * fix broadcast rank0 tensor
2022-09-23 10:24:36 +08:00
"FullLikeModuleDefaultDtype_basic",
"FullLikeModuleFalsePinMemory_basic",
"FullLikeModuleFloat2D_basic",
"FullLikeModuleFloat3DStatic_basic",
"FullLikeModuleFloat3D_basic",
"FullLikeModuleInt2DStatic_basic",
"FullLikeModuleInt2D_basic",
"FullLikeModuleInt3D_basic",
"FullModuleDefaultDtype_basic",
"FullModuleFalsePinMemory_basic",
"FullModuleFloat2D_basic",
"FullModuleFloat3D_basic",
"FullModuleInt2D_basic",
"FullModuleInt3D_basic",
fix mhlo e2e ci crashes (#1620) * fix mhlo e2e ci crashes * add passed tests * calc dynamic positive dim
2022-11-21 21:50:35 +08:00
"GatherStaticModule_basic",
"GatherModule_basic",
"Gather2DInputModdule_basic",
"GatherRandomIndexModule_basic",
[MLIR][TORCH] Patch up Ops and their lowerings to deal with +ve `dim` -- In Python we have the concept of negative dimension indexing. -- We would want to normalize such dimensions to be +ve and within the expected range instead. -- This commit takes care of a few remaining set of Ops and their lowerings by applying `toPositiveDim` and `isValidDim` to the extracted integer `dim` value. Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
2023-04-07 19:49:35 +08:00
"GatherNegativeDimModule_basic",
Added GeluBackward: MHLO support (#1725)
2022-12-21 20:09:43 +08:00
"GeluBackwardModule_basic",
mhlo: migrate conversion to stablehlo (#1840) This patch replaces all MHLO operations with their StableHLO counterparts and adds a validation pass to ensure that no MHLO operations remain before translating all Stablehlo operations to the MHLO dialect for further lowering to the Linalg dialect. This patch also updates all lit tests so that they refer to the `convert-torch-to-stablehlo` pass and so that they check for StableHLO operations.
2023-02-02 21:29:47 +08:00
"HardswishModule_basic",
"HardswishRandomModule_basic",
fix mhlo e2e ci crashes (#1620) * fix mhlo e2e ci crashes * add passed tests * calc dynamic positive dim
2022-11-21 21:50:35 +08:00
"HardTanhIntModule_basic",
"HardTanhModule_basic",
"HardsigmoidModule_basic",
"HardsigmoidRandomModule_basic",
"IndexSelectDynamicIndexSizeModule_basic",
"IndexSelectSingleIdxModule_basic",
"IndexSelectTwoIdxModule_basic",
"IndexSelectWholeDimensionModule_basic",
"IndexSelectWholeTensorModule_basic",
[MLIR][TORCH] Patch up Ops and their lowerings to deal with +ve `dim` -- In Python we have the concept of negative dimension indexing. -- We would want to normalize such dimensions to be +ve and within the expected range instead. -- This commit takes care of a few remaining set of Ops and their lowerings by applying `toPositiveDim` and `isValidDim` to the extracted integer `dim` value. Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
2023-04-07 19:49:35 +08:00
"IndexSelectNegativeDimModule_basic",
[Torch][MHLO] Decompose aten.copy op. Lower aten.rsqrt & sigmoid to mhlo. (#1734)
2022-12-22 10:13:59 +08:00
"LayerNormLastDimModule_basic",
"LayerNormModule_basic",
"LayerNormNormalizeOverAllDimsModule_basic",
Add E2E support for LeakyRelu and LeakyReluBackward ops (#1733) Co-authored-by: srirammaswamy <srirammaswamy@gmail.com>
2023-01-04 00:30:16 +08:00
"LeakyReluBackwardStaticModule_basic",
[MHLO] add conversion for aten.linalg_vector_norm (#1850)
2023-03-21 05:14:27 +08:00
"LinalgVectorNormModule_basic",
"LinalgVectorNormKeepDimModule_basic",
[MLIR][MHLO] Add AtenFrobeniusNormDimOp and add its conversion pattern to MHLO and linalg (#1306) * Add aten.frobenius_norm.dim op and init its conversion pattern to linalg and MHLO, * run symbolic-shape-optimization before hlo-legalize-to-linalg to fit more mhlo e2e tests.
2022-09-08 10:15:36 +08:00
"MatmulBroadcastBatchDim_basic",
"MatmulSingleDynamicBatchDim_basic",
"Matmul_3d",
"Matmul_4d",
fix #1626 return type mismatch (#1634)
2022-11-23 15:02:41 +08:00
"MeanDimEmptyDimModule_basic",
[MLIR][MHLO] Add AtenFrobeniusNormDimOp and add its conversion pattern to MHLO and linalg (#1306) * Add aten.frobenius_norm.dim op and init its conversion pattern to linalg and MHLO, * run symbolic-shape-optimization before hlo-legalize-to-linalg to fit more mhlo e2e tests.
2022-09-08 10:15:36 +08:00
"MeanDtypeModule_basic",
fix #1626 return type mismatch (#1634)
2022-11-23 15:02:41 +08:00
"MeanDynamicSizesModule_basic",
"MeanLargeInputModule_basic",
"MeanModule_basic",
mhlo: migrate conversion to stablehlo (#1840) This patch replaces all MHLO operations with their StableHLO counterparts and adds a validation pass to ensure that no MHLO operations remain before translating all Stablehlo operations to the MHLO dialect for further lowering to the Linalg dialect. This patch also updates all lit tests so that they refer to the `convert-torch-to-stablehlo` pass and so that they check for StableHLO operations.
2023-02-02 21:29:47 +08:00
"Mlp1LayerModule_basic",
"Mlp2LayerModule_basic",
[MLIR][MHLO] Add AtenFrobeniusNormDimOp and add its conversion pattern to MHLO and linalg (#1306) * Add aten.frobenius_norm.dim op and init its conversion pattern to linalg and MHLO, * run symbolic-shape-optimization before hlo-legalize-to-linalg to fit more mhlo e2e tests.
2022-09-08 10:15:36 +08:00
"MmTanhModule_basic",
fix mhlo e2e ci crashes (#1620) * fix mhlo e2e ci crashes * add passed tests * calc dynamic positive dim
2022-11-21 21:50:35 +08:00
"Mv_basic",
[Torch][MHLO] Decompose aten.copy op. Lower aten.rsqrt & sigmoid to mhlo. (#1734)
2022-12-22 10:13:59 +08:00
"NativeLayerNormModule4D_basic",
"NativeLayerNormModule_basic",
[Torch Dialect] support for aten.one_hot (#1852)
2023-04-11 16:02:28 +08:00
"OneHotModule_basic",
fix #1626 return type mismatch (#1634)
2022-11-23 15:02:41 +08:00
"PrimsConvertElementTypeModule_basic",
[MLIR][MHLO] Add AtenFrobeniusNormDimOp and add its conversion pattern to MHLO and linalg (#1306) * Add aten.frobenius_norm.dim op and init its conversion pattern to linalg and MHLO, * run symbolic-shape-optimization before hlo-legalize-to-linalg to fit more mhlo e2e tests.
2022-09-08 10:15:36 +08:00
"ReduceFrobeniusNormKeepDimModule_basic",
fix #1626 return type mismatch (#1634)
2022-11-23 15:02:41 +08:00
"ReduceSumDimIntListElementTypeBoolModule_basic",
"ReduceSumElementTypeBoolModule_basic",
"ReduceSumDimIntListEmptyDimModule_basic",
[MLIR][MHLO] Add AtenFrobeniusNormDimOp and add its conversion pattern to MHLO and linalg (#1306) * Add aten.frobenius_norm.dim op and init its conversion pattern to linalg and MHLO, * run symbolic-shape-optimization before hlo-legalize-to-linalg to fit more mhlo e2e tests.
2022-09-08 10:15:36 +08:00
"ReduceSumDimIntListDtypeFloatModule_basic",
"ReduceSumDimIntListDtypeIntModule_basic",
"ReduceSumDimIntListKeepDimFloatModule_basic",
"ReduceSumDimIntListKeepDimIntModule_basic",
"ReduceSumDtypeFloatModule_basic",
"ReduceSumDtypeIntModule_basic",
[MHLO] add conversion for aten.linalg_vector_norm (#1850)
2023-03-21 05:14:27 +08:00
"ReduceL1NormModule_basic",
"ReduceL1NormWithDTypeModule_basic",
"ReduceL2NormModule_basic",
"ReduceL3NormAllDimsModule_basic",
"ReduceL3NormKeepDimModule_basic",
"ReduceLN3NormModule_basic",
"NormScalarOptDimKeepDimModule_basic",
"NormScalarOptDimModule_basic",
"NormalizeModule_basic",
[MLIR][MHLO] Add AtenFrobeniusNormDimOp and add its conversion pattern to MHLO and linalg (#1306) * Add aten.frobenius_norm.dim op and init its conversion pattern to linalg and MHLO, * run symbolic-shape-optimization before hlo-legalize-to-linalg to fit more mhlo e2e tests.
2022-09-08 10:15:36 +08:00
"SelectIntModule_basic",
Fix empty tensor when select -1 (#1787)
2023-01-18 02:14:14 +08:00
"SelectIntNegativeDimAndIndexStaticModule_basic",
[MLIR][MHLO] Add AtenFrobeniusNormDimOp and add its conversion pattern to MHLO and linalg (#1306) * Add aten.frobenius_norm.dim op and init its conversion pattern to linalg and MHLO, * run symbolic-shape-optimization before hlo-legalize-to-linalg to fit more mhlo e2e tests.
2022-09-08 10:15:36 +08:00
"SliceSingleIdxModule_basic",
"SqueezeDimModule_dynamic",
"SqueezeDimModule_negDim",
[Torch][MHLO] Decompose aten.copy op. Lower aten.rsqrt & sigmoid to mhlo. (#1734)
2022-12-22 10:13:59 +08:00
"ToCopyBoolDTypeStaticModule_basic",
"ToCopyModule_basic",
"ToCopyWithDTypeFalsePinMemoryModule_basic",
"ToCopyWithDTypeModule_basic",
[MLIR][MHLO] Add AtenFrobeniusNormDimOp and add its conversion pattern to MHLO and linalg (#1306) * Add aten.frobenius_norm.dim op and init its conversion pattern to linalg and MHLO, * run symbolic-shape-optimization before hlo-legalize-to-linalg to fit more mhlo e2e tests.
