experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
STT-tensorflow/tensorflow/compiler/xla/service
History
George Karpenkov de5bfc8bb6 [XLA:GPU] [NFC] Clarify types in AllReduceCombiner 
PiperOrigin-RevId: 361234109
Change-Id: I5a89b41f600d6e03c75366fb41e1b5fdbefe9f1a
2021-03-05 15:16:41 -08:00
..
cpu
[XLA] Have XLA:CPU depend on AArch64CodeGen in all ARM configurations
2021-03-04 17:34:20 -08:00
g3doc
…
gpu
[XLA:GPU] Enforce collectives ordering to be their appearence in the module
2021-03-04 21:47:17 -08:00
graphcycles
Update benchmarks to use newer API
2020-11-24 11:59:06 -08:00
interpreter
[XLA] Change eigh client library to produce a CustomCall that is expanded by an expander pass.
2021-03-01 08:12:43 -08:00
llvm_ir
Ensure that trivial types are passed by value rather than reference
2021-03-04 22:09:46 -08:00
mlir_gpu
[XLA:GPU] Fix build failure
2021-02-26 14:24:18 -08:00
spmd
[XLA] Make the canonicalize all-gather pass add a new/exclusive all-gather dimension.
2021-03-03 01:06:58 -08:00
algebraic_simplifier_proof_distributive_property.py
…
algebraic_simplifier_test.cc
Internal clean up
2021-02-22 08:46:38 -08:00
algebraic_simplifier.cc
[XLA] Simplify unsigned comparisons against 0
2021-02-12 23:10:45 -08:00
algebraic_simplifier.h
[XLA] Adding an option to disable negative padding replacement in the algebraic_simplifier.
2021-01-22 16:35:03 -08:00
all_gather_decomposer_test.cc
[XLA] Fix some all-gather issues.
2020-05-19 17:55:08 -07:00
all_gather_decomposer.cc
[XLA] Fix some all-gather issues.
2020-05-19 17:55:08 -07:00
all_gather_decomposer.h
[XLA] Fix some all-gather issues.
2020-05-19 17:55:08 -07:00
all_reduce_combiner_test.cc
Verify replica count from AllReduce replica group config
2020-04-27 08:53:44 -07:00
all_reduce_combiner.cc
[XLA:GPU] [NFC] Clarify types in AllReduceCombiner
2021-03-05 15:16:41 -08:00
all_reduce_combiner.h
[XLA:GPU] Add an AllReduceCombiner pass, that merges AllReduce operations.
2020-02-19 22:07:07 -08:00
all_reduce_simplifier_test.cc
[XLA] replace all-reduces with a singleton replica_group_size with the operand.
2020-09-11 08:58:29 -07:00
all_reduce_simplifier.cc
[XLA] replace all-reduces with a singleton replica_group_size with the operand.
2020-09-11 08:58:29 -07:00
all_reduce_simplifier.h
…
all_to_all_decomposer.cc
[XLA] Use array all to all in the client frontend
2021-01-29 20:50:10 -08:00
all_to_all_decomposer.h
[XLA] Use array all to all in the client frontend
2021-01-29 20:50:10 -08:00
allocation_tracker.cc
Remove platform field from shaped buffer.
2020-10-30 14:26:55 -07:00
allocation_tracker.h
Prefixing TensorFlow thread annotation macros with TF_.
2020-03-05 08:42:01 -08:00
ar_crs_combiner_test.cc
[XLA] Use CollectiveOpGroup mode to drive some of the HLO verification
2021-02-23 10:15:41 -08:00
ar_crs_combiner.cc
[XLA] Identical check shouldn't skip operands for all-reduces.
2020-12-18 10:30:34 -08:00
ar_crs_combiner.h
…
backend.cc
…
backend.h
Prefixing TensorFlow thread annotation macros with TF_.
2020-03-05 08:42:01 -08:00
batch_dot_simplification_test.cc
…
batch_dot_simplification.cc
[XLA] Add an optional preferred_element_type argument to Dot/Conv builder methods to enable generating HLOs that has wider accumulation type than default shape inference result.
