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
f3295324e1
Integrate LLVM at llvm/llvm-project@000cf84cf1
...
Updates LLVM usage to match
[000cf84cf1bb](https://github.com/llvm/llvm-project/commit/000cf84cf1bb )
PiperOrigin-RevId: 367179026
2021-04-07 02:23:20 -07:00
a62382cf1f
Integrate LLVM at llvm/llvm-project@0e92cbd6a6
...
Updates LLVM usage to match
[0e92cbd6a652](https://github.com/llvm/llvm-project/commit/0e92cbd6a652 )
PiperOrigin-RevId: 367062980
2021-04-06 12:40:51 -07:00
0800423d27
[LMHLO] Simplify FusionOp::getInputBuffers() and friends.
...
- No need to walk the entire region, instead just iterate over the top level operations in
the region attached to the fusion op.
PiperOrigin-RevId: 366528833
2021-04-02 15:55:49 -07:00
38d0f96709
Switch deps AllPassesAndDialectsNoRegistration -> AllPassesAndDialects
...
These targets are now identical as all registration is explicit.
Temporarily leaving the old target as a (deprecated) alias while
changes propagate.
PiperOrigin-RevId: 366513211
2021-04-02 14:26:13 -07:00
c315b07d9c
Integrate LLVM at llvm/llvm-project@8e5f3d04f2
...
Updates LLVM usage to match
[8e5f3d04f269](https://github.com/llvm/llvm-project/commit/8e5f3d04f269 )
PiperOrigin-RevId: 366508804
2021-04-02 14:02:15 -07:00
ad442fd99a
Integrate LLVM at llvm/llvm-project@17800f900d
...
Updates LLVM usage to match
[17800f900dca](https://github.com/llvm/llvm-project/commit/17800f900dca )
PiperOrigin-RevId: 366356934
2021-04-01 16:46:09 -07:00
763ff55970
Restore SingleBlockImplicitTerminator verification to mhlo.while
...
The internal users have been cleaned up, so we can roll this forward again.
PiperOrigin-RevId: 366313960
2021-04-01 13:04:26 -07:00
f1bed7b340
Integrate LLVM at llvm/llvm-project@d61b40ed27
...
Updates LLVM usage to match
[d61b40ed2750](https://github.com/llvm/llvm-project/commit/d61b40ed2750 )
PiperOrigin-RevId: 366288494
2021-04-01 11:05:39 -07:00
ff2cbfa2ec
[MLIR] Add support for representing variadic reduce-window in HLO/LMHLO dialect.
...
- Fixed a subset of transformations to handle variadic reduce-window.
PiperOrigin-RevId: 366278650
2021-04-01 10:24:50 -07:00
d1f697e618
Integrate LLVM at llvm/llvm-project@abbe80fa52
...
Updates LLVM usage to match
[abbe80fa52c5](https://github.com/llvm/llvm-project/commit/abbe80fa52c5 )
PiperOrigin-RevId: 366236030
2021-04-01 05:58:20 -07:00
c23be1841c
[MLIR] Add example test case for `move-up-dynamic-broadcasts-for-fusion` pass
...
Add exemplary test case as it appears in the lowering of two subsequent `tf.Sub`
ops.
PiperOrigin-RevId: 366219139
2021-04-01 03:24:43 -07:00
eb4d20ba04
Integrate LLVM at llvm/llvm-project@e1d4fb1ebf
...
Updates LLVM usage to match
[e1d4fb1ebfff](https://github.com/llvm/llvm-project/commit/e1d4fb1ebfff )
PiperOrigin-RevId: 366207149
2021-04-01 01:51:23 -07:00
f25ef97943
Integrate LLVM at llvm/llvm-project@777a58e05b
...
Updates LLVM usage to match
[777a58e05b22](https://github.com/llvm/llvm-project/commit/777a58e05b22 )
PiperOrigin-RevId: 366149625
2021-03-31 17:18:25 -07:00
7b0a6bfeee
Integrate LLVM at llvm/llvm-project@fcf6800506
...
Updates LLVM usage to match
[fcf680050686](https://github.com/llvm/llvm-project/commit/fcf680050686 )
PiperOrigin-RevId: 366101230
2021-03-31 13:16:11 -07:00
af3bc47a8b
Integrate LLVM at llvm/llvm-project@8396aeb07c
...
Updates LLVM usage to match
[8396aeb07cdd](https://github.com/llvm/llvm-project/commit/8396aeb07cdd )
PiperOrigin-RevId: 366034463
2021-03-31 08:01:34 -07:00
bbe0aa204c
[MLIR][MHLO] Merge assuming ops with compatible witnesses
...
PiperOrigin-RevId: 366018349
2021-03-31 06:11:38 -07:00
c8157ba4df
Move code from helper struct to the only user.
...
We don't need the separate helper struct anymore, because it is now only used
in one place.
PiperOrigin-RevId: 366012639
2021-03-31 05:21:34 -07:00
4033a56750
Add special cases for SelectOp rank specialization.
...
We now use the same special cases for all ops with arity >= 2.
For binary ops, we now have only one special case if at least one of the
operands has exactly one element. In that case, we reshape both operands to
rank 1. Before, we had separate special cases whether the left-hand side
or the right-hand side have a scalar shape.
PiperOrigin-RevId: 366005835
2021-03-31 04:28:51 -07:00
9206805c58
[MLIR][MHLO] Do not yield results of ops that were moved out of assuming regions
...
When an op is moved out of an assuming region we already know statically that it
is independent of the assuming region. Hence, there is no need to yield its
results.
PiperOrigin-RevId: 366001405
2021-03-31 03:50:27 -07:00
8ade5d78c8
[MLIR][MHLO] Move `cstr_broadcastable` and `shape_of` out of `assuming` regions
...
Add pattern to move operations out of assuming op. This only valid for
constraint-independent ops, like `cstr_broadcastable` and `shape_of`. It will
eventually allow to make assuming regions' constraints independent from each
other so that they can be merged.
PiperOrigin-RevId: 365993145
2021-03-31 02:39:07 -07:00
af2aaa6144
Integrate LLVM at llvm/llvm-project@afed50a14b
...
Updates LLVM usage to match
[afed50a14b34](https://github.com/llvm/llvm-project/commit/afed50a14b34 )
PiperOrigin-RevId: 365986449
2021-03-31 01:37:43 -07:00
eade942635
[MLIR][MHLO] Add pattern to move ops into the assuming region
...
This will eventually allow to make assuming regions' constraints independent
from each other.
PiperOrigin-RevId: 365985081
2021-03-31 01:23:31 -07:00
5ec66775d4
Temporarily relax restriction on mhlo.while terminator
...
Some internal tests are failing, so relaxing this restriction
temporarily while we investigate.
PiperOrigin-RevId: 365949611
2021-03-30 19:44:07 -07:00
5d65758e8c
Canonicalize MHLO Case and If Ops with constant conditions
...
ReplaceOpWithRegion was taken directly from ScfOps. We should maybe put that somewhere common in core.
PiperOrigin-RevId: 365936724
2021-03-30 17:58:01 -07:00
2fb2a92c6e
Verify mhlo.if region return types match op
...
This matches the behavior of mhlo.case. Additionally, fix the verification of CaseOp in the case of nested ops with mhlo.return-containing regions.
PiperOrigin-RevId: 365936672
2021-03-30 17:57:20 -07:00
Rahul Joshi
Prashant Kumar
A. Unique TensorFlower
Jacques Pienaar
Hanhan Wang
Alexander Belyaev
Adrian Kuegel
Geoffrey Martin-Noble