346a536c9f
[Torch Dialect] decompose all index_put-like op to aten.index_put.hacked_twin for stricter semantics ( #3071 )
...
This PR decomposes all index_put-like op to aten.index_put.hacked_twin for stricter semantics, i.e., no None index in indices argument.
2024-05-08 22:44:57 +08:00
abef114c0c
[torch] emit aten.Softshrink and aten.Hardshrink ( #3248 )
...
as title
2024-05-08 15:20:45 +08:00
6f911ba3d7
[torch] Add OnnxToTorch lowering for `onnx.HammingWindow` ( #3283 )
...
Adds OnnxToTorch lowering for the `onnx.HammingWindow` op.
2024-05-06 10:21:45 -07:00
e60160d793
Revert "Decompose AtenNonzeroOp" ( #3289 )
...
Reverts llvm/torch-mlir#3281
2024-05-06 09:52:04 -07:00
17c3c15131
[ONNX] Add OnnxToTorch lowering for SoftmaxCrossEntropyLoss op ( #3278 )
...
Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
2024-05-06 17:26:32 +05:30
1af00e6040
Decompose AtenNonzeroOp ( #3281 )
...
This fixes some onnx lit tests not lowering to linalg in
https://github.com/nod-ai/SHARK-Turbine/issues/450
2024-05-05 21:59:25 +08:00
321b844df7
Revert hyperbolic trigonometric decompositions ( #3271 )
...
We should be using the `torch` path and handling decomposition in the
`math` dialect.
2024-05-03 12:06:44 -04:00
67d6a665a4
[torch] Add OnnxToTorch lowering for `onnx.HannWindow` ( #3276 )
...
Adds OnnxToTorch lowering for the `onnx.HannWindow` op. Also factors out
common implementation between the window functions.
2024-05-03 12:04:57 -04:00
a46fe2c9db
[MLIR][ONNX] Add OnnxToTorch support for ReduceSumSquare Op ( #3188 )
...
This commit adds the OnnxToTorch support for ReduceSumSquare ops.
---------
Co-authored-by: Ubuntu <archana@archana-cpu.judsoscro3wupi0qm4bjlj5m3b.bx.internal.cloudapp.net>
2024-05-02 22:17:45 +05:30
0bb62e4347
Revert Onnx.Selu lowering to corresponding Aten op ( #3275 )
2024-05-02 09:00:24 -07:00
11cd7cd9e7
Folder and Canonicalizer for PrimsConvertElementTypeOp and AtenMaxPool2dWithIndicesOp ( #3272 )
...
While playing with TorchDynamo on ResNet18. I notice following issues:
- `prims.convert_element_type` can’t be canonicalized even if the input
and the output share the same type
- `aten.max_pool2d_with_indices` is always used instead of
`aten.max_pool2d`, even if the second returned output (indices) has no
user
This PR fixes above issues by adding a folder to the
PrimsConvertElementTypeOp and a canonicalizer to the
AtenMaxPool2dWithIndicesOp
Lit test:
`cmake --build build --target check-torch-mlir-all`
---------
Co-authored-by: Ze Zhang <ze.zhang@getcruise.com>
2024-05-02 00:03:41 -07:00
8c48135a42
[linalg] Fix bug for conversion of complex dtype ( #3269 )
...
The conversion of complex type wasn't supported or checked; the support
and required tests were added.
Fixes:
https://github.com/iree-org/iree/issues/17226#issuecomment-2087779158
2024-05-01 12:06:53 +05:30
33eef15e42
Support onnx.If ( #2825 )
...
This is probably a decent PR for learning about blocks and regions.
If you're here to learn about that, consider also looking at
lib/Conversion/TorchToSCF/TorchToSCF.cpp
While this doesn't include an e2e test, it is tested downstream in
https://github.com/nod-ai/SHARK-TestSuite/blob/main/e2eshark/onnx/operators/If/model.py
---------
Co-authored-by: Xida Ren <xida.ren.dev@gmail.com>
2024-04-30 18:36:40 +00:00
315dc6c3e3
[torch] `aten.eye` should use dynamic dims when no static dims are available ( #3202 )
...
Co-authored-by: Xida Ren <xida.ren.dev@gmail.com>
2024-04-30 17:41:03 +00:00
72349f7522
[TorchToLinalg] Adds Quantization Support for ConvTranspose ( #3240 )
...
