4fd48f57cd
The CL is organized as follows: - The main change is in jit/partially_decluster_pass. - tf2xla/const_analysis now takes an "edge_filter" to facilitate use by jit/partially_decluster_pass. - tests/dense_layer_test.py was using the execution of ListDiff as what I assume is a sanity check to see that the XLA cluster ran. With this CL the ListDiff op gets declustered so we now check for "MatMult" for the sanity check. - Some tests were dropping TF_XLA_FLAGS; fixed them to not do so. PiperOrigin-RevId: 212071118
36 lines
1.3 KiB
C++
36 lines
1.3 KiB
C++
/* Copyright 2018 The TensorFlow Authors. All Rights Reserved.
|
|
|
|
Licensed under the Apache License, Version 2.0 (the "License");
|
|
you may not use this file except in compliance with the License.
|
|
You may obtain a copy of the License at
|
|
|
|
http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
Unless required by applicable law or agreed to in writing, software
|
|
distributed under the License is distributed on an "AS IS" BASIS,
|
|
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
See the License for the specific language governing permissions and
|
|
limitations under the License.
|
|
==============================================================================*/
|
|
|
|
#ifndef TENSORFLOW_COMPILER_JIT_PARTIALLY_DECLUSTER_PASS_H_
|
|
#define TENSORFLOW_COMPILER_JIT_PARTIALLY_DECLUSTER_PASS_H_
|
|
|
|
#include "tensorflow/core/common_runtime/optimization_registry.h"
|
|
|
|
namespace tensorflow {
|
|
|
|
// Clones or moves nodes from within a cluster to outside the cluster if
|
|
// profitable. There are two reasons why we do this:
|
|
//
|
|
// - Reducing device-to-host copies.
|
|
// - Reducing the number of XLA recompilations.
|
|
class PartiallyDeclusterPass : public GraphOptimizationPass {
|
|
public:
|
|
Status Run(const GraphOptimizationPassOptions& options) override;
|
|
};
|
|
|
|
} // namespace tensorflow
|
|
|
|
#endif // TENSORFLOW_COMPILER_JIT_PARTIALLY_DECLUSTER_PASS_H_
|