2020-11-20 13:16:56 -08:00
batch_dot_simplification.h
…
batchnorm_expander_test.cc
…
batchnorm_expander.cc
…
batchnorm_expander.h
…
bfloat16_conversion_folding_test.cc
Enable using global ids for replica groups in AllReduce
2020-02-21 19:01:52 -08:00
bfloat16_conversion_folding.cc
[XLA] Stop the bf16 conversion folding from converting unused tuple outputs.
2020-11-09 13:08:11 -08:00
bfloat16_conversion_folding.h
…
bfloat16_normalization_test.cc
Add optional layout constraint to AllToAll
2020-04-27 18:37:21 -07:00
bfloat16_normalization.cc
…
bfloat16_normalization.h
…
bfloat16_propagation_test.cc
[XLA] Bug fix for bfloat16 propagation where fixed-point repetition of resolving aliasing operands are needed.
2020-11-04 14:12:17 -08:00
bfloat16_propagation.cc
TPU layout method cleanup by removing one parameter.
2021-03-01 15:38:15 -08:00
bfloat16_propagation.h
TPU layout method cleanup by removing one parameter.
2021-03-01 15:38:15 -08:00
bfloat16_support.cc
[XLA] Introducing AllGather HLO and a decomposition pass
2020-05-09 12:22:17 -07:00
bfloat16_support.h
…
buffer_assignment_test.cc
[XLA] Adding method to construct log of buffer liveness information in BufferAssignment.
2021-01-27 15:53:40 -08:00
buffer_assignment.cc
[XLA] Print live ranges by every moment.
2021-02-12 17:48:57 -08:00
buffer_assignment.h
[XLA] Adding method to construct log of buffer liveness information in BufferAssignment.
2021-01-27 15:53:40 -08:00
buffer_value_containers.h
…
buffer_value.cc
[XLA] BufferValue::Color now type aliases int64.
2020-05-27 09:35:14 -07:00
buffer_value.h
[XLA] Deprecate BufferValue::color.
2020-06-29 14:37:43 -07:00
BUILD
[XLA:GPU] Enforce collectives ordering to be their appearence in the module
2021-03-04 21:47:17 -08:00
call_graph_test.cc
…
call_graph.cc
This CL optimizes C++11 range-based for loops where the variable is copied in each iteration but it would suffice to obtain it by const reference. This is only applied to loop variables of types that are expensive to copy which means they are not trivially copyable or have a non-trivial copy constructor or destructor.
2020-04-06 17:55:23 -07:00
call_graph.h
…
call_inliner_test.cc
Convert absl string_view constants to const, rather than constexpr.
2020-02-05 11:15:53 -08:00
call_inliner.cc
[XLA] Fix VLOG interaction with CallInliner
2021-01-06 16:15:13 -08:00
call_inliner.h
…
channel_tracker.cc
…
channel_tracker.h
Prefixing TensorFlow thread annotation macros with TF_.
2020-03-05 08:42:01 -08:00
cholesky_expander.cc
[XLA] Add complex number support to HLO cholesky decomposition implementation.
2020-09-18 07:08:30 -07:00
cholesky_expander.h
[XLA] Make the inner block kernel of CholeskyExpander override-able.
2020-08-31 09:33:25 -07:00
collective_ops_utils_test.cc
[XLA:GPU] Fix collective communication ops to work correctly in SPMD mode.
2021-02-22 12:42:21 -08:00
collective_ops_utils.cc
[XLA] Use CollectiveOpGroup mode to drive some of the HLO verification
2021-02-23 10:15:41 -08:00
collective_ops_utils.h
[XLA:GPU][NFC] Add some additional logging for collective thunks.
2021-02-22 14:47:14 -08:00
collectives_schedule_linearizer_test.cc
[XLA:GPU] [NFC] CollectiveScheduleLinearizer: test for dependent collectives
2021-03-05 15:01:35 -08:00
collectives_schedule_linearizer.cc
[XLA:GPU] [NFC] CollectiveScheduleLinearizer: test for dependent collectives
2021-03-05 15:01:35 -08:00
collectives_schedule_linearizer.h
[XLA:GPU] Enforce collectives ordering to be their appearence in the module
2021-03-04 21:47:17 -08:00
comparison_expander.cc
Adding total-order comparison support in proto and HloInstruction.
