Replace the previously used `TransformUnrankedHloPass` which rank-specializes
only one operation at a time. The new generalized rank specialization clusters
compatible operations and rank-specializes them collectively.
PiperOrigin-RevId: 376127752
Take advantage of the fact that scalars are already ranked and that they are
neutral elements to broadcasting. Do not reshape scalars, do not consider them
for broadcasting, and materialize ranked operations on scalars accordingly.
PiperOrigin-RevId: 375968371
Rank specialization cases can be applied to all argument tensors of smaller
ranks than the expected maximum rank. This is crucial if all operands are
effectively scalars and the maximum reduced rank is 0.
PiperOrigin-RevId: 375712020
We can lower it to the DivOp in the complex dialect.
Also add tests to hlo-legalize-to-linalg.mlir for CompareOp lowering of complex
types. These were forgotten in a previous commit.
PiperOrigin-RevId: 375669125
Imported from GitHub PR https://github.com/tensorflow/tensorflow/pull/49454
The new interface is more safe to be used during dialect conversion
(e.g. converting from tensor world to buffer world).
Copybara import of the project:
--
a6968072d59bec3c3bbaef0121d297e807c37c91 by Wenyi Zhao <reyizero@gmail.com>:
[MLIR][DISC] Upgrade to use the new `reifyReturnTypeShapes` interface.
The new interface is more safe to be used during dialect conversion
(e.g. converting from tensor world to buffer world).
--
55e7c6b7f2f99b99e226645a57e2433fae3e90ed by Wenyi Zhao <reyizero@gmail.com>:
minor fix
PiperOrigin-RevId: 375500273
This only works for updating tensors, not add/min/max computations. It requires
the index depth to be 1 because of the limitation in Linalg. We can not compare
multiple indices without packing indices.
PiperOrigin-RevId: 375137721
For rank specialization clusters that have only two operands, we can materialize
two extra cases in which either of them is a scalar. This avoids redundant index
computations in these cases.
PiperOrigin-RevId: 375037390
Imported from GitHub PR https://github.com/tensorflow/tensorflow/pull/49228
We are porting our MLIR-based dynamic shape compiler to tf community (From OP def, Patttern, to Optimization pass, etc).
This is the first PR, which including some dynamic shape OPs def in mhlo and lmhlo dialect.
For mhlo dialect, we add:
- HLO_RealDynamicSliceOp
- HLO_DynamicPadOp
- HLO_DynamicGatherOp
- HLO_DynamicConvOp
For lmhlo dialect, we add:
- LHLO_RealDynamicSliceOp
- LHLO_DynamicBroadcastInDimOp
- LHLO_DynamicGatherOp
- LHLO_DynamicPadOp
- LHLO_DynamicBitcastOp
- LHLO_DynamicConvOp
- LHLO_DynamicIotaOp
- LHLO_DynamicReshapeOp
- LHLO_DotGeneralOp
- LHLO_BitcastOp
Rest Ops to add:
* We will send a separate PR containing LHLO_DynamicWhileOp and LHLO_DynamicCaseOp for control flow.
* We will add a separate dedicated dialect like mhlo_ral, which including D2HOp/H2DOp/DebugPrintOp/TopKOp, etc.
Previous discussions：[RFC](https://groups.google.com/a/tensorflow.org/g/mlir/c/_X48poNcbDI/m/jCC8BWIICQAJ), [discussion_1](https://llvm.discourse.group/t/updates-on-mlir-based-dynamic-shape-compiler/2384), [Recording of meeting](https://drive.google.com/file/d/1_uEISlV5MUWdG9faKAdKlCWnPtGjRC-D/view?usp=sharing).
Copybara import of the project:
--
e22d9e61106e00a1a1c6f368cc4a03e3bd1f414c by azazhu <azazhu@gmail.com>:
[DISC]fea: porting mhlo and lmhlo OPs
--
9ec3e76290da07cbd53d7da5fa86ff67179441a1 by azazhu <azazhu@gmail.com>:
[DISC][MLIR] 1. add summary and description for dynamic OPs in mhlo and lmhlo; 2. rm InferOutputTypes; 3. add verify for RealDynamicSliceOp and DynamicPadOp
--
0d68cd135555fd935991c12456b21329e628f23f by azazhu <azazhu@gmail.com>:
[DISC][MLIR] 1.remove D2H,H2D and DebugPrint Ops from mhlo/lmhlo dialect; 2. add type constraint to DynamicPadOp and RealDynamicSliceOp; 3.refine lmhlo type constraint; 4.rename RealDynamicSliceOp as name conflict.
--
698762a77d60f6a844cb1ab3f32740d4ef3c5843 by azazhu <azazhu@gmail.com>:
[DISC][MLIR] 1. replace dyn_cast to cast 2. refine code
PiperOrigin-RevId: 375022260
* The op defines this to be index, any integer, or pred (i1).
* Many TensorFlow legalizations produce integers for the shape.
PiperOrigin-RevId: 374566113
* The former is typically invariant regardless of backend.
* The latter may need to be done differently depending on capabilities of the lowering target.
PiperOrigin-RevId: 374492924
Add lowering pattern for rank specialization clusters with more than one
non-scalar operand. The lowering resembles that of the `TransformUnrankedHlo`
pass and switches cases for maximal ranks from 1 through 8.
PiperOrigin-RevId: 374377002
The pattern can be generalized to also rank specialize operations with a single
non-scalar operand. Also extract helper functions that can be reused in
following specializations.
PiperOrigin-RevId: 374198381
Benjamin Kramer
A. Unique TensorFlower
Adrian Kuegel
Hanhan Wang
Mehdi Amini
Robert Suderman
wyzhao
Stella Laurenzo
Feiwen
Rahul Joshi