2022-09-08 10:15:36 +08:00
"ReduceFrobeniusNormModule_basic",
[MHLO] Init end to end unit tests (#1223)
2022-08-23 16:47:21 +08:00
"FlattenStaticModule_basic",
"FlattenRank0Module_basic",
"TensorsConcatNegativeDimModule_basic",
[TORCH] Improve type refinement for aten.cat. (#1908) * [TORCH] Fix type refinement for aten.cat. * Add test. * Address comments. * Update. * Update. * Update. * Update. * Update. --------- Co-authored-by: Ziheng Jiang <ziheng.jiang@bytedance.com>
2023-03-10 08:17:35 +08:00
"TensorsConcatPromoteDTypeModule_basic",
Support aten.stack op and decompose it into unsqueeze & cat (#1747)
2023-03-11 09:25:25 +08:00
"TensorsStackModule_basic",
"TensorsStackNegativeDimModule_basic",
"TensorsStackPromoteDTypeModule_basic",
Replace empty_like && empty_memory_format with full/full_like (#1398) * Replace empty_like && empty_memory_format with full/full_like * fix broadcast rank0 tensor
2022-09-23 10:24:36 +08:00
"LiftFreshCopyModule_basic",
"Mlp2LayerModuleNoBias_basic",
[MHLO] Init end to end unit tests (#1223)
2022-08-23 16:47:21 +08:00
"NumelModule_basic",
mhlo: migrate conversion to stablehlo (#1840) This patch replaces all MHLO operations with their StableHLO counterparts and adds a validation pass to ensure that no MHLO operations remain before translating all Stablehlo operations to the MHLO dialect for further lowering to the Linalg dialect. This patch also updates all lit tests so that they refer to the `convert-torch-to-stablehlo` pass and so that they check for StableHLO operations.
2023-02-02 21:29:47 +08:00
"SiluModule_basic",
"SquareModule_basic",
[MHLO] Init end to end unit tests (#1223)
2022-08-23 16:47:21 +08:00
"SqueezeModule_allUnitDim",
"SqueezeDimModule_unitDim",
Implement Expand/Collapse Functionality for Aten.View (#1353)
2022-09-28 02:08:14 +08:00
"ViewCollapseOnesMiddleModule_basic",
fix mhlo e2e ci crashes (#1620) * fix mhlo e2e ci crashes * add passed tests * calc dynamic positive dim
2022-11-21 21:50:35 +08:00
"ViewDoubleMergeStaticModule_basic",
"ViewExpandDynamicDimModule_basic",
"ViewFlattenAndExpandModule_basic",
Implement Expand/Collapse Functionality for Aten.View (#1353)
2022-09-28 02:08:14 +08:00
"ViewFiveTestStaticModule_basic",
"ViewOffsetTestStaticModule_basic",
"ViewTwoFiveThreeStaticModule_basic",
"ViewTwoToThreeStaticModule_basic",
"ViewExpandOnesMiddleOppModule_basic",
"ViewOffsetBackwardTestStaticModule_basic",
[MHLO] Init end to end unit tests (#1223)
2022-08-23 16:47:21 +08:00
"NumToTensorFloatModule_basic",
"AtenToDeviceModule_basic",
"AvgPool2dStaticModule_basic",
"Conv2dWithPaddingDilationStrideStaticModule_basic",
"Convolution2DStaticModule_basic",
Update MHLO xfails.
2022-08-27 06:29:07 +08:00
"ConvolutionModule2DTransposeStridedStatic_basic",
[MHLO] Init end to end unit tests (#1223)
2022-08-23 16:47:21 +08:00
"ElementwiseCloneContiguousModule_basic",
[MLIR][TORCH] Add support for clone op with channels last memory format Fixes https://github.com/llvm/torch-mlir/issues/1829 Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2023-02-01 19:13:59 +08:00
"ElementwiseCloneChannelsLastMemoryFormatModule_basic",
[MHLO] Init end to end unit tests (#1223)
2022-08-23 16:47:21 +08:00
"ElementwiseCloneModule_basic",
"ElementwiseBinaryStaticShapeModule_basic",
"ReturnThreeTensorFloat32_basic",
"BoolTensorReturnFalseModule_basic",
"BoolTensorReturnTrueModule_basic",
"BoolTensorReturnMixedModule_basic",
"SqueezeModule_static",
"TModuleRank1_basic",
"TModuleRank0_basic",
"ElementwiseToDtypeIdentityModule_basic",
Revert "build: update llvm tag to 147fe9de" This reverts commit e45ad313d4395195ad8764623067aa2a645223d7.
2022-11-24 21:02:59 +08:00
"View1DFoldModule_basic",
"UnsafeView1DFoldModule_basic",
fix mhlo e2e ci crashes (#1620) * fix mhlo e2e ci crashes * add passed tests * calc dynamic positive dim
2022-11-21 21:50:35 +08:00
"RsubFloatModule_basic",
"RsubFloatModule_noalpha_basic",
"RsubIntModule_basic",
"RsubIntModule_noalpha_basic",
[Torch Dialect] add RSub, ScalarImplicit canonicalize (#1899) * add rsub, scalarimplit canonicalizer * reformat * address comments * fix bug * fix test * Update elementwise.py * resolve merge conflict * change to 3 * change to 3 * real fix * fix name * add torchdynamo fail test --------- Co-authored-by: zhekun.zhang <zhekun.zhang@bytedance.com>
2023-03-07 09:38:27 +08:00
"RsubInt0d_NumToTensor_Module_basic",
[StableHLO] Support for slice_scatter (#1960) Co-authored-by: zhekun.zhang <zhekun.zhang@bytedance.com>
2023-03-23 04:41:04 +08:00
"SelectScattertModule_basic",
"SelectScattertStaticModule_basic",
fix mhlo e2e ci crashes (#1620) * fix mhlo e2e ci crashes * add passed tests * calc dynamic positive dim
2022-11-21 21:50:35 +08:00
"SliceStaticModule_basic",
[MHLO] Init end to end unit tests (#1223)
2022-08-23 16:47:21 +08:00
"SliceModule_basic",
"SliceNegIdxModule_basic",
"SliceOutOfLowerBoundStartIndexModule_basic",
"SliceOutOfUpperBoundIndexModule_basic",
"SliceStartEqEndModule_basic",
"SliceSizeTwoStepModule_basic",
"SliceWholeTensorModule_basic",
[StableHLO] Support for slice_scatter (#1960) Co-authored-by: zhekun.zhang <zhekun.zhang@bytedance.com>
2023-03-23 04:41:04 +08:00
"SliceScatterModule_basic",
"SliceScatterNegativeDimModule_basic",
"SliceScatterNegativeEndModule_basic",
"SliceScatterStaticModule_basic",
"SliceScatterStepVariationModule_basic",
"SliceScatterZeroDimModule_basic",
fix mhlo e2e ci crashes (#1620) * fix mhlo e2e ci crashes * add passed tests * calc dynamic positive dim
2022-11-21 21:50:35 +08:00
"SqueezeDimModule_static",
"SqueezeDimModule_identity",
"SqueezeModule_broadcast",
[MHLO] Init end to end unit tests (#1223)
2022-08-23 16:47:21 +08:00
"ReturnTwoTensorF32I64_basic",
"Matmul4dStatic_basic",
"Matmul_dot",
"Matmul_2d",
"Matmul_matvec",
"Matmul_vecmat",
"MaxPool2dWithIndicesStaticModule_basic",
"MmDagModule_basic",
"MmModule_basic",
"MmModule_chained",
"MaxPool2dStaticModule_basic",
"PermuteModule_basic",
"PermuteNegativeIndexModule_basic",
Replace empty_like && empty_memory_format with full/full_like (#1398) * Replace empty_like && empty_memory_format with full/full_like * fix broadcast rank0 tensor
2022-09-23 10:24:36 +08:00
"ReduceSumDimIntListKeepDimNegativeDimStaticModule_basic",
"ZerosLikeModule_defaultDtype",
"ZerosLikeModule_falsePinMemory",
"ZerosLikeModule_float",
"ZerosLikeModule_int",
[MHLO] Init end to end unit tests (#1223)
2022-08-23 16:47:21 +08:00
"ZerosModuleDefaultDtype_basic",
"ZerosModuleInt2D_basic",
"ZerosModuleInt3D_basic",
"ZerosModuleFloat2D_basic",
"ZerosModuleFloat3D_basic",
"ZerosModuleFalsePinMemory_basic",
"OnesModuleDefaultDtype_basic",
"OnesModuleInt_basic",
"OnesModuleFloat_basic",
"OnesModuleFalsePinMemory_basic",
Replace empty_like && empty_memory_format with full/full_like (#1398) * Replace empty_like && empty_memory_format with full/full_like * fix broadcast rank0 tensor
2022-09-23 10:24:36 +08:00
"OnesLikeModule_defaultDtype",
"OnesLikeModule_falsePinMemory",
"OnesLikeModule_float",
"OnesLikeModule_int",
[MHLO] Init end to end unit tests (#1223)
2022-08-23 16:47:21 +08:00
"NewZerosModuleDefaultDtype_basic",
"NewZerosModuleInt2D_basic",
"NewZerosModuleInt3D_basic",
"NewZerosModuleFloat2D_basic",
"NewZerosModuleFloat3D_basic",
"NewZerosModuleFalsePinMemory_basic",
"NewOnesModuleDefaultDtype_basic",
"NewOnesModuleInt2D_basic",
"NewOnesModuleInt3D_basic",
"NewOnesModuleFloat2D_basic",
"NewOnesModuleFloat3D_basic",
"NewOnesModuleFalsePinMemory_basic",
[TOSA] Add support for AtenZerosOp 0/strided layout (#1983)
2023-03-30 22:08:20 +08:00
"NewZerosStaticModuleLayoutStrided_basic",
[MHLO] Init end to end unit tests (#1223)
2022-08-23 16:47:21 +08:00
"DropoutEvalIntModule_basic",
"DropoutEvalFloatModule_basic",
"ContiguousModule_basic",
"DropoutModule_basic",
"ViewCollapseModule_basic",
Revert "build: update llvm tag to 147fe9de" This reverts commit e45ad313d4395195ad8764623067aa2a645223d7.
2022-11-24 21:02:59 +08:00
"ViewCollapseInferredDimModule_basic",
[MHLO] Init end to end unit tests (#1223)
2022-08-23 16:47:21 +08:00
"ViewDynamicExpandCollapseModule_basic",
"ViewDynamicExpandModule_basic",
"ViewExpandModule_basic",
"ViewExpandOnesModule_basic",
"ViewExpandOnesBeforeAndAfterModule_basic",
"ViewExpandOnesMiddleModule_basic",
"ViewExpandCollapseModule_basic",
"ViewExpandCollapseWithOnesModule_basic",
Revert "build: update llvm tag to 147fe9de" This reverts commit e45ad313d4395195ad8764623067aa2a645223d7.
