commit | dcf1e8946e44d715b6536887c175769118b55250 | [log] [tgz] |
---|---|---|
author | Justin Lebar <jlebar@google.com> | Tue May 31 19:06:50 2022 -0700 |
committer | TensorFlower Gardener <gardener@tensorflow.org> | Tue May 31 19:13:02 2022 -0700 |
tree | 79220b389b018bae9c438686aca530357f2d6392 | |
parent | db3f6eaa9f2d4990ce11b0cb8c4170dc6d60a93f [diff] |
[XLA:GPU] Decompose bitcast inside fusion into bitcast+transpose. Within XLA:GPU fusions, bitcast ops can be either fast (ReshapeIsBitcast is true) or slow (ReshapeIsBitcast is false). Previously we tried to avoid creating slow ones by telling algsimp to avoid translating transpose ops to bitcasts (which generally do not have ReshapeIsBitcast true). The problem with this is that if you have a transpose+bitcast that *doesn't* end up as part of a larger fusion, this approach ends up creating a fusion just for the transpose+bitcast (tantamount to a memcpy). Whereas if we *had* converted the transpose to a bitcast, then we'd have had bitcast+bitcast => bitcast, and, if that bitcast is outside of a fusion node, it's free. This patch takes us in a different direction. Now we always transform transpose to bitcast where possible. But then right before codegen, we find all the bitcast ops inside fusion nodes and split them up into transpose+reshape-is-bitcast. We prove empirically that we can *always* split a bitcast into transpose+reshape-is-bitcast, so this shouldn't make any fusions slower than they were. We leave removing the don't-rewrite-transposes-into-bitcasts feature in algsimp for a later patch, after this one sticks. PiperOrigin-RevId: 452191666
Documentation |
---|
TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries, and community resources that lets researchers push the state-of-the-art in ML and developers easily build and deploy ML-powered applications.
TensorFlow was originally developed by researchers and engineers working on the Google Brain team within Google's Machine Intelligence Research organization to conduct machine learning and deep neural networks research. The system is general enough to be applicable in a wide variety of other domains, as well.
TensorFlow provides stable Python and C++ APIs, as well as non-guaranteed backward compatible API for other languages.
Keep up-to-date with release announcements and security updates by subscribing to announce@tensorflow.org. See all the mailing lists.
See the TensorFlow install guide for the pip package, to enable GPU support, use a Docker container, and build from source.
To install the current release, which includes support for CUDA-enabled GPU cards (Ubuntu and Windows):
$ pip install tensorflow
A smaller CPU-only package is also available:
$ pip install tensorflow-cpu
To update TensorFlow to the latest version, add --upgrade
flag to the above commands.
Nightly binaries are available for testing using the tf-nightly and tf-nightly-cpu packages on PyPi.
$ python
>>> import tensorflow as tf >>> tf.add(1, 2).numpy() 3 >>> hello = tf.constant('Hello, TensorFlow!') >>> hello.numpy() b'Hello, TensorFlow!'
For more examples, see the TensorFlow tutorials.
If you want to contribute to TensorFlow, be sure to review the contribution guidelines. This project adheres to TensorFlow's code of conduct. By participating, you are expected to uphold this code.
We use GitHub issues for tracking requests and bugs, please see TensorFlow Discuss for general questions and discussion, and please direct specific questions to Stack Overflow.
The TensorFlow project strives to abide by generally accepted best practices in open-source software development:
You can find more community-supported platforms and configurations in the TensorFlow SIG Build community builds table.
Build Type | Status | Artifacts |
---|---|---|
Linux CPU | PyPI | |
Linux GPU | PyPI | |
Linux XLA | TBA | |
macOS | PyPI | |
Windows CPU | PyPI | |
Windows GPU | PyPI | |
Android | Download | |
Raspberry Pi 0 and 1 | Py3 | |
Raspberry Pi 2 and 3 | Py3 | |
Libtensorflow MacOS CPU | Status Temporarily Unavailable | Nightly Binary Official GCS |
Libtensorflow Linux CPU | Status Temporarily Unavailable | Nightly Binary Official GCS |
Libtensorflow Linux GPU | Status Temporarily Unavailable | Nightly Binary Official GCS |
Libtensorflow Windows CPU | Status Temporarily Unavailable | Nightly Binary Official GCS |
Libtensorflow Windows GPU | Status Temporarily Unavailable | Nightly Binary Official GCS |
Learn more about the TensorFlow community and how to contribute.