Ecosyste.ms: OpenCollective
An open API service for software projects hosted on Open Collective.
github.com/llvm/torch-mlir
The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.
https://github.com/llvm/torch-mlir
454fa9d12338b289805d295a934a076aaf460e88 authored over 2 years ago by Anup Gangwar <[email protected]>
The added e2e maxpool testcase from #545 was not getting a static shape
due to an unfolded prim....
e1b3e5bc92decafc7d99cd093e47ec909c62d0fa authored over 2 years ago by Yi Zhang <[email protected]>
* external/llvm-project 881ff4e4ebe8...84fe34a0b7fd (466):
> [MLIR] Workaround for python det...
* [tosa] Support for AtenBatchNormOp
Signed-off-by: Anup Gangwar <[email protected]>
Co...
7a5736facd37a7cd9de197074491d20ec714934d authored over 2 years ago by Anup Gangwar <[email protected]>
This commit adds a test module specifically for table batch embedding
algorithm. This test case ...
Signed-off-by: Suraj Sudhir <[email protected]>
eb06d21765acc78dc68f8fcdd54223e3082aa271 authored over 2 years ago by Suraj Sudhir <[email protected]>3fd9b7789e55c3a2692389f2345acee1411fa1b9 authored over 2 years ago by stephenneuendorffer <[email protected]>
17a4843cf766e2d041ef8239f198ff45e938ac04 authored over 2 years ago by Nirvedh <[email protected]>
Refactor matmul into separate class and derive variants:
- matmul
- mm, bmm
- linear
Signe...
cadea678e5e2cfc62a1625af6e50cac34144e710 authored over 2 years ago by Suraj Sudhir <[email protected]>ad4b9e036992cfc09ea071da2a709466bbc49ca6 authored over 2 years ago by Yi Zhang <[email protected]>
* [tosa] Support for AtenCeilOp and AtenReciprocalOp
* [tosa] Support for comparator ops, Aten[...
In addition, use add_llvm_executable so that the relative rpath of
the installed binaries is se...
76728491cbefc8469a9a7bd467d783b5402461da authored over 2 years ago by Sean Silva <[email protected]>
Signed-off-by: Suraj Sudhir <[email protected]>
5d6c4f48dcdc64a09fdd338170d04a95a60b4386 authored over 2 years ago by Suraj Sudhir <[email protected]>This commit adds lowering of `aten.index.Tensor` op
Signed-Off By: Vivek Khandelwal <vivek@nod-...
6fe70c77948753bc2d3bd97855b276f3cb2b96fb authored over 2 years ago by Vivek Khandelwal <[email protected]>- Also handles braodcasting n-D tensors, dynamic shapes
Signed-off-by: Suraj Sudhir <suraj.su...
0188ca549879b76120b7075955f4978d710442b8 authored over 2 years ago by Suraj Sudhir <[email protected]>This reverts commit c9a343267c863186d5127fb8e38a76f62a53e2ac.
40efd2cb8e7b8160db106c97175001d2f5fc8931 authored over 2 years ago by Yi Zhang <[email protected]>
- Add `qualified` to ods because of
https://reviews.llvm.org/D113873 and https://reviews.llvm.or...
- Common code as TF repository, being moved to MLIR core.
- Will support further legalizations ...
Signed-off-by: Suraj Sudhir <[email protected]>
5ded7d096f7d4504044ce15950f1f0f0e97cf174 authored almost 3 years ago by Suraj Sudhir <[email protected]>
This commit adds the aten ops which do not require random number
support to aten dialect. This c...
disable ElementwisePowModule_basic
* Update nll_loss_forward to align to the change in PyTorch
...
Signed-off-by: Anup Gangwar <[email protected]>
d69d29b7a65b7fa6a46c8cf49efeaabad4ecbb94 authored almost 3 years ago by Anup Gangwar <[email protected]>
Note that to enable folding of the code coming from an example
like the ConstantPad2dStaticModul...
This commit adds support for two return values of type
memref f32 and i64.
Signed-Off By: Vivek ...
35cf8d18f749c91e396ae0c4674208eaaea7c866 authored almost 3 years ago by Vivek Khandelwal <[email protected]>This commit adds lowering of `aten.threshold` op
This commit adds lowering of `aten.threshold_bac...
The element type of tensor literal should be signless when converted to
builtin tensor types.
Signed-off-by: Suraj Sudhir <[email protected]>
d6b6c0268cfd6ead0aa5f2f21ba02bbe8ead3180 authored almost 3 years ago by Suraj Sudhir <[email protected]>
This involes the following 2 parts:
- Change refine type to propagate more static shape info.
- ...
Templated variants for squeeze and squeeze.dim
b4842d98638d192833f3aaa360eb9a3181b40091 authored almost 3 years ago by Suraj Sudhir <[email protected]>
- This commit adds E2E support for `aten.ones_like` and
`aten.zeros_like` ops.