2022-11-24 21:02:59 +08:00
"ViewExpandInferredDimModule_basic",
[TOSA] Add aten.view shape -1 support (#1815)
2023-01-21 03:56:26 +08:00
"ViewNegativeStaticModule_basic",
[MHLO] Init end to end unit tests (#1223)
2022-08-23 16:47:21 +08:00
"ViewNoChangeStaticModule_basic",
"ViewNoChange1dModule_basic",
"ViewNoChange2dModule_basic",
"ViewNoChange3dModule_basic",
"UnsafeViewExpandModule_basic",
"ReduceMaxAllDims_basic",
"ReduceMaxFloatModule_basic",
"ReduceMaxSignedIntModule_basic",
"ReduceMaxUnsignedIntModule_basic",
"ReduceSumDimIntListFloatModule_basic",
"ReduceSumDimIntListIntModule_basic",
"ReduceSumFloatModule_basic",
"ReduceSumSignedIntModule_basic",
"ReduceSumUnsignedIntModule_basic",
"RepeatModule_basic",
"ReshapeAliasCollapseModule_basic",
"ReshapeAliasExpandModule_basic",
"ReshapeExpandModule_basic",
Add decomposition for aten.roll (#1170) * Add decomposition for aten.roll * add e2e unittest * refine type of torch.roll * fix aten::cat output type
2022-08-24 08:36:05 +08:00
"RollModule_basic",
[MHLO] Init end to end unit tests (#1223)
2022-08-23 16:47:21 +08:00
"TestMultipleTensorReturn_basic",
"AdaptiveAvgPool2dUnitOutputSizeStaticModule_basic",
"BaddbmmStaticModule_basic",
"BaddbmmBroadcast1DInputModule_basic",
"BaddbmmBroadcast2DInputModule_basic",
"NarrowHorizontalTest2_basic",
"NarrowHorizontalTest_basic",
"NarrowVerticalTest2_basic",
"NarrowVerticalTest_basic",
"NumToTensorIntModule_basic",
"NumpyTRank0Module_basic",
"NumpyTRank1Module_basic",
"NumpyTRank2Module_basic",
"NumpyTRankNStaticModule_basic",
"NumpyTRankNDynamicModule_basic",
"TModuleRank2_basic",
"TensorLiteralModule_basic",
"TensorsConcatModule_basic",
"TensorOpaqueLiteralModule_basic",
"TransposeIntModule_basic",
"TransposeIntNegDimsModule_basic",
Replace empty_like && empty_memory_format with full/full_like (#1398) * Replace empty_like && empty_memory_format with full/full_like * fix broadcast rank0 tensor
2022-09-23 10:24:36 +08:00
"ToDtypeBoolLayoutNoneModule_basic",
fix mhlo e2e ci crashes (#1620) * fix mhlo e2e ci crashes * add passed tests * calc dynamic positive dim
2022-11-21 21:50:35 +08:00
"ToDtypeBoolLayoutNoneStaticModule_basic",
Replace empty_like && empty_memory_format with full/full_like (#1398) * Replace empty_like && empty_memory_format with full/full_like * fix broadcast rank0 tensor
2022-09-23 10:24:36 +08:00
"ToDtypeLayoutNoneModule_basic",
"ToDtypeLayoutStridedModule_basic",
"TypeAsSameModule_basic",
"TypeConversionF32ToF64Module_basic",
"TypeConversionF64ToF32Module_basic",
"TypeConversionI1ToF32Module_basic",
"TypeConversionI1ToF64Module_basic",
"TypeConversionI1ToI32Module_basic",
"TypeConversionI1ToI64Module_basic",
"TypeConversionI32ToI64Module_basic",
"TypeConversionI64ToI32Module_basic",
fix mhlo e2e ci crashes (#1620) * fix mhlo e2e ci crashes * add passed tests * calc dynamic positive dim
2022-11-21 21:50:35 +08:00
"TypePromotionAlphaWiderModule_basic",
"TypePromotionSameCategoryZeroRankWider_basic",
"TypePromotionZeroRankHigherCategoryModule_basic",
[MHLO] Init end to end unit tests (#1223)
2022-08-23 16:47:21 +08:00
"OnesModuleCPUDevice_basic",
"Permute0RankModule_basic",
"UnsafeViewCollapseModule_basic",
"UnsafeViewDynamicExpandModule_basic",
[LINALG] Add lowering for aten::round op. -- Added the lowering for aten::round op. -- Added the folding for integer cases.
2022-10-11 17:52:01 +08:00
"AtenRoundIntModule_basic",
Add float16 support in the refbackend. This will require https://reviews.llvm.org/D139121 patch to go through.
2022-12-01 23:46:17 +08:00
"TestF16Return_basic",
mhlo: migrate conversion to stablehlo (#1840) This patch replaces all MHLO operations with their StableHLO counterparts and adds a validation pass to ensure that no MHLO operations remain before translating all Stablehlo operations to the MHLO dialect for further lowering to the Linalg dialect. This patch also updates all lit tests so that they refer to the `convert-torch-to-stablehlo` pass and so that they check for StableHLO operations.
2023-02-02 21:29:47 +08:00
"_LogSoftmaxModuleStable_basic",
[MLIR][TORCH] Add decomposition for prims::squeeze op This commit adds the decomposition for the prims.squeeze op. Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-11-16 13:57:58 +08:00
"PrimsSqueezeModule_basic",
"PrimsSqueezeEmptyDimensionsModule_basic",
[MLIR][TORCH] Add e2e support aten.movedim.int op Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2023-01-02 22:34:39 +08:00
"MoveDimIntModule_basic",
"MoveDimIntNegativeIndexModule_basic",
[MLIR][TORCH] Add support for non-unit stride for conv backward This commit also adds the support for non-unit output padding in the case of transposed convolution. Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-12-08 22:15:31 +08:00
"ConvolutionBackwardModule2DStatic_basic",
[StableHlo] Fix transposed convolution conversion (#2026) * fix conv bwd * fix * fix group case * clean up --------- Co-authored-by: zhekun.zhang <zhekun.zhang@bytedance.com>
2023-04-14 02:24:39 +08:00
"ConvolutionBackwardModule2DStrided_basic",
[MLIR][TORCH] Add support for prims::view_of op This op does nothing and just returns the input operand as the result of the op. Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2023-04-10 11:50:26 +08:00
"PrimsViewOfModule_basic",
"PrimsViewOfZeroRankModule_basic",
[MHLO] Init end to end unit tests (#1223)
2022-08-23 16:47:21 +08:00
}
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 10:07:03 +08:00
# Write the TOSA set as a "passing" set as it is very early in development
# and very few tests work yet.
Bump llvm-project to f1b922188ead5ca492c8d8edd47921b013a22ae0. Includes a fix to use `add_mlir_public_c_api_library` for Torch-MLIR's CAPI library, which is now required (note: upstream sample has it the right way). Disabled a TOSA test per discussion: https://github.com/llvm/torch-mlir/issues/379
2021-10-26 02:43:21 +08:00
TOSA_PASS_SET = {
[MLIR][TORCH] Add TorchToTosa lowering for aten.clone op (#1388) Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com> Co-authored-by: Suraj Sudhir <16977902+sjarus@users.noreply.github.com>
2022-09-21 06:07:46 +08:00
"ElementwiseCloneContiguousModule_basic",
[MLIR][TORCH] Add support for clone op with channels last memory format Fixes https://github.com/llvm/torch-mlir/issues/1829 Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2023-02-01 19:13:59 +08:00
"ElementwiseCloneChannelsLastMemoryFormatModule_basic",
[MLIR][TORCH] Add TorchToTosa lowering for aten.clone op (#1388) Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com> Co-authored-by: Suraj Sudhir <16977902+sjarus@users.noreply.github.com>
2022-09-21 06:07:46 +08:00
"ElementwiseCloneModule_basic",
Rename `tosa-to-linalg-on-tensors` to `tosa-to-linalg` The pass name changed upstream.
2021-10-26 04:43:54 +08:00
"ElementwiseUnaryModule_basic",
Update external llvm to 966b72098363d44adf2882b9c34 The external llvm is updated to point to https://reviews.llvm.org/rG966b72098363d44adf2882b9c34fcdbe344ff913. Some of the changes wrt. NamedAttr has been addressed. Signed-off-by: Prashant Kumar <prashant@nod-labs.com>
2021-12-04 15:31:38 +08:00
"ElementwiseBinaryModule_basic",
[tosa] Add Torch.sigmoid fp32 to TOSA (#386) * [tosa] Add Torch.sigmoid fp32 to TOSA Signed-off-by: Suraj Sudhir <suraj.sudhir@arm.com>
2021-10-29 01:09:12 +08:00
"ElementwiseSigmoidModule_basic",
Add non-default dtype support for a few elementwise math ops. (#687) * fix type inference * fix Torch2Linalg conversion * add test cases
2022-03-24 04:35:43 +08:00
"ElementwiseExpModule_basic",
build: update llvm tag to 00d648bd (#1307) - Update MHLO commit to build with LLVM commit hash 00d648bd - Update TorchToMhlo code to work with Stablehlo - Re-enabled two failing TOSA tests, thus resolving Github Issue #1231
2022-08-31 03:44:00 +08:00
"ElementwiseReluModule_basic",
[TOSA] Add LeakyReLU conversion pass (#1790) * feat(TorchToTOSA): LeakyReLU legalization * test(LeakyReLU): Add LIT test and enable e2e test Co-authored-by: Philipp Braun <philipp.braun@amd.com>
2023-01-11 13:42:07 +08:00
"ElementwiseLeakyReluModule_basic",
[tosa] Add structure for eltwise ops Add a bunch of op legalizations. Signed-off-by: Suraj Sudhir <suraj.sudhir@arm.com>
2021-11-11 11:03:36 +08:00
"ElementwiseFloorModule_basic",
"ElementwiseLogModule_basic",
Make broadcasting result shape more static This involes the following 2 parts: - Change refine type to propagate more static shape info. - Get as much static shape info as possible when creating the result tensor when converting to linalg.
2021-12-29 10:11:07 +08:00
"ElementwiseBinaryStaticShapeModule_basic",
Add aten.hardtanh e2e support.
2022-02-09 04:57:23 +08:00
"ElementwiseMinimumModule_basic",
"ElementwiseMinimumIntModule_basic",
"ElementwiseMaximumModule_basic",
"ElementwiseMaximumIntModule_basic",
Implement Expand/Collapse Functionality for Aten.View (#1353)
2022-09-28 02:08:14 +08:00
"ViewDoubleMergeStaticModule_basic",
"ViewCollapseOnesMiddleModule_basic",
"ViewFiveTestStaticModule_basic",
"ViewOffsetTestStaticModule_basic",
"ViewTwoFiveThreeStaticModule_basic",
"ViewTwoToThreeStaticModule_basic",
"ViewExpandOnesMiddleOppModule_basic",
"ViewOffsetBackwardTestStaticModule_basic",
[mlir][tosa] Refactor conversions to use templates (#416) - Remove use of conversion construction macros - Add mul and div op conversions - Add corresponding tests Signed-off-by: Suraj Sudhir <suraj.sudhir@arm.com>
2021-11-12 08:15:58 +08:00
"TanhBackward_basic",
Add HardtanhBackward TOSA and LINALG support (#1721)
2023-03-07 02:16:37 +08:00
"HardtanhBackward_basic",
[tosa] Add TosaMakeBroadcastable pass to torch-to-tosa pipeline. Fixes broken e2e test ElementwiseAddModule_basic Signed-off-by: Suraj Sudhir <suraj.sudhir@arm.com>
2021-11-24 14:25:59 +08:00
"ElementwiseAddModule_basic",
Add support for multiple return values This change is to unblock the work of some backprop ops returning more than one tensors. We will need to think of a more scalable approach in the future if more flexible return types combinations are needed.
