aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/compiler/xla/service/hlo_cost_analysis.cc
Commit message (Expand)AuthorAge
...
* Add plumbing for a ReducePrecision operation.Gravatar A. Unique TensorFlower2017-06-16
* We believe a fused version of batch_norm_op can speed the algorithm up. This ...Gravatar A. Unique TensorFlower2017-06-13
* Normalize arguments for HandleDynamicSlice. NFC.Gravatar A. Unique TensorFlower2017-05-16
* [XLA] Only pass instruction in instruction visitor functions.Gravatar A. Unique TensorFlower2017-04-14
* [XLA] Don't crash when analyzing ops with no layout contained in a fused op.Gravatar A. Unique TensorFlower2017-03-31
* [XLA] Add support for profiling multiple computationsGravatar David Majnemer2017-03-01
* Add bytes accessed to HLO profile output. Bytes accessed is a measure of the ...Gravatar Mark Heffernan2017-02-10
* Add HLO rematerialization transformation to reduce memory usage.Gravatar Mark Heffernan2017-02-10
* Add bytes_accessed field to HloCostAnalysis.Gravatar Mark Heffernan2017-02-08
* [XLA] Correctly count FLOPs for fusion nodes in HloCostAnalysisGravatar David Majnemer2017-01-29
* Addition of Outfeed HLO op.Gravatar Tayo Oguntebi2017-01-27
* [XLA] Improve cost analysis for certain operationsGravatar David Majnemer2017-01-26
* 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 2024-06-18 12:40:29 +0000