- Adds support ...
This commit adds include statements of the file
`torch/csrc/jit/ir/ir.h` for files that use type...
ccfdfd1b808b19b738306c8acc0a69d7d6e285a4 authored almost 3 years ago by Liam Fitzpatrick <[email protected]>
This commit adds lowering of `aten.arange.start_step` op.
This commit decomposes `aten.arange` an...
- It folds `aten.to.dtype` when the input tensor type and result type
are exactly same.
- It f...
`aten.add.Scalar` and `aten.sub.Scalar` op conversions have been added.
The changes have been ma...
3cb46cecefa9512e4a413e892cf7a86813fdb9cb authored almost 3 years ago by Nirvedh <[email protected]>
5eed562e19916ba178f5e8836898ef2d8615e1aa authored almost 3 years ago by xndcn <[email protected]>
We only handle the expanding OR collapsing cases, we do not handle
expanding And collapsing happ...
This commit adds decomposition of `aten.empty_like` into `aten.empty`
op.
Signed-Off-by: Gaurav...
bc9abbc1c97ed9c66768bf9d7675323732f27826 authored almost 3 years ago by Gaurav Shukla <[email protected]>
- Added E2E support for `aten.eq.Tensor` and `aten.lt.Tensor` ops. Both
the operands are expec...
0cd95b5c6888fa6b09242d2ac909f1db61c43daa authored almost 3 years ago by Suraj Sudhir <[email protected]>
396ab35c9d29b14dc2a55406edaa29d06a8c68fc authored almost 3 years ago by Daniel Garvey <[email protected]>
Signed-off-by: Anup Gangwar <[email protected]>
a6c3050dd0d4a4ac05f8f7dbaf949381055fc616 authored almost 3 years ago by Anup Gangwar <[email protected]>
This commit fixes the naming of results in the torch ODS generator
when dealing with multiple re...
Signed-off-by: Suraj Sudhir <[email protected]>
829cf8afc34e5a0d0138d3c71d4b371dd7e8c9f4 authored almost 3 years ago by Suraj Sudhir <[email protected]>
The existing implementation of `ConvertConstantTensorAllocOp<>` requires
a C++17 feature `if con...
Add the required lowerings and correct test cases.
These op produce zero-d tensors and it was in...
Signed-off-by: Anup Gangwar <[email protected]>
Co-authored-by: Anup Gangwar <anup.gangwar...
cce490d71d79d41c7652d4d1e8d2d36d7c302a37 authored almost 3 years ago by Anup Gangwar <[email protected]>
Support for integer types in gtScalar op has been added.
The code share same logic with gtTensor...
- Templatize `aten.zeros` and `aten.ones` ops lowering.
- Add E2E support for `aten.empty` op.
-...
`aten.gt.Tensor` op has been added in torch dialect and the
lowering of the op has been done to ...
This commit adds lowering of `aten.ceil` op as a part of element-wise
ops lowering.
Signed-Off-...
a778f990e97de355af4be33d92dbb8cf77cffa19 authored almost 3 years ago by Gaurav Shukla <[email protected]>
This patch adds the where, gt, bucketize and reshape
ops to the Torch dialect. These ops are pre...
This commit adds support for aten.native_layer_norm operation. Here
the previous code for aten....
This commit adds lowering of `aten.squeeze.dim` op into
`linalg.TensorCollapseShape` op. Here, t...
This commit adds lowering of `aten.index_select` op.
Signed-Off By: Vivek Khandelwal <vivek@nod-...
8130354c0903dcd6323bb54564f3ffddf061a658 authored almost 3 years ago by Vivek Khandelwal <[email protected]>https://github.com/llvm/torch-mlir/pull/464#discussion_r765065092
Signed-Off By: Vivek Khandelw...
0a0a1b4476ffe1ab59d7b39cf91650c4f68c6caa authored almost 3 years ago by Vivek Khandelwal <[email protected]>
This commit adds lowering of `aten.gt.Scalar` and `aten.where.self` as a
part of element-wise op...
Previously aten.conv2d was only lowered if there was no bias.
Here lowering is extended to suppo...
Support for passing memref of bool types as a function argument
and return is added in ref-backe...
This commit adds lowering of `aten.zeros` op.
Signed-Off By: Vivek Khandelwal <[email protected]>
9958cf08b6fbde00079e41cf08d474d6b6792ec1 authored almost 3 years ago by Vivek Khandelwal <[email protected]>
The op lowering has been added as a part of `torch-lower-to-linalg`
pass. This takes care of ign...
The external llvm is updated to point to
https://reviews.llvm.org/rG966b72098363d44adf2882b9c34f...
b0cb49ca93fbd2dc66983f3e192d9a90d33a6a3a authored almost 3 years ago by Daniel Garvey <[email protected]>
- Supports variants with multiple dims, one dim, all dime
- Leverages legalize_common and legali...