2021-11-08 23:56:40 +08:00
"ReturnThreeTensorFloat32_basic",
lowered addcmul and addcdiv to linalg
2021-11-25 06:01:48 +08:00
"AddCMulModule_basic",
"AddCDivModule_basic",
Fix forward XPASS
2021-12-01 05:48:10 +08:00
"SqueezeModule_broadcast",
Add support for passing & returning memref of bool types Support for passing memref of bool types as a function argument and return is added in ref-backend. Signed-off-by: Prashant Kumar <prashant@nod-labs.com>
2021-12-08 22:05:02 +08:00
"BoolTensorReturnFalseModule_basic",
"BoolTensorReturnTrueModule_basic",
"BoolTensorReturnMixedModule_basic",
Fixes https://github.com/llvm/torch-mlir/issues/751 where `torch.bool` is parsed as signless `i1`. (#752)
2022-04-14 01:28:27 +08:00
"BoolTensorHandleSignless_basic",
* [tosa] Support for Rsqrt legalization (#480) Signed-off-by: Anup Gangwar <anup.gangwar@arm.com> Co-authored-by: Anup Gangwar <anup.gangwar@arm.com>
2021-12-15 02:03:58 +08:00
"ElementwiseRsqrtModule_basic",
Fix empty tensor when select -1 (#1787)
2023-01-18 02:14:14 +08:00
"SelectIntNegativeDimAndIndexStaticModule_basic",
[tosa] Support for Torch.squeeze (#487)
2021-12-16 13:40:29 +08:00
"SqueezeModule_static",
"SqueezeModule_noUnitDim",
"SqueezeModule_allUnitDim",
Added aten::t() Op
2021-12-17 12:08:07 +08:00
"TModuleRank1_basic",
"TModuleRank0_basic",
[TORCH][MLIR] Fold trivial cases of `aten.to.dtype` and `aten.view` op - It folds `aten.to.dtype` when the input tensor type and result type are exactly same. - It folds `aten.view` when the rank of both the input tensor type and result type is unity. Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2021-12-23 20:04:29 +08:00
"ElementwiseToDtypeIdentityModule_basic",
Add lowering for aten.to.device (#1107)
2022-08-11 07:24:02 +08:00
"AtenToDeviceModule_basic",
Revert "build: update llvm tag to 147fe9de" This reverts commit e45ad313d4395195ad8764623067aa2a645223d7.
2022-11-24 21:02:59 +08:00
"View1DFoldModule_basic",
"UnsafeView1DFoldModule_basic",
[tosa] Implement squeeze.dim support (#511) Templated variants for squeeze and squeeze.dim
2022-01-07 00:31:29 +08:00
"SqueezeDimModule_static",
"SqueezeDimModule_identity",
"SqueezeDimModule_unitDim",
Add support for two return values This commit adds support for two return values of type memref f32 and i64. Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-01-10 21:24:08 +08:00
"ReturnTwoTensorF32I64_basic",
[tosa] Add tosa-to-standard before tosa-to-linalg pass (#524) Signed-off-by: Suraj Sudhir <suraj.sudhir@arm.com>
2022-01-15 03:05:11 +08:00
"ElementwisePowModule_basic",
[tosa] Enable tosa-to-linalg-named so Matmul works again (#530) Signed-off-by: Suraj Sudhir <suraj.sudhir@arm.com>
2022-01-20 04:10:04 +08:00
"BmmModule_basic",
Add static type information support to `aten.mm` (#602) This commit adds static type information support to `aten.mm`. This is needed for the forward pass of Bert training.
2022-02-19 01:56:48 +08:00
"MmDagModule_basic",
[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>
2022-06-16 23:45:10 +08:00
"Matmul4dStatic_basic",
[tosa] Enable tosa-to-linalg-named so Matmul works again (#530) Signed-off-by: Suraj Sudhir <suraj.sudhir@arm.com>
2022-01-20 04:10:04 +08:00
"Matmul_dot",
"Matmul_3d",
[MLIR][TORCH] Add integer dtype support for aten.rsub.Scalar op Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-06-14 20:31:30 +08:00
"RsubFloatModule_basic",
"RsubFloatModule_noalpha_basic",
[Torch Dialect] add RSub, ScalarImplicit canonicalize (#1899) * add rsub, scalarimplit canonicalizer * reformat * address comments * fix bug * fix test * Update elementwise.py * resolve merge conflict * change to 3 * change to 3 * real fix * fix name * add torchdynamo fail test --------- Co-authored-by: zhekun.zhang <zhekun.zhang@bytedance.com>
2023-03-07 09:38:27 +08:00
"RsubInt0d_NumToTensor_Module_basic",
[LINALG][TOSA][MHLO] Add e2e support for aten bitwise ops (#1753)
2023-01-12 06:40:03 +08:00
"ElementwiseBitwiseAndModule_basic",
"ElementwiseBitwiseAndStaticShapeModule_basic",
"ElementwiseBitwiseNotInt32Module_basic",
"ElementwiseBitwiseNotInt64Module_basic",
"ElementwiseBitwiseOrModule_basic",
"ElementwiseBitwiseOrStaticShapeModule_basic",
"ElementwiseBitwiseXorModule_basic",
"ElementwiseBitwiseXorStaticShapeModule_basic",
* [tosa] Support for AtenRsubScalarOp for scalar constants (#531) * [tosa] Support for AtenCeilOp and AtenReciprocalOp * [tosa] Support for comparator ops, Aten[Gt|Lt|Eq][Tensor|Scalar]Op with scalar constant * [tosa] Support for Scalar variants of Aten[Mul|Div|Add|Sub] Ops with scalar constants Signed-off-by: Anup Gangwar <anup.gangwar@arm.com> Co-authored-by: Anup Gangwar <anup.gangwar@arm.com>
2022-01-21 02:58:30 +08:00
"ElementwiseGtFloatScalarModule_basic",
"ElementwiseGtIntScalarModule_basic",
"ElementwiseGtMixed2ScalarModule_basic",
"ElementwiseGtFloatTensorModule_basic",
"ElementwiseGtIntTensorModule_basic",
"ElementwiseLtFloatScalarModule_basic",
"ElementwiseLtIntScalarModule_basic",
"ElementwiseLtDiffWidthScalarModule_basic",
"ElementwiseLtFloatTensorModule_basic",
"ElementwiseLtIntTensorModule_basic",
"ElementwiseEqFloatScalarModule_basic",
"ElementwiseEqIntScalarModule_basic",
"ElementwiseEqDiffWidthScalarModule_basic",
"ElementwiseEqFloatTensorModule_basic",
"ElementwiseEqIntTensorModule_basic",
"ElementwiseMulScalarModule_int",
"ElementwiseMulScalarModule_float",
"ElementwiseMulTensorIntModule_basic",
"ElementwiseDivScalarModule_basic",
"ElementwiseSubScalarFloatModule_basic",
"ElementwiseAddScalarFloatModule_basic",
Fix handling of non-int tensors in `getScalarValue` (#1914) The current implementation of `getScalarValue` does not check that the input to a `ValueTensorLiteralOp` is an i64 before extracting the value, and it does not check that the result type of the `PrimNumToTensorScalarOp` is also an i64. This leads to crashes or invalid IR generated when the `input` is something other than an i64 tensor or `!torch.int`. This commit addresses those issues. In addition, the function `getScalarValue` is renamed to `getScalarIntValue` to make it clear that it *only* extracts scalar integers.
2023-03-07 02:12:58 +08:00
"ElementwiseAddScalar_TensorLiteralInt32_Module_basic",
* [tosa] Support for AtenRsubScalarOp for scalar constants (#531) * [tosa] Support for AtenCeilOp and AtenReciprocalOp * [tosa] Support for comparator ops, Aten[Gt|Lt|Eq][Tensor|Scalar]Op with scalar constant * [tosa] Support for Scalar variants of Aten[Mul|Div|Add|Sub] Ops with scalar constants Signed-off-by: Anup Gangwar <anup.gangwar@arm.com> Co-authored-by: Anup Gangwar <anup.gangwar@arm.com>
2022-01-21 02:58:30 +08:00
"ElementwiseMulScalarModule_float",
"ElementwiseCeilModule_basic",
"ElementwiseReciprocalModule_basic",
"TypePromotionAlphaWiderModule_basic",
[tosa] Implement conv2d support (#541) Signed-off-by: Suraj Sudhir <suraj.sudhir@arm.com>
2022-01-27 11:16:13 +08:00
"Conv2dWithPaddingDilationStrideStaticModule_basic",
Revert "[LINALG] Decompose `aten.batch_norm` into `aten.native_batch_norm`" This reverts commit 442ff4605c54f836afa17d2780bd9bddcc2a5ed8.
2022-02-25 03:41:55 +08:00
"BatchNorm1DModule_basic",
Fix typo in `inputRank` check of `AtenBatchNormOp` (#1046) The original conversion pattern for `AtenBatchNormOp` required that the input rank be greater than 2; however, the only expectation in the conversion pattern and in Pytorch is that the input rank is greater than 1, since the second dimension of the input must match the size of the `weight`, `bias`, `runningMean`, and `runningVar` inputs. This commit fixes the `inputRank` check.
2022-07-16 00:35:59 +08:00
"BatchNorm1DWith2DInputModule_basic",
Revert "[LINALG] Decompose `aten.batch_norm` into `aten.native_batch_norm`" This reverts commit 442ff4605c54f836afa17d2780bd9bddcc2a5ed8.
