diff options
| author |  Benjamin Kramer <kramerb@google.com> | 2018-08-03 10:24:13 -0700 |
|---|---|---|
| committer |  TensorFlower Gardener <gardener@tensorflow.org> | 2018-08-03 10:28:08 -0700 |
| commit | e36c16c6720dd64ae5d8a1f8555102a1323af9ae (patch) | |
| tree | 9076cc7fa753542490bac8b1fcd2bc3a3c2ac62a /CODE_OF_CONDUCT.md | |
| parent | 7935c176118f0e50aa657a1c68a85430b70d2245 (diff) | |
[XLA:GPU] Use strided batched gemm instead of building pointer tables.
This is mostly a huge amount of plumbing just to call into the cublas functions.
blasGemmStridedBatched has been available since CUDA 8.0.
For autotuning we'd need cublasGemmStridedBatchedEx, which is new in CUDA 9.2
so I didn't wire that up yet.
PiperOrigin-RevId: 207285707
Diffstat (limited to 'CODE_OF_CONDUCT.md')
0 files changed, 0 insertions, 0 deletions