projects / platform / upstream / tensorflow.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: cd67e8e) | patch
Reuse the linear index when broadcasting a contiguous range of dimensions.
authorA. Unique TensorFlower <gardener@tensorflow.org>
Mon, 12 Mar 2018 14:26:13 +0000 (07:26 -0700)
committerTensorFlower Gardener <gardener@tensorflow.org>
Mon, 12 Mar 2018 14:30:43 +0000 (07:30 -0700)
commit12496b26049384b78f63940907078f9269c9866f
tree423958b64a69a2aa8debbf8b3c4125ca772a613atree | snapshot
parentcd67e8eb088537874b53b4fa52d02ff50c4a66facommit | diff
Reuse the linear index when broadcasting a contiguous range of dimensions.

This potentially allows us to get rid of additional mod and div operations.

PiperOrigin-RevId: 188719238
tensorflow/compiler/xla/service/elemental_ir_emitter.cc diff | blob | history
tensorflow/compiler/xla/service/llvm_ir/ir_array.cc diff | blob | history
tensorflow/compiler/xla/service/llvm_ir/ir_array.h diff | blob | history
Domain: Machine Learning / ML Framework;