I spent a little while debugging numerics issues with some tests similar
to the ones in quantized_models.py, only to find that pytorch's
quantized conv transpose is catastrophically inaccurate. I'll upstream
the issue and only leave the tests here which are of the form quantize
-> dequantize -> op.
2024-04-30 09:23:09 -07:00
05f8b69bf6
[MLIR][TORCH] Add OnnxToTorch support for BlackmanWindow function ( #3181 )
...
Implements OnnxToTorch lowering for the BlackmanWindow Function.
2024-04-30 12:21:27 -04:00
f32ada993d
[Stablehlo] Improve the lowering of pool op in stablehlo ( #3259 )
...
1. Handle case stride == None
2. add avgpool3d maxpool1d maxpool3d lowering
2024-05-01 00:06:13 +08:00
fbbad2d81e
Fix onnx atanh lowering ( #3264 )
...
iree tests `test_atanh` and `test_atanh_example` passed
2024-04-30 00:50:08 -07:00
bf04b53b07
Fix onnx asinh lowering ( #3263 )
...
iree tests `test_asinh` and `test_asinh_example` passed
2024-04-30 00:49:57 -07:00
fb499192df
Fix onnx acosh lowering ( #3262 )
...
iree tests `test_acosh` and `test_acosh_example` passed
2024-04-30 00:49:44 -07:00
aa471f1d96
Fix onnx cosh lowering ( #3254 )
...
iree tests `test_cosh` and `test_cosh_example` passed
2024-04-30 00:49:29 -07:00
b64c22cfc1
Fix onnx sinh lowering ( #3253 )
...
iree tests `test_sinh` and `test_sinh_example` passed
2024-04-30 00:44:41 -07:00
db6721084a
Integrate LLVM at llvm/llvm-project@593f6fdcb4 ( #3260 )
2024-04-29 12:01:40 -07:00
0a5ff68d9d
[stablehlo] Support PrimsCollapseOp and PrimsSplitDimOp in stablehlo ( #3230 )
2024-04-29 17:40:30 +08:00
b1e2241479
[ONNX] Fix Onnx.Selu lowering and canonicalizer for IntImplicit op ( #3221 )
...
Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
2024-04-29 04:00:01 +00:00
aed2cf3351
[Torch] emit aten.__contains__.str_list and add folder ( #3249 )
2024-04-29 10:51:17 +08:00
5684dc0441
[Torch] emit aten.celu and decompose it ( #3247 )
...
CELU(x)=max(0,x)+min(0,α∗(exp(x/α)−1))
2024-04-28 17:23:40 +08:00
46c0f3cad0
[Torch] emit aten.log_sigmoid and decompose it to log(sigmoid) ( #3246 )
2024-04-28 11:47:43 +08:00
5d4b803914
[NFC reformat] Run pre-commit on all files and format misc.
...
This is part 1 of ~3, formatting all miscellaneous text files and CPP files matched by a first run of pre-commit. These tend to be low change-traffic and are likely not disruptive.
Subsequent patches will format Python files and remaining CPP files.
2024-04-27 14:08:09 -07:00
6679728c56
Fix deprecated uses of cast/dyn_cast/dyn_cast_or_null/isa ( #3243 )
...
Like #3130 , gradually replace the deprecated code
https://github.com/llvm/mlir-www/blob/main/website/content/deprecation/_index.md#deprecated
2024-04-27 14:00:56 -07:00
f173a06fa7
[Torch] emit aten.ne.str and add folder ( #3242 )
2024-04-28 00:58:50 +08:00
9a12a093a6
[onnx] Support `onnx.OneHot` lowering to `torch` ( #3196 )
...
[onnx] Support `onnx.OneHot` lowering to `torch`
Leverage the `aten.onehot` implementation along with `aten.transpose`
and `aten.where.scalar`.
2024-04-26 12:08:15 -07:00
ac85338491
[Stablehlo] Support AtenPowScalarOp, AtenTanOp, AtenAsinhOp, AtenAcoshOp, AtenAtanhOp, Atan2Op ( #3233 )
2024-04-26 15:47:44 +08:00
634a796933
[Torch] fold aten.log ( #3223 )
2024-04-26 10:10:02 +08:00
122eb69a98
[stablehlo] add aten left/right shift op conversion support ( #3234 )
2024-04-26 09:20:49 +08:00
cd33d8b011
[onnx] Update DefaultDomainGtoP.cpp gridsampler ( #3228 )
...
