diff options
author | Vijay Vasudevan <vrv@google.com> | 2015-12-08 09:58:59 -0800 |
---|---|---|
committer | Vijay Vasudevan <vrv@google.com> | 2015-12-08 09:58:59 -0800 |
commit | ddd4aaf5286de24ba70402ee0ec8b836d3aed8c7 (patch) | |
tree | 4efdf6cf4d69b45041fd2a02cd2b7327ea9f1f58 /tensorflow/stream_executor/kernel.cc | |
parent | cd53f3c3302c9312c1840389a9988a879b8b9dd5 (diff) |
TensorFlow: upstream changes to git.
Change 109695551
Update FAQ
Change 109694725
Add a gradient for resize_bilinear op.
Change 109694505
Don't mention variables module in docs
variables.Variable should be tf.Variable.
Change 109658848
Adding an option to create a new thread-pool for each session.
Change 109640570
Take the snapshot of stream-executor.
+ Expose an interface for scratch space allocation in the interface.
Change 109638559
Let image_summary accept uint8 input
This allows users to do their own normalization / scaling if the default
(very weird) behavior of image_summary is undesired.
This required a slight tweak to fake_input.cc to make polymorphically typed
fake inputs infer if their type attr is not set but has a default.
Unfortunately, adding a second valid type to image_summary *disables* automatic
implicit conversion from np.float64 to tf.float32, so this change is slightly
backwards incompatible.
Change 109636969
Add serialization operations for SparseTensor.
Change 109636644
Update generated Op docs.
Change 109634899
TensorFlow: add a markdown file for producing release notes for our
releases. Seed with 0.5.0 with a boring but accurate description.
Change 109634502
Let histogram_summary take any realnumbertype
It used to take only floats, not it understands ints.
Change 109634434
TensorFlow: update locations where we mention python 3 support, update
them to current truth.
Change 109632108
Move HSV <> RGB conversions, grayscale conversions, and adjust_* ops back to tensorflow
- make GPU-capable version of RGBToHSV and HSVToRGB, allows only float input/output
- change docs to reflect new size constraints
- change HSV format to be [0,1] for all components
- add automatic dtype conversion for all adjust_* and grayscale conversion ops
- fix up docs
Change 109631077
Improve optimizer exceptions
1. grads_and_vars is now a tuple, so must be wrapped when passed to format.
2. Use '%r' instead of '%s' for dtype formatting
Base CL: 109697989
Diffstat (limited to 'tensorflow/stream_executor/kernel.cc')
-rw-r--r-- | tensorflow/stream_executor/kernel.cc | 23 |
1 files changed, 3 insertions, 20 deletions
diff --git a/tensorflow/stream_executor/kernel.cc b/tensorflow/stream_executor/kernel.cc index ee0b706eef..64a4e6f49e 100644 --- a/tensorflow/stream_executor/kernel.cc +++ b/tensorflow/stream_executor/kernel.cc @@ -25,7 +25,6 @@ limitations under the License. #include "tensorflow/stream_executor/platform.h" #include "tensorflow/stream_executor/platform/logging.h" #include "tensorflow/stream_executor/stream_executor.h" -#include "tensorflow/stream_executor/stream_executor_internal.h" namespace perftools { namespace gputools { @@ -58,29 +57,13 @@ void KernelMetadata::set_shared_memory_bytes(int shared_memory_bytes) { has_shared_memory_bytes_ = true; } -static internal::KernelInterface *KernelImplementationFromPlatformKind( - PlatformKind platform_kind) { - if (platform_kind == PlatformKind::kCuda) { - return (*internal::MakeCUDAKernelImplementation())(); - } else if (platform_kind == PlatformKind::kOpenCL || - platform_kind == PlatformKind::kOpenCLAltera) { - return (*internal::MakeOpenCLKernelImplementation())(); - } else { - LOG(FATAL) << "cannot create kernel implementation for platform kind: " - << PlatformKindString(platform_kind); - } -} - KernelBase::KernelBase(StreamExecutor *parent) - : implementation_( - KernelImplementationFromPlatformKind(parent->platform_kind())), - parent_(parent) { - DCHECK(parent_ != nullptr); -} + : parent_(parent), + implementation_(parent->implementation()->CreateKernelImplementation()) {} KernelBase::KernelBase(StreamExecutor *parent, internal::KernelInterface *implementation) - : implementation_(implementation), parent_(parent) {} + : parent_(parent), implementation_(implementation) {} KernelBase::~KernelBase() {} |