2020-08-10 09:40:29 -07:00
comparison_expander.h
Adding total-order comparison support in proto and HloInstruction.
2020-08-10 09:40:29 -07:00
compilation_cache.cc
…
compilation_cache.h
Prefixing TensorFlow thread annotation macros with TF_.
2020-03-05 08:42:01 -08:00
compilation_stats.cc
…
compilation_stats.h
…
compile_only_service.cc
Deprecate broadcast-replicated-params option in xla::ExecutionOptions proto.
2021-02-18 12:50:44 -08:00
compile_only_service.h
…
compiler.cc
[mlir] Add FusionOp to XLA HLO -> LMHLO
2020-10-13 14:20:52 -07:00
compiler.h
Updates weight broadcast option to go through different proto.
2021-02-27 01:55:04 -08:00
computation_layout.cc
This CL adds the following changes:
2020-07-01 16:45:34 -07:00
computation_layout.h
This CL adds the following changes:
2020-07-01 16:45:34 -07:00
computation_placer.cc
[XLA][NFC] Add a struct to describe the LogicalID of a device.
2021-02-22 19:40:16 -08:00
computation_placer.h
[XLA][NFC] Add a struct to describe the LogicalID of a device.
2021-02-22 19:40:16 -08:00
conditional_canonicalizer_test.cc
Canonicalize dense array conditional into tuple conditional with one element.
2020-07-17 11:55:43 -07:00
conditional_canonicalizer.cc
Fix conditional canonicalizer to use clone instead of mutating existing conditional's shape.
2020-07-27 13:44:30 -07:00
conditional_canonicalizer.h
Canonicalize dense array conditional into tuple conditional with one element.
2020-07-17 11:55:43 -07:00
conditional_code_motion_test.cc
[XLA] Add auto-tuning support for conditional code motion.
2021-02-22 14:41:21 -08:00
conditional_code_motion.cc
[XLA] Add auto-tuning support for conditional code motion.
2021-02-22 14:41:21 -08:00
conditional_code_motion.h
[XLA] Add auto-tuning support for conditional code motion.
2021-02-22 14:41:21 -08:00
conditional_simplifier_test.cc
[XLA] Add token support to conditional_simplifier
2020-06-02 11:00:01 -07:00
conditional_simplifier.cc
Condintional Simplifier: Return early before creating any instruction.
2020-11-20 18:39:27 -08:00
conditional_simplifier.h
Add interface for HLO passes which run on HloModuleGroup.
2018-09-19 08:16:42 -07:00
conditional_to_select_test.cc
…
conditional_to_select.cc
…
conditional_to_select.h
…
convert_operand_folding_test.cc
[XLA] IntegralUpcaster->OperandUpcaster to allow auto upcasting floating point types.
2020-12-29 11:14:04 -08:00
convert_operand_folding.cc
[XLA] IntegralUpcaster->OperandUpcaster to allow auto upcasting floating point types.
2020-12-29 11:14:04 -08:00
convert_operand_folding.h
[XLA] Add a pass to fold hlo(convert(a),convert(b)) into hlo(a,b) to enable an alternative way of specifying wider accumulation type than the shape inference result for HLOs that support it.
2020-11-25 12:57:30 -08:00
convolution_4d_expander_test.cc
…
convolution_4d_expander.cc
…
convolution_4d_expander.h
…
convolution_group_converter_test.cc
[XLA] Fix the condition for rewriting batch group convolutions to include when the input batch is not equal to the batch group count.
2020-04-08 16:50:13 -07:00
convolution_group_converter.cc
[XLA] Add an optional preferred_element_type argument to Dot/Conv builder methods to enable generating HLOs that has wider accumulation type than default shape inference result.
2020-11-20 13:16:56 -08:00
convolution_group_converter.h
…
copy_insertion_test.cc
[XLA/GPU] Re-enable h-loop-fusion to share operands with users.
2021-02-24 15:34:18 -08:00
copy_insertion.cc
[XLA] Fix TryElideCopy in copy insertion to traverse all related sources/destinations when considering removing a copy. Also modify the constructor of CopyRemover to check the ordering of aliased live ranges only when using the default dependence-based HloOrdering.
