Commit Graph

807 Commits (f4bfe3f948a11abc308c9fe46c571ee67406e109)

Author SHA1 Message Date
Yuanqiang Liu f4bfe3f948
Bump llvm and stablehlo (#3377)
* bump llvm to 1e5f29af81a5f6fda308074f6345b9fba4faa71c
* bump stablehlo to c44d9af8d4879adccf1054cb61a53377ae5898cb
2024-05-22 23:28:45 +08:00
Angel Zhang 52be4bdc18
[ONNX] Fix bugs for the `onnx.OneHot` operator (#3334)
This commit fixes the bugs for the `onnx.OneHot` operator by:

1) Converting negative indices to non-negative indices
2) Handling both `int` and `float` types for `off` and `on` values
3) Using the correct result type

It also includes a new unit test.
2024-05-22 08:32:00 -04:00
Aart Bik 560ca24771
[torch-mlir][sparse] replace xavier with ones initialization (#3374)
ensures stability of results between different set ups
2024-05-21 17:12:55 -07:00
RattataKing fcf48872b3
[ONNX] Implement Softsign op (#3373) 2024-05-21 12:10:26 -07:00
Aart Bik c0e7d2667d
[torch-mlir][sparse] inference mode for sparse GCN test (#3369) 2024-05-20 19:52:16 -07:00
zjgarvey 297c270980
onnx.Resize and aten._interpolate : allow n spatial dims. (#3368)
The old lowering only had logic for 2d (i.e. images). this patch allows
interpolation for n spatial dims, which is required for some 3d vision
models such as

- onnx/models/pytorch-3dunet_vaiq_int8

which successfully compiles and runs with this patch.
2024-05-20 13:35:27 -07:00
lialan 99511cef82
Implement `onnx.Hardmax` lowering (#3342)
Co-authored-by: Ubuntu <xunli@wsno1.judsoscro3wupi0qm4bjlj5m3b.bx.internal.cloudapp.net>
Co-authored-by: Hasekawa-Takumi <bewater.private476@passmail.net>
2024-05-20 20:56:24 +05:30
Wu Yuan cc28d566ff
[Stablehlo] Support AtenTrilOp (#3359)
1. lower aten.tril to stablehlo composed by iota, select and so forth
2. add related e2e test cases
2024-05-20 15:49:24 +08:00
Aart Bik e80f072ba4
[torch-mlir][sparse] example of a sparse graph convolution (#3363) 2024-05-17 15:43:50 -07:00
zjgarvey 6cba93b16e
[ONNX][TorchToLinalg] Add support for dynamic dims in Interpolate lowering (#3351)
Addresses [Shark-Turbine
#196](https://github.com/nod-ai/SHARK-TestSuite/issues/196)

Related tracker [Shark-Turbine
#566](https://github.com/nod-ai/SHARK-Turbine/issues/566)

Related onnx.Resize issues [Shark-Turbine
#616](https://github.com/nod-ai/SHARK-Turbine/issues/616)
2024-05-17 12:18:57 -07:00
Andrew Woloszyn 513d89c16d
Add support for the onnx.SequenceLength op. (#3362) 2024-05-17 12:17:43 -07:00
Andrew Woloszyn 72e38dcbbc
Add support for the onnx.SequenceConstruct op. (#3316) 2024-05-17 22:51:28 +05:30
Peiming Liu ccb772cd0f
[sparse] propagate sparsity properly when decompose torch operations. (#3318) 2024-05-15 10:09:27 -07:00
Aaron St George ba32b9cee7
Don't fold `aten.clone` if result isn't same type as input (#3347)
Similar to https://github.com/llvm/torch-mlir/pull/2824, we were seeing
some assertion failures after the addition checks around folders were
tightened up in LLVM: https://github.com/llvm/llvm-project/pull/75887 .
This PR essentially moves the logic that used to be applied at the LLVM
level into the folder, which seems to be the suggested fix.
2024-05-16 00:07:45 +08:00
Aart Bik 44fa6c3afd
[torch-mlir][sparse] sparse diagonal feature scaling test (#3344) 2024-05-14 12:13:54 -07:00
Peiming Liu 8e74d64e8f
[sparse] convert to sparse before any use in sparse test. (#3337) 2024-05-14 09:10:36 -07:00
NeverRaR 26b78285bf
[MLIR][ONNX] Add OnnxToTorch support for GlobalMaxPool Op (#3232)
https://github.com/nod-ai/SHARK-Turbine/issues/658

