aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/compiler/xla/service/gpu/cudnn_convolution_algorithm_picker.cc
Commit message (Expand)AuthorAge
* Add more logging to the convolution transformations.Gravatar Tim Shen2018-10-08
* [XLA:GPU] Use a struct for the return value of CudnnConvolutionAlgorithmPicke...Gravatar Justin Lebar2018-10-05
* Add cuDNN fused convolution forward support.Gravatar Tim Shen2018-09-24
* Further simplify the cuDNN wrappers. Instead of passing aroundGravatar Tim Shen2018-09-24
* Move winograd algorithm workaround to stream executor.Gravatar Tim Shen2018-09-21
* Simplify the initialization function in algortihm picker. No functional change.Gravatar Tim Shen2018-09-13
* Simplify algorithm picker's internal interface.Gravatar Tim Shen2018-09-10
* Cleanup cudnn_convolution_runner's interface. Use a struct to pack mostGravatar Tim Shen2018-09-10
* [XLA:GPU] Make sure the input for ThenMemcpy stays alive when it executesGravatar Benjamin Kramer2018-09-04
* [XLA:GPU] Flush out any pending work before starting autotuneGravatar Benjamin Kramer2018-09-03
* Call Cudnn also for grouped convolutions.Gravatar Adrian Kuegel2018-09-03
* [XLA] Rename all (Mutable)ArraySlice to absl::Span.Gravatar Tim Shen2018-08-30
* [XLA] Switch to absl::StrFormat.Gravatar Justin Lebar2018-08-27
* [XLA] Use absl string types and functions instead of the TF versions.Gravatar Justin Lebar2018-08-23
* [XLA] gtl::optional->absl::optionalGravatar Yunxing Dai2018-08-21
* Add a flag to crash on cuDNN cross checking failures.Gravatar Tim Shen2018-08-16
* In auto-tuning, initialize fp16 buffers with 0.1.Gravatar Tim Shen2018-08-15
* Implmenet cuDNN algorithm cross checking.Gravatar Tim Shen2018-08-15
* Change PickBestAlgorithm to return a StatusOr object.Gravatar Tim Shen2018-08-14
* [XLA:GPU] Don't run convolution autotuning concurrently on the same GPU.Gravatar Justin Lebar2018-08-06
* [TF:XLA] Split literal_util into {literal, literal_util}.Gravatar Kay Zhu2018-07-03
* [XLA:GPU] Specify cudnn conv algorithm via backend_config.Gravatar Justin Lebar2018-05-31
* [XLA] Make XLA's memory allocator return an owning smart pointer.Gravatar Justin Lebar2018-05-09
* [XLA:GPU] Zero out input buffers before running cudnn conv autotune.Gravatar Justin Lebar2018-05-07
* Merge changes from github.Gravatar Yifei Feng2018-04-23
* [XLA] Convert XLA to use xla::se as a namespace alias for ::stream_executor.Gravatar Justin Lebar2018-04-17
* [XLA:GPU] Eliminate the guard around Winograd non-fused convolutions with cud...Gravatar Justin Lebar2018-04-07
* Enable half precision convolution for the CPU and GPU backends.Gravatar Bixia Zheng2018-02-15
* [XLA:GPU] Extend the CustomCall for cudnn convolutions to representGravatar Bixia Zheng2018-02-12
* Internal changeGravatar Justin Lebar2018-02-02
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-07 14:18:53 +0000