aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/stream_executor
Commit message (Expand)AuthorAge
...
* [TF:STREAM_EXECUTOR] move declaration of multi_platform_manager to headerGravatar Nick Desaulniers2018-05-17
* Small polishing changes in stream executor, no functional changes.Gravatar A. Unique TensorFlower2018-05-15
* avoid having stream_executor depend on tensorflow/coreGravatar A. Unique TensorFlower2018-05-14
* Remove 'using' of dnn types in CudnnSupport implementation file.Gravatar A. Unique TensorFlower2018-05-11
* Use parenthesis based construction instead of brace initializationGravatar Smit Hinsu2018-05-09
* [XLA] Make XLA's memory allocator return an owning smart pointer.Gravatar Justin Lebar2018-05-09
* Unifying argument documentation style in CudnnSupport.Gravatar A. Unique TensorFlower2018-05-09
* Better wrapping of stream executor's cuDNN API calls. Replacing mutex locking...Gravatar A. Unique TensorFlower2018-05-08
* Remove unused threadpool from stream executor.Gravatar A. Unique TensorFlower2018-05-07
* Replaced calls to tensorflow::StringPiece::ToString with std::string conversi...Gravatar A. Unique TensorFlower2018-05-02
* Replaced calls to tensorflow::StringPiece::ToString with std::string conversi...Gravatar Peter Hawkins2018-05-02
* Adding a depthwise convolution kernel op (with label 'cudnn_grouped_convoluti...Gravatar A. Unique TensorFlower2018-04-30
* Cudnn RNN v2 kernels with autotune capabilityGravatar James Qin2018-04-25
* Stop using gpu:: as an alias for stream_executor::.Gravatar Justin Lebar2018-04-25
* Add variants of DoBlasGemmWithAlgorithm with alpha being on device.Gravatar A. Unique TensorFlower2018-04-24
* Merge changes from github.Gravatar Yifei Feng2018-04-23
* [StreamExecutor] [XLA] Delete copy/pasted implementations of MakeUnique.Gravatar Justin Lebar2018-04-22
* Temporarily set cudnn Rnn math precision to fp32.Gravatar James Qin2018-04-20
* [StreamExecutor] Rename ::perftools::gputools -> ::stream_executor, part 1.Gravatar Justin Lebar2018-04-17
* Add more logging for failure cases in CUDATimerGravatar James Qin2018-04-13
* Add debugging checks for setting cuda stream, so it will check fail if theGravatar Guangda Lai2018-04-13
* Print error msg in CUDATimer.Init() when CreateEvent() is not ok().Gravatar James Qin2018-04-12
* Internal change.Gravatar Anna R2018-04-11
* [StreamExecutor] Merge StreamExecutor's and XLA's StatusOr classes.Gravatar Justin Lebar2018-04-10
* Revamp a few ScratchAllocator classes in cudnn_rnn_opsGravatar James Qin2018-04-07
* [XLA:GPU] Eliminate the guard around Winograd non-fused convolutions with cud...Gravatar Justin Lebar2018-04-07
* Support RNN profiling in StreamExecutor for CUDA GPUs.Gravatar James Qin2018-04-06
* Remove dependency on absl to fix tf-nightly-gpu windows GPU buildGravatar Smit Hinsu2018-04-04
* Relax CuDNN version requirements because CuDNN is backwards compatible withinGravatar Smit Hinsu2018-03-28
* Replaced calls to deprecated tensorflow::StringPiece methods with theirGravatar A. Unique TensorFlower2018-03-27
* Set the stream in TransformTensor.Gravatar Guangda Lai2018-03-25
* Make strcat.{h,cc} independent of Eigen.Gravatar A. Unique TensorFlower2018-03-21
* Merge changes from github.Gravatar Jacques Pienaar2018-03-21
* Automated g4 rollback of changelist 189231636Gravatar A. Unique TensorFlower2018-03-15
* Merge changes from github.Gravatar Jacques Pienaar2018-03-15
* [SE] [XLA:GPU] Inform --xla_hlo_profile of the GPU's memory bandwidth.Gravatar Justin Lebar2018-03-15
* [StreamExecutor] Remove ThenDoHostCallbackForTest -- it's identical to ThenDo...Gravatar Justin Lebar2018-03-09
* [SE] Initial perftools::gputools::Platform initialization supportGravatar A. Unique TensorFlower2018-03-08
* StreamExecutor support for float64 convolutions and backprop.Gravatar Brian Patton2018-03-06
* [XLA] FP16 Dot support for the CPU and GPU backends.Gravatar Bixia Zheng2018-02-28
* Do not set cudnn batch norm persistent mode when doing inference.Gravatar Yangzihao Wang2018-02-21
* Merge changes from github.Gravatar Ankur Taly2018-02-16
* Add env-var to specify whether to use CUDNN_BATCHNORM_SPATIAL_PERSISTENT for ...Gravatar Yangzihao Wang2018-02-14
* Remove header dependence on cuda_config.h to fix opensource custom op support.Gravatar Gunhan Gulsoy2018-02-09
* Remove cudnn_type parameter from a few template member functions in classGravatar Bixia Zheng2018-02-08
* Merge changes from github.Gravatar Michael Case2018-02-07
* Performance improvements to some GPU code to use shared locks instead of uniq...Gravatar Rohan Jain2018-01-26
* Merge changes from github.Gravatar Sourabh Bajaj2018-01-17
* Avoid unloading kernels that haven't been loaded and fix replay_computation toGravatar A. Unique TensorFlower2018-01-15
* [XLA:GPU] Warn if ptxas or the driver JIT has known bugs.Gravatar Justin Lebar2018-01-08
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-03 15:41:05 +0000