index
:
tensorflow
master
machine learning framework
about
summary
refs
log
tree
commit
diff
homepage
log msg
author
committer
range
path:
root
/
tensorflow
/
stream_executor
/
cuda
Commit message (
Expand
)
Author
Age
*
Disable the cuDNN workarounds if the version number is new enough to get the ...
Tim Shen
2018-10-02
*
Merge pull request #21958 from MattConley:CudaOccupancy
TensorFlower Gardener
2018-10-01
|
\
*
|
Move winograd algorithm workaround to stream executor.
Tim Shen
2018-09-21
*
|
[SE] Restore int8x4 data types if that's the requested DataLayout for fused conv
Benjamin Kramer
2018-09-18
*
|
Fix and complete StreamExecutor's DoFusedConvolve:
Tim Shen
2018-09-17
*
|
Zero out the result buffer for strided conv backward filter for NHWC layouts.
Tim Shen
2018-09-06
|
*
Fully fixed clang errors
Matt Conley
2018-09-06
|
*
Fixed clang formatting
Matt Conley
2018-09-06
|
*
Recommended typo fix
Matt Conley
2018-09-04
|
*
Fixed transition typo
Matt Conley
2018-09-04
|
*
Move CUDA-specific occupancy calculation into proper file
Matt Conley
2018-09-04
*
|
Remove (Mutable)ArraySlice implementation and alias them to absl::Span.
Tim Shen
2018-08-30
|
*
Update GPU occupancy checking to utilize CUDA's occupancy calculator functions
Matt Conley
2018-08-28
|
/
*
Replaced calls to tensorflow::StringPiece::ToString with string conversions.
A. Unique TensorFlower
2018-08-22
*
Merge pull request #20708 from ROCmSoftwarePlatform:upstream-staging-stream-e...
TensorFlower Gardener
2018-08-07
|
\
*
|
[XLA:GPU] Add a fast version of gemmStridedBatched for cuda 9.1
Benjamin Kramer
2018-08-03
*
|
[XLA:GPU] Use strided batched gemm instead of building pointer tables.
Benjamin Kramer
2018-08-03
|
*
Add scratch memory size in AlgorithmDesc
Wen-Heng (Jack) Chung
2018-08-02
*
|
[SE] Allow context reuse in CreatedContexts::Add.
Justin Lebar
2018-08-01
*
|
[SE] Add an nvbugs link.
Justin Lebar
2018-08-01
*
|
[SE] Add additional log statements to DoBlasGemmWithAlgorithmImpl.
Justin Lebar
2018-07-31
*
|
[SE] Add new cublas algorithms from CUDA 9.2.
Justin Lebar
2018-07-31
*
|
[SE] Add missing cublas algorithms for cuda 9.0, CUBLAS_GEMM_ALGO{3,4}_TENSOR...
Justin Lebar
2018-07-31
|
/
*
Set the correct context when calling cudnnCreate.
A. Unique TensorFlower
2018-07-26
*
[SE] Try again to query the GPU driver for error descriptions
Benjamin Kramer
2018-07-26
*
Teach StreamExecutor to load modules and resolve symbols in them
Sanjoy Das
2018-07-23
*
Automated rollback of commit 36a66347e8e344cddee4a8d9123ccbcae40011b1
A. Unique TensorFlower
2018-07-18
*
Merge pull request #20675 from ROCmSoftwarePlatform:upstream-staging-stream-e...
TensorFlower Gardener
2018-07-18
|
\
*
|
Support identity activation function in Cudnn implementation of fused conv2d ...
A. Unique TensorFlower
2018-07-17
*
|
Error on some documented invalid Cudnn inputs. Cudnn should have
A. Unique TensorFlower
2018-07-17
*
|
Merge pull request #20706 from ROCmSoftwarePlatform:upstream-staging-stream-e...
TensorFlower Gardener
2018-07-16
|
\
\
|
|
*
[ROCm] Interface changes for StreamExecutor to support both CUDA and ROCm
Wen-Heng (Jack) Chung
2018-07-12
|
|
/
|
/
|
|
*
[ROCm] Interface changes for pooling APIs in StreamExecutor
Wen-Heng (Jack) Chung
2018-07-11
|
/
*
Workaround the cudnn 7.1.4 correctness bug, where the workspace is required t...
A. Unique TensorFlower
2018-07-02
*
Improve filter for cuBLAS bug.
A. Unique TensorFlower
2018-06-19
*
Rollback of changelist 200200356. We might want to support GPUs on MacOS agai...
A. Unique TensorFlower
2018-06-19
*
Fix a build failure when cuda version is less than 9000.
A. Unique TensorFlower
2018-06-13
*
Detect configurations that would be hitting a bug in cuBLAS and report an error.
A. Unique TensorFlower
2018-06-13
*
Remove OS X code from CUDA stream executor because that platform is no longer...
A. Unique TensorFlower
2018-06-12
*
Unify cuDNN descriptor wrapper names.
A. Unique TensorFlower
2018-06-12
*
Detect configurations that would be hitting bugs in cuDNN and report an error.
A. Unique TensorFlower
2018-06-08
*
Do not enable tensor ops for cuDNN RNN unless explicitly specified.
A. Unique TensorFlower
2018-06-05
*
Unify error handling in CudnnSupport.
A. Unique TensorFlower
2018-06-01
*
Fix GPU build on windows
Smit Hinsu
2018-05-29
*
Merge changes from github.
Yifei Feng
2018-05-24
*
Add convolution with NHWC layout to stream executor.
A. Unique TensorFlower
2018-05-22
*
Introduce an option to allocate CUDA unified memory
Smit Hinsu
2018-05-21
*
Rollforward of CL 197167501, without enabling CUDNN_FFT_TILING_FORWARD becaus...
A. Unique TensorFlower
2018-05-20
*
Automated g4 rollback of changelist 197118212
A. Unique TensorFlower
2018-05-18
*
Dropping support for CUDA < 8.
A. Unique TensorFlower
2018-05-18
[next]