49df46893c
Add support for lowering variadic mhlo.reduce op.
...
Also add more lowering for body ops. Some MinOp and MaxOp can be legalized to
SelectOp + CompareOp.
PiperOrigin-RevId: 369891551
2021-04-22 09:50:49 -07:00
2dfea55d0c
Integrate LLVM at llvm/llvm-project@2f69975683
...
Updates LLVM usage to match
[2f69975683f5](https://github.com/llvm/llvm-project/commit/2f69975683f5 )
PiperOrigin-RevId: 369861751
2021-04-22 06:55:00 -07:00
ca672cc0a4
Integrate LLVM at llvm/llvm-project@1a3f88658a
...
Updates LLVM usage to match
[1a3f88658a02](https://github.com/llvm/llvm-project/commit/1a3f88658a02 )
PiperOrigin-RevId: 369789544
2021-04-21 20:22:09 -07:00
a791d9cefc
Integrate LLVM at llvm/llvm-project@4bb60c285c
...
Updates LLVM usage to match
[4bb60c285cb3](https://github.com/llvm/llvm-project/commit/4bb60c285cb3 )
PiperOrigin-RevId: 369750761
2021-04-21 15:44:37 -07:00
57d7c94a24
Integrate LLVM at llvm/llvm-project@9430efa18b
...
Updates LLVM usage to match
[9430efa18b02](https://github.com/llvm/llvm-project/commit/9430efa18b02 )
PiperOrigin-RevId: 369706935
2021-04-21 12:15:23 -07:00
4d435a817e
[mhlo:linalg] Add support for lowering mhlo.concatenate to Linalg ops.
...
This uses a indexed linalg.generic, which is rather awkward standalone but
allows fusing into the output of the concatenate and avoid to ever materialize
it in memory. I think this is the only way to get that with the current linalg
stack, fusion across a concatenate would require more infrastructure.
PiperOrigin-RevId: 369677652
2021-04-21 10:01:08 -07:00
c5302511f0
Integrate LLVM at llvm/llvm-project@e0adf7e06a
...
Updates LLVM usage to match
[e0adf7e06a9e](https://github.com/llvm/llvm-project/commit/e0adf7e06a9e )
PiperOrigin-RevId: 369646018
2021-04-21 06:55:33 -07:00
a76445839c
Integrate LLVM at llvm/llvm-project@01ace074fc
...
Updates LLVM usage to match
[01ace074fcb6](https://github.com/llvm/llvm-project/commit/01ace074fcb6 )
PiperOrigin-RevId: 369621404
2021-04-21 03:19:58 -07:00
dedf76105e
Integrate LLVM at llvm/llvm-project@aa80ea8a61
...
Updates LLVM usage to match
[aa80ea8a617b](https://github.com/llvm/llvm-project/commit/aa80ea8a617b )
PiperOrigin-RevId: 369605459
2021-04-21 01:14:39 -07:00
87e7d9f9eb
Integrate LLVM at llvm/llvm-project@fb69b92c7b
...
Updates LLVM usage to match
[fb69b92c7b33](https://github.com/llvm/llvm-project/commit/fb69b92c7b33 )
PiperOrigin-RevId: 369590351
2021-04-20 22:58:57 -07:00
200957ec54
Integrate LLVM at llvm/llvm-project@f549176ad9
...
Updates LLVM usage to match
[f549176ad976](https://github.com/llvm/llvm-project/commit/f549176ad976 )
PiperOrigin-RevId: 369568340
2021-04-20 19:19:59 -07:00
8db96f54d3
[mhlo] Add a folder for mhlo.map which does nothing but return one of the arguments.
...
Add a folder for maps whose body returns only one of the arguments. When this arises the fold replaces the map output with one of the operand tensors.
PiperOrigin-RevId: 369304322
2021-04-19 14:36:08 -07:00
9374a1c0c5
[MLIR] Fix merge of assuming ops
...
Assuming ops can only be merged if their witnesses will dominate the merged
assuming op. This is not the case if the second op's witness is a result of the
first.
PiperOrigin-RevId: 369192868
2021-04-19 04:21:08 -07:00
0bb866a799
Integrate LLVM at llvm/llvm-project@80e166f81a
...
Updates LLVM usage to match
[80e166f81abd](https://github.com/llvm/llvm-project/commit/80e166f81abd )
PiperOrigin-RevId: 369176305
2021-04-19 02:08:50 -07:00
411ee907e3
Integrate LLVM at llvm/llvm-project@517c3aee4d
...
Updates LLVM usage to match
[517c3aee4de5](https://github.com/llvm/llvm-project/commit/517c3aee4de5 )
PiperOrigin-RevId: 369017690
2021-04-17 09:50:27 -07:00
d938913704
Integrate LLVM at llvm/llvm-project@bb907b26e2
...
Updates LLVM usage to match
[bb907b26e2bf](https://github.com/llvm/llvm-project/commit/bb907b26e2bf )
PiperOrigin-RevId: 368850216
2021-04-16 08:21:21 -07:00
216447323a
Integrate LLVM at llvm/llvm-project@3bc88eb392
...
