Commit Graph

1037 Commits

Author SHA1 Message Date
Jacques Pienaar a7e645f37e Fix incorrect include
PiperOrigin-RevId: 352820426
2021-01-20 10:24:41 -08:00
Tres Popp ba0346b071 Integrate LLVM at llvm/llvm-project@96ef4f307d
Updates LLVM usage to match
[96ef4f307df2](https://github.com/llvm/llvm-project/commit/96ef4f307df2)

PiperOrigin-RevId: 352786460
2021-01-20 07:09:47 -08:00
A. Unique TensorFlower ec5f5667e1 [MLIR][KernelGen] Add `tf.Asinh` kernels and complete their lowerings
PiperOrigin-RevId: 352773540
2021-01-20 05:31:15 -08:00
A. Unique TensorFlower 0e85b4d511 [MLIR][KernelGen] Add `tf.Asinh` kernels and complete their lowerings
PiperOrigin-RevId: 352604725
2021-01-19 10:51:41 -08:00
A. Unique TensorFlower 96fb617413 [MLIR][KernelGen] Add erf kernel and missing lowering for f16 type
PiperOrigin-RevId: 352416184
2021-01-18 08:21:15 -08:00
Alexander Belyaev 9e07bdf4ea [HLO] Move `SameOperandsAndResultShape` trait to Unary/BinaryElemenwiseOp classes.
PiperOrigin-RevId: 352404756
2021-01-18 06:47:36 -08:00
A. Unique TensorFlower c11ea4ef5a [MLIR][KernelGen] Add `tf.Atanh` kernels
PiperOrigin-RevId: 352393602
2021-01-18 05:14:09 -08:00
Tres Popp ba2ee556f1 Handle negative exponents for lowering of hlo.pow
PiperOrigin-RevId: 352382812
2021-01-18 03:47:28 -08:00
A. Unique TensorFlower 3763740910 [MLIR][KernelGen] Add erf kernel for f32 arguments and missing lowerings
PiperOrigin-RevId: 352381016
2021-01-18 03:35:13 -08:00
A. Unique TensorFlower b5dc600860 [MLIR] Fix line wraps in hlo_ops.td
PiperOrigin-RevId: 352364076
2021-01-18 01:41:41 -08:00
A. Unique TensorFlower 6cb01c89b7 Integrate LLVM at llvm/llvm-project@8456c3a789
Updates LLVM usage to match
[8456c3a78928](https://github.com/llvm/llvm-project/commit/8456c3a78928)

PiperOrigin-RevId: 352152981
2021-01-16 01:26:03 -08:00
A. Unique TensorFlower 38a7c136ae Integrate LLVM at llvm/llvm-project@86e604c4d6
Updates LLVM usage to match
[86e604c4d685](https://github.com/llvm/llvm-project/commit/86e604c4d685)

PiperOrigin-RevId: 352105071
2021-01-15 16:25:15 -08:00
Stephan Herhut 92a203f4f0 Integrate LLVM at llvm/llvm-project@104a9f99cc
Updates LLVM usage to match
[104a9f99ccab](https://github.com/llvm/llvm-project/commit/104a9f99ccab)

PiperOrigin-RevId: 352006778
2021-01-15 07:43:39 -08:00
A. Unique TensorFlower bcdb3c3548 [MLIR] Lower mhlo.clamp to linalg
PiperOrigin-RevId: 351998800
2021-01-15 06:45:38 -08:00
Stephan Herhut 2af0dcd3e7 Integrate LLVM at llvm/llvm-project@7803636057
Updates LLVM usage to match
[78036360573c](https://github.com/llvm/llvm-project/commit/78036360573c)

PiperOrigin-RevId: 351994130
2021-01-15 06:06:44 -08:00
A. Unique TensorFlower 791d5afd28 [MLIR][KernelGen] Add `tf.Asinh` kernels and complete their lowerings
PiperOrigin-RevId: 351989552
2021-01-15 05:26:57 -08:00
A. Unique TensorFlower 316f630728 [MLIR][KernelGen] Add cosh kernels and tests
Allow for relative tolerance in unary kernel tests. In case of the cosh kernels,
this allows to accept an observed difference of 5.6e-8 between the kernel and
the `std::cosh` reference (32829984.568665262 vs. 32829984.568665318) in one of
the test cases.

