aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/compiler/xla/service/hlo_cost_analysis.cc
Commit message (Expand)AuthorAge
* [XLA] Add support for convolution feature groups to HloCostAnalysisGravatar David Majnemer2018-09-06
* [XLA] Handle kDomain in HloCostAnalysis.Gravatar Yuanzhong Xu2018-09-06
* Automated rollback of commit 065f9b833ffbb3b2f03d63febb186275674ba133Gravatar Michael Kuperstein2018-08-29
* Automated rollback of commit 150dee25d82589ca109957cc996efbd2a236e044Gravatar Michael Kuperstein2018-08-29
* [XLA] Implement variadic reduce in the evaluator. It is currently supported o...Gravatar Michael Kuperstein2018-08-29
* [XLA] Add the xla interface for CollectivePermute.Gravatar A. Unique TensorFlower2018-08-28
* [XLA] Cleanup Alltoall.Gravatar A. Unique TensorFlower2018-08-22
* Remove HostCompute HLO.Gravatar Tong Shen2018-08-21
* [XLA] Add the xla interface for AllToAll.Gravatar A. Unique TensorFlower2018-08-08
* [XLA] Clean up clang tidy readability warnings in compiler/xlaGravatar Benjamin Kramer2018-08-06
* [XLA] Add guard for bytes accessed in HloCostAnalysis, need layout to determine.Gravatar Chris Leary2018-08-02
* [XLA] Add Scatter HLO.Gravatar A. Unique TensorFlower2018-08-01
* Start implementation of Iota HLO.Gravatar Nick Desaulniers2018-07-20
* [TF:XLA] Split select HLO into array- and tuple-select.Gravatar A. Unique TensorFlower2018-07-03
* Rename HLO opcode kGenerateToken to kAfterAll.Gravatar Mark Heffernan2018-06-25
* [XLA] Handle kDynamicSlice and kDynamicUpdateSlice correctly in HloCostAnalysisGravatar Michael Kuperstein2018-06-12
* Add kGenerateToken HLO instruction.Gravatar Mark Heffernan2018-06-08
* [XLA] Handle kSlice correctly in HloCostAnalysisGravatar David Majnemer2018-06-07
* [XLA] Ergonomic improvements to --xla_hlo_profile.Gravatar Justin Lebar2018-05-14
* Automated g4 rollback of changelist 192180356Gravatar Dimitris Vardoulakis2018-04-18
* Add opcode for new instruction that broadcasts degenerate dimensions.Gravatar Dimitris Vardoulakis2018-04-09
* [XLA] Accurately measure FLOPs for base-dilated convolutionsGravatar David Majnemer2018-03-27
* [XLA] Add some plumbing, documentation, verification and shape inference for ...Gravatar Sanjoy Das2018-02-16
* [TF:XLA] Adds HostCompute HLO - a pseudo-op to represent host-side computation.Gravatar A. Unique TensorFlower2018-02-16
* Internal changeGravatar Justin Lebar2018-02-02
* Automated g4 rollback of changelist 180000981Gravatar A. Unique TensorFlower2018-01-02
* Automated g4 rollback of changelist 179983419Gravatar A. Unique TensorFlower2017-12-23
* Adds FFT for XLA: CPU via Eigen, GPU via cuFFT.Gravatar A. Unique TensorFlower2017-12-22
* Allow CrossReplicaSum to take multiple operands internally.Gravatar Bjarke Hammersholt Roune2017-12-05
* [XLA] Adds Dot with DotDimensionNumbers proto for specifying arbitrary contra...Gravatar A. Unique TensorFlower2017-11-30
* [XLA] Add conditional HloInstruction and handle conditional in DFS visitors.Gravatar A. Unique TensorFlower2017-11-17
* Rename optimal to optimal_seconds in HloCostAnalysis etc.Gravatar Sanjoy Das2017-11-17
* Change for asynchronous Send and Recv by splitting Send into {Send, SendDone}Gravatar HyoukJoong Lee2017-11-10
* [TF:XLA] Add a const HLO visitor.Gravatar A. Unique TensorFlower2017-11-02
* [TF:XLA] Reduce boilerplate code in HLO visitors.Gravatar A. Unique TensorFlower2017-10-30
* [XLA] Add support for convolutions with no spatial dimensionsGravatar David Majnemer2017-10-23
* Automated g4 rollback of changelist 170358888Gravatar David Majnemer2017-10-12
* Automated g4 rollback of changelist 170130811Gravatar David Majnemer2017-09-28
* [XLA] Split input and output in ConvolutionDimensionNumbersGravatar David Majnemer2017-09-26
* Verify the output shapes of (almost) all HLO opcodes in the HloVerifier.Gravatar Mark Heffernan2017-09-14
* [TF:XLA] Don't pass opcode separately in two HLO visitor functions.Gravatar A. Unique TensorFlower2017-08-30
* Implement Batchnorm Inference by expanding them into smaller ops.Gravatar A. Unique TensorFlower2017-08-17
* Improve handling of transcendental operations in the Hlo profile:Gravatar A. Unique TensorFlower2017-08-02
* Allow cost estimates to differ per backend and include the estimates into the...Gravatar Bjarke Hammersholt Roune2017-07-31
* [BatchNorm] Skeleton code to implement BatchNormGradGravatar A. Unique TensorFlower2017-07-06
* Add a time estimation to HloCostAnalysis and represent properties as a map so...Gravatar Bjarke Hammersholt Roune2017-06-27
* [XLA] Remove "operand" argument from HandleReducePrecision.Gravatar A. Unique TensorFlower2017-06-27
* Remove operand parameters from Handle{Maximum,Minimum,Convert,Copy}.Gravatar A. Unique TensorFlower2017-06-20
* [XLA] Update hlo_cost_analysis to account for fusion nodes with multiple outputsGravatar David Majnemer2017-06-19
* Remove operand parameters from HandleElementwiseUnary and HandleElementwiseBi...Gravatar A. Unique TensorFlower2017-06-19