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
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
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
e3754d7b5c
[MLIR:HLO] Change LHLO Infeed to support multiple outputs.
...
PiperOrigin-RevId: 348851612
2020-12-23 14:57:08 -08:00
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
8252eafa99
[NFC] Factor out repeated code out of InferFusibilityOpInterface.
...
PiperOrigin-RevId: 348671671
2020-12-22 12:04:29 -08:00
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
ccdd07f8e4
Prepare to remove tensor_load and tensor_store special handling from hlo to lhlo legalization.
...
This updates the tests to no longer rely on tensor_store. Once all users of this behavior have adopted, the tensor_store support will be removed.
PiperOrigin-RevId: 348624899
2020-12-22 06:29:12 -08:00
c4accdcc41
Integrate LLVM at llvm/llvm-project@1b97cdf885
...
Updates LLVM usage to match
[1b97cdf885d6](https://github.com/llvm/llvm-project/commit/1b97cdf885d6 )
PiperOrigin-RevId: 348587513
2020-12-21 23:49:18 -08:00
a42213b870
Define lowering of [l]mhlo.pow.
...
For floating point operations, this uses std.pow.
For integer operations, this lowers to a loop.
This adds a dependency on scf.
PiperOrigin-RevId: 348537232
2020-12-21 15:27:40 -08:00
99a0ee378c
Integrate LLVM at llvm/llvm-project@511cfe9441
...
Updates LLVM usage to match
[511cfe944195](https://github.com/llvm/llvm-project/commit/511cfe944195 )
PiperOrigin-RevId: 348482094
2020-12-21 09:50:18 -08:00
9fd87f5939
Integrate LLVM at llvm/llvm-project@f4c8b80318
...
Updates LLVM usage to match
[f4c8b8031800](https://github.com/llvm/llvm-project/commit/f4c8b8031800 )
PiperOrigin-RevId: 348453089
2020-12-21 05:34:47 -08:00
ee74c519a6
Integrate LLVM at llvm/llvm-project@17b3ff511c
...
Updates LLVM usage to match
[17b3ff511c0a](https://github.com/llvm/llvm-project/commit/17b3ff511c0a )
PiperOrigin-RevId: 348245062
2020-12-18 21:59:48 -08:00
1e36f6d38d
Integrate LLVM at llvm/llvm-project@9ca67d7f44
...
Updates LLVM usage to match
[9ca67d7f4467](https://github.com/llvm/llvm-project/commit/9ca67d7f4467 )
PiperOrigin-RevId: 348211935
2020-12-18 13:09:17 -08:00
9466cffaf3
Restrict CHLO Acos and Sinh op lowering to non complex types
...
These are failing for complex types. Complex types require special handling. We have a fallback lowering for these ops so we can disable complex element types for now.
PiperOrigin-RevId: 348205002
2020-12-18 11:32:10 -08:00
8d051723c0
Use InferTypeOpInterface for HLO AbsOp and fix result shape inference
...
Shape inference in case of ops with complex element types need to use the element type of complex as the result element type and not the full operand type.
Before:
"mhlo.abs"(%arg0) : (tensor<4xcomplex<f32>>) -> tensor<4xtensor<4xcomplex<f32>>>
After:
"mhlo.abs"(%arg0) : (tensor<4xcomplex<f32>>) -> tensor<4xf32>
PiperOrigin-RevId: 348123967
2020-12-17 17:37:07 -08:00
43ede42ce1
Integrate LLVM at llvm/llvm-project@e113317958
...
Updates LLVM usage to match
[e1133179587d](https://github.com/llvm/llvm-project/commit/e1133179587d )
PiperOrigin-RevId: 348115823
2020-12-17 16:35:29 -08:00
737d15ded5
Handle operands with zero elements in HLO PadOp folder
...
PiperOrigin-RevId: 348034821
2020-12-17 09:27:36 -08:00
8134bff98d
[XLA:GPU] Add layout attributes to LHLO_GPU Convolution operations.
...
- MLIR MemRefs do not preserve layout information correctly when unit dimensions
are involved. Operations like convolution that use cuDNN however need the correct
layout to be preserved so that we do not end up creating an incompatible combination
of input/filter/output layout that is not supported by cuDNN.
- Add these layouts to convolution attributes in the form of I32ArrayAttr for representing
the layout in "minor_to_major" form similar to XLA.