PiperOrigin-RevId: 351983698
2021-01-15 04:31:30 -08:00
A. Unique TensorFlower 9a1abaa212 Integrate LLVM at llvm/llvm-project@e2d7d3cb0e
Updates LLVM usage to match
[e2d7d3cb0ead](https://github.com/llvm/llvm-project/commit/e2d7d3cb0ead)

PiperOrigin-RevId: 351915841
2021-01-14 18:05:33 -08:00
Stephan Herhut 4d62cd4dee Integrate LLVM at llvm/llvm-project@6abbba3fca
Updates LLVM usage to match
[6abbba3fca9f](https://github.com/llvm/llvm-project/commit/6abbba3fca9f)

PiperOrigin-RevId: 351790911
2021-01-14 06:54:14 -08:00
Stephan Herhut 5fff92f2b4 Integrate LLVM at llvm/llvm-project@ed205f63b4
Updates LLVM usage to match
[ed205f63b4a2](https://github.com/llvm/llvm-project/commit/ed205f63b4a2)

PiperOrigin-RevId: 351759914
2021-01-14 02:36:48 -08:00
A. Unique TensorFlower 3b9981fc60 Integrate LLVM at llvm/llvm-project@f4f158b2f8
Updates LLVM usage to match
[f4f158b2f89e](https://github.com/llvm/llvm-project/commit/f4f158b2f89e)

PiperOrigin-RevId: 351719348
2021-01-13 20:17:14 -08:00
A. Unique TensorFlower 14ae39bc95 Integrate LLVM at llvm/llvm-project@17863614da
Updates LLVM usage to match
[17863614da1e](https://github.com/llvm/llvm-project/commit/17863614da1e)

PiperOrigin-RevId: 351620042
2021-01-13 10:54:07 -08:00
A. Unique TensorFlower 181d2cad31 [MLIR][KernelGen] Add `tf.Log1p` kernel and tests
PiperOrigin-RevId: 351566460
2021-01-13 05:37:25 -08:00
Hanhan Wang 300a7c11ce Upstream mhlo.dot_general lowering to Linalg to MHLO repo
PiperOrigin-RevId: 351514250
2021-01-12 22:08:46 -08:00
A. Unique TensorFlower 97a618f91a Integrate LLVM at llvm/llvm-project@6f4d460762
Updates LLVM usage to match
[6f4d46076200](https://github.com/llvm/llvm-project/commit/6f4d46076200)

PiperOrigin-RevId: 351474229
2021-01-12 16:38:25 -08:00
Rahul Joshi 0651d58edf [MLIR:HLO] Change LHLO Outfeed to support multiple inputs.
PiperOrigin-RevId: 351447034
2021-01-12 14:13:47 -08:00
A. Unique TensorFlower 0b85d5c510 [MLIR][KernelGen] Add asin kernels and tests
PiperOrigin-RevId: 351381423
2021-01-12 09:02:46 -08:00
Stephan Herhut b0e0ca830c Integrate LLVM at llvm/llvm-project@c8a914db5c
Updates LLVM usage to match
[c8a914db5c60](https://github.com/llvm/llvm-project/commit/c8a914db5c60)

PiperOrigin-RevId: 351363798
2021-01-12 07:09:38 -08:00
A. Unique TensorFlower d52092a5cc Integrate LLVM at llvm/llvm-project@aefeb5f136
Updates LLVM usage to match
[aefeb5f136e7](https://github.com/llvm/llvm-project/commit/aefeb5f136e7)

PiperOrigin-RevId: 351291118
2021-01-11 20:24:58 -08:00
Stephan Herhut 5359ea620a Integrate LLVM at llvm/llvm-project@89878e8c96
Updates LLVM usage to match
[89878e8c966a](https://github.com/llvm/llvm-project/commit/89878e8c966a)

PiperOrigin-RevId: 351192927
2021-01-11 11:08:35 -08:00
Hanhan Wang 8f58f844e5 Upstream mhlo.dot lowering to Linalg to MHLO repo.
We prototyped the lowering from mhlo.dot to linalg.matmul in IREE. Since Linalg
now supports matmul in tensors world, we can move the lowering logic to tensors
world, and upstream to legalize_to_linalg.cc. The patch lowers the mhlo.dot to
the linalg.matmul/matvec/dot in tensors world.

PiperOrigin-RevId: 351184911
2021-01-11 10:35:24 -08:00
Alexander Belyaev 180f917446 [KERNEL_GEN] Add a pattern for hlo.dyn_broadcast->linalg to enable is_inf kernel.
PiperOrigin-RevId: 351179620
2021-01-11 10:13:31 -08:00
Alexander Belyaev ecf1bf5132 [KERNEL_GEN] Add a canonicalization pattern to drop a redundant dynamic reshape.
PiperOrigin-RevId: 351141868
2021-01-11 06:38:03 -08:00
Geoffrey Martin-Noble 47848764a5 Change hardcoded external/ include to match repository name
This is the preferred name for the Bazel repository when included from
another project.