---------

Co-authored-by: root <root@i32b01216.sqa.eu95>
2024-05-14 15:55:39 +05:30
Archana Ramalingam 20f312853c
[MLIR][ONNX] Add OnnxToTorch support for ReduceLogSumExp Op (#3201)
This commit adds the OnnxToTorch support for ReduceLogSumExp op
2024-05-14 09:54:26 +05:30
Aart Bik 667dfcbc5a
[torch-mlir][sparse] enable test on ReLu (#3336)
Downstream MLIR sparsifier has some (rudimentary) support for ReLU now,
and this test can now be enabled with correct end-to-end behavior.

Also see discussion at:

https://discourse.llvm.org/t/min-max-abs-relu-recognition-starter-project/78918
2024-05-13 15:34:26 -07:00
zjgarvey 75d1d72059
Generalize Operand Quantization in FuseQuantizeOps (#3327)
This change enables more customization with operand quantization, and
generalizes the patterns QuantizeOperands and QuantizeTransposeOperands
to QuantizeOperandsPastCommutingOps.

This allows for passing quantization through operations which are
functionally unaffected by quantization, such as view-like ops. The
purpose of this change is to address a myriad of quantization issues
seen in quantized onnx models that have some reshape-like operations
sandwiched in between a dequant and something like a matmul (whose other
operand is immediately quantizable).
2024-05-12 20:49:59 -07:00
Yuanqiang Liu 0b7cbf5e60
[Stablehlo] fix aten.randn's lowering with f32 element type (#3329) 2024-05-11 17:40:04 +08:00
Yuanqiang Liu 5f7cb9e253
[Stablehlo] lowering aten.randn & aten.normal_functional to mhlo.rng … (#3328)
…NORMAL

* split lowering of uniform, randn, normal from Basic.cpp into Rng.cpp
2024-05-11 15:33:37 +08:00
Stella Laurenzo 00efec0b73
[linalg] Implement strict mode lowering for aten.view. (#3319)
* Enables assume_strict_symbolic_shapes on fx_importer imported
programs, indicating strict shape semantics.
* Reworks the view->reshape lowering to take advantage of strict mode
and do one of:
  * Collapse to 0D
  * Flatten/Unflatten when there is an inferred dim.
  * Fallback to tensor.reshape
* Splits some test cases up and adds an attribute to control the old
pattern (so new corners can be tested in strict mode in isolation).
* Dynamic inferred mode needs upstream work to generalize expand_shape
(so that case is suppressed here).
* Deletes the assert from the existing tensor.reshape lowering if strict
shape mode is enabled (since the condition it is dynamically asserting
cannot happen).
2024-05-10 13:45:50 -07:00
Andreas Falkenberg adafd51823
[onnx] Gridsampler addition of nearest mode (#3320)
Added nearest neighbor selection for onnx.Gridsampler
2024-05-10 11:42:10 -07:00
jinchen 4b24909427
Add attributes support for onnx cumsum op (#3241) 2024-05-11 02:09:01 +08:00
NeverRaR 1d4859699b
MaxPool1d lowering to linalg (#3295)
Co-authored-by: root <root@i32b01216.sqa.eu95>
2024-05-10 22:05:26 +05:30
Angel Zhang 261074f594
[ONNX] Handle one-input case for Min ONNX operator (#3326)
This commit handles the one-input case for the "Min" ONNX operator. A
new unit test has also been added.
2024-05-10 22:04:03 +05:30
Angel Zhang 7c289d9522
[ONNX] Handle one-input case for `onnx.Max` operator (#3325)
This commit handles the one-input case for the "Max" ONNX operator. A
new unit test has also been added.
2024-05-10 08:58:46 -07:00
Peiming Liu 2c22087cab
[sparse] match fx node using target name instead of variables name (#3315) 2024-05-09 12:34:14 -07:00
penguin_wwy afe87d62b4
[Linalg] [Stablehlo] Promote type for compare scalar op (#3306) 2024-05-10 02:20:06 +08:00
Aart Bik 97a822de0a
[torch-mlir][sparse] minor tweaks in sparse tests (#3311)
(1) test full pytorch output for eltwise
(2) use "random" input for LIF, to get general sparse tensor 
(3) introduce way to get true sparsity into network (needs backend fix
first)
2024-05-09 10:03:25 -07:00
Aart Bik a033bbfe6c
[torch-mlir][sparse] recognize to_dense primitive (#3308)
also maps simply to sparse_tensor.convert
the sparsity types do the rest!
2024-05-08 22:50:17 -07:00
Aart Bik 89bb7404c1
[torch-mlir][sparse] add a true network to our NN tests (#3305)
Objective: make the to_sparse work end-to-end!
2024-05-08 21:18:42 -07:00
Peiming Liu cff144b3ac
[sparse] fix double free due to incompatibility between buffer-deallo… (#3303)
…cation and sparse tensors.

