8c87057f50
update PyTorch version to 2.1.0.dev20230704 ( #2282 )
...
- torch version: 2.1.0.dev20230704
- torch commit hash: e5472fd3c324c5ecb343884e5399e0227cc30a6c
- torchvision version: 0.16.0.dev20230704
Co-authored-by: Roll PyTorch Action <torch-mlir@users.noreply.github.com>
2023-07-04 08:23:00 -07:00
c7fa42b7d3
[Torch Dialect] Add canonicalizer for aten.to.other op ( #2273 )
...
Canonicalize aten.to.other to prim.device + prim.dtype + aten.to.device
Co-authored-by: wujiawei.aml <wujiawei.aml@bytedance.com>
2023-06-30 09:43:08 +08:00
449cfb8375
[Torch Dialect] add more scalar op folders ( #2265 )
2023-06-29 10:37:13 +08:00
ddd0c06970
[TORCH] Fix recompose off by -1 error ( #2271 )
2023-06-27 13:34:14 -07:00
859885c1d3
[Torch Dialect] Support aten.native_dropout ( #2259 )
...
* [Torch Dialect] Support aten.native_dropout
* update
2023-06-27 14:19:33 +08:00
1ea2b57ab7
[Torch Dialect] add folder for aten.add ( #2264 )
...
* [Torch Dialect] add folder for aten.add
* update
* update
* update
2023-06-27 10:55:28 +08:00
fbb5ed52cf
update PyTorch version to 2.1.0.dev20230623 ( #2260 )
...
- torch version: 2.1.0.dev20230623
- torch commit hash: ad724c83fb0d94cb3bb2cec94e15d88023c64e0d
- torchvision version: 0.16.0.dev20230623
Co-authored-by: Roll PyTorch Action <torch-mlir@users.noreply.github.com>
2023-06-23 09:03:50 -07:00
64afc08dab
[Torch Dialect] add missing one_hot dtype function ( #2143 )
...
* [Torch Dialect] add missing one_hot dtype function
* update
* update
* update
2023-06-23 16:11:33 +08:00
39201a4be5
[Torch Dialect] avoid assertion failure when PrimNumToTensorScalarOp'… ( #2256 )
...
* [Torch Dialect] avoid assertion failure when PrimNumToTensorScalarOp's input is torch.number
* update
2023-06-23 16:02:45 +08:00
96b14e952e
[Torch Dialect] Support aten.device.with_index ( #2254 )
2023-06-23 01:07:14 +08:00
4fd4477e15
[Torch Dialect] require hasSizes when decompose aten.amax ( #2248 )
2023-06-22 11:26:51 +08:00
a0d2789840
[MLIR][TORCH] Add e2e support for aten.alias
...
-- This commit adds e2e support for aten.alias op.
Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
2023-06-21 12:15:31 +05:30
7c6961bcbf
[Torch Dialect] Support aten.cuda and add canonicalizer for aten.cuda ( #2231 )
2023-06-14 09:56:39 +08:00
0caaf8d32a
Bump LLVM ( #2176 )
...
* Bump LLVM
---------
Co-authored-by: Matthias Gehre <matthias.gehre@xilinx.com>
2023-06-13 16:17:23 +02:00
ddea56a832
[Torch Dialect] fix torch.uint8's dtype infer ( #2227 )
2023-06-13 10:38:20 +08:00
4e2ba2e0af
Support aten.sign ( #2205 )
2023-06-10 20:45:35 +02:00
27a3d09917
Torch: Fold RuntimeAssertOp when condition is true ( #2198 )
2023-06-09 19:06:25 +08:00
5a7bf4e4cb
[Torch Dialect] Add canonicalize pattern for aten.is_floating_point ( #2194 )
...
* [Torch Dialect] Add canonicalize pattern for aten.is_floating_point
* implement as fold
* add lit test
2023-06-07 17:05:31 +08:00
e4f8fb1b8c
[Torch Dialect] add support for AtenIsnanOp ( #2170 )
...
* add support for mhlo
* Add Test for torch.ne
* fix torch.ne shape/add static test case
* add support for static torch.ne
---------
Co-authored-by: root <root@n31-177-039.byted.org>
2023-06-07 10:06:27 +08:00
faec8698ea
[Torch Dialect] Support recompose aten.split.Tensor + prim.ListUnpack ( #2192 )
2023-06-07 01:38:04 +08:00
da886280fe
[MLIR][TORCH] Add E2E support for aten.tril op ( #2202 )
...
Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2023-06-05 16:17:01 -07:00
a46b5c6af2
Fix types + off-by-1 error, clamp `end` in slice+copy_ recomposition
...
The `copy_` op being replaced by `RecomposeSliceCopy_` operates on a
subset of the tensor being mutated, while the `index_put` op being
used to replace the `copy_` op operates on the entire tensor being
mutated. This means that the result type of the `index_put` should be
the type of the input to `index_put` and we need to make sure that
`copy_` does not have users before replacing to avoid type conflicts.
This commit also fixes the result type used for the
`AtenArangeStartStepOp`, and an off-by-1 error when creating the
indices vector.
Lastly, this commit also clamps the `end` value from the slice to the
size of the dimension.
2023-06-01 11:14:53 -07:00
8af3e50662
[Torch Dialect] Add support for AtenScalarTensorOp ( #2085 )
...
* add scalar_tensor op
* add dynamo pass test; needs PR2062
* try to fix
* Empty commit, trigger test
* Empty commit, trigger test
* address comments
* use dtype function
* fix decompose rule
* remove unused include
* Empty commit, trigger test
* fix test
* disable ltc
* fix dtype
---------
Co-authored-by: zhekun.zhang <zhekun.zhang@bytedance.com>
2023-06-01 11:38:50 +08:00
552887783a
[TM_TENSOR] Add `aten.scatter.[src|value]` op
...
This commit adds support of `aten.scatter.src` and `aten.scatter.value`
ops.
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2023-05-29 12:35:53 +05:30
69e993b03f
[Torch Op] Add AtenChunkOp support ( #2152 )
...
* add chunkOp support
* update LTC xfail list
* address comments
* address comments
---------
Co-authored-by: zhekun.zhang <zhekun.zhang@bytedance.com>
2023-05-26 10:05:19 +08:00
dff3405d5a
Add alias analysis for cast-like ops to maximize-value-semantics ( #2160 )
...
When `use_tracing=True` is used to import a model into Torch-MLIR,
several casts get inserted in the IR to bridge the untyped inputs and
outputs with the typed body of the computation. These casts create
extra aliases of tensors that cause the current analysis in
`maximize-value-semantics` to fail.
In particular, the `maximize-value-semantics` analysis assumes that the
only valid alias right after an overwrite is the overwritten
alias. So, if there is a use of a casted version of the overwritten
alias after the overwrite, the analysis fails.
This commit improves the analysis by identifying all cast-like aliases
of the overwritten alias and allowing such aliases to be used after an
overwrite.
Because this issue only arises when using tracing, it cannot be
currently tested e2e, so only lit test is added.
2023-05-25 17:05:41 +00:00
a426363b7d
[Torch Dialect] Add split.tensor support + recompose rules ( #2102 )
...
* add split.tensor support + recompose rules
* add e2e test
* address comments
* address comments
* erase op in recomposeOp
---------
Co-authored-by: zhekun.zhang <zhekun.zhang@bytedance.com>
2023-05-23 12:43:33 -07:00
5b63138d55
[Torch Dialect] Enforce signless attribute for ConstantIntOp ( #2078 )
...
* fix torch_c.to_i64
* restore dialect.cpp
* Empty commit, trigger test
* Empty commit, trigger test
* fix uint case
* address comments
* update error msg
* clean up
* use i64 for ConstantIntOp
* use I64Attr
---------
Co-authored-by: zhekun.zhang <zhekun.zhang@bytedance.com>
2023-05-22 19:21:34 -05:00
588bdc1344
Fix sign-compare warning ( #2136 )
2023-05-22 09:15:33 -07:00
aa97c8383e
[Torch Op] Add unbind.int support with ListUnpack ( #2058 )
...
* add unbind int
* reformat
* use unpack canonicalize
* address comments
* Empty commit, trigger test
* add ltc blacklist
* clean up
* address comments
* check permute list
* erase in recompose
---------
Co-authored-by: zhekun.zhang <zhekun.zhang@bytedance.com>
2023-05-18 19:07:58 -07:00
5698893ae4
build: manually update PyTorch version
...
Set PyTorch and TorchVision version to nightly release 2023-05-16.
Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2023-05-18 21:30:11 +05:30
e98f2ba04a
[Torch Dialect] require dtype exists when decompose to aten.where.self ( #2094 )
...