2022-02-25 03:41:55 +08:00
"BatchNorm2DModule_basic",
"BatchNorm3DModule_basic",
* [tosa] Support for AtenFlattenUsingIntsOp (#548)
2022-01-29 13:38:56 +08:00
"FlattenStaticModule_basic",
"FlattenRank0Module_basic",
"ElementwiseFlattenBroadcastModule_basic",
[TORCH] Add aten.std e2e support
2022-01-30 01:10:50 +08:00
"SquareModule_basic",
[tosa] Add maxpool2d and adaptive_avgpool2d support (#550) Signed-off-by: Suraj Sudhir <suraj.sudhir@arm.com>
2022-02-01 05:34:09 +08:00
"MaxPool2dStaticModule_basic",
Max pool2d ceil mode to tosa (#1957) * implemented ceil_mode== true support for lowering aten.max_pool2d to tosa * add e2e test for lowering aten.max_pool2d to tosa with ceil_mode=true --------- Co-authored-by: Lisa Liu <lingl@xilinx.com>
2023-03-22 01:17:39 +08:00
"MaxPool2dStaticCeilModeTrueModule_basic",
build: update llvm tag to 00d648bd (#1307) - Update MHLO commit to build with LLVM commit hash 00d648bd - Update TorchToMhlo code to work with Stablehlo - Re-enabled two failing TOSA tests, thus resolving Github Issue #1231
2022-08-31 03:44:00 +08:00
"ResNet18StaticModule_basic",
[MLIR][TORCH] Add e2e support for `aten.amax` op -- This commit adds e2e support for `atend.amax` op. Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
2022-11-23 02:37:28 +08:00
"ReduceAmaxKeepDim_basic",
* [tosa] Support for AtenNativeLayerNormOp * [tosa] Support for AtenPermuteOp Signed-off-by: Anup Gangwar <anup.gangwar@arm.com>
2022-02-04 06:08:19 +08:00
"NativeLayerNormModule4D_basic",
"LayerNormNormalizeOverAllDimsModule_basic",
"PermuteModule_basic",
"PermuteNegativeIndexModule_basic",
[tosa] Support for some ops and fix for Issue #532 (#575) * [tosa] Support for AtenNe[Tensor|Scalar]Op, AtenLog2Op, AtenBitwiseAndTensorOp, AtenSquareOp and AtenThresholdOp * Fix for Issue #532 - Mixed input types for few ops and updated few tests to use i32 instead of i64 Signed-off-by: Anup Gangwar <anup.gangwar@arm.com> Co-authored-by: Anup Gangwar <anup.gangwar@arm.com>
2022-02-12 04:30:02 +08:00
"ElementwiseLog2Module_basic",
"Threshold1dIntI32Module_basic",
"Threshold1dFloatModule_basic",
"Threshold2dFloatModule_basic",
"Threshold3dFloatModule_basic",
"ElementwiseSubScalarIntModule_basic",
"ElementwiseAddScalarIntModule_basic",
"ElementwiseMulScalarModule_basic",
[tosa] Support for Aten[Zeros|Ones|Fill_Scalar] ops (#604) Signed-off-by: Anup Gangwar <anup.gangwar@arm.com> Co-authored-by: Anup Gangwar <anup.gangwar@arm.com>
2022-02-17 01:53:51 +08:00
"ZerosModuleDefaultDtype_basic",
"ZerosModuleInt2D_basic",
"ZerosModuleInt3D_basic",
"ZerosModuleFloat2D_basic",
"ZerosModuleFloat3D_basic",
"ZerosModuleFalsePinMemory_basic",
"OnesModuleDefaultDtype_basic",
"OnesModuleInt_basic",
"OnesModuleFloat_basic",
"OnesModuleFalsePinMemory_basic",
[MLIR][TORCH] Add torch.Device type to backend contract scalar types Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-08-19 14:53:21 +08:00
"OnesModuleCPUDevice_basic",
[MLIR][TORCH] Add E2E support for aten.new_zeros, aten.new_ones op This commit adds lowering of `aten.new_zeros` and `aten.new_ones` op Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-02-28 14:14:40 +08:00
"NewZerosModuleDefaultDtype_basic",
"NewZerosModuleInt2D_basic",
"NewZerosModuleInt3D_basic",
"NewZerosModuleFloat2D_basic",
"NewZerosModuleFloat3D_basic",
"NewZerosModuleFalsePinMemory_basic",
"NewOnesModuleDefaultDtype_basic",
"NewOnesModuleInt2D_basic",
"NewOnesModuleInt3D_basic",
"NewOnesModuleFloat2D_basic",
"NewOnesModuleFloat3D_basic",
"NewOnesModuleFalsePinMemory_basic",
Decompose aten.silu op Decomposition of aten.silu.op is added as silu(x) = x * sigmoid(x).
2022-03-02 01:30:58 +08:00
"SiluModule_basic",
[LINALG] Add decomposition of `aten.dropout` op - This commit adds decomposition of `aten.dropout` op. It also covers the training mode of the same op. - It also adds lowering of `aten.sub.float` op. Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2022-02-17 00:34:03 +08:00
"DropoutEvalIntModule_basic",
"DropoutEvalFloatModule_basic",
[tosa] Support for Aten[Unsqueeze|Contiguous|Dropout|Reshape|View] ops (#700)
2022-03-26 05:15:07 +08:00
"ContiguousModule_basic",
"DropoutModule_basic",
"ViewExpandModule_basic",
[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`.
2022-06-23 06:58:40 +08:00
"ViewExpandOnesModule_basic",
[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.
2022-07-01 07:39:25 +08:00
"ViewExpandOnesBeforeAndAfterModule_basic",
"ViewExpandOnesMiddleModule_basic",
Allow expanding and collapsing in aten::view (#1082) - Supports cases where the view op expands and collapses dims simulataneously. This does not handle the case where it is neither expanding nor collapsing (e.g. [2, 3] -> [3, 2]) - Additionally fixes a previous bug with adding 1-sized dims on both sides of a tensor with aten.view
2022-07-21 05:35:51 +08:00
"ViewExpandCollapseModule_basic",
"ViewExpandCollapseWithOnesModule_basic",
Revert "build: update llvm tag to 147fe9de" This reverts commit e45ad313d4395195ad8764623067aa2a645223d7.
2022-11-24 21:02:59 +08:00
"ViewCollapseInferredDimModule_basic",
"ViewExpandInferredDimModule_basic",
[TOSA] Add aten.view shape -1 support (#1815)
2023-01-21 03:56:26 +08:00
"ViewNegativeStaticModule_basic",
[tosa] Support for Aten[Unsqueeze|Contiguous|Dropout|Reshape|View] ops (#700)
2022-03-26 05:15:07 +08:00
"ViewNoChangeStaticModule_basic",
"UnsafeViewExpandModule_basic",
"ReshapeCollapseModule_basic",
tosa] Support for Aten[Gelu|GeluBackward] ops (#720) Signed-off-by: Anup Gangwar <anup.gangwar@arm.com> Co-authored-by: Anup Gangwar <anup.gangwar@arm.com>
2022-03-31 08:00:55 +08:00
"ElementwiseGeluModule_basic",
"GeluBackwardModule_basic",
[LINALG] Add the lowering of `aten.ne.Scalar` op The lowering of `aten.ne.Scalar` op has been added to the linalg backend.
2022-04-04 00:19:01 +08:00
"ElementwiseNeIntScalarModule_basic",
"ElementwiseNeFloatTensorModule_basic",
Add lowering for _convolution
2022-07-08 14:44:03 +08:00
"Convolution2DStaticModule_basic",
test: add end-to-end test for aten.neg (#760)
2022-04-16 03:37:57 +08:00
"ElementwiseNegModule_basic",
[REFBACKEND] Add support for returning multiple different return types. Added the dynamic registration of return function to the execution engine. This makes sure that different/multiple return types are supported. Also, updated the .style.yapf indentation to 4.
2022-04-19 21:47:47 +08:00
"TestMultipleTensorReturn_basic",
Fold away type_as (#1358)
2022-09-13 06:59:12 +08:00
"TypeAsSameModule_basic",
[tosa] Support for AtenAvgPool2d op Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-05-19 20:35:59 +08:00
"AdaptiveAvgPool2dUnitOutputSizeStaticModule_basic",
[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>
2022-05-30 16:08:54 +08:00
"BaddbmmDynamicModule_basic",
"BaddbmmStaticModule_basic",
"BaddbmmWithAlphaBetaModule_basic",
"BaddbmmWithAlphaModule_basic",
"BaddbmmWithBetaModule_basic",
"BaddbmmBroadcast1DInputModule_basic",
"BaddbmmBroadcast2DInputModule_basic",
[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>
2022-06-03 20:38:59 +08:00
"NumpyTRank1Module_basic",
"NumpyTRank2Module_basic",
"NumpyTRankNStaticModule_basic",
"NumpyTRankNDynamicModule_basic",
[tosa] aten.embedding op support (#991) Enables BERT legalization. Signed-off-by: Suraj Sudhir <suraj.sudhir@arm.com>
2022-07-01 04:13:52 +08:00
"EmbeddingModuleI32Static_basic",
[tosa] aten.transpose.int support (#1017) Signed-off-by: Suraj Sudhir <suraj.sudhir@arm.com>
2022-07-08 04:05:33 +08:00
"TModuleRank2_basic",
"TransposeIntModule_basic",
"TransposeIntNegDimsModule_basic",
[tosa] aten.max.dim , aten.slice.tensor ops (#1027) Signed-off-by: Suraj Sudhir <suraj.sudhir@arm.com>
2022-07-14 01:10:18 +08:00
"ArgmaxModule_keepDim",
"ArgmaxModule_with_dim",
E2E support for AtenRemainderScalarOp (#1200)
2022-08-11 08:02:06 +08:00
"_LogSoftmaxModuleStable_basic",
[MLIR][TORCH] Add TorchToTosa lowering for aten.where.self op (#1454)
2022-10-19 00:39:39 +08:00
"ElementwiseAtenWhereSelfModule_basic",
[MLIR][TORCH] Fix aten.unsqueeze op (#1578) The range of the unsqueeze dim is: [-input.dim() - 1, input.dim() + 1), the bug forgets to add 1.
