colin
/
mlir-hlo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
953 Commits 1 Branch 0 Tags 2.6 MiB
Commit Graph

953 Commits

Author SHA1 Message Date
A. Unique TensorFlower 7629dfdd81 Integrate LLVM at llvm/llvm-project@df6d0579e1 
Updates LLVM usage to match
[df6d0579e18e](https://github.com/llvm/llvm-project/commit/df6d0579e18e)

PiperOrigin-RevId: 361855926
 2021-03-09 11:27:27 -08:00
Benjamin Kramer 5be8be31b5 Integrate LLVM at llvm/llvm-project@3f3f88fb95 
Updates LLVM usage to match
[3f3f88fb9503](https://github.com/llvm/llvm-project/commit/3f3f88fb9503)

PiperOrigin-RevId: 361762801
 2021-03-09 02:19:24 -08:00
A. Unique TensorFlower daf6bde6f5 Integrate LLVM at llvm/llvm-project@c9ff39a3f9 
Updates LLVM usage to match
[c9ff39a3f984](https://github.com/llvm/llvm-project/commit/c9ff39a3f984)

PiperOrigin-RevId: 361655071
 2021-03-08 14:18:24 -08:00
A. Unique TensorFlower 55eda81407 [MLIR][HLO] Reify shape extents as `index` values 
PiperOrigin-RevId: 361519167
 2021-03-08 02:42:47 -08:00
Benjamin Kramer 5a415de33b Integrate LLVM at llvm/llvm-project@9b302513f6 
Updates LLVM usage to match
[9b302513f6d8](https://github.com/llvm/llvm-project/commit/9b302513f6d8)

PiperOrigin-RevId: 361120223
 2021-03-05 04:50:04 -08:00
A. Unique TensorFlower d5f80f0469 Integrate LLVM at llvm/llvm-project@cedc53254a 
Updates LLVM usage to match
[cedc53254a5d](https://github.com/llvm/llvm-project/commit/cedc53254a5d)

PiperOrigin-RevId: 361090577
 2021-03-05 00:37:48 -08:00
Marius Brehler 29f70cb892 PR #46723: Adjust types of loop counters 
Imported from GitHub PR https://github.com/tensorflow/tensorflow/pull/46723

Reduces some warnings about comparison of integers of different signs.
Copybara import of the project:

--
311f436f77b334f5462127d8cf179cce067969ca by Marius Brehler <marius.brehler@iml.fraunhofer.de>:

Adjust types of loop counters

Reduces some warnings about comparison of integers of different signs.

PiperOrigin-RevId: 360912203
 2021-03-04 07:36:12 -08:00
Benjamin Kramer 57e9941d5d Integrate LLVM at llvm/llvm-project@b3a33553ae 
Updates LLVM usage to match
[b3a33553aec7](https://github.com/llvm/llvm-project/commit/b3a33553aec7)

PiperOrigin-RevId: 360910047
 2021-03-04 07:24:01 -08:00
A. Unique TensorFlower 39650a5d5a Remove rank 1 specialization from TransformUnrankedHloPass. 
For binary ops, we already special-case rank 0 vs rank 1, and same shape. So we
don't need to special-case a maximum rank of 1.

PiperOrigin-RevId: 360891955
 2021-03-04 05:24:53 -08:00
Benjamin Kramer e5a6706260 Integrate LLVM at llvm/llvm-project@c907681b07 
Updates LLVM usage to match
[c907681b077c](https://github.com/llvm/llvm-project/commit/c907681b077c)

PiperOrigin-RevId: 360891677
 2021-03-04 05:22:16 -08:00
Adrian Kuegel 62b357b601 Remove rank 1 specialization from TransformUnrankedHloPass. 
For binary ops, we already special-case rank 0 vs rank 1, and same shape. So we
don't need to special-case a maximum rank of 1.

PiperOrigin-RevId: 360881387
 2021-03-04 04:04:11 -08:00
Geoffrey Martin-Noble 50a516fb9c Adopt td_library 
This avoids needing to list all transitive include dependencies and tracks include directories.