Updates LLVM usage to match
[3bc88eb3924f](https://github.com/llvm/llvm-project/commit/3bc88eb3924f )
PiperOrigin-RevId: 368828718
2021-04-16 05:33:26 -07:00
4f8c0e6066
Integrate LLVM at llvm/llvm-project@3f97c66b00
...
Updates LLVM usage to match
[3f97c66b0040](https://github.com/llvm/llvm-project/commit/3f97c66b0040 )
PiperOrigin-RevId: 368763888
2021-04-15 19:22:44 -07:00
b1435bff87
Integrate LLVM at llvm/llvm-project@f28cb01be0
...
Updates LLVM usage to match
[f28cb01be071](https://github.com/llvm/llvm-project/commit/f28cb01be071 )
PiperOrigin-RevId: 368712932
2021-04-15 14:02:42 -07:00
a16b4f17e0
Integrate LLVM at llvm/llvm-project@93f54fae9d
...
Updates LLVM usage to match
[93f54fae9dda](https://github.com/llvm/llvm-project/commit/93f54fae9dda )
PiperOrigin-RevId: 368656637
2021-04-15 09:38:07 -07:00
0dcbe56bd7
Integrate LLVM at llvm/llvm-project@49cbf4cd85
...
Updates LLVM usage to match
[49cbf4cd85a9](https://github.com/llvm/llvm-project/commit/49cbf4cd85a9 )
PiperOrigin-RevId: 368630894
2021-04-15 06:59:31 -07:00
2589ffe49f
Integrate LLVM at llvm/llvm-project@71a45e7c63
...
Updates LLVM usage to match
[71a45e7c6328](https://github.com/llvm/llvm-project/commit/71a45e7c6328 )
PiperOrigin-RevId: 368611924
2021-04-15 04:11:17 -07:00
3b3a61377e
Integrate LLVM at llvm/llvm-project@c3f1271464
...
Updates LLVM usage to match
[c3f127146415](https://github.com/llvm/llvm-project/commit/c3f127146415 )
PiperOrigin-RevId: 368598603
2021-04-15 02:24:43 -07:00
db9f298505
Generate Equal and NotEqual kernels for complex types.
...
PiperOrigin-RevId: 368586877
2021-04-15 00:35:52 -07:00
bfc8cca38f
Integrate LLVM at llvm/llvm-project@8f9477b067
...
Updates LLVM usage to match
[8f9477b067b0](https://github.com/llvm/llvm-project/commit/8f9477b067b0 )
PiperOrigin-RevId: 368569183
2021-04-14 21:50:44 -07:00
c75cbf4ac7
[MLIR][NFC] Rename ReduceOp operands() => inputs().
...
- Rename to avoid confusion as operands generally includes all operands of an operation
PiperOrigin-RevId: 368479524
2021-04-14 12:08:23 -07:00
236e7db5c0
PR #47315 : [MLIR] Add concatenateOp lowering from lmhlo to Affine.
...
Imported from GitHub PR https://github.com/tensorflow/tensorflow/pull/47315
Lowering of `concatenateOp` is added from lmhlo to Affine. The lowering
has been added as a part of `lhlo-legalize-to-affine` pass.
Signed-off-by: Prashant Kumar <prashantk@polymagelabs.com>
Copybara import of the project:
--
15314e4579f7a6901cf3475eff25962a34772eaf by Prashant Kumar <prashantk@polymagelabs.com>:
[MLIR] Add concatenateOp lowering from lmhlo to Affine.
Lowering of `concatenateOp` is added from lmhlo to Affine. The lowering
has been added as a part of `lhlo-legalize-to-affine` pass.
Signed-off-by: Prashant Kumar <prashantk@polymagelabs.com>
PiperOrigin-RevId: 368465992
2021-04-14 11:06:38 -07:00
c10167d4a8
Integrate LLVM at llvm/llvm-project@c4c9e4d6df
...
Updates LLVM usage to match
[c4c9e4d6df3c](https://github.com/llvm/llvm-project/commit/c4c9e4d6df3c )
PiperOrigin-RevId: 368450496
2021-04-14 09:54:28 -07:00
2db0e6280d
Integrate LLVM at llvm/llvm-project@7975dd033c
...
Updates LLVM usage to match
[7975dd033cb9](https://github.com/llvm/llvm-project/commit/7975dd033cb9 )
PiperOrigin-RevId: 368399684
2021-04-14 04:06:34 -07:00
79c7c48989
Integrate LLVM at llvm/llvm-project@32e264921b
...
Updates LLVM usage to match
[32e264921b7a](https://github.com/llvm/llvm-project/commit/32e264921b7a )
PiperOrigin-RevId: 368352219
2021-04-13 20:55:55 -07:00
fdd75daed6
Add shape function for MHLO RngNormal and RngUniform
...
PiperOrigin-RevId: 368276963
2021-04-13 12:59:42 -07:00
c01e96d095
Integrate LLVM at llvm/llvm-project@dad5caa59e
...
Updates LLVM usage to match
[dad5caa59e6b](https://github.com/llvm/llvm-project/commit/dad5caa59e6b )
PiperOrigin-RevId: 368257770
2021-04-13 11:28:38 -07:00
a3fc99efe0
Add support for lowering mhlo.dynamic_slice to Linalg ops.