2022-11-15 01:09:15 +08:00
"ElementwiseUnsqueezeBroadcastModule_basic",
[MHLO] Support AtenMaskedFillScalar (#1839) * [MHLO] Support MaskedFillScalar. * Update. * Update. * Update. --------- Co-authored-by: Ziheng Jiang <ziheng.jiang@bytedance.com>
2023-02-11 05:58:39 +08:00
"MaskedFillScalarIntValueModule_basic",
[TOSA] Add aten.masked_fill.Tensor/Scalar support (#1735)
2022-12-22 00:56:07 +08:00
"MaskedFillScalarIntValueStaticModule_basic",
"MaskedFillTensorIntValueStaticModule_basic",
[TOSA] Add aten.add/sub.Scalar/Tensor si64 type support (#1604)
2022-12-13 04:13:07 +08:00
"ElementwiseAddScalarInt64Module_basic",
"TensorLiteralModule_basic",
[TOSA] Add support for AtenZerosOp 0/strided layout (#1983)
2023-03-30 22:08:20 +08:00
"NewZerosStaticModuleLayoutStrided_basic",
[TOSA] Add aten.add/sub.Scalar/Tensor si64 type support (#1604)
2022-12-13 04:13:07 +08:00
"TensorOpaqueLiteralModule_basic",
"TypePromotionDifferentCategoryModule_basic",
"TypePromotionSameCategoryDifferentWidthModule_basic",
build: update llvm tag to 5e111eb275 - Update llvm tag to 5e111eb275eee3bec1123b4b85606328017e5ee5 - mhlo now points to a99159c45ee5c497f8dce01eff807a6d57629b61 Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2023-02-23 20:56:43 +08:00
"TypePromotionSameCategoryZeroRankWider_basic",
[TOSA] Add aten.add/sub.Scalar/Tensor si64 type support (#1604)
2022-12-13 04:13:07 +08:00
"TypePromotionZeroRankHigherCategoryModule_basic",
[TOSA] Add aten.gather support for tosa (#1680)
2022-12-22 03:04:07 +08:00
"GatherStaticModule_basic",
[TOSA] Add aten.Index.Tensor support (#1771)
2023-01-20 13:19:00 +08:00
"IndexTensorStaticModule_basic",
[TOSA] aten.index.tensor multiple indexes support (#1868)
2023-02-14 15:07:15 +08:00
"IndexTensorMultiIndexStaticModule_basic",
[MLIR][TORCH] Add TorchToTosa lowering for aten.clone op (#1388) Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com> Co-authored-by: Suraj Sudhir <16977902+sjarus@users.noreply.github.com>
2022-09-21 06:07:46 +08:00
"LiftFreshCopyModule_basic",
[MLIR][TORCH] Add a test for sum.dim_IntList op working for tosa (#1387) Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com> Co-authored-by: Suraj Sudhir <16977902+sjarus@users.noreply.github.com>
2022-09-21 02:38:09 +08:00
"ReduceSumDimIntListKeepDimNegativeDimStaticModule_basic",
build: update llvm tag to 4546397e (#1502) This commit makes the following changes needed to update bump LLVM: - Replace `linalg.init_tensor` with `tensor.empty` (see: https://reviews.llvm.org/D135129) - Replace `NoSideEffect` with `Pure` (see https://reviews.llvm.org/D135505) - Replace `body` region accessor for `ReduceOp` and `ReduceWindowOp` with `getBody` - Fix incorrect use of `tosa::ReduceSumOp` in `AtenNativeLayerNormOp` conversion pattern. The result type of `tosa::ReduceSumOp` must have the same rank as the input type. (see: https://www.mlplatform.org/tosa/tosa_spec.html#_reduce_sum) Co-authored-by: Ashay Rane <ashay@users.noreply.github.com> Co-authored-by: Ashay Rane <ashay@users.noreply.github.com>
2022-10-18 12:22:53 +08:00
"ReduceSumDimIntListFloatModule_basic",
"ReduceSumDimIntListIntModule_basic",
"ReduceSumDimIntListKeepDimFloatModule_basic",
"ReduceSumDimIntListKeepDimIntModule_basic",
"ReduceSumFloatModule_basic",
"ReduceSumSignedIntModule_basic",
"ReduceSumUnsignedIntModule_basic",
[tosa] Add support for some cases of aten.broadcast_to op (#1429) This commit adds support for TorchToTosa lowering of `aten.broadcast_to` op for cases: 1.) When the rank of input and output tensor is equal. 2.) When the rank of input tensor is zero. Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-09-30 00:40:56 +08:00
"BroadcastToSameRankStaticModule_basic",
"BroadcastZeroRankInputStaticModule_basic",
[tosa] Add "-tosa-to-tensor" pass in the lowering pipeline Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-09-23 16:23:09 +08:00
"SliceStaticModule_basic",
[tosa] Add TorchToTosa lowering for aten.arange.start_step op (#1442)
2022-09-30 22:33:41 +08:00
"ArangeStartStepIntModule_basic",
"ArangeDtypeFloatModule_basic",
"ArangeIntModule_basic",
"ArangeNegativeStartIntModule_basic",
"ArangeStartIntModule_basic",
"ArangeStartNegativeStepIntModule_basic",
"ArangeZeroElementOutputModule_basic",
[tosa] Add TorchToTosa lowering for torch.prim.NumToTensor.Scalar op Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-10-04 22:00:16 +08:00
"NumToTensorIntModule_basic",
[tosa] Add lowering for aten.to.dtype and aten._to_copy op This commit adds the TorchToTosa lowering for `aten.to.dtype` and `aten._to_copy` op. Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-10-04 21:05:59 +08:00
"ToDtypeBoolLayoutNoneStaticModule_basic",
"ToCopyBoolDTypeStaticModule_basic",
"HardTanhIntModule_basic",
[MLIR][TORCH] Add E2E support for aten.mse_loss op This commit adds decomposition for the `aten.mse_loss` op. Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-10-20 19:02:09 +08:00
"AtenRoundIntModule_basic",
"MseLossNoReductionModule_basic",
[MLIR][TORCH] Add E2E support for aten.addcmul_ and aten.addcdiv_ op Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-10-26 20:41:52 +08:00
"AddCMul_Module_basic",
"AddCDiv_Module_basic",
Add float16 support in the refbackend. This will require https://reviews.llvm.org/D139121 patch to go through.
2022-12-01 23:46:17 +08:00
"TestF16Return_basic",
Add E2E support for LeakyRelu and LeakyReluBackward ops (#1733) Co-authored-by: srirammaswamy <srirammaswamy@gmail.com>
2023-01-04 00:30:16 +08:00
"ElementwiseLeakyReluModule_basic",
"ElementwiseLeakyReluStaticModule_basic",
"LeakyReluBackwardModule_basic",
"LeakyReluBackwardStaticModule_basic",
"ElementwiseRelu6Module_basic",
"HardTanhModule_basic",
"HardsigmoidModule_basic",
"HardsigmoidRandomModule_basic",
"HardswishModule_basic",
"HardswishRandomModule_basic",
[TOSA] Add aten.le.tensor support (#2033)
2023-04-14 23:43:14 +08:00
"BucketizeTensorStaticFloatModule_basic",
"BucketizeTensorStaticModule_basic",
"ElementwiseLeFloatTensorModule_basic",
"ElementwiseLeIntTensorModule_basic",
[TOSA] Fix broadcast_to input and output different shape support (#1855)
2023-02-10 01:15:14 +08:00
"FullLikeModuleInt2DStatic_basic",
"FullModuleInt3D_basic",
"FullModuleFloat2D_basic",
[TOSA] Add aten.abs support (#2032)
2023-04-14 23:43:39 +08:00
"ElementwiseAbsModule_basic",
Constant pad nd to tosa (#1933) * implemented lowering torch.aten.constant_pad_nd to tosa * add constant_pad_nd e2e tests to TOSA_PASS_SET * add PadModule_basic & PadWithNoneValModule_basic to TOSA_PASS_SET --------- Co-authored-by: Lisa Liu <lingl@xilinx.com>
2023-03-15 23:42:15 +08:00
"RepeatModule_basic",
"ConstantPad2dStaticModule_basic",
"ConstantPadNdModule_basic",
"ConstantPadNdPartialStaticModule_basic",
"ConstantPadNdStaticModule_basic",
"PadModule_basic",
Add support for aten_remainder in TorchToTosa (#1966)
2023-03-24 08:55:58 +08:00
"PadWithNoneValModule_basic",
"ElementwiseRemainderScalarModule_Float_basic",
"ElementwiseRemainderScalarModule_Int_Float_basic",
[MLIR][TORCH] Add decomposition for prims::squeeze op This commit adds the decomposition for the prims.squeeze op. Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-11-16 13:57:58 +08:00
"ElementwiseRemainderScalarModule_Int_basic",
"PrimsSqueezeEmptyDimensionsModule_basic",
[MLIR][TORCH] Add e2e support aten.movedim.int op Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2023-01-02 22:34:39 +08:00
"MoveDimIntModule_basic",
"MoveDimIntNegativeIndexModule_basic",
[MLIR][TORCH] Add support for non-unit stride for conv backward This commit also adds the support for non-unit output padding in the case of transposed convolution. Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-12-08 22:15:31 +08:00
"ElementwiseRemainderScalarModule_Int_basic",
"MoveDimIntModule_basic",
[MLIR][TORCH] Add support for prims::view_of op This op does nothing and just returns the input operand as the result of the op. Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2023-04-10 11:50:26 +08:00
"PrimsViewOfModule_basic",
"PrimsViewOfZeroRankModule_basic",
Bump llvm-project to f1b922188ead5ca492c8d8edd47921b013a22ae0. Includes a fix to use `add_mlir_public_c_api_library` for Torch-MLIR's CAPI library, which is now required (note: upstream sample has it the right way). Disabled a TOSA test per discussion: https://github.com/llvm/torch-mlir/issues/379
2021-10-26 02:43:21 +08:00
}
Added e2e LTC tests (#916) * Added e2e LTC Torch MLIR tests * Fix seed for reproducability * Check if computation is None before getting debug string * Updated unit tests, and added numeric tests * Print name of the model layer that fails numeric validation * Run LTC e2e test with CI/CD * Set seed in main function, instead of beginning of execution * Add comment to specify number of digits of precision * Fixed typo * Remove tests for LTC example models * Added LTC option to torchscript e2e * Implement compile and run for LTC e2e test * xfail all tests that use ops that aren't currently supported
2022-06-10 03:56:01 +08:00
LTC_XFAIL_SET = {
Blacklist _convolution op (#1048) * Blacklist _convolution op in LTC * Removed duplicate Torch_AtenSelectScatterOp instance from autogen .td * Removed duplicate Torch_AtenSliceScatterOp instance from autogen .td
2022-07-14 01:28:05 +08:00
"_Convolution2DAllFalseModule_basic",
"_Convolution2DBenchmarkModule_basic",
"_Convolution2DCudnnModule_basic",
"_Convolution2DDeterministicModule_basic",
"_Convolution2DTF32Module_basic",
[MLIR][TORCH] Fix CI failure due to failing tests Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-08-22 13:44:44 +08:00
"_ConvolutionDeprecated2DAllFalseModule_basic",
"_ConvolutionDeprecated2DBenchmarkModule_basic",
Fix as_strided/slice symint (#1401) * Fix as_strided symint * Re-enable LTC tests * Re-enable LTC * Add hardtanh shape inference function * Fix slice symint
2022-09-27 00:16:49 +08:00
"_ConvolutionDeprecated2DCudnnModule_basic",
[MLIR][TORCH] Fix CI failure due to failing tests Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-08-22 13:44:44 +08:00
"_ConvolutionDeprecated2DDeterministicModule_basic",
Added e2e LTC tests (#916) * Added e2e LTC Torch MLIR tests * Fix seed for reproducability * Check if computation is None before getting debug string * Updated unit tests, and added numeric tests * Print name of the model layer that fails numeric validation * Run LTC e2e test with CI/CD * Set seed in main function, instead of beginning of execution * Add comment to specify number of digits of precision * Fixed typo * Remove tests for LTC example models * Added LTC option to torchscript e2e * Implement compile and run for LTC e2e test * xfail all tests that use ops that aren't currently supported
2022-06-10 03:56:01 +08:00
"AdaptiveAvgPool2dNonUnitOutputSizeDynamicModule_basic",
"AdaptiveAvgPool2dNonUnitOutputSizeStaticModule_basic",
"AddIntModule_basic",
Fix empty tensor when select -1 (#1787)
2023-01-18 02:14:14 +08:00
"AtenIntBoolOpModule_basic",