PiperOrigin-RevId: 360779798
 2021-03-03 16:11:21 -08:00
Benjamin Kramer 5eac983723 Integrate LLVM at llvm/llvm-project@5d7e0a23c6 
Updates LLVM usage to match
[5d7e0a23c6f2](https://github.com/llvm/llvm-project/commit/5d7e0a23c6f2)

PiperOrigin-RevId: 360712976
 2021-03-03 11:09:13 -08:00
Benjamin Kramer ab8bc35efd Integrate LLVM at llvm/llvm-project@8da090381d 
Updates LLVM usage to match
[8da090381d56](https://github.com/llvm/llvm-project/commit/8da090381d56)

PiperOrigin-RevId: 360684382
 2021-03-03 09:10:41 -08:00
Benjamin Kramer bf14340316 Integrate LLVM at llvm/llvm-project@1a4990a4f7 
Updates LLVM usage to match
[1a4990a4f71a](https://github.com/llvm/llvm-project/commit/1a4990a4f71a)

PiperOrigin-RevId: 360642978
 2021-03-03 04:57:35 -08:00
A. Unique TensorFlower 24c98d5211 Integrate LLVM at llvm/llvm-project@99a6d003ed 
Updates LLVM usage to match
[99a6d003edbe](https://github.com/llvm/llvm-project/commit/99a6d003edbe)

PiperOrigin-RevId: 360588460
 2021-03-02 21:49:11 -08:00
Geoffrey Martin-Noble 8687f3e4cf Lower MHLO Dot to type-polymorphic linalg named ops 
The linalg named ops are now type polymorphic, so the type-monomorphic
varieties are redundant (and will be deleted soon).

PiperOrigin-RevId: 360509010
 2021-03-02 14:00:58 -08:00
Benjamin Kramer 1facbe9eb5 Integrate LLVM at llvm/llvm-project@7f086d74c3 
Updates LLVM usage to match
[7f086d74c347](https://github.com/llvm/llvm-project/commit/7f086d74c347)

PiperOrigin-RevId: 360434104
 2021-03-02 08:33:21 -08:00
Adrian Kuegel 0683db3b24 Legalize MinimumBroadcastShapes op. 
Use it in TransformUnrankedHloPass, which allows to reduce the maximum
rank for rank specialized broadcast from 6 to 5.

PiperOrigin-RevId: 360415743
 2021-03-02 06:39:01 -08:00
Jacques Pienaar 329b1fd071 Verify compatible shapes in unpack verification rather than exact 
Previously this would be too strict and fail if dynamic and static dims were
compared. Dynamic/unknown are treated as "maybe equal" to a static value without further info, so at this layer don't flag as invalid unless truly are.

PiperOrigin-RevId: 360189086
 2021-03-01 08:00:16 -08:00
Christian Sigg 70ee9369d5 Use mlir::OpState::operator->() to get to Operation::getAttrs(). 
This is a preparation step to remove getAttrs() from OpState.

PiperOrigin-RevId: 360159716
 2021-03-01 04:53:00 -08:00
Benjamin Kramer 7c071e8ee6 Integrate LLVM at llvm/llvm-project@99c24f7aa8 
Updates LLVM usage to match
[99c24f7aa8cc](https://github.com/llvm/llvm-project/commit/99c24f7aa8cc)

PiperOrigin-RevId: 360150476
 2021-03-01 03:44:30 -08:00
Benjamin Kramer e19ccf975e Filter static dimensions from dynamic_broadcast_in_dim's init_tensor 
Otherwise we'd generate invalid IR for those cases.

PiperOrigin-RevId: 360144122
 2021-03-01 03:03:54 -08:00
Adrian Kuegel e6a1f5f0f9 Add MinimumBroadcastShapesOp to chlo dialect. 
This op is useful for rank specialization of broadcasts. Kernel Generator
needs to generate one kernel for each rank, so if we can minimize the rank
of the broadcast shape, we can support more cases with the same number of
special-cased kernels.

PiperOrigin-RevId: 360137827
 2021-03-01 02:23:52 -08:00
Christian Sigg 2d818c4fd9 Use mlir::OpState::operator->() to get to methods of mlir::Operation. 
This is a preparation step to remove those methods from OpState.