PiperOrigin-RevId: 348034757
2020-12-17 09:26:28 -08:00
dc7e63f74c
Use mlir::OpState::operator->() to get to methods of mlir::Operation.
...
This is a preparation step to remove those methods from OpState.
PiperOrigin-RevId: 348010582
2020-12-17 06:29:33 -08:00
1f244c3e2c
Fix SignOp lowering for floating point values.
...
It didn't return 0 for 0.0 and -0.0.
Currently we emit -0.0 for -0.0 which is correct according to the HLO dialect.
For the TF_SignOp we should emit 0.0 in that case, we will leave that as a TODO.
Enable the tests which work now, and add another one for Int64.
Also improve the registration code, we should not register the Int32 kernel.
PiperOrigin-RevId: 347981124
2020-12-17 01:45:54 -08:00
099c130daf
Fix MLIR include paths.
...
PiperOrigin-RevId: 347976151
2020-12-17 00:56:04 -08:00
5da9190dd9
Integrate LLVM at llvm/llvm-project@0cf7e4b252
...
Updates LLVM usage to match
[0cf7e4b252fe](https://github.com/llvm/llvm-project/commit/0cf7e4b252fe )
PiperOrigin-RevId: 347948887
2020-12-16 20:30:17 -08:00
5a080ad795
Add Bazel build configuration to MLIR HLO standalone repo.
...
Tested that this works in OSS in tree with `bazel build //...` and as a submodule in IREE.
PiperOrigin-RevId: 347919106
2020-12-16 16:23:31 -08:00
65222893ae
[KERNEL_GEN] Convert LHLO AddOp, SubOp (ComplexType) to complex ops.
...
PiperOrigin-RevId: 347805898
2020-12-16 05:45:06 -08:00
61244b136c
Try to avoid a segfault if we don't support a lowering.
...
It can happen that a lowering for a certain type is not implemented yet.
We should not segfault in such a case, but instead return a failure().
PiperOrigin-RevId: 347801106
2020-12-16 04:58:17 -08:00
e6e8920921
[KERNEL_GEN] Switch the pipeline to Linalg-on-Tensors.
...
PiperOrigin-RevId: 347781190
2020-12-16 01:51:15 -08:00
5ab94a00a7
[mlir][NFC] Replace usages or mlir/IR/StandardTypes.h with mlir/IR/BuiltinTypes.h
...
StandardTypes.h was moved to BuiltinTypes.h and is being removed.
PiperOrigin-RevId: 347751511
2020-12-15 21:28:18 -08:00
ccbf39842f
Integrate LLVM at llvm/llvm-project@7aeb3804c4
...
Updates LLVM usage to match
[7aeb3804c46c](https://github.com/llvm/llvm-project/commit/7aeb3804c46c )
PiperOrigin-RevId: 347727361
2020-12-15 17:40:25 -08:00
6d7812bbc5
Correct non ConversionRewriter transformation in LegalizeToLinalg
...
PiperOrigin-RevId: 347622657
2020-12-15 08:56:58 -08:00
f0c2695d31
Fix SignOp lowering for floating point values.
...
It didn't return 0 for 0.0 and -0.0.
Currently we emit -0.0 for -0.0 which is correct according to the HLO dialect.
For the TF_SignOp we should emit 0.0 in that case, we will leave that as a TODO.
Enable the tests which work now, and add another one for Int64.
Also improve the registration code, we should not register the Int32 kernel.
PiperOrigin-RevId: 347602378
2020-12-15 06:49:48 -08:00
ddda2699fb
[KERNEL_GEN] Switch the pipeline to Linalg-on-Tensors.
...
PiperOrigin-RevId: 347600145
2020-12-15 06:32:25 -08:00
79fa36bcbc
Fix SignOp lowering for floating point values.
...
It didn't return 0 for 0.0 and -0.0.
Currently we emit -0.0 for -0.0 which is correct according to the HLO dialect.
For the TF_SignOp we should emit 0.0 in that case, we will leave that as a TODO.
Enable the tests which work now, and add another one for Int64.
Also improve the registration code, we should not register the Int32 kernel.
PiperOrigin-RevId: 347590340
2020-12-15 05:12:48 -08:00
9540e51617
[mlir][NFC] Replace usages or mlir/IR/StandardTypes.h with mlir/IR/BuiltinTypes.h
...
StandardTypes.h was moved to BuiltinTypes.h and is being removed.