Added e2e LTC tests (#916) * Added e2e LTC Torch MLIR tests * Fix seed for reproducability * Check if computation is None before getting debug string * Updated unit tests, and added numeric tests * Print name of the model layer that fails numeric validation * Run LTC e2e test with CI/CD * Set seed in main function, instead of beginning of execution * Add comment to specify number of digits of precision * Fixed typo * Remove tests for LTC example models * Added LTC option to torchscript e2e * Implement compile and run for LTC e2e test * xfail all tests that use ops that aren't currently supported
2022-06-10 03:56:01 +08:00
"BernoulliTensorModule_basic",
"BincountMinlengthModule_basic",
"BincountModule_basic",
"BincountStaticSizeModule_basic",
"BoolFloatFalseModule_basic",
"BoolFloatTrueModule_basic",
"BoolIntFalseModule_basic",
"BoolIntTrueModule_basic",
"CeilFloatModule_basic",
"DivFloatModule_basic",
Prune xfail e2e LTC tests & fix bugs from functionalization pass (#1044) - Pruned number of xfailed e2e LTC tests from 305 to 134 - Reviewed every failure to ensure the error genuinely warrants an xfail - Fixed bug where non-tensor outputs of LTC computation had `.to('cpu')` called, which caused a failure and inflated the xfail count - Fixed bug with `HBC_basic` test where a constant tensor was created in its constructor without being declared as a buffer, which prevented the device from being updated when the parent `torch.nn.Module` got moved to the `lazy` device - Note that this test is still xfail'd due to some unsupported ops. Left a comment about some potential issues that may arise if it gets reenabled in the future - Updated autogen `GeneratedTorchOps.td` to reflect the latest set of supported ops - Renamed `aten.zero.functionalization` to `aten.zero` to reflect upstream PyTorch changes
2022-07-13 03:21:50 +08:00
"ElementwiseAtenFloorDivideBroadcastModule_basic",
"ElementwiseAtenFloorDivideModule_basic",
Added e2e LTC tests (#916) * Added e2e LTC Torch MLIR tests * Fix seed for reproducability * Check if computation is None before getting debug string * Updated unit tests, and added numeric tests * Print name of the model layer that fails numeric validation * Run LTC e2e test with CI/CD * Set seed in main function, instead of beginning of execution * Add comment to specify number of digits of precision * Fixed typo * Remove tests for LTC example models * Added LTC option to torchscript e2e * Implement compile and run for LTC e2e test * xfail all tests that use ops that aren't currently supported
2022-06-10 03:56:01 +08:00
"EqIntModule_basic",
"GeFloatIntModule_basic",
"GeFloatModule_basic",
Resolve remaining LTC CI failures (#1110) * Replace CHECK_EQ with TORCH_CHECK_EQ * Check value of TORCH_MLIR_USE_INSTALLED_PYTORCH during LTC build * Update LTC XFAIL with NewZerosModule ops * Explicitly blacklist _like ops * Automatically blacklist new_/_like ops * Prune away unused Python dependencies from LTC * Add flag to disable LTC * Autogen dummy _REFERENCE_LAZY_BACKEND library when LTC is disabled * Implement compute_shape_var * Removed Var tests from XFAIL Set * XFAIL tests using _local_scalar_dense or index.Tensor * Add StdDim tests to XFAIL set * Autogen aten::cat
2022-07-30 17:54:40 +08:00
"GeIntModule_basic",
Added e2e LTC tests (#916) * Added e2e LTC Torch MLIR tests * Fix seed for reproducability * Check if computation is None before getting debug string * Updated unit tests, and added numeric tests * Print name of the model layer that fails numeric validation * Run LTC e2e test with CI/CD * Set seed in main function, instead of beginning of execution * Add comment to specify number of digits of precision * Fixed typo * Remove tests for LTC example models * Added LTC option to torchscript e2e * Implement compile and run for LTC e2e test * xfail all tests that use ops that aren't currently supported
2022-06-10 03:56:01 +08:00
"GtFloatIntModule_basic",
"GtIntModule_basic",
"HBC_basic",
Add HardtanhBackward TOSA and LINALG support (#1721)
2023-03-07 02:16:37 +08:00
"HardtanhBackward_basic",
Added e2e LTC tests (#916) * Added e2e LTC Torch MLIR tests * Fix seed for reproducability * Check if computation is None before getting debug string * Updated unit tests, and added numeric tests * Print name of the model layer that fails numeric validation * Run LTC e2e test with CI/CD * Set seed in main function, instead of beginning of execution * Add comment to specify number of digits of precision * Fixed typo * Remove tests for LTC example models * Added LTC option to torchscript e2e * Implement compile and run for LTC e2e test * xfail all tests that use ops that aren't currently supported
2022-06-10 03:56:01 +08:00
"IndexPut1DFloatAccumulateModule_basic",
"IndexPut1DFloatNonAccumulateModule_basic",
"IndexPut1DIntAccumulateModule_basic",
"IndexPut1DIntNonAccumulateModule_basic",
"IndexPut2DFloatAccumulateModule_basic",
"IndexPut2DFloatNonAccumulateModule_basic",
"IndexPut2DIntAccumulateModule_basic",
"IndexPut2DIntNonAccumulateModule_basic",
"IndexPut3DFloatAccumulateModule_basic",
"IndexPut3DFloatNonAccumulateModule_basic",
"IndexPut3DIntAccumulateModule_basic",
"IndexPut3DIntNonAccumulateModule_basic",
"IndexPutHackedTwin1DFloatAccumulateModule_basic",
"IndexPutHackedTwin1DFloatNonAccumulateModule_basic",
"IndexPutHackedTwin1DIntAccumulateModule_basic",
"IndexPutHackedTwin1DIntNonAccumulateModule_basic",
"IndexPutHackedTwin2DFloatAccumulateModule_basic",
"IndexPutHackedTwin2DFloatNonAccumulateModule_basic",
"IndexPutHackedTwin2DIntAccumulateModule_basic",
"IndexPutHackedTwin2DIntNonAccumulateModule_basic",
"IndexPutHackedTwin3DFloatAccumulateModule_basic",
"IndexPutHackedTwin3DFloatNonAccumulateModule_basic",
"IndexPutHackedTwin3DIntAccumulateModule_basic",
"IndexPutHackedTwin3DIntNonAccumulateModule_basic",
"IndexPutImpl1DFloatAccumulateModule_basic",
"IndexPutImpl1DFloatNonAccumulateModule_basic",
"IndexPutImpl1DIntAccumulateModule_basic",
"IndexPutImpl1DIntNonAccumulateModule_basic",
"IndexPutImpl2DFloatAccumulateModule_basic",
"IndexPutImpl2DFloatNonAccumulateModule_basic",
[MLIR][TORCH] Extend implementation of aten._index_put_impl op. This commits adds the support for cases for index_put_op: 1.) where index is a 2-d tensor. 2.) where indices is a list of tensors and none, with exactly 2 non none tensors along the consecutive dimensions. This commit also adds a utility to compute the broadcast shape given the two input tensors. Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-12-08 13:46:54 +08:00
"IndexPutImpl2DIndexModule_basic",
Added e2e LTC tests (#916) * Added e2e LTC Torch MLIR tests * Fix seed for reproducability * Check if computation is None before getting debug string * Updated unit tests, and added numeric tests * Print name of the model layer that fails numeric validation * Run LTC e2e test with CI/CD * Set seed in main function, instead of beginning of execution * Add comment to specify number of digits of precision * Fixed typo * Remove tests for LTC example models * Added LTC option to torchscript e2e * Implement compile and run for LTC e2e test * xfail all tests that use ops that aren't currently supported
2022-06-10 03:56:01 +08:00
"IndexPutImpl3DFloatAccumulateModule_basic",
"IndexPutImpl3DFloatNonAccumulateModule_basic",
[MLIR][TORCH] Extend implementation of aten._index_put_impl op. This commits adds the support for cases for index_put_op: 1.) where index is a 2-d tensor. 2.) where indices is a list of tensors and none, with exactly 2 non none tensors along the consecutive dimensions. This commit also adds a utility to compute the broadcast shape given the two input tensors. Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-12-08 13:46:54 +08:00
"IndexPutImplIndexWithNoneModule_basic",
Prune xfail e2e LTC tests & fix bugs from functionalization pass (#1044) - Pruned number of xfailed e2e LTC tests from 305 to 134 - Reviewed every failure to ensure the error genuinely warrants an xfail - Fixed bug where non-tensor outputs of LTC computation had `.to('cpu')` called, which caused a failure and inflated the xfail count - Fixed bug with `HBC_basic` test where a constant tensor was created in its constructor without being declared as a buffer, which prevented the device from being updated when the parent `torch.nn.Module` got moved to the `lazy` device - Note that this test is still xfail'd due to some unsupported ops. Left a comment about some potential issues that may arise if it gets reenabled in the future - Updated autogen `GeneratedTorchOps.td` to reflect the latest set of supported ops - Renamed `aten.zero.functionalization` to `aten.zero` to reflect upstream PyTorch changes
2022-07-13 03:21:50 +08:00
"IndexTensorModule3dInput_basic",
Added e2e LTC tests (#916) * Added e2e LTC Torch MLIR tests * Fix seed for reproducability * Check if computation is None before getting debug string * Updated unit tests, and added numeric tests * Print name of the model layer that fails numeric validation * Run LTC e2e test with CI/CD * Set seed in main function, instead of beginning of execution * Add comment to specify number of digits of precision * Fixed typo * Remove tests for LTC example models * Added LTC option to torchscript e2e * Implement compile and run for LTC e2e test * xfail all tests that use ops that aren't currently supported
2022-06-10 03:56:01 +08:00
"IndexTensorModule_basic",
[TOSA] Add aten.Index.Tensor support (#1771)
2023-01-20 13:19:00 +08:00
"IndexTensorStaticModule_basic",
[TOSA] aten.index.tensor multiple indexes support (#1868)
2023-02-14 15:07:15 +08:00
"IndexTensorMultiIndexStaticModule_basic",
Resolve remaining LTC CI failures (#1110) * Replace CHECK_EQ with TORCH_CHECK_EQ * Check value of TORCH_MLIR_USE_INSTALLED_PYTORCH during LTC build * Update LTC XFAIL with NewZerosModule ops * Explicitly blacklist _like ops * Automatically blacklist new_/_like ops * Prune away unused Python dependencies from LTC * Add flag to disable LTC * Autogen dummy _REFERENCE_LAZY_BACKEND library when LTC is disabled * Implement compute_shape_var * Removed Var tests from XFAIL Set * XFAIL tests using _local_scalar_dense or index.Tensor * Add StdDim tests to XFAIL set * Autogen aten::cat
2022-07-30 17:54:40 +08:00
"IndexTensorMultiInputContiguousCenter_basic",
"IndexTensorMultiInputNonContiguous_basic",
"IndexTensorMultiInputOneDim_basic",
"IndexTensorMultiInputThreeIndexers_basic",
"IndexTensorMultiInput_basic",
Resolve CI testing failure for Lazy Tensor Core (#1088) * Xfail unsupported ops * Register FuncDialect * Include dynamic_ir in build * Code reformat * Enable LTC tests for macOS and Source Build
2022-07-26 07:40:25 +08:00
"IndexTensorSelectDimModule_basic",
[MLIR][TORCH] Fix dynamic cases for aten.index.Tensor
2022-08-16 20:46:42 +08:00
"IndexTensorMultiInputContiguousOneDimDynamic_basic",
"IndexTensorMultiInputNonContiguousOneDimDynamic_basic",
"IndexTensorMultiInputNonContiguousDynamic_basic",
"IndexTensorMultiInputNonContiguousMultipleStaticDims_basic",
