diff options
author | Justin Lebar <jlebar@google.com> | 2017-03-02 17:49:45 -0800 |
---|---|---|
committer | TensorFlower Gardener <gardener@tensorflow.org> | 2017-03-02 18:08:01 -0800 |
commit | 01194694948eb883e99af597d9dbbf3fc9f5c9e2 (patch) | |
tree | ab3517cf656259681283a90c6682c5b320ac36e3 /tensorflow/stream_executor/stream_executor_pimpl.h | |
parent | e065b3093f4fec5a5f79ad9de81f6baab361962e (diff) |
[XLA] [StreamExecutor] Tune GEMMs when possible.
cublas 8 adds the cublasGemmEx function, which lets you specify an
explicit "algorithm" for the computation. This functions as an opaque
tuning hint to cublas.
This patch adds support for cublasGemmEx to StreamExecutor, and wires up
XLA's GemmThunk to use the new function.
This patch does not add GEMM autotuning support in TensorFlow proper,
only XLA.
Change: 149068961
Diffstat (limited to 'tensorflow/stream_executor/stream_executor_pimpl.h')
-rw-r--r-- | tensorflow/stream_executor/stream_executor_pimpl.h | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/tensorflow/stream_executor/stream_executor_pimpl.h b/tensorflow/stream_executor/stream_executor_pimpl.h index 29ba63af05..5c52afa794 100644 --- a/tensorflow/stream_executor/stream_executor_pimpl.h +++ b/tensorflow/stream_executor/stream_executor_pimpl.h @@ -353,6 +353,9 @@ class StreamExecutor { bool GetConvolveBackwardFilterAlgorithms( std::vector<dnn::AlgorithmType> *out_algorithms); + // Get the list of supported algorithms for BLAS gemm. + bool GetBlasGemmAlgorithms(std::vector<blas::AlgorithmType> *out_algorithms); + // Create an RNN descriptor based on model shapes and configurations. // The caller retains the ownership of the descriptor. port::StatusOr<std::unique_ptr<dnn::RnnDescriptor>> createRnnDescriptor( |