PiperOrigin-RevId: 347559927
2020-12-15 00:59:29 -08:00
9df327d88f
Forward listeners in LhloLegalizeToParallelLoops builders
...
PiperOrigin-RevId: 347554379
2020-12-15 00:13:15 -08:00
1a58f19664
[NFC] Make function names follow style guide.
...
Functions should start with a capital letter and have a capital letter for each
new word. See https://google.github.io/styleguide/cppguide.html#Function_Names
PiperOrigin-RevId: 347420402
2020-12-14 10:46:55 -08:00
8b35a75d4a
[KERNEL_GEN] Switch the pipeline to Linalg-on-Tensors.
...
PiperOrigin-RevId: 347368063
2020-12-14 05:46:47 -08:00
6b439f7eee
[mlir][NFC] Replace usages or mlir/IR/StandardTypes.h with mlir/IR/BuiltinTypes.h
...
StandardTypes.h was moved to BuiltinTypes.h and is being removed.
PiperOrigin-RevId: 347115952
2020-12-11 19:01:25 -08:00
3abdd556de
[mlir][NFC] Replace usages or mlir/IR/StandardTypes.h with mlir/IR/BuiltinTypes.h
...
StandardTypes.h was moved to BuiltinTypes.h and is being removed.
PiperOrigin-RevId: 347111863
2020-12-11 18:12:59 -08:00
22b91d62ff
[XLA/GPU] Migrate all unnested elementwise emitters.
...
Also fix GetHloOutputs/GetHloOperands to treat aliased operands correctly.
PiperOrigin-RevId: 347055290
2020-12-11 12:45:21 -08:00
21bb9e8c9a
Integrate LLVM at llvm/llvm-project@38d32e4fd7
...
Updates LLVM usage to match
[38d32e4fd70c](https://github.com/llvm/llvm-project/commit/38d32e4fd70c )
PiperOrigin-RevId: 346994267
2020-12-11 07:28:49 -08:00
9930c20c31
[mlir][hlo] Fix lowering of NE comparison. It should return true if either side is NaN
...
PiperOrigin-RevId: 346988987
2020-12-11 06:46:14 -08:00
ab6ee11813
Fix folding of HLO SliceOp with zero elements
...
This was causing division by zero in this case.
PiperOrigin-RevId: 346920942
2020-12-10 20:22:48 -08:00
f232da1f9d
[MLIR:HLO] Add window_reversal attribute to convolution attributes.
...
- Add this attribute to match the corresponding XLA HLO attribute on convolution
operations.
- A true value indicates a reversal of the corresponding kernel spatial dimension.
- Since XLA builder does not support this attribute, use a custom HLO converted to map
from mlir::mhlo::ConvOp to XLA.
PiperOrigin-RevId: 346891737
2020-12-10 16:39:19 -08:00
3442ac270d
Integrate LLVM at llvm/llvm-project@997a719d5a
...
Updates LLVM usage to match
[997a719d5a70](https://github.com/llvm/llvm-project/commit/997a719d5a70 )
PiperOrigin-RevId: 346834025
2020-12-10 11:58:16 -08:00
6a05893169
[XLA/GPU] Migrate all unnested elementwise emitters.
...
PiperOrigin-RevId: 346725498
2020-12-10 00:21:36 -08:00
51f535454d
Use OpState::operator->() to get to member functions in Operation so we can remove the corresponding methods from OpState.
...
PiperOrigin-RevId: 346721668
2020-12-09 23:54:07 -08:00
c36afd275e
[HLO] Add a pattern for HLO ConstOp to HLO -> Linalg conversion.
...
PiperOrigin-RevId: 346718273
2020-12-09 23:24:57 -08:00
cfcf741932
[XLA/GPU] Migrate all unnested elementwise emitters.
...
PiperOrigin-RevId: 346716519
2020-12-09 23:08:13 -08:00
65ebd85563
[XLA/GPU] Migrate all unnested elementwise emitters.
...
PiperOrigin-RevId: 346658288
2020-12-09 16:05:43 -08:00
A. Unique TensorFlower
Adrian Kuegel
Rahul Joshi
Stephan Herhut
Tres Popp
Smit Hinsu
Christian Sigg
Phoenix Meadowlark
Alexander Belyaev
River Riddle
Hanhan Wang
Tim Shen
Benjamin Kramer