projects / platform / upstream / tensorflow.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: a42d2f4) | patch
[XLA:GPU] Emit the final write of the tuple pointers
authorBenjamin Kramer <kramerb@google.com>
Wed, 16 May 2018 18:45:56 +0000 (11:45 -0700)
committerTensorFlower Gardener <gardener@tensorflow.org>
Wed, 16 May 2018 18:48:33 +0000 (11:48 -0700)
commit0f7bb5b3d6da395e69e8daa236355dfbd91cbf93
treec945d0fd7593941329c2e53376aec1b11cd66db3tree | snapshot
parenta42d2f4e9af8cdb8662c2dd3edabb6a25a848eb6commit | diff
[XLA:GPU] Emit the final write of the tuple pointers

Turns out this doesn't matter when the fusion is emitted as a kernel, but does
when the whole thing is inlined. Oops.

PiperOrigin-RevId: 196863545
tensorflow/compiler/xla/service/gpu/ir_emitter_nested.cc diff | blob | history
tensorflow/compiler/xla/tests/multioutput_fusion_test.cc diff | blob | history
Domain: Machine Learning / ML Framework;