aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/stream_executor
Commit message (Expand)AuthorAge
* Output the error message when stream_executor's ValueOrDie, ConsumeValueOrDie...Gravatar A. Unique TensorFlower2017-04-14
* Merge changes from github.Gravatar Rohan Jain2017-04-07
* Merge changes from github.Gravatar A. Unique TensorFlower2017-04-04
* Add a multi-pass mode for autotuning. It tests the autotune multiple times,Gravatar Xiaoqiang Zheng2017-03-21
* [SE:Host] Temporarily revert the determination of host frequency.Gravatar A. Unique TensorFlower2017-03-14
* Merge changes from github.Gravatar Dandelion Mané2017-03-10
* Set the default flag for using nonfused winograd convolution in fowrad convol...Gravatar A. Unique TensorFlower2017-03-03
* [XLA] [StreamExecutor] Tune GEMMs when possible.Gravatar Justin Lebar2017-03-02
* [StreamExecutor] Minor comment cleanups.Gravatar Justin Lebar2017-03-02
* [XLA:GPU] Cache GPU substreams across executionsGravatar A. Unique TensorFlower2017-03-02
* Merge changes from github.Gravatar Andrew Harp2017-03-01
* [TF:XLA] Silence a number of compiler warnings, in particular warnings repeat...Gravatar Peter Hawkins2017-02-27
* Set the clock rate for the host accuratelyGravatar David Majnemer2017-02-27
* Fixed the logic for winograd_nonfused for cudnn v>=5100Gravatar A. Unique TensorFlower2017-02-18
* Merge changes from github.Gravatar Vijay Vasudevan2017-02-17
* Only record cuDNN profiling results if the operation was successful.Gravatar A. Unique TensorFlower2017-02-17
* Add std:: prefix to STL non-type names.Gravatar A. Unique TensorFlower2017-02-16
* [XLA:GPU] Cache kernels in `KernelThunk::ExecuteOnStream`Gravatar A. Unique TensorFlower2017-02-14
* Fix code that ignores tensorflow::Status.Gravatar Peter Hawkins2017-02-13
* [StreamExecutor] Only check occupancy info at -v 2 and above.Gravatar Justin Lebar2017-02-10
* Remove problematic SE_RETURN_STATUS_AS_BOOL macroGravatar Peter Hawkins2017-02-10
* Fix double evaluation of macro argument that was causing duplicate CUDA batch...Gravatar Peter Hawkins2017-02-09
* Adding support for non-fused Winograd algorithm from Cudnn 5.1.Gravatar Xiaoqiang Zheng2017-02-07
* Make dependencies on CUDA SDK libraries only if CUDA is configuredGravatar A. Unique TensorFlower2017-02-02
* Merge changes from github.Gravatar A. Unique TensorFlower2017-02-01
* Use map for platform-specific SE device optionsGravatar A. Unique TensorFlower2017-01-30
* Remove Eigen/Core includes from public SE headersGravatar A. Unique TensorFlower2017-01-30
* Default impl for StreamExecutorInterface::MemsetGravatar A. Unique TensorFlower2017-01-27
* Remove "using StringPiece" from StreamExecutor lib/path.ccGravatar A. Unique TensorFlower2017-01-27
* Change the way the host platform stream blocks so that it is usable with a co...Gravatar A. Unique TensorFlower2017-01-26
* Stop using DSO loader for CUDA SDK librariesGravatar A. Unique TensorFlower2017-01-25
* Add options argument for DNN activationGravatar A. Unique TensorFlower2017-01-24
* Merge changes from github.Gravatar Shanqing Cai2017-01-23
* Add default ScopedDeviceMemory ctor in StreamExecutorGravatar A. Unique TensorFlower2017-01-20
* Better StreamExecutor constructorGravatar A. Unique TensorFlower2017-01-20
* Add hooks for StreamExecutor module initialization orderingGravatar A. Unique TensorFlower2017-01-19
* Add convolve quantized ops to StreamExecutor APIGravatar A. Unique TensorFlower2017-01-19
* Addition of platform-specific key-value options to StreamExecutor DeviceOptions.Gravatar A. Unique TensorFlower2017-01-19
* StreamExecutor param to specify cuDNN or TF paddingGravatar A. Unique TensorFlower2017-01-19
* Add several operations to the StreamExecutor APIGravatar A. Unique TensorFlower2017-01-17
* Plumb port::Status through the internal synchronous memcopy routines.Gravatar A. Unique TensorFlower2017-01-17
* Fix initialization order problem for mutexes on Mac GPU opensource build.Gravatar Peter Hawkins2016-12-19
* Merge changes from github.Gravatar Martin Wicke2016-12-14
* Find libdevice files in .runfiles when TEST_SRCDIR is not set.Gravatar Jingyue Wu2016-12-13
* Merge changes from github.Gravatar Andrew Harp2016-12-08
* Remove undefined function GetRunfilesDirectory.Gravatar Jingyue Wu2016-12-08
* Separate the stream executor CUDA plugin into its own build target. This allo...Gravatar Peter Hawkins2016-12-07
* Add a Host platform to the stream executor library that runs code on the CPU.Gravatar Peter Hawkins2016-12-05
* Add missing include to tensorflow/stream_executor/kernel.hGravatar Peter Hawkins2016-11-30
* StreamExecutor: Optimize kernel argument packingGravatar Peter Hawkins2016-11-29