Gridsampler
In onnx the interpolation mode is called 'linear' whereas in pytorch it
is called 'bilinear'. This led to the problem that everything other than
'bilinear' was rejected. It needed to be changed to linear.
2024-04-25 18:07:05 -07:00
ac11ec796d
[MLIR][ONNX] Add OnnxToTorch support for ReduceLogSum Op ( #3229 )
...
This commit adds the OnnxToTorch support for ReduceLogSum op
2024-04-25 19:37:57 -04:00
2eac8a992f
[torch-mlir][sparse] sparse tensor dialect is a legal dialect ( #3227 )
2024-04-26 02:36:42 +08:00
b0ba3def93
[Torch] support AtenScalarImplicitOp canonicalize with float ( #3231 )
2024-04-26 02:36:13 +08:00
4361178caa
[torch-mlir][sparse] recognize sparse tensor conversion ( #3226 )
...
Sparse tensor conversions are represented by special aten operators.
This PR ensures the conversions are recognized (instead of failing the
full torch aten lowering to linalg).
2024-04-26 02:32:07 +08:00
7030eacb76
[stablehlo] Support aten.any and aten.all lowering ( #3217 )
2024-04-25 11:15:52 +08:00
678c03b762
Fix nan issue for fp16 torch.randn/randn_like in ConvertAtenUniformOp ( #3184 )
...
For ops that use ConvertAtenUniformOp (e.g. torch.randn/randn_like),
fp16 datatype returns nan values. Trying to lower [this
repro](https://gist.github.com/aviator19941/1c65e658241dea6906ca423f9abaee69 )
will result in nan's, this PR fixes the issue.
2024-04-24 12:28:08 +05:30
fab2696489
[Torch] support aten.trunc ( #3219 )
...
decompose `trunc(x)` to `sign(x) * floor(abs(x))`
2024-04-24 14:32:33 +08:00
e18bf42d0e
[stablehlo] Support ConstantPadNdOp in stablehlo ( #3211 )
...
as title
2024-04-24 14:15:11 +08:00
f77d88390a
[onnx] handle dynamic padSize tensor in onnx.Pad ( #3214 )
...
- Fix pad size to data_rank for dynamic paddingSize Tensor.
- This fix is in accordance with [input
specification](https://onnx.ai/onnx/operators/onnx__Pad.html#inputs ) for
onnx.Pad
- Impl will need to be updated for dynamic padSize when support for
`axes` is added.
2024-04-24 11:31:37 +08:00
42b9eccdb3
[Stablehlo] Fix AtenSumDimIntListOp when dim==None ( #3216 )
...
as titile
2024-04-24 11:25:46 +08:00
4da3d714cc
[Torch] Support AtenProdOp on linalg and stablehlo ( #3215 )
2024-04-24 11:14:04 +08:00
a8ba865fca
[torch] Adds Quantization Support for `aten.relu` ( #3177 )
...
A choice was made to quantize the return type of Relu with a scale and
zero point copied from the input's quantization scheme. With this
choice, the torch-to-linalg conversion of quantized Relu essentially
computes max(input, zeroPoint) in the elementwise payload.
2024-04-23 11:01:36 -07:00
09d42044b4
Support select_last_index attribute of onnx argmin op ( #3212 )
...
The tests listed in https://github.com/nod-ai/SHARK-Turbine/issues/648
all compiled, and the values of results match, but having runtime issue
of dtype mismatch of i/si.
2024-04-23 10:43:38 -07:00
61e6312c87
Support select_last_index attribute of onnx argmax op ( #3192 )
...
The tests listed in https://github.com/nod-ai/SHARK-Turbine/issues/635
all compiled, but having run issue of dtype mismatch of i/si.
2024-04-23 10:16:08 -07:00
Jiawei Wu
Xinyu Yang
Vinayak Dev
Vivek Khandelwal
Xida Ren (Cedar)
Rob Suderman
Archana Ramalingam
Ze Zhang
Prashant Kumar
zjgarvey
jinchen
Yuanqiang Liu
Stella Laurenzo
penguin_wwy
Andreas Falkenberg
Aart Bik
Avinash Sharma
Phaneesh Barwaria