...
PiperOrigin-RevId: 368033540
2021-04-12 10:34:55 -07:00
0ec0a23e61
[MLIR][HLO] Generalize merged witnesses in `move-up-dynamic-broadcasts-for-fusion`
...
PiperOrigin-RevId: 368012460
2021-04-12 08:55:29 -07:00
1007995ea2
Integrate LLVM at llvm/llvm-project@5a5a94ed34
...
Updates LLVM usage to match
[5a5a94ed34b0](https://github.com/llvm/llvm-project/commit/5a5a94ed34b0 )
PiperOrigin-RevId: 368012265
2021-04-12 08:53:33 -07:00
7965f7fa79
Integrate LLVM at llvm/llvm-project@67b39661c8
...
Updates LLVM usage to match
[67b39661c847](https://github.com/llvm/llvm-project/commit/67b39661c847 )
PiperOrigin-RevId: 367984223
2021-04-12 05:43:23 -07:00
bc95a4652f
Integrate LLVM at llvm/llvm-project@2dd22da965
...
Updates LLVM usage to match
[2dd22da965ff](https://github.com/llvm/llvm-project/commit/2dd22da965ff )
PiperOrigin-RevId: 367965285
2021-04-12 03:11:45 -07:00
8a9bf05d78
Integrate LLVM at llvm/llvm-project@6ce76ff7eb
...
Updates LLVM usage to match
[6ce76ff7eb76](https://github.com/llvm/llvm-project/commit/6ce76ff7eb76 )
PiperOrigin-RevId: 367678843
2021-04-09 12:11:56 -07:00
6d2209e301
[MLIR][HLO] Canonicalize chained broadcasts
...
Compose two subsequent `dynamic_broadcast_in_dim` ops into one.
PiperOrigin-RevId: 367630360
2021-04-09 07:35:34 -07:00
fdb653788c
Add support for lowering and/or within mhlo.reduce op body.
...
PiperOrigin-RevId: 367627034
2021-04-09 07:09:13 -07:00
2ef77c1c0c
Integrate LLVM at llvm/llvm-project@39ae25fb8c
...
Updates LLVM usage to match
[39ae25fb8c64](https://github.com/llvm/llvm-project/commit/39ae25fb8c64 )
PiperOrigin-RevId: 367597627
2021-04-09 02:35:49 -07:00
768234b077
[NFC] Fix a typo in ScalarLimit comments.
...
PiperOrigin-RevId: 367593932
2021-04-09 01:57:50 -07:00
bf487d51d4
Integrate LLVM at llvm/llvm-project@1b589172bd
...
Updates LLVM usage to match
[1b589172bd19](https://github.com/llvm/llvm-project/commit/1b589172bd19 )
PiperOrigin-RevId: 367482146
2021-04-08 12:23:42 -07:00
39430e04da
Integrate LLVM at llvm/llvm-project@b601c67192
...
Updates LLVM usage to match
[b601c6719226](https://github.com/llvm/llvm-project/commit/b601c6719226 )
PiperOrigin-RevId: 367413533
2021-04-08 05:56:16 -07:00
cc607bc72d
Support up to rank 8 in rank specialization for SelectOp.
...
PiperOrigin-RevId: 367406557
2021-04-08 04:55:41 -07:00
f068d26843
Integrate LLVM at llvm/llvm-project@6e8601ff4a
...
Updates LLVM usage to match
[6e8601ff4ae1](https://github.com/llvm/llvm-project/commit/6e8601ff4ae1 )
PiperOrigin-RevId: 367406032
2021-04-08 04:52:04 -07:00
11c1bc4bd2
Integrate LLVM at llvm/llvm-project@628dda08b8
...
Updates LLVM usage to match
[628dda08b82f](https://github.com/llvm/llvm-project/commit/628dda08b82f )
PiperOrigin-RevId: 367238750
2021-04-07 09:47:33 -07:00
f003df084b
Integrate LLVM at llvm/llvm-project@c0ef93bec8
...
Updates LLVM usage to match
[c0ef93bec85a](https://github.com/llvm/llvm-project/commit/c0ef93bec85a )
PiperOrigin-RevId: 367215596
2021-04-07 07:30:33 -07:00
c466f08993
Add checks in ReduceWindowOpOnTensorsConversion.
...
The pattern does not support ops with non-zero padding config. Add a check to
prevent unexpected lowering.
It is not easy to add tests because other patterns will convert body ops, and
it causes issues like invalid IRs.
PiperOrigin-RevId: 367202450
2021-04-07 05:46:01 -07:00
c6894333b9
Integrate LLVM at llvm/llvm-project@f37ea62e57
...
Updates LLVM usage to match
[f37ea62e57b5](https://github.com/llvm/llvm-project/commit/f37ea62e57b5 )
PiperOrigin-RevId: 367189460
2021-04-07 03:56:23 -07:00
Hanhan Wang
A. Unique TensorFlower
Benjamin Kramer
Adrian Kuegel
Rahul Joshi
Prashant Kumar
Jacques Pienaar
Alexander Belyaev