Note: These hardcoded "external/" includes are a horrible hack that we
can hopefully get rid of soon with more robust Bazel tablegen rules.
PiperOrigin-RevId: 350810768
2021-01-08 12:07:53 -08:00
Alexander Belyaev ac38478350 Integrate LLVM at llvm/llvm-project@bcbdeafa9c
Updates LLVM usage to match
[bcbdeafa9cb3](https://github.com/llvm/llvm-project/commit/bcbdeafa9cb3)

PiperOrigin-RevId: 350763293
2021-01-08 07:57:20 -08:00
Alexander Belyaev 6c42f54298 [KERNEL_GEN] Restrict broadcast -> reshape canonicalization to identity dims.
This is needed to avoid the case, when the broadcast_in_dims also performs permutation.

PiperOrigin-RevId: 350650342
2021-01-07 15:30:28 -08:00
Alexander Belyaev a8c0f2b944 Integrate LLVM at llvm/llvm-project@7f7b0dc4e1
Updates LLVM usage to match
[7f7b0dc4e15f](https://github.com/llvm/llvm-project/commit/7f7b0dc4e15f)

PiperOrigin-RevId: 350576840
2021-01-07 09:24:01 -08:00
Alexander Belyaev 49a540bf72 Integrate LLVM at llvm/llvm-project@d38a0258a5
Updates LLVM usage to match
[d38a0258a5f4](https://github.com/llvm/llvm-project/commit/d38a0258a5f4)

PiperOrigin-RevId: 350140950
2021-01-05 08:03:11 -08:00
Alexander Belyaev 095dc28e5c [KERNEL_GEN] Add canonicalizaton pattern to drop a redundant broadcast op.
PiperOrigin-RevId: 350105790
2021-01-05 03:01:00 -08:00
A. Unique TensorFlower 2727ed4cf2 Integrate LLVM at llvm/llvm-project@8bee4d4e8f
Updates LLVM usage to match
[8bee4d4e8f54](https://github.com/llvm/llvm-project/commit/8bee4d4e8f54)

PiperOrigin-RevId: 349678834
2020-12-31 07:35:45 -08:00
A. Unique TensorFlower f8fbfdd061 Integrate LLVM at llvm/llvm-project@51a292d994
Updates LLVM usage to match
[51a292d99453](https://github.com/llvm/llvm-project/commit/51a292d99453)

PiperOrigin-RevId: 349610524
2020-12-30 15:45:59 -08:00
A. Unique TensorFlower 181f19881b Integrate LLVM at llvm/llvm-project@2016f2c8a7
Updates LLVM usage to match
[2016f2c8a76d](https://github.com/llvm/llvm-project/commit/2016f2c8a76d)

PiperOrigin-RevId: 349565754
2020-12-30 09:11:29 -08:00
A. Unique TensorFlower 2e215f75a5 Integrate LLVM at llvm/llvm-project@8001dcbd50
Updates LLVM usage to match
[8001dcbd50ce](https://github.com/llvm/llvm-project/commit/8001dcbd50ce)

PiperOrigin-RevId: 349514172
2020-12-29 22:42:21 -08:00
A. Unique TensorFlower a9e2b45bd5 Integrate LLVM at llvm/llvm-project@930c74f12d
Updates LLVM usage to match
[930c74f12d79](https://github.com/llvm/llvm-project/commit/930c74f12d79)

PiperOrigin-RevId: 349426692
2020-12-29 08:32:16 -08:00
Adrian Kuegel 50fc56a208 Fix header include.
It should not have the third_party prefix, this doesn't work in open source.

PiperOrigin-RevId: 348905548
2020-12-24 01:40:31 -08:00
A. Unique TensorFlower b0bf2ef45b Integrate LLVM at llvm/llvm-project@c3acda0798
Updates LLVM usage to match
[c3acda0798f9](https://github.com/llvm/llvm-project/commit/c3acda0798f9)

PiperOrigin-RevId: 348896724
2020-12-23 23:53:54 -08:00
Rahul Joshi e3754d7b5c [MLIR:HLO] Change LHLO Infeed to support multiple outputs.
PiperOrigin-RevId: 348851612
2020-12-23 14:57:08 -08:00
Rahul Joshi bd8e768e23 [MLIR:HLO] Rename LMHLO Infeed and Outfeed to InfeedOp and OutfeedOp.
- To be consistent with other operation names.

PiperOrigin-RevId: 348824379
2020-12-23 11:38:05 -08:00
Rahul Joshi 8252eafa99 [NFC] Factor out repeated code out of InferFusibilityOpInterface.
PiperOrigin-RevId: 348671671
2020-12-22 12:04:29 -08:00
Rahul Joshi bc367971ec [MLIR:LHLO_GPU] Add additional constraints for batchnorm
- Constrain batchnorm inputs and outputs to be fp memrefs.

PiperOrigin-RevId: 348665747
2020-12-22 11:30:40 -08:00