PiperOrigin-RevId: 360043992
 2021-02-28 09:02:33 -08:00
A. Unique TensorFlower 006b58c476 Integrate LLVM at llvm/llvm-project@5077d42cfa 
Updates LLVM usage to match
[5077d42cfa42](https://github.com/llvm/llvm-project/commit/5077d42cfa42)

PiperOrigin-RevId: 359899172
 2021-02-26 22:19:53 -08:00
Hanhan Wang a8f99ee0f5 Fix the shape of linalg.init_tensor in conv op lowering. 
The output spatial dims are not as same as the input spatial dims. Only supports
static output spatial dims for now.

PiperOrigin-RevId: 359775479
 2021-02-26 09:34:11 -08:00
A. Unique TensorFlower c616963501 Integrate LLVM at llvm/llvm-project@72b18a86e1 
Updates LLVM usage to match
[72b18a86e11e](https://github.com/llvm/llvm-project/commit/72b18a86e11e)

PiperOrigin-RevId: 359762921
 2021-02-26 08:22:16 -08:00
A. Unique TensorFlower c68b71b5dc Integrate LLVM at llvm/llvm-project@cb81135f94 
Updates LLVM usage to match
[cb81135f94e5](https://github.com/llvm/llvm-project/commit/cb81135f94e5)

PiperOrigin-RevId: 359746866
 2021-02-26 06:47:30 -08:00
A. Unique TensorFlower c63ac91206 Integrate LLVM at llvm/llvm-project@bf6380c096 
Updates LLVM usage to match
[bf6380c0966b](https://github.com/llvm/llvm-project/commit/bf6380c0966b)

PiperOrigin-RevId: 359728311
 2021-02-26 04:05:03 -08:00
A. Unique TensorFlower fe4234bcff Integrate LLVM at llvm/llvm-project@5d64dd8e3c 
Updates LLVM usage to match
[5d64dd8e3c22](https://github.com/llvm/llvm-project/commit/5d64dd8e3c22)

PiperOrigin-RevId: 359653225
 2021-02-25 17:37:37 -08:00
A. Unique TensorFlower e7a3ec18ad Integrate LLVM at llvm/llvm-project@7f6e331645 
Updates LLVM usage to match
[7f6e3316456f](https://github.com/llvm/llvm-project/commit/7f6e3316456f)

PiperOrigin-RevId: 359595260
 2021-02-25 13:12:35 -08:00
A. Unique TensorFlower bb22553219 Integrate LLVM at llvm/llvm-project@f4d78a5e3a 
Updates LLVM usage to match
[f4d78a5e3aee](https://github.com/llvm/llvm-project/commit/f4d78a5e3aee)

PiperOrigin-RevId: 359543192
 2021-02-25 09:40:18 -08:00
Hanhan Wang 90f0d7f935 Add support for lowering mhlo.conv to Linalg on tensors. 
This pattern only works for normal convolutions. It does not work for depthwise
convolutions. The Linalg conv ops are defined with static rank, so it only
supports 1d/2d/3d cases, which are the most typical cases.

This also refactors out the same check in lmhlo.conv lowering.

PiperOrigin-RevId: 359503527
 2021-02-25 05:59:08 -08:00
Rahul Joshi c5f5d13930 [MLIR] Add dependency from "lhlo_ops_structs_inc_gen" to "lhlo" target. 
PiperOrigin-RevId: 359488020
 2021-02-25 03:51:36 -08:00
Hanhan Wang 45a1249fe2 Add support for lowering mhlo.pad to linalg.pad_tensor 
The change upstreams the pattern from IREE repo to MHLO repo.