* [Torch Dialect] require dtype exists when decompose to aten.where.self
* update
2023-05-17 09:04:26 -07:00
0302cf1d92
Add TMTensor::Attention and lower ScaledDotProductAttentionOp to it ( #2027 )
2023-05-16 15:17:45 -04:00
de02b56e17
Replace RefineTypes with dtype functions ( #2105 )
...
This commit adds dtype functions for all the torch ops that did not
previously have one and removes the pass `RefineTypes`, since the
abstract interpretation library now takes care of all the dtype
propagation.
All dtype functions added are tested except for
- `aten.embedding`
- `aten._embedding_bag`
- `aten.embedding_bag`
These functions need a change to the testing framework to allow
specifying the actual data inside the tensor used for testing. I will
fix this in a follow up patch.
Co-authored-by: Jiahao Li <liplus17@163.com>
2023-05-12 13:40:45 -07:00
8eb0c7e656
torch.complex to builtin complex types matching.
...
The right approach would be to create our own !torch.complex type
and use that during import than have a pass that converts to the MLIR
complex types.
2023-05-11 21:29:07 +05:30
ab694dfbc1
Add complex dtype support on refbackend
2023-05-11 21:29:07 +05:30
3cd91affbc
Add complex types support with basic complex ops.
...
Add complex types support with basic complex types.
Add aten.imag and aten.real op lowering via linalg_backend.
2023-05-11 21:29:07 +05:30
d7614c261d
Integrate LLVM
...
LLVM: 26ee8947702d79ce2cab8e577f713685a5ca4a55
MHLO: 4805d8498dfb81566076f56f52273b426c1cc5bf
Per: https://github.com/llvm/torch-mlir/issues/1178#issuecomment-1538492185
2023-05-09 10:14:27 -07:00
9f1ed4b2ba
[Torch Dialect] typo fix for RefineTypes ( #2087 )
2023-05-05 15:22:14 -07:00
378860f51b
[MLIR][TORCH] Add E2E support for aten.topk op
...
This commit adds the decomposition for the aten.topk op.
Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2023-05-05 15:50:33 +05:30
0cf9ee340b
[Torch Dialect] Add to.dtype_layout canonicalize patterns ( #2062 )
...
* add to.dtype_layout canonicalize patterns
* update comment
---------
Co-authored-by: zhekun.zhang <zhekun.zhang@bytedance.com>
2023-05-02 20:06:02 -07:00
c596d11b98
[Torch Dailect] add canonicalize pattern for prim.device ( #2066 )
2023-05-02 20:05:46 -07:00
7b73e0cfaf
Add e2e linalg support for aten.atan ( #2070 )
...
* new atan op
* update shape
---------
Co-authored-by: Ze Zhang <ze.zhang@getcruise.com>
2023-04-28 00:04:58 -07:00
491ae5eda4
[MLIR][TORCH] Add E2E support for aten.var_mean.dim op
...
This commit adds the decomposition for the aten.var_mean.dim op.
Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2023-04-27 22:00:44 +05:30
f85f5799e4
Fix creation of empty tensor in decomposition for randn ops ( #2043 )
...
The current decomposition for `aten.randn.generator` does not specify
the `dtype` argument of the empty tensors created to store the random
values. This leads to invalid IR when the output type of the `randn`
op is not the default PyTorch dtype.
2023-04-19 08:25:39 -07:00
4d98f76d4f
[Torch Dialect] fold aten.detach ( #2021 )
2023-04-18 08:59:14 -07:00
ed56e614b7
[MLIR][TORCH] Add E2E support for cross entropy lowering
...
Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2023-04-18 08:00:20 +05:30
811f330283
update PyTorch version to 2.1.0.dev20230414
2023-04-14 17:10:36 +00:00
318fe13468
[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>
2023-04-14 13:12:56 +05:30
a13d301356
[MLIR][TORCH] Add e2e support for aten.sort op
...
-- This commit adds e2e support for atend.sort op.
-- 1. Adds aten.sort op in torch dialect.
-- 2. Adds tm_tensor.sort op in TMTensor dialect.
-- 3. Adds lowering of aten.sort -> tm_tensor.sort.
Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
2023-04-13 12:59:43 +05:30
Sean Silva
Jiawei Wu
Yuanqiang Liu
Chi_Liu
Abhishek Varma
Maksim Levental
Matthias Gehre
JianzheXiao
Vivek Khandelwal
Ramiro Leal-Cavazos
Zhekun Zhang
Gaurav Shukla
gpetters94
Prashant Kumar
Ze Zhang
Roll PyTorch Action
Abhishek Varma