**NOTE**: This PR _doges_ the issue in buffer-deallocation pass instead
of resolving it. In the future, we need to fix the bug in
buffer-deallocation pass when handling code generated by sparse
compiler.
2024-05-08 21:18:17 -07:00
Yuanqiang Liu 5213557b87
[Stablehlo] fix lowering gelu(x, tanh) (#3307)
* lowering gelu("none") to erf
* lowering gelu("tanh") to tanh
2024-05-09 11:39:13 +08:00
Aart Bik c4b28e8d9f
[torch-mlir][sparse] test for sparse "activation" (#3304)
Example of introducing sparsity into the forward pass. With a bespoke
propagation (but upstream PyTorch will support this).
2024-05-08 19:01:24 -07:00
aldesilv ec6d7aa5d2
OnnxToTorch lowering resize op (#3013)
https://github.com/nod-ai/SHARK-Turbine/issues/358
adds a lowering from onnx to linalg for bilinear and nearest resize with
support for using scales or sizes to get resize shape. uses coordinate
transform half pixel for bilinear mode and asymmetrical for nearest
mode. See
https://github.com/onnx/onnx/blob/main/docs/Operators.md#Resize. Added
two passes -- one for bilinear and the other for nearest.
2024-05-08 21:35:03 +00:00
Benoit Jacob bce800a3f4
Integrate llvm-project at dabdec1001dc368373dd581cf72f37a440873ce3 (#3300)
Co-authored-by: Jacques Pienaar <jpienaar@google.com>
2024-05-08 14:43:06 -04:00
Aart Bik c77f3b559a
[torch-mlir][sparse] add simple sparsity "propagation" rules (#3297)
While waiting for the full resolution of feature request
https://github.com/pytorch/pytorch/issues/117188
(which will propagate sparsity the right way in upstream PyTorch for all
FX Graphs), this minor change allows us to start testing sparsity
"within" a network, rather than just the parameters. Feel free to add
your own rules for testing (but within reason for what will be done
upstream).

Note, two TODOs need to be addressed to work around some pending issues
to make the JIT execution work.
2024-05-07 15:27:36 -07:00
Vinayak Dev 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
Vivek Khandelwal e60160d793
Revert "Decompose AtenNonzeroOp" (#3289)
Reverts llvm/torch-mlir#3281
2024-05-06 09:52:04 -07:00
Vivek Khandelwal 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
Xida Ren (Cedar) 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
Yuanqiang Liu 53299eb224
[Stablehlo] Bump stablehlo to ab92adeda9119a6c3914cd42367b0a2b70765e91 (#3285) 2024-05-05 19:56:12 +08:00
Rob Suderman 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
Vinayak Dev 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
Archana Ramalingam 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
Vivek Khandelwal 0bb62e4347
Revert Onnx.Selu lowering to corresponding Aten op (#3275) 2024-05-02 09:00:24 -07:00
Ze Zhang 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
Xida Ren (Cedar) 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