Commit Graph

211 Commits (883b986eda846d7d37e651b6c9e0492546d8ae91)

Author SHA1 Message Date
Vivek Khandelwal d9cbf01d1e Revert "build: update llvm tag to 147fe9de"
This reverts commit e45ad313d4.
2022-11-25 12:41:56 +05:30
Vivek Khandelwal e45ad313d4 build: update llvm tag to 147fe9de
Summary of changes:
- Update call to `hasNoEffect` utility
- `KDynamicSize` value changed to
  `std::numeric_limits<int64_t>::min()` from `-1`
- Update tags
  llvm: 147fe9de29dc13c14835127b35280c4d95c8e8ba
  mhlo: 1944b5fa6062ec4c065d726c9c5d64f1487ee8c5

Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-11-24 12:44:43 +05:30
Abhishek Varma 1d949f3ac2 [MLIR][TORCH] Fix aten.upsample_nearest2d op
-- aten.upsample_nearest2d.vec op is not present
   owing to https://github.com/pytorch/pytorch/pull/85638
-- So this commit adds a lowering on aten.upsample_nearest2d.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
2022-11-18 13:41:47 +05:30
Gaurav Shukla 0d209998d1
llvm: update tag to e864ac6945 (#1600)
Summary of changes:
1. Replace `string` iterator types by `IteratorType` enum.
(e6598b053d)
2. Update `includes` wrt new directory layout of MLIR HLO codebase.
(9fd8d251a8)
3. Update tags
   llvm: e864ac694540342d5e59f59c525c5082f2594fb8
   MHLO: eab364ba2a66bd0613efb94f8a738c1c97aaee92

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>

Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
2022-11-16 14:40:36 -08:00
Ramiro Leal-Cavazos 09ca07bca0
`m_TorchConstant{Int/Bool}List` -> `m_TorchListOfConstant{Int/Bool}s` (#1601)
This commit renames the patterns used to match on lists of constant
values to `m_TorchListOfConstant{valueType}s`. This is needed to avoid
ambiguity for when `valueType` has `Optional` in it. In particular, it
makes it clear whether the values in the list are optional or the list
itself is optional.
2022-11-16 20:33:12 +00:00
George Petterson 92f385bd9f [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.
2022-11-15 07:38:26 +05:30
Vivek Khandelwal a558034c1a [MLIR][TORCH] Fix aten.upsample_nearest2d_backward op
Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-11-12 00:05:36 +05:30
Vivek Khandelwal fedf8c0640 [MLIR][TORCH] Add E2E support for aten.upsample_nearest2d_backward.vec op
Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
2022-11-04 22:10:07 +05:30
Tanyo Kwok 17bc7c89cc
build: update llvm tag to 74fb770d (#1539)
* build: update llvm tag to 74fb770d

This commit makes the following changes needed to update bump LLVM:

+ replace usages of `tensor::createPadScalarOp`, see https://reviews.llvm.org/D136493
+ Update file checks
2022-11-01 15:27:09 +08:00
xndcn 759057cbdd [MLIR][TORCH] Fix wrong parameter name "supportFPInputOnly"
The parameter "supportFPInputOnly" of function createPoolingOp() is
supposed to be "supportNonFPInput", which was added to distinguish
between "MaxPool2d" and "AvgPool2d" op in #718
2022-10-30 23:18:08 +08:00
Vivek Khandelwal c86177730d [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>
2022-10-30 18:40:47 +05:30
Ramiro Leal-Cavazos b723186983
Remove all but one of valsem ops + move fill.Scalar to elementwise (#1531)
This commit removes almost all of the valsem ops, since the value
semantics version of the ops now exist in PyTorch. The only op missing
is `aten.bernoulli_.float`. In addition, this commit also simplifies
the implementation of `aten.fill.Scalar` by moving it to the pattern
that converts elementwise ops.
2022-10-28 15:06:11 +00:00
Ramiro Leal-Cavazos 82a3860e25
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 04:22:53 +00:00
Prashant Kumar 3a2cd23380 [LINALG] Add lowering for aten::round op.
-- Added the lowering for aten::round op.
-- Added the folding for integer cases.
2022-10-13 02:41:26 +05:30
Ramiro Leal-Cavazos 8f76c74be9
Remove unused input tensor from linalg.generic in aten.convolution (#1487)
This commit removes the `weight` tensor from the inputs of one of the
`linalg.generic` ops generated by the `aten.convolution` linalg
lowering, since the indexed values are not actually used by the body
of the `linalg.generic`. Moreover, in general the `weight` tensor does
not have the same shape as the output tensor of the `linalg.generic`,
so both tensors being indexed by the same indexing maps is wrong.
2022-10-12 14:01:24 -07:00
Gaurav Shukla da90a25f90 [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>
2022-10-10 22:28:51 +05:30
Ramiro Leal-Cavazos 8201e7b067
[LINALG] Make `AtenMaxDimOp` use `arith.maxf` to calculate maximum (#1466)
This commit updates the linalg conversion of `AtenMaxDimOp` to use
`arith.maxf` instead of `arith.select` to calculate the maximum. This
allows better vectorization further downstream, since the operation
can be converted to a simple max reduction when the `indices` result
is not used. See: https://github.com/iree-org/iree/issues/10666.
2022-10-05 18:22:59 -07:00
Ashay Rane faa9a78e38
build: update llvm tag to 6f46ff37 (#1448)
Summary of changes:
 - Updated references to the Arith dialect
   (https://reviews.llvm.org/D134762)
 - Switched to prefixed accessors for MemRef dialect
   (https://reviews.llvm.org/D134995)
 - Fixed warnings about signed/unsigned comparisons, ignored return
   values, and unused variables
2022-10-05 08:28:06 -05:00
Prashant Kumar 6777a9484d [LINALG] Add lowering for the aten.upsample_nearest2d op. 2022-10-04 17:20:29 +05:30
AmosLewis 940959589b [MLIR][TORCH] Add Byte and Char Dtype support 2022-09-30 13:19:31 +05:30
JakopinA 8ef0c874c2
Implement Expand/Collapse Functionality for Aten.View (#1353) 2022-09-27 11:08:14 -07:00
Quinn Dawkins 53bf09ceef
Fix iterator types for embedding bag sum mode (#1371) 2022-09-23 13:13:47 -04:00
Vivek Khandelwal e35741fb1d [MLIR][TORCH] Add E2E support for aten.bitwise_not op
This commit adds lowering of `aten.bitwise_not` op.

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-09-08 17:52:12 +05:30
Vivek Khandelwal c19fccfca2 [MLIR][TORCH] Add E2E support for aten.pow.Tensor_Tensor op
This commit adds lowering of `aten.pow.Tensor_Tensor` op.

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-09-08 10:01:42 +05:30
武家伟 6a1893a517
[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
Gaurav Shukla 99093d0623 [TORCH] Add decomposition of `aten.linear` op
This commit adds decomposition of `aten.linear` op. Due to limited
support at tosa backend in case of dynamic dimensions, this
decomposition is currently disabled for tosa backend.

