fb819c1de8
[MLIR][MHLO] Apply patterns in MoveUpDynamicBroadcastsForFusionPass greedily
...
PiperOrigin-RevId: 365556488
2021-03-29 06:02:06 -07:00
238c1d8a92
Integrate LLVM at llvm/llvm-project@594e0ba969
...
Updates LLVM usage to match
[594e0ba96967](https://github.com/llvm/llvm-project/commit/594e0ba96967 )
PiperOrigin-RevId: 365282704
2021-03-26 16:45:20 -07:00
9b7479f907
Integrate LLVM at llvm/llvm-project@4157a079af
...
Updates LLVM usage to match
[4157a079afbf](https://github.com/llvm/llvm-project/commit/4157a079afbf )
PiperOrigin-RevId: 365150758
2021-03-25 16:39:37 -07:00
a2b6060c0c
Add folder for HLO NotOp
...
PiperOrigin-RevId: 364989658
2021-03-25 02:08:38 -07:00
cbef26c6a8
Integrate LLVM at llvm/llvm-project@1f6a57c1a0
...
Updates LLVM usage to match
[1f6a57c1a0fa](https://github.com/llvm/llvm-project/commit/1f6a57c1a0fa )
PiperOrigin-RevId: 364804812
2021-03-24 08:11:34 -07:00
52d1744285
Integrate LLVM at llvm/llvm-project@3e0ad11543
...
Updates LLVM usage to match
[3e0ad1154396](https://github.com/llvm/llvm-project/commit/3e0ad1154396 )
PiperOrigin-RevId: 364790509
2021-03-24 06:45:22 -07:00
a34aa699f8
Fix tanh lowering for NaN input.
...
If the input is NaN, the result should be NaN, too.
PiperOrigin-RevId: 364788902
2021-03-24 06:34:36 -07:00
7dd0fe4592
Integrate LLVM at llvm/llvm-project@d709dcc090
...
Updates LLVM usage to match
[d709dcc09097](https://github.com/llvm/llvm-project/commit/d709dcc09097 )
PiperOrigin-RevId: 364688656
2021-03-23 17:58:45 -07:00
7f2bf48b8b
Integrate LLVM at llvm/llvm-project@b24436ac96
...
Updates LLVM usage to match
[b24436ac96bd](https://github.com/llvm/llvm-project/commit/b24436ac96bd )
PiperOrigin-RevId: 364615807
2021-03-23 12:20:17 -07:00
8987dfd1d6
[MLIR][HLO] Move broadcasts over n-ary shape-preserving ops
...
This will open up more fusion opportunities.
PiperOrigin-RevId: 364577231
2021-03-23 09:38:39 -07:00
5bc4bf0834
Integrate LLVM at llvm/llvm-project@0776eca7a4
...
Updates LLVM usage to match
[0776eca7a4e7](https://github.com/llvm/llvm-project/commit/0776eca7a4e7 )
PiperOrigin-RevId: 364552759
2021-03-23 07:26:28 -07:00
618223778d
Integrate LLVM at llvm/llvm-project@5657f93e78
...
Updates LLVM usage to match
[5657f93e788f](https://github.com/llvm/llvm-project/commit/5657f93e788f )
PiperOrigin-RevId: 364541987
2021-03-23 06:15:46 -07:00
1a6483e229
Integrate LLVM at llvm/llvm-project@e990fa2170
...
Updates LLVM usage to match
[e990fa217031](https://github.com/llvm/llvm-project/commit/e990fa217031 )
PiperOrigin-RevId: 364529739
2021-03-23 04:39:42 -07:00
54f37abc28
[MHLO] Move broadcasts over elementwise ops
...
Move up dynamic broadcasts and shape computations to allow for more fusion
opportunities.
PiperOrigin-RevId: 364514158
2021-03-23 02:34:41 -07:00
98debb127d
Update Tensorflow to prepare for changing the default value of `preloadDialectsInContext`
...
This makes tf-opt more strict on the dialect dependencies, and immediately reduces
the number of dialects loaded.
The canonicalization of TensorFlow graphs showed on the profile that Linalg pattern
were dominated the time, which is unexpected since Linalg is not even intended to be
used there.
PiperOrigin-RevId: 364087027
2021-03-20 11:01:55 -07:00
431be0e9b2
Integrate LLVM at llvm/llvm-project@cd442157cf
...
Updates LLVM usage to match
[cd442157cff4](https://github.com/llvm/llvm-project/commit/cd442157cff4 )
PiperOrigin-RevId: 363873565
2021-03-19 05:55:54 -07:00
59fa7c0ef7
[MHLO:linalg] Lower all dynamic broadcasts of static shapes to linalg.generic
...
We only need the memref_reinterpret_cast if we don't know whether a dimension
gets expanded or not. With static shapes we know that a dimension can only be
expanded if it's a static 1, so lower it in the same way we lower fully
static broadcasts.
