aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/stream_executor
Commit message (Expand)AuthorAge
* [StreamExecutor] LOG(ERROR) the driver version when cudnnCreate fails.Gravatar Justin Lebar2017-11-10
* Clean up kernels cached by CUDAExecutor.Gravatar Artem Belevich2017-11-07
* Support Cudnn RNN Fp16Gravatar James Qin2017-11-03
* Merge changes from github.Gravatar Andrew Harp2017-11-02
* Prefer cubin over PTX when we launch CUDA kernels.Gravatar Artem Belevich2017-10-31
* Use Windows compatible string comparisons for setting cuda device flags.Gravatar A. Unique TensorFlower2017-10-18
* Add environment variable to enable setting of CUDA context flags.Gravatar A. Unique TensorFlower2017-10-17
* Add an env-var to choose between FP16 and FP32 as the internal compute type f...Gravatar Yangzihao Wang2017-10-10
* Allow tensorflow devices to report their load. This may be used to improve ba...Gravatar A. Unique TensorFlower2017-10-10
* Make error message more explicit when running FusedConv2DBiasActivationOp wit...Gravatar A. Unique TensorFlower2017-10-09
* Merge changes from github.Gravatar Frank Chen2017-10-06
* Add dilation rates support for ConvolutionDescriptor...Gravatar Yangzihao Wang2017-10-05
* Add float16 support to tf.nn.fused_batch_norm on the GPU.Gravatar Reed Wanderman-Milne2017-09-27
* Merge changes from github.Gravatar Shanqing Cai2017-09-25
* Remove RTLD_GLOBAL when loading pywrap_tensorflowGravatar Allen Lavoie2017-09-21
* Add an env-var TF_ENABLE_FFT_TILING_FORWARD.Gravatar Yangzihao Wang2017-09-19
* Automated g4 rollback of changelist 168625243Gravatar Olivia Nordquist2017-09-13
* Log only initial warnings from cuda_dnn scratch allocator.Gravatar A. Unique TensorFlower2017-09-13
* Add int8 version of fused_conv2d_bias_activation operator for the forward phase,Gravatar A. Unique TensorFlower2017-09-06
* Merge changes from github.Gravatar Martin Wicke2017-09-02
* Error out normally instead of asserting if TensorFlow fails to enqueue a conv...Gravatar Benoit Steiner2017-08-24
* Automated g4 rollback of changelist 166276461Gravatar A. Unique TensorFlower2017-08-24
* Add int8 version of fused_conv2d_bias_activation operator for the forward phase,Gravatar A. Unique TensorFlower2017-08-23
* [SE] Change comments/identifiers/logs from when StreamExecutor was GPUExecutor.Gravatar Chris Leary2017-08-22
* Make tensorflow::mutex implement a shared (reader/writer) lock, usingGravatar A. Unique TensorFlower2017-08-17
* Merge changes from github.Gravatar A. Unique TensorFlower2017-08-15
* Re-enable winograd nonfused flag by default.Gravatar Yangzihao Wang2017-08-14
* Return error status for invalid argument for ScratchAllocator.Gravatar Yangzihao Wang2017-08-10
* Fix warnings about non-primary contexts.Gravatar Jingyue Wu2017-08-07
* BUILD dependency cleanup in tensorflow/stream_executor/cudaGravatar A. Unique TensorFlower2017-08-07
* Remove superfluous derived class member "status_"Gravatar A. Unique TensorFlower2017-08-04
* Allows cudnn convolution algorithms to proceed when only find one type of alg...Gravatar Yangzihao Wang2017-08-01
* Support bidi-Cudnn LSTM save/restore.Gravatar James Qin2017-08-01
* Merge changes from github.Gravatar Benoit Steiner2017-08-01
* Fix some typos in StreamExecutor's cuFFT support.Gravatar RJ Ryan2017-07-31
* [SE] Make ExecutorCache thread-safe, change ExecutorCache::Insert to Executor...Gravatar Peter Hawkins2017-07-31
* Let GetBlasGemmAlgorithms() always return true.Gravatar Yangzihao Wang2017-07-21
* Add fused_conv2d_bias_activation operator for the forward phase.Gravatar Yangzihao Wang2017-07-20
* Automated g4 rollback of changelist 162423171Gravatar A. Unique TensorFlower2017-07-18
* Add autotuning code for matmul operator.Gravatar Yangzihao Wang2017-07-18
* Support float64 CuDNN RNNGravatar James Qin2017-07-18
* Add scratch allocator option for 1D, 2D, 3D, and batched cufft plan creation.Gravatar Yangzihao Wang2017-07-11
* Add support for int8 x int8 -> int32 matrix multiplication via cublasGemmEx t...Gravatar A. Unique TensorFlower2017-07-06
* Turn off winograd-nonfused by default again.Gravatar Yangzihao Wang2017-07-06
* [SE] ThenConvolveWithAlgorithm vlogs algorithm configs.Gravatar Jingyue Wu2017-06-27
* In SE_ASSIGN_OR_RETURN change ConsumeValueOrDie to the preferred std::move Va...Gravatar Jacques Pienaar2017-06-22
* [SE] Support alpha scale in cudnnTransformTensorGravatar A. Unique TensorFlower2017-06-20
* Automated g4 rollback of changelist 158939543Gravatar A. Unique TensorFlower2017-06-13
* After synchronizing CUDA device, check for errors.Gravatar A. Unique TensorFlower2017-06-13
* TransformTensor supports NCHW_VECT_C layout and int8 data type.Gravatar Jingyue Wu2017-06-12
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-27 17:54:16 +0000