[MLIR][TORCH] Add E2E support for aten.index.Tensor_hacked_twin op This commit adds lowering of `index.Tensor_hacked_twin` op. Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-09-06 21:29:24 +08:00
"IndexTensorHackedTwinModule_basic",
"IndexTensorHackedTwinModule3dInput_basic",
"IndexTensorHackedTwinMultiInputNonContiguousMultipleStaticDims_basic",
Fix as_strided/slice symint (#1401) * Fix as_strided symint * Re-enable LTC tests * Re-enable LTC * Add hardtanh shape inference function * Fix slice symint
2022-09-27 00:16:49 +08:00
"LiftFreshCopyModule_basic",
Added e2e LTC tests (#916) * Added e2e LTC Torch MLIR tests * Fix seed for reproducability * Check if computation is None before getting debug string * Updated unit tests, and added numeric tests * Print name of the model layer that fails numeric validation * Run LTC e2e test with CI/CD * Set seed in main function, instead of beginning of execution * Add comment to specify number of digits of precision * Fixed typo * Remove tests for LTC example models * Added LTC option to torchscript e2e * Implement compile and run for LTC e2e test * xfail all tests that use ops that aren't currently supported
2022-06-10 03:56:01 +08:00
"Matmul_dot",
"MulIntModule_basic",
[MLIR][TORCH] Add E2E support for `aten.[div.int|bitwise_or.Tensor]` ops This commit adds lowering of `aten.div.int` and `aten.bitwise_or.Tensor` ops. Both these ops are required in order to support bloom_560m model. Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2022-10-06 21:11:52 +08:00
"DivIntModule_basic",
Added e2e LTC tests (#916) * Added e2e LTC Torch MLIR tests * Fix seed for reproducability * Check if computation is None before getting debug string * Updated unit tests, and added numeric tests * Print name of the model layer that fails numeric validation * Run LTC e2e test with CI/CD * Set seed in main function, instead of beginning of execution * Add comment to specify number of digits of precision * Fixed typo * Remove tests for LTC example models * Added LTC option to torchscript e2e * Implement compile and run for LTC e2e test * xfail all tests that use ops that aren't currently supported
2022-06-10 03:56:01 +08:00
"NeFloatIntModule_basic",
"NeIntModule_basic",
"QuantizedMLP_basic",
"RandLikeDtypeModule_basic",
"RandLikeModule_basic",
Add decomposition for aten.roll (#1170) * Add decomposition for aten.roll * add e2e unittest * refine type of torch.roll * fix aten::cat output type
2022-08-24 08:36:05 +08:00
"RollModule_basic",
Added e2e LTC tests (#916) * Added e2e LTC Torch MLIR tests * Fix seed for reproducability * Check if computation is None before getting debug string * Updated unit tests, and added numeric tests * Print name of the model layer that fails numeric validation * Run LTC e2e test with CI/CD * Set seed in main function, instead of beginning of execution * Add comment to specify number of digits of precision * Fixed typo * Remove tests for LTC example models * Added LTC option to torchscript e2e * Implement compile and run for LTC e2e test * xfail all tests that use ops that aren't currently supported
2022-06-10 03:56:01 +08:00
"ScalarImplicitFloatModule_basic",
"ScalarImplicitIntModule_basic",
"SliceEndSleStartModule_basic",
"SliceOutOfUpperBoundIndexModule_basic",
"SliceStartEqEndModule_basic",
"SqrtIntModule_basic",
"SubFloatModule_basic",
"SubIntModule_basic",
Resolve CI testing failure for Lazy Tensor Core (#1088) * Xfail unsupported ops * Register FuncDialect * Include dynamic_ir in build * Code reformat * Enable LTC tests for macOS and Source Build
2022-07-26 07:40:25 +08:00
"TensorsConcatNegativeDimModule_basic",
[TORCH] Improve type refinement for aten.cat. (#1908) * [TORCH] Fix type refinement for aten.cat. * Add test. * Address comments. * Update. * Update. * Update. * Update. * Update. --------- Co-authored-by: Ziheng Jiang <ziheng.jiang@bytedance.com>
2023-03-10 08:17:35 +08:00
"TensorsConcatPromoteDTypeModule_basic",
Support aten.stack op and decompose it into unsqueeze & cat (#1747)
2023-03-11 09:25:25 +08:00
"TensorsStackPromoteDTypeModule_basic",
Added e2e LTC tests (#916) * Added e2e LTC Torch MLIR tests * Fix seed for reproducability * Check if computation is None before getting debug string * Updated unit tests, and added numeric tests * Print name of the model layer that fails numeric validation * Run LTC e2e test with CI/CD * Set seed in main function, instead of beginning of execution * Add comment to specify number of digits of precision * Fixed typo * Remove tests for LTC example models * Added LTC option to torchscript e2e * Implement compile and run for LTC e2e test * xfail all tests that use ops that aren't currently supported
2022-06-10 03:56:01 +08:00
"TensorToBoolZeroRank_basic",
"TensorToBool_basic",
"TensorToFloatZeroRank_basic",
"TensorToFloat_basic",
"TensorToIntZeroRank_basic",
"TensorToInt_basic",
"TensorsConcatModule_basic",
"UniformModule_basic",
Replace LCG algorithm with squares64 algorithm in AtenUniformOp (#1633) This commit replaces the LCG algorithm that was being used by the `TorchToLinalg` lowering of `AtenUniformOp` to generate random numbers with the `squares64` algorithm, for the LCG algorithm was producing tensors that were highly correlated with one another. Squares64 algorithm: https://arxiv.org/abs/2004.06278 Closes https://github.com/llvm/torch-mlir/issues/1608
2022-12-02 00:30:10 +08:00
"UniformNoCorrelationModule_basic",
Added e2e LTC tests (#916) * Added e2e LTC Torch MLIR tests * Fix seed for reproducability * Check if computation is None before getting debug string * Updated unit tests, and added numeric tests * Print name of the model layer that fails numeric validation * Run LTC e2e test with CI/CD * Set seed in main function, instead of beginning of execution * Add comment to specify number of digits of precision * Fixed typo * Remove tests for LTC example models * Added LTC option to torchscript e2e * Implement compile and run for LTC e2e test * xfail all tests that use ops that aren't currently supported
2022-06-10 03:56:01 +08:00
"UnsafeViewCollapseDynamicWithAtenSizeIntModule_basic",
"ViewCollapseDynamicWithAtenSizeIntModule_basic",
Add embedding Bag e2e case in xfail set (#1130)
2022-08-02 06:23:45 +08:00
"AtenEmbeddingBagSumExample_basic",
Add decomposition and E2E support for Aten_EmbeddingBag (#1137) * Add decomposition and E2E support for Aten_EmbeddingBag
2022-08-09 06:56:49 +08:00
"Aten_EmbeddingBagExample_basic",
E2E support for AtenRemainderScalarOp (#1200)
2022-08-11 08:02:06 +08:00
"ElementwiseRemainderScalarModule_Int_Float_basic",
"ElementwiseRemainderScalarModule_Float_basic",
"ElementwiseRemainderScalarModule_Int_basic",
"ElementwiseRemainderScalarModule_Bool_basic",
[MLIR][TORCH] Add Byte and Char Dtype support
2022-09-20 02:50:51 +08:00
"AtenIntTensorByteDtypeModule_basic",
"AtenIntTensorCharDtypeModule_basic",
[MLIR][TORCH] Add E2E support for aten.fill.Tensor op This commit adds the decomposition for `aten.fill.Tensor` op. Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-10-26 20:18:49 +08:00
"Fill_TensorFloat32WithFloat32_basic",
"Fill_TensorFloat32WithFloat64_basic",
"Fill_TensorFloat32WithInt64_basic",
[MLIR][TORCH] Add E2E support for aten.upsample_nearest2d_backward.vec op Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-11-01 21:08:04 +08:00
"UpSampleNearest2dBackwardVec_basic",
"UpSampleNearest2dBackwardOutputSizeNone_basic",
[MLIR][TORCH] Add E2E support aten.convolution_backward op This commit adds the decomposition for the `aten.convolution_backward` and `aten.convolution_backward_overrideable` op.
2022-11-04 15:57:29 +08:00
"ConvolutionBackwardModule2D_basic",
"ConvolutionBackwardModule2DPadded_basic",
[MLIR][TORCH] Add decomposition for aten.var_mean.correction op Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-11-15 22:39:40 +08:00
"VarMeanCorrectionModule_basic",
[MLIR][TORCH] Add E2E support for prims.convert_element_type op Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-11-21 16:38:47 +08:00
"VarMeanCorrectionNoneModule_basic",
"PrimsConvertElementTypeModule_basic",
Prelu lowering to linalg (#1712) Prelu lowering to linalg
2022-12-28 11:21:33 +08:00
"ElementwisePreluModule_basic",
[MLIR][TORCH] Add e2e support for aten.var_mean op Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-12-09 23:22:26 +08:00
"VarMeanBiasedModule_basic",
"VarMeanUnbiasedModule_basic",
[MLIR][TORCH] Add decomposition for aten.randn_like op This commit decomposes aten.randn_like op into aten.randn.generator op. Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2023-01-16 19:40:21 +08:00
"RandnLikeModule_basic",
"RandnLikeDtypeModule_basic",
build: manually update PyTorch version Set PyTorch and TorchVision version to nightly release 2023-02-27. This commit also adds the lowering for aten.add and aten.Float.Scalar op. Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2023-02-28 10:32:21 +08:00
"BernoulliFloatModule_basic",
"BernoulliModule_basic",
"BernoulliPModule_basic",
"DropoutTrainModule_basic",
"StdCorrectionKeepDimModule_basic",
"StdCorrectionNoneModule_basic",
"VarBiasedModule_basic",
"VarCorrectionAllDimReduceModule_basic",
"VarCorrectionEmptyDimModule_basic",
"VarCorrectionKeepDimModule_basic",
"VarCorrectionLargeInputModule_basic",
"VarCorrectionModule_basic",
"VarCorrectionNoneModule_basic",
"VarCorrectionSingleDimReduceModule_basic",
"VarDimAllDimReduceModule_basic",
"VarDimBiasedModule_basic",
"VarDimEmptyDimModule_basic",
"VarDimModule_basic",
"VarDimMultiDimModule_basic",
"VarDimNegativeModule_basic",
"VarDimNoneDimModule_basic",
"VarDimSingleDimModule_basic",
"VarDimUnbiasedModule_basic",
"VarUnbiasedModule_basic",
[MLIR][TORCH] Add decomposition for prims::squeeze op This commit adds the decomposition for the prims.squeeze op. Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-11-16 13:57:58 +08:00
"AtenFloatScalarModule_basic",
"PrimsSqueezeModule_basic",
"PrimsSqueezeEmptyDimensionsModule_basic",
[MLIR][TORCH] Add support for prims::view_of op This op does nothing and just returns the input operand as the result of the op. Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2023-04-10 11:50:26 +08:00
"PrimsViewOfModule_basic",
"PrimsViewOfZeroRankModule_basic",
[Torch Dialect] support for aten.one_hot (#1852)
2023-04-11 16:02:28 +08:00
"OneHotModule_basic",
Added e2e LTC tests (#916) * Added e2e LTC Torch MLIR tests * Fix seed for reproducability * Check if computation is None before getting debug string * Updated unit tests, and added numeric tests * Print name of the model layer that fails numeric validation * Run LTC e2e test with CI/CD * Set seed in main function, instead of beginning of execution * Add comment to specify number of digits of precision * Fixed typo * Remove tests for LTC example models * Added LTC option to torchscript e2e * Implement compile and run for LTC e2e test * xfail all tests that use ops that aren't currently supported
2022-06-10 03:56:01 +08:00
}