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2022-09-07 16:58:27 +05:30
Quinn Dawkins cc86cc0f02
Revert "Implement Non-Expand/Collapse Functionality for Aten.View (#1309)" (#1347)
Reverting commit a6a48ba233 to revise unit tests and address dynamic shape handling based on comments in #1309
2022-09-07 01:38:11 -04:00
JakopinA a6a48ba233
Implement Non-Expand/Collapse Functionality for Aten.View (#1309)
Focuses on statically sized cases such as [2, 3] -> [3, 2].
2022-09-06 14:46:04 -04:00
Tanyo Kwok 37f57a9828
Delete ConvertAtenNativeLayerNormOp from TorchToLinalg (#1336)
The ConvertAtenNativeLayerNormOp is delete because we have decomposition already
see https://github.com/llvm/torch-mlir/pull/1332
2022-09-05 10:19:20 +08:00
gpetters94 f012279fa2
Add transposed case for at::convolution (#917)
Also adds a decomposition for aten::conv_transposed2d.input
2022-08-24 12:19:35 -04:00
Vivek Khandelwal 65d811e267 [MLIR][TORCH] Fix dynamic cases for aten.index.Tensor 2022-08-19 12:13:20 +05:30
nithinsubbiah fde390c766 Re-enable custom op support 2022-08-16 22:49:08 +05:30
Ashay Rane 84d345c650
build: update llvm tag to 2dde4ba6 (#1229)
Summary of changes:
 - Tensor dialect now sets `emitAccessorPrefix` to prefixed, thus
   requring updates to methods that retrieve arguments
   [https://reviews.llvm.org/D131361]
 - Update MHLO to build with LLVM commit hash 2dde4ba6
 - Replace `AbsOp` with `AbsFOp` [https://reviews.llvm.org/D131325]
 - Replace deprecated `getValue()` with `value()`
   [https://reviews.llvm.org/D131349]
 - Remove `AnalysisState::defaultInitialize()`
   [https://reviews.llvm.org/D131746]
 - Update MHLO MLIR tests to use the updated assembly format
 - Disabled two failing TOSA tests (Github Issue link:
   https://github.com/llvm/torch-mlir/issues/1231)
2022-08-15 23:54:45 -07:00
Ramiro Leal-Cavazos 9d6ee48661
Fix unused-variables warnings about EmbeddingBag ops (#1220)
According to the documentation for
`torch.embedding_bag` (https://pytorch.org/docs/stable/generated/torch.nn.functional.embedding_bag.html),
the default value for `scale_grad_by_freq` is False.
2022-08-15 09:43:55 -07:00
Prashant Kumar b1a506624c Add decomposition of `aten.masked.tensor` op.
`aten.masked.tensor` op has been decomposed to `aten.masked.scalar` op.
2022-08-11 07:48:04 +05:30
Vidush Singhal dd2da5a038
E2E support for AtenRemainderScalarOp (#1200) 2022-08-10 20:02:06 -04:00
powderluv e55fc4deb5
Revert "E2E support for AtenRemainderScalarOp (#1119)" (#1190)
This reverts commit 34e207eeb5.
2022-08-08 22:59:57 -07:00
Ashay Rane bb47c166a0
llvm: update tag to 061e0189 (#1180)
Summary of changes:
 - Switch to C++17 (similar to https://reviews.llvm.org/D131348)
 - Update MHLO to build with LLVM commit hash 061e0189
 - Replace deprecated `hasValue()` and `getValue()` with `has_value()`
   and `value()` respectively (https://reviews.llvm.org/D131349)
 - Use `TypedAttr` (https://reviews.llvm.org/D130092)
 - Use updated assembly format of `mhlo.compare` op (commit
   d03ef01e70fbf9afd0fa1976fbb7ed31838929b3 in MHLO repo)
2022-08-08 20:17:35 -07:00
Vidush Singhal 34e207eeb5
E2E support for AtenRemainderScalarOp (#1119)
* E2E support for AtenRemainderScalarOp
2022-08-08 20:02:52 -04:00
gpetters94 08fc2d89bb
Add non-unit groups support to aten.convolution (#858) 2022-08-04 02:18:38 -04:00
Quinn Dawkins 38d8498b21
add e2e support for aten.atan2 (#1117)
- Includes math-to-libm pass in refbackend for math::atan2 support
2022-08-02 11:39:41 -04:00
Vidush Singhal ed13ebfd8d
E2E support for AtenEmbeddingBagPaddingIdxOp SUM Mode (#1066) 2022-08-01 16:44:11 -04:00
Vivek Khandelwal c681c3497a [MLIR][TORCH} Fix empty dim cases for the .dim ops
This commit fixes the shape calculation for:
1.) aten.mean.dim
2.) aten.var.dim
3.) aten.sum.dim_IntList op

Also, it fixes the lowering of `aten.mean.dim` and
`aten.sum.dim_IntList` for handling the cases of empty dim list.

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com
2022-07-29 11:08:57 +05:30
Quinn Dawkins 11a8901078
[MLIR][TORCH] Add support for multiple indexing tensors for aten.index.Tensor (#1097)
- Includes a canonicalizer for `aten.add.t`needed for successfully lowering the shape function
 - Only offers support for statically sized index tensors when there is more than one
 - Dynamic shape support remains for single indexing tensors
2022-07-28 19:00:02 -04:00
Quinn Dawkins 3c9addf19c Add e2e support for aten.expm1 2022-07-27 12:31:35 +05:30
Kevin Kiningham e8f327cc00 Add lowering to linalg for softplus and log1p
Follows existing conventions for unary operators.
2022-07-25 21:25:57 +05:30
Quinn Dawkins 647e75e029
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
2022-07-20 17:35:51 -04:00
Quinn Dawkins c73a39e40a Add support for index.Tensor on dimensions other than the first
This patch still only supports a single indexing tensor.
2022-07-19 11:36:52 +05:30
Vivek Khandelwal df0b1e77a4 [MLIR][TORCH] Add negative dim support for aten.cat and aten.slice op
This commit adds the support for negative dim cases for `aten.cat`,
`aten.slice.Tensor` and `aten.slice_scatter` op.

Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
2022-07-18 14:01:33 +05:30
Ramiro Leal-Cavazos afdaa60dd4
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.
2022-07-15 09:35:59 -07:00