PiperOrigin-RevId: 363859181
2021-03-19 03:52:02 -07:00
22b27dbaa2
Integrate LLVM at llvm/llvm-project@628f5c9da2
...
Updates LLVM usage to match
[628f5c9da29b](https://github.com/llvm/llvm-project/commit/628f5c9da29b )
PiperOrigin-RevId: 363858631
2021-03-19 03:46:45 -07:00
dc3dbb9d17
Integrate LLVM at llvm/llvm-project@80df56f7f9
...
Updates LLVM usage to match
[80df56f7f9ef](https://github.com/llvm/llvm-project/commit/80df56f7f9ef )
PiperOrigin-RevId: 363843825
2021-03-19 01:35:15 -07:00
a26e227b46
Integrate LLVM at llvm/llvm-project@16c30c3c23
...
Updates LLVM usage to match
[16c30c3c23ef](https://github.com/llvm/llvm-project/commit/16c30c3c23ef )
PiperOrigin-RevId: 363806028
2021-03-18 20:16:47 -07:00
76d61d4d51
Integrate LLVM at llvm/llvm-project@078b338ba6
...
Updates LLVM usage to match
[078b338ba67a](https://github.com/llvm/llvm-project/commit/078b338ba67a )
PiperOrigin-RevId: 363661770
2021-03-18 08:26:26 -07:00
8ac890d531
Integrate LLVM at llvm/llvm-project@388fbefb4f
...
Updates LLVM usage to match
[388fbefb4f2a](https://github.com/llvm/llvm-project/commit/388fbefb4f2a )
PiperOrigin-RevId: 363641472
2021-03-18 06:11:13 -07:00
0c4a89e52c
[MLIR][MHLO] Implement shape reification for `dynamic_broadcast_in_dim`
...
PiperOrigin-RevId: 363622714
2021-03-18 03:39:15 -07:00
aad6d39952
Integrate LLVM at llvm/llvm-project@0604e0bc68
...
Updates LLVM usage to match
[0604e0bc683e](https://github.com/llvm/llvm-project/commit/0604e0bc683e )
PiperOrigin-RevId: 363601445
2021-03-18 00:52:33 -07:00
f7464dfa62
Integrate LLVM at llvm/llvm-project@2416f24363
...
Updates LLVM usage to match
[2416f2436334](https://github.com/llvm/llvm-project/commit/2416f2436334 )
PiperOrigin-RevId: 363568447
2021-03-17 20:22:14 -07:00
f5c9955056
Integrate LLVM at llvm/llvm-project@ecfa874531
...
Updates LLVM usage to match
[ecfa87453113](https://github.com/llvm/llvm-project/commit/ecfa87453113 )
PiperOrigin-RevId: 363495160
2021-03-17 13:33:18 -07:00
f1408e791e
[MLIR][HLO] Add `Elementwise` trait to unary element-wise ops
...
PiperOrigin-RevId: 363428909
2021-03-17 08:51:17 -07:00
cd52adb20e
Integrate LLVM at llvm/llvm-project@967b64beb4
...
Updates LLVM usage to match
[967b64beb4bf](https://github.com/llvm/llvm-project/commit/967b64beb4bf )
PiperOrigin-RevId: 363410962
2021-03-17 07:05:09 -07:00
2e0ee7759b
Add support for lowering mhlo.torch_index_select to Linalg on tensors.
...
The change upstreams the pattern from IREE repo to MHLO repo.
PiperOrigin-RevId: 363406294
2021-03-17 06:33:41 -07:00
1336c95920
Integrate LLVM at llvm/llvm-project@506df1bbfd
...
Updates LLVM usage to match
[506df1bbfd16](https://github.com/llvm/llvm-project/commit/506df1bbfd16 )
PiperOrigin-RevId: 363377317
2021-03-17 02:51:58 -07:00
a58e62590e
Restrict canonicalization to avoid changing type
...
Issue #47516
PiperOrigin-RevId: 363300979
2021-03-16 16:54:05 -07:00
caae2525ef
Integrate LLVM at llvm/llvm-project@85ab413b53
...
Updates LLVM usage to match
[85ab413b53ae](https://github.com/llvm/llvm-project/commit/85ab413b53ae )
PiperOrigin-RevId: 363298500
2021-03-16 16:42:27 -07:00
c54527fe88
Integrate LLVM at llvm/llvm-project@678241795c
...
Updates LLVM usage to match
[678241795c95](https://github.com/llvm/llvm-project/commit/678241795c95 )
PiperOrigin-RevId: 363257913
2021-03-16 13:33:00 -07:00
2be112a603
[MLIR][MHLO] Approximate `tf.Tanh` as constant +/-1 for small/large values
...
Fix issue raised in https://github.com/tensorflow/tensorflow/issues/47724
PiperOrigin-RevId: 363210296
2021-03-16 10:14:30 -07:00
3de2024a9b
Avoid creating tuple type only for verification
...
Make the error message a bit more verbose & it is cheaper to verify the elements rather than creating a (potentially) new type.
PiperOrigin-RevId: 363073909
2021-03-15 17:58:19 -07:00
01d729d35d
Integrate LLVM at llvm/llvm-project@6878be5dc3
...
Updates LLVM usage to match
[6878be5dc3ec](https://github.com/llvm/llvm-project/commit/6878be5dc3ec )
PiperOrigin-RevId: 362984365
2021-03-15 11:14:24 -07:00
570d29d643
Integrate LLVM at llvm/llvm-project@e9e788d145
...
Updates LLVM usage to match
[e9e788d145f5](https://github.com/llvm/llvm-project/commit/e9e788d145f5 )
PiperOrigin-RevId: 362834717
2021-03-14 16:16:45 -07:00
d16860d26d
[MLIR] Change LMHLO Conditional and While to capture needed buffers, instead of passing them by operands.
...
This is consistent with the design of LMHLO FusionOp, and it simplifies the
usage. Before the change, those redundant operands ended up unused as all sub-regions can already capture needed buffers.
PiperOrigin-RevId: 362381155
2021-03-11 14:42:41 -08:00
8066794eea
Integrate LLVM at llvm/llvm-project@720a828045
...
Updates LLVM usage to match
[720a828045e1](https://github.com/llvm/llvm-project/commit/720a828045e1 )
PiperOrigin-RevId: 362375825
2021-03-11 14:18:36 -08:00
4f5e1c51dd
Add support for lowering NHWC pooling mhlo.reduce_window to Linalg on tensors.
...
The change upstreams the pattern from IREE repo to MHLO repo.
PiperOrigin-RevId: 362312573
2021-03-11 09:41:34 -08:00
630cabefb0
Add support for lowering 2D depthwise mhlo.conv to Linalg on tensors.
...
The change upstreams the pattern from IREE repo to MHLO repo.
PiperOrigin-RevId: 362300550
2021-03-11 08:41:38 -08:00
94f9740c67
[MLIR][HLO:Linalg] Lower mhlo.dynamic_iota to indexed_generic
...
This is the same as iota, but instead of taking the dimensions from the result
tensor we use the supplied shape extents tensor.
PiperOrigin-RevId: 362298548
2021-03-11 08:31:29 -08:00
09f8046816
[MLIR:HLO:LINALG] Fix codegen for mhlo.reshape when one side is rank 0
...
This is an annoying edge case because the collapse->expand lowering expects at
least R1 or it will produce invalid linalg reshapes. Using the direct lowering
works fine.
PiperOrigin-RevId: 362269199
2021-03-11 05:29:56 -08:00
d77b556822
[MLIR][MHLO] Allow recursion in the shape_of mover
...
This allows it to push shape_of over a chain of ops all the way to the top.
PiperOrigin-RevId: 362249009
2021-03-11 02:52:21 -08:00
67a770e4e0
[HLO:MLIR] Make binary op type reification emit shape_of instead of tensor ops
...
This gives cleaner code and allows shape optimizations to happen on the result.
PiperOrigin-RevId: 362242975
2021-03-11 02:01:35 -08:00
9902e6ee32
[HLO] Add LMHLO CollectivePermute verification.
...
- Extract verification of source target pairs attached to collective permute into a common
helper function and use that to verify both MHLO and LMHLO variants.
- Change MlirGpuTestBase::ParseMlirModule to allow returning back a failure, and use
that to update the mlir_gpu_compile_test to check the new behavior.
PiperOrigin-RevId: 362156962
2021-03-10 15:37:12 -08:00
4f16b10ce2
Integrate LLVM at llvm/llvm-project@4c973ae51b
...
Updates LLVM usage to match
[4c973ae51b85](https://github.com/llvm/llvm-project/commit/4c973ae51b85 )
PiperOrigin-RevId: 362116801
2021-03-10 12:36:24 -08:00
b212bd66ae
Build fix for missing precision_config.
...
THe conversion from dot_general to dot fails when trying to retrieve
and use the precision config, since precision_config is optional.
PiperOrigin-RevId: 362095296
2021-03-10 11:10:51 -08:00
e199df1dbf
[MLIR][MHLO] Declare `shape_of` dynamically legal in move-up-dynamic-broadcasts
...
This allows shape reification to produce `shape_of` ops while they can still be
moved up.
PiperOrigin-RevId: 362075609
2021-03-10 09:59:17 -08:00
c217a6ef61
[MHLO] Add pass to move up dynamic broadcasts for fusion
...
For now, the pass only reifies the required shape computations. Moving
broadcasts will follow to allow for fusion across them.
PiperOrigin-RevId: 362033715
2021-03-10 06:21:57 -08:00
A. Unique TensorFlower
Geoffrey Martin-Noble
Adrian Kuegel
Stella Laurenzo
Mehdi Amini
Benjamin Kramer
Hanhan Wang
Jacques Pienaar
Tim Shen
Rahul Joshi
Mahesh Ravishankar