PiperOrigin-RevId: 359481543
 2021-02-25 03:00:39 -08:00
A. Unique TensorFlower 459362b206 Integrate LLVM at llvm/llvm-project@d8a8e5d624 
Updates LLVM usage to match
[d8a8e5d6240a](https://github.com/llvm/llvm-project/commit/d8a8e5d6240a)

PiperOrigin-RevId: 359475769
 2021-02-25 02:20:12 -08:00
A. Unique TensorFlower 7dc1543bb2 Integrate LLVM at llvm/llvm-project@96a3dfeb93 
Updates LLVM usage to match
[96a3dfeb9303](https://github.com/llvm/llvm-project/commit/96a3dfeb9303)

PiperOrigin-RevId: 359394503
 2021-02-24 16:17:23 -08:00
A. Unique TensorFlower d9d6ab105e Integrate LLVM at llvm/llvm-project@5c74c6be3c 
Updates LLVM usage to match
[5c74c6be3c29](https://github.com/llvm/llvm-project/commit/5c74c6be3c29)

PiperOrigin-RevId: 359354498
 2021-02-24 13:19:53 -08:00
Geoffrey Martin-Noble 89f7f2bd65 Lower integer matmuls to linalg 
PiperOrigin-RevId: 359306495
 2021-02-24 09:45:07 -08:00
Hanhan Wang 475b4a06a5 Add support for lowering mhlo.slice to subtensor. 
PiperOrigin-RevId: 359297978
 2021-02-24 09:06:09 -08:00
A. Unique TensorFlower b478bdf00e Integrate LLVM at llvm/llvm-project@de40423c85 
Updates LLVM usage to match
[de40423c8512](https://github.com/llvm/llvm-project/commit/de40423c8512)

PiperOrigin-RevId: 359280337
 2021-02-24 07:32:25 -08:00
A. Unique TensorFlower 3e2ff6e253 Integrate LLVM at llvm/llvm-project@861dbe1a02 
Updates LLVM usage to match
[861dbe1a021e](https://github.com/llvm/llvm-project/commit/861dbe1a021e)

PiperOrigin-RevId: 359091800
 2021-02-23 11:28:36 -08:00
A. Unique TensorFlower ac0552f127 [MLIR][HLO] Remove duplicate `PopulateTransformUnrankedHloPatterns` 
PiperOrigin-RevId: 359046173
 2021-02-23 07:50:47 -08:00
A. Unique TensorFlower 2df1bb3d6b Integrate LLVM at llvm/llvm-project@6c9541d4dd 
Updates LLVM usage to match
[6c9541d4ddfd](https://github.com/llvm/llvm-project/commit/6c9541d4ddfd)

PiperOrigin-RevId: 359020255
 2021-02-23 04:38:26 -08:00
A. Unique TensorFlower 855cd484fc Integrate LLVM at llvm/llvm-project@557d2ade01 
Updates LLVM usage to match
[557d2ade016f](https://github.com/llvm/llvm-project/commit/557d2ade016f)

PiperOrigin-RevId: 358925409
 2021-02-22 16:05:25 -08:00
A. Unique TensorFlower b45eaf8d33 Integrate LLVM at llvm/llvm-project@12edddafac 
Updates LLVM usage to match
[12edddafac45](https://github.com/llvm/llvm-project/commit/12edddafac45)

PiperOrigin-RevId: 358889182
 2021-02-22 13:21:11 -08:00
Rahul Joshi 0da7ea2545 [MLIR][HLO] Cleanup CMakeLists and comments. 
- Cleanup CMakeLists file to remove unused argument and use a new function for
  setting up lmhlo and lmhlo_gpu dialect targets.
- Fix inconsistently formatted copyright comment and fix header include guards.

PiperOrigin-RevId: 358865838
 2021-02-22 11:36:29 -08:00
Rahul Joshi 5adb7c6e12 [MLIR:LHLO] Add optional call target arg mapping to LMHLO CustomCall operations. 
- XLA:HLO -> LMHLO conversion drops all token arguments and return values, however
  custom calls that users write still expect to get buffer pointers for these token types.
- To be able to support this, add an optional call target argument mapping attribute to
  LMHLO custom calls. When this attribute is present, it indicates the number of
  arguments and returns that the custom call expects and also indicates which LMHLO
  arg() or output() maps to which arg or result number of the custom call.

PiperOrigin-RevId: 358826664
 2021-02-22 08:43:00 -08:00
Benjamin Kramer a9cc1dcfa0 [mlir][hlo] Add basic rank-specialization for select 
This just blows up everything to ranked (up to 6) and is probably quite slow.
This is sufficient to make kernelgen compile SelectV2.

PiperOrigin-RevId: 358777728
 2021-02-22 02:41:12 -08:00