There is an op name change that requires trivial changes.
Also, some of the warning has been fix...
24bc06fc8d19ea6da819b0f8a9fd6e562540cd8b authored almost 3 years ago by Yi Zhang <[email protected]>
a52aded0b90918fec8f6367726524a39b0aacfc3 authored almost 3 years ago by Daniel Garvey <[email protected]>
This commit adds lowering of `aten.bitwise_and.tensor` op.
Signed-Off By: Vivek Khandelwal vivek...
46a2189a417100a17659a096a18560a89a34255e authored almost 3 years ago by Vivek Khandelwal <[email protected]>This commit adds lowering of `aten.mean` and `aten.numel` op.
Signed-Off By: Vivek Khandelwal <...
46a0668b3b59f208c1fddd723a0708a066535feb authored almost 3 years ago by Vivek Khandelwal <[email protected]>5475d02a0d03b2bda7ef9cc240773041d22a926b authored almost 3 years ago by Sean Silva <[email protected]>
Fixes broken e2e test ElementwiseAddModule_basic
Signed-off-by: Suraj Sudhir <suraj.sudhir@arm....
1251c186b553003709c28ce64e7d2d9f808f39e1 authored almost 3 years ago by Suraj Sudhir <[email protected]>
Many reduction ops take as an argument an optional output dtype that
can change the type of the ...
This commit adds lowering of `aten.Squeeze` op into
`linalg.TensorCollapseShape` op. The size 1 ...
9ad5954e41f1734bf03d2c8930db9e912d582c23 authored almost 3 years ago by ds1231h <[email protected]>
This is to fold the common pattern from Bert inference like:
```
%111 = torch.prim.NumToTensor.S...
The lowering of aten.fill.Scalar has been added.
The changes have been made as a part of -torch-...
Co-authored-by: dan <[email protected]>
539511c19b1acef704d8399f814e3a847cc6a719 authored almost 3 years ago by Daniel Garvey <[email protected]>03fdf56f2104c67bbc4a943671202584b62c3fbc authored almost 3 years ago by dan <[email protected]>
7616d28ce1614b3a3649dedb07c89a9d2b385bc4 authored almost 3 years ago by Liam Fitzpatrick <[email protected]>
Signed-Off-By: Prateek Gupta <[email protected]>
f461a7ebcef872b82bdf9ab8ab980a44ca32a4ec authored almost 3 years ago by Prateek Gupta <[email protected]>67ce816fca3398c08940bbe1a41d6487bdaa3071 authored almost 3 years ago by nodlabs <[email protected]>
This commit adds lowering of `aten.div.Scalar`.
Signed-Off By: Vivek Khandelwal <vivek@nod-labs....
8d8d2c2fb881f19e2a0e97dcf354cbd878547f51 authored almost 3 years ago by Vivek Khandelwal <[email protected]>
This commit fixes a type promotion bug when NumToTensor was given a
float as an argument. In par...
Share code in `log_softmax_backward` and `softmax_backward` ops.
1dc374014b4539651fdf36c83b896b93fd5703a5 authored almost 3 years ago by Prashant Kumar <[email protected]>
aten.log_softmax_back_data op lowering and required
tests has been added. Some NFC have also bee...
This commit adds lowering of `aten.mul.Scalar` and also adds
decomposition of `aten.addmm` to `a...
Now, aten::linear supports rank 3 inputs. This is a fix
for upcoming bert-inference task. The co...
This commit adds minor non functional changes to the aten.gelu_backward
operation.
Signed-Off-B...
146f109152385b63310d8215c11dbdef029d8ba7 authored almost 3 years ago by Prateek Gupta <[email protected]>
This commit adds new operation `aten.gelu_backward` in the aten
dialect and adds lowering of th...
This change is to unblock the work of some backprop ops returning more
than one tensors. We will...
6e8d39642e43ab07903bf3ab82f029dca966a171 authored almost 3 years ago by Sean Silva <[email protected]>
Update AsmPrinter/Parser and MatchAndRewrite
53733933a4aaaa1e362481c149c34c7c2e68a4b7 authored almost 3 years ago by Yi Zhang <[email protected]>
This commit fixes a bug with the way ConvertAtenOnesOp was matching on
the pin_memory bool argum...
- Remove use of conversion construction macros
- Add mul and div op conversions
- Add correspo...
Add a bunch of op legalizations.
Signed-off-by: Suraj Sudhir <[email protected]>
1019ddf5a0edc388666bf88cd16d8cbbf9c66d9a authored almost 3 years ago by Suraj Sudhir <[email protected]>
The e2e testing for aten_tanh_backward op has been added.
The testing is done for ref_backend.
2764e86f0244e13f88c55249765a912b409fc256 authored almost 3 years ago by George Petterson <[email protected]>