2021-02-25 10:10:41 -08:00
copy_insertion.h
[XLA] Fix TryElideCopy in copy insertion to traverse all related sources/destinations when considering removing a copy. Also modify the constructor of CopyRemover to check the ordering of aliased live ranges only when using the default dependence-based HloOrdering.
2021-02-25 10:10:41 -08:00
custom_call_target_registry.cc
…
custom_call_target_registry.h
…
defuser_test.cc
…
defuser.cc
[XLA] Migrate from gtl::FlatMap to absl::flat_hash_map
2018-10-01 13:53:07 -07:00
defuser.h
…
despecializer.cc
…
despecializer.h
…
dfs_hlo_visitor_with_default_test.cc
…
dfs_hlo_visitor_with_default.h
Introduce dynamic reshape op.
2020-08-14 15:48:19 -07:00
dfs_hlo_visitor.cc
…
dfs_hlo_visitor.h
Introduce dynamic reshape op.
2020-08-14 15:48:19 -07:00
dot_as_convolution_util.cc
[XLA] Add an optional preferred_element_type argument to Dot/Conv builder methods to enable generating HLOs that has wider accumulation type than default shape inference result.
2020-11-20 13:16:56 -08:00
dot_as_convolution_util.h
[XLA:SPMD] 1st step to refactor convolution_handler.
2020-09-11 19:33:47 -07:00
dot_decomposer_test.cc
Improve DotDecomposer to not add unnecessary non-contracting dimensions.
2020-05-26 05:49:19 -07:00
dot_decomposer.cc
[XLA] Invert the permutation convention for xla::ShapeUtil::PermuteDimensions.
2021-02-10 13:20:44 -08:00
dot_decomposer.h
…
dump.cc
Minor changes on dumping utility functions.
2021-03-04 21:54:25 -08:00
dump.h
Minor changes on dumping utility functions.
2021-03-04 21:54:25 -08:00
dynamic_dimension_inference_test.cc
Fix a bug reshape dynamic dimension inference bug.
2020-11-18 16:51:43 -08:00
dynamic_dimension_inference.cc
Support more cases for strided_slice gradient.
2021-02-17 12:18:39 -08:00
dynamic_dimension_inference.h
Support dynamic spatial dimensions in convolution.
2020-10-27 10:26:50 -07:00
dynamic_index_splitter_test.cc
…
dynamic_index_splitter.cc
…
dynamic_index_splitter.h
…
dynamic_padder_test.cc
Add a field in hlo proto to record if graph has dynamic shapes.
2021-02-22 21:37:05 -08:00
dynamic_padder.cc
Add a field in hlo proto to record if graph has dynamic shapes.
2021-02-22 21:37:05 -08:00
dynamic_padder.h
[XLA]Add HLO infrastructure to support dynamic op lowering.
2020-04-30 17:00:49 -07:00
dynamic_parameter_binding_test.cc
…
dynamic_parameter_binding.cc
…
dynamic_parameter_binding.h
…
dynamic_update_slice_test.cc
…
dynamic_window_utils.cc
Support dynamic spatial dimensions in convolution.
2020-10-27 10:26:50 -07:00
dynamic_window_utils.h
Support dynamic spatial dimensions in convolution.
2020-10-27 10:26:50 -07:00
eigh_expander.cc
[XLA] Add support for Hermitian eigendecompositions in eigh expander pass.
2021-03-02 06:58:20 -08:00
eigh_expander.h
[XLA] Change eigh client library to produce a CustomCall that is expanded by an expander pass.
2021-03-01 08:12:43 -08:00
elemental_ir_emitter_test.cc
…
elemental_ir_emitter.cc
[XLA:CPU] More accurate expm1 when x is small, take two
2021-02-22 11:29:40 -08:00
elemental_ir_emitter.h
Merge pull request #47164 from nouiz:upstream-llvm_var_name
2021-02-17 06:12:19 -08:00
executable.cc
[XLA] Use DumpToFileInDir for hlo_execution_profile_data
2021-02-05 15:13:22 -08:00
executable.h
Do not creates MaybeOwningDeviceMemory and ExecutionInput object in TF/XLA. This lower XLA launch overhead.
2021-01-07 07:04:22 -08:00
execution_tracker.cc
…
execution_tracker.h
Prefixing TensorFlow thread annotation macros with TF_.
2020-03-05 08:42:01 -08:00
flatten_call_graph_test.cc
…
flatten_call_graph.cc
…
flatten_call_graph.h
…
fusion_node_indexing_evaluation_test.cc
Evaluate the maximum code duplication in fusion nodes instead of average.
2020-09-02 07:36:23 -07:00
fusion_node_indexing_evaluation.cc
Prevent creating fusions which could cause problems.
2020-10-29 09:12:46 -07:00
fusion_node_indexing_evaluation.h
Refactor the code to avoid duplication (NFC).
2020-10-01 05:16:36 -07:00
fusion_queue.h
* Add virtual function NotFusingInstruction to FusionQueue to get necessary information for some subclasses.
2021-02-16 10:38:49 -08:00
gather_expander_test.cc
Expand simple gathers into dynamic-slice.
2020-08-07 16:06:09 -07:00
gather_expander.cc
Expand simple gathers into dynamic-slice.
2020-08-07 16:06:09 -07:00
gather_expander.h
Expand simple gathers into dynamic-slice.
2020-08-07 16:06:09 -07:00
generic_transfer_manager.cc
[XLA] Drop useless shape argument from TransferManager::TransferLiteralFromOutfeed.
2021-01-25 17:29:36 -08:00
generic_transfer_manager.h
[XLA] Drop useless shape argument from TransferManager::TransferLiteralFromOutfeed.
2021-01-25 17:29:36 -08:00
global_device_id.cc
[NFC] Moved GlobalDeviceId into its own file as it is also used by the CPU runtime.
2020-11-24 04:21:38 -08:00
global_device_id.h
[NFC] Moved GlobalDeviceId into its own file as it is also used by the CPU runtime.
2020-11-24 04:21:38 -08:00
heap_simulator_test.cc
[XLA/GPU] Size-constrained buffer allocation.
2020-10-07 15:40:30 -07:00
heap_simulator.cc
Merge pull request #43850 from trentlo:size_constrained_buf_alloc_upstream
2020-10-28 04:19:38 -07:00
heap_simulator.h
[TF/XLA] Fix a compilation warning due to -Werror,-Wreorder-ctor.
2020-10-22 10:33:49 -07:00
hlo_alias_analysis_test.cc
[XLA] Try committing DUS buffer sharing again with fixes.
2020-09-17 09:20:11 -07:00
hlo_alias_analysis.cc
[XLA] Try committing DUS buffer sharing again with fixes.
2020-09-17 09:20:11 -07:00
hlo_alias_analysis.h
Internal change
2020-09-12 16:03:35 -07:00
hlo_buffer.cc
…
hlo_buffer.h
…
hlo_casting_utils_test.cc
…
hlo_casting_utils.h
Add an error message when HLO casting fails.
2021-02-18 12:30:57 -08:00
hlo_clone_context.h
…
hlo_computation_test.cc
…
hlo_computation.cc
[XLA] Move HLO instruction OpMetadata dummy names to a new field.
2021-02-08 17:19:21 -08:00
hlo_computation.h
Add add new option in HloComputation::AddInstruction to add instruction with different name.
2020-10-08 13:08:57 -07:00
hlo_constant_folding_test.cc
[XLA] Invert the meaning of xla::Permute, add an inverse xla::PermuteInverse().
2021-02-10 12:21:04 -08:00
hlo_constant_folding.cc
…
hlo_constant_folding.h
…
hlo_cost_analysis_test.cc
[XLA] Make HloCostAnalysis account for nested shapes to calculate bytes accessed in fusion, infeed and outfeed
2021-02-10 11:44:40 -08:00
hlo_cost_analysis.cc
[XLA] Make HloCostAnalysis account for nested shapes to calculate bytes accessed in fusion, infeed and outfeed
2021-02-10 11:44:40 -08:00
hlo_cost_analysis.h
Update hlo cost function