diff options
| author |  A. Unique TensorFlower <nobody@tensorflow.org> | 2016-01-24 17:16:23 -0800 |
|---|---|---|
| committer |  Vijay Vasudevan <vrv@google.com> | 2016-01-24 19:32:03 -0800 |
| commit | ff8522de343a90813fc4e5cbb249e308c1819f1d (patch) | |
| tree | d6dab3a0a36bcc5797edeec16aaa6228c0eb46bb /navbar.md | |
| parent | 62e7dec65a90d736d864f2a663f91bbd4a73b2d0 (diff) | |
Eliminate per-op allocation of gpu device wrapper. The PerOpGpuDevice is allocated once in the OpKernelContext::Params struct, then re-used every time a new OpKernelContext uses the Params. Thus in the executor, as long as there is more work to do the PerOpGpuDevice is not freed.
Change: 112909215
Diffstat (limited to 'navbar.md')
0 files changed, 0 insertions, 0 deletions