index
:
tensorflow
master
machine learning framework
about
summary
refs
log
tree
commit
diff
homepage
log msg
author
committer
range
path:
root
/
tensorflow
/
compiler
/
xla
/
service
/
gpu
/
ir_emission_utils.cc
Commit message (
Expand
)
Author
Age
*
Add cuDNN fused convolution forward support.
Tim Shen
2018-09-24
*
Remove the public uses of CreateCudnnConv* in the favor of
Tim Shen
2018-09-24
*
Further simplify the cuDNN wrappers. Instead of passing around
Tim Shen
2018-09-24
*
Simplify convolution_thunk's interface.
Tim Shen
2018-09-10
*
Call Cudnn also for grouped convolutions.
Adrian Kuegel
2018-09-03
*
[XLA] Rename all (Mutable)ArraySlice to absl::Span.
Tim Shen
2018-08-30
*
[XLA] Use absl string types and functions instead of the TF versions.
Justin Lebar
2018-08-23
*
[XLA:GPU] cuBlas supports complex floats, use gemm instead of our O(n^3) impl...
Benjamin Kramer
2018-08-03
*
[XLA:GPU] Forward batched dot to cublas instead of expanding it
Benjamin Kramer
2018-08-03
*
[XLA:GPU] Allow `dot`s inside of while loops (etc) to be lowered to cublas ca...
Justin Lebar
2018-07-25
*
[XLA] Use shfl.sync.down instead of shfl.sync.
Justin Lebar
2018-07-13
*
Fix assumptions that a Shape must be a tuple or an array.
Mark Heffernan
2018-06-13
*
[XLA:GPU] Specify cudnn conv algorithm via backend_config.
Justin Lebar
2018-05-31
*
Reland improve fusion logic of (a dot b) * alpha
A. Unique TensorFlower
2018-05-15
*
Delete kTransposeDot (it is no longer in use)
Sanjoy Das
2018-05-07
*
Automated g4 rollback of changelist 195638795
A. Unique TensorFlower
2018-05-07
*
Improve fusion logic of (a dot b) * alpha
A. Unique TensorFlower
2018-05-07
*
Remove uses of the kTransposeDot fusion
Sanjoy Das
2018-05-07
*
[XLA:GPU] Pass all four args to custom-call convs when they're created.
Justin Lebar
2018-04-12
*
Introduce output fusion for (A dot B) * alpha
A. Unique TensorFlower
2018-03-13
*
[XLA] FP16 Dot support for the CPU and GPU backends.
Bixia Zheng
2018-02-28
*
Internal change
Justin Lebar
2018-02-02
*
[XLA:GPU] Implement BatchNormThunk as a call into cudnn.
Justin Lebar
2017-12-21
*
Resolves an issue that came up with ResNet50 when using the CPU backend as a ...
Bjarke Hammersholt Roune
2017-12-15
*
[XLA] Separate input and output spatial dimensions for convolution
David Majnemer
2017-11-27
*
[XLA] Factor out repeated LatestNonGteAncestorAndIndex helper.
Justin Lebar
2017-10-09
*
Update Dataset API documentation.
Jiri Simsa
2017-07-27
*
Clean up usage of HloModuleConfig in more places.
Eli Bendersky
2017-05-19
*
[XLA] Run transpose_folding on nested computations
David Majnemer
2017-04-26
*
[XLA] Support 1D and 3D convolutions in GPU backend.
A. Unique TensorFlower
2017-02-17
*
[XLA] Recognize any reduction where dimensions to keep are consecutive in mem...
A. Unique TensorFlower
2017-01-12
*
Initial open-source release of XLA: Accelerated Linear Algebra.
Peter Hawkins
2017-01-09