aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/compiler/xla/service/gpu/ir_emitter_unnested.cc
Commit message (Expand)AuthorAge
* [XLA:GPU] Elide the SequentialThunk when emitting scatter with no copyGravatar Benjamin Kramer2018-10-09
* [XLA:GPU] Add an implementation of scatter for GPUGravatar Benjamin Kramer2018-10-09
* Simplify ir_emitter_unnested so that it doesn't take a look at convGravatar Tim Shen2018-09-19
* Simplify convolution_thunk's interface.Gravatar Tim Shen2018-09-10
* [XLA:GPU] Clean up init thunk handling to handle arbitrary fused init valuesGravatar Benjamin Kramer2018-09-07
* [XLA:GPU] Refactor some code for fusion output handling.Gravatar Bixia Zheng2018-09-06
* Call Cudnn also for grouped convolutions.Gravatar Adrian Kuegel2018-09-03
* Change headers to directly include absl::Span, and clean up the buildGravatar Tim Shen2018-08-30
* [XLA] Rename all (Mutable)ArraySlice to absl::Span.Gravatar Tim Shen2018-08-30
* [XLA] xla::ContainersEqual -> absl::c_equalGravatar Benjamin Kramer2018-08-30
* Use a mixin to reduce llvm::IRBuilder<> related boilerplate.Gravatar Sanjoy Das2018-08-27
* [XLA] Switch to absl::StrFormat.Gravatar Justin Lebar2018-08-27
* [XLA] Unify spelling of 'fusible'Gravatar Benjamin Kramer2018-08-27
* [XLA] Use absl string types and functions instead of the TF versions.Gravatar Justin Lebar2018-08-23
* [XLA] gtl::optional->absl::optionalGravatar Yunxing Dai2018-08-21
* Merged commit includes the following changes:Gravatar Yifei Feng2018-08-21
* [XLA] Use absl::make_unique instead of xla::MakeUnique.Gravatar Justin Lebar2018-08-20
* [XLA] Switch to absl versions of the c_foo functions.Gravatar Justin Lebar2018-08-20
* Automated rollback of commit 4a41f50648929197954d892559587cb76458d306Gravatar A. Unique TensorFlower2018-08-17
* [XLA] Switch to absl versions of the c_foo functions.Gravatar Justin Lebar2018-08-17
* [XLA] Make sure backends that don't support variadic reduce reject it.Gravatar Michael Kuperstein2018-08-09
* [XLA:GPU] Add a generic trip count analysis based on HloEvaluatorGravatar Benjamin Kramer2018-08-08
* [XLA:GPU] Forward batched dot to cublas instead of expanding itGravatar Benjamin Kramer2018-08-03
* [XLA:GPU] Don't emit HostToDevice copiesGravatar Sanjoy Das2018-08-02
* Allow Sort to share the buffer with the operand if it is the only user.Gravatar Adrian Kuegel2018-07-31
* Use constant buffer allocations for XLA:CPUGravatar Sanjoy Das2018-07-27
* Implement constant buffer allocation for XLA:GPUGravatar Sanjoy Das2018-07-26
* Support sorting of key/value pairs on GPU.Gravatar Adrian Kuegel2018-07-26
* [XLA:GPU] Remember to execute non-root outfeed instructions in nested computa...Gravatar Sanjoy Das2018-07-25
* [XLA:CPU/GPU] Implement the parallel Philox random number generation algorithm.Gravatar Bixia Zheng2018-07-25
* [XLA:GPU] Don't lie about buffer alignment to LLVMGravatar Sanjoy Das2018-07-24
* Parallelize BitonicSort on GPU.Gravatar Adrian Kuegel2018-07-24
* [XLA:GPU] Add an operator<< to Thunk::Kind.Gravatar Bixia Zheng2018-07-23
* [XLA:GPU] Make sure that buffers for tuple() have a unique top-level allocationGravatar Benjamin Kramer2018-07-23
* [XLA:GPU] Limit the number of shmem tiles XLA:GPU will use for 021 transposes.Gravatar Justin Lebar2018-07-20
* [XLA] s/ir_builder/b/Gravatar Justin Lebar2018-07-20
* Support unsigned indices for in-place DynamicUpdateSlice.Gravatar Adrian Kuegel2018-07-18
* Implement BitonicSort for GPU.Gravatar Adrian Kuegel2018-07-18
* [XLA:GPU] Generalize the column reduction algorithm to handle tile widths gre...Gravatar Thomas Joerg2018-07-17
* [XLA] Use shfl.sync.down instead of shfl.sync.Gravatar Justin Lebar2018-07-13
* [XLA:GPU] s/llvm_ir::IrArray/IrArray/ in ir_emitter_unnested.Gravatar Justin Lebar2018-07-11
* [XLA:GPU] Cleanups to fused 021 transpose implementation.Gravatar Justin Lebar2018-07-11
* [XLA:GPU] Implement outfeedGravatar Benjamin Kramer2018-07-10
* [XLA:GPU] Delete AnnotateBufferLoadStoreInstructionWithMetadata.Gravatar Justin Lebar2018-07-10
* [XLA:GPU] Enhance the tiled 0-2-1 transpose algorithm to handle fusion.Gravatar Bixia Zheng2018-07-04
* Profile SequentialThunks if they represent one HloInstruction.Gravatar Adrian Kuegel2018-07-04
* [TF:XLA] Split literal_util into {literal, literal_util}.Gravatar Kay Zhu2018-07-03
* [TF:XLA] Split select HLO into array- and tuple-select.Gravatar A. Unique TensorFlower2018-07-03
* Fix check whether there is more than one tile.Gravatar Adrian Kuegel2018-06-27
* [XLA:GPU] Make the input-fused reduce emitter work on 16-bit typesGravatar Benjamin Kramer2018-06-26
generated by cgit v1.2.3 (git 2.39.1) at 2024-05-17 06:15:07 +0000