aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/compiler/xla/service/layout_assignment.cc
Commit message (Expand)AuthorAge
* [XLA] Try to pass layouts through reshapes.Gravatar A. Unique TensorFlower2017-10-17
* [XLA:LLVM] Remove SetTbaaForInstruction.Gravatar Justin Lebar2017-10-06
* [XLA] Make HloModule::computations() return raw pointers.Gravatar Justin Lebar2017-09-29
* [XLA] Make HloComputation::instructions() return a view of HloInstruction*s.Gravatar Justin Lebar2017-09-28
* [XLA] Adds an API to attach a device assignment to HLO operators.Gravatar Peter Hawkins2017-09-24
* Lower vector-matrix dot to LLVM IR if the RHS of the dot can be madeGravatar Sanjoy Das2017-09-14
* [XLA] Separate logical buffer creation and ownership out of tuple pointer ana...Gravatar A. Unique TensorFlower2017-08-21
* Reduce XLA compile time by ~7% for a convolutional image model:Gravatar A. Unique TensorFlower2017-08-18
* [XLA] Do not recompute points-to analysis in iterations of layout assignment.Gravatar Chris Leary2017-08-16
* Do not assign the default layout in case of rank 1 -> effective rank 1 reshapesGravatar A. Unique TensorFlower2017-08-05
* Sped up TuplePointsToAnalysis module by consolidating three hashGravatar Jeffrey A. Dean2017-08-03
* Remove ShapeWithoutPadding() utility function, as it is no longer needed.Gravatar Tayo Oguntebi2017-07-27
* [XLA] Finish normalizing fusion computations into standard computationsGravatar A. Unique TensorFlower2017-07-26
* [XLA] Move remaining hlo graph dumper flags into debug_options.Gravatar Eli Bendersky2017-06-28
* Make transpose layout assignement more clear since reasoning about theGravatar Blake Hechtman2017-06-20
* Add a utility function to ShapeUtil to return a Shape without padding.Gravatar A. Unique TensorFlower2017-06-20
* Improve layout assignment for reshape.Gravatar A. Unique TensorFlower2017-06-20
* Add the ability to verify assumptions about layout assignment after propagationGravatar A. Unique TensorFlower2017-06-12
* [XLA] Simplify Shape traversal visitors.Gravatar Mark Heffernan2017-06-06
* [XLA] Don't add constraints for computations we're not currently looking at.Gravatar Benjamin Kramer2017-05-31
* [XLA] Remove unused InstructionRequiresInputLayoutEqualToOutputLayout hookGravatar Benjamin Kramer2017-05-23
* Merge changes from github.Gravatar A. Unique TensorFlower2017-05-18
* [XLA] Add a way to classify constraints as mandatory or non-mandatory.Gravatar Benjamin Kramer2017-05-18
* Generalize layout assignment for bitcast reshapes.Gravatar A. Unique TensorFlower2017-05-16
* [XLA] Add a target hook to force input layout equal to output layout in layou...Gravatar Benjamin Kramer2017-05-04
* [TF:XLA] Reduce sequential memory usage via better ordering and simulated heap.Gravatar A. Unique TensorFlower2017-03-02
* [XLA] Add basic outfeed support.Gravatar Jacques Pienaar2017-02-27
* [XLA] Make `HloPass` an interface, NFCGravatar A. Unique TensorFlower2017-01-24
* Don't remove send, recv, or trace instructions in DCE pass. Also,Gravatar Mark Heffernan2017-01-19
* Initial open-source release of XLA: Accelerated Linear Algebra.Gravatar Peter Hawkins2017-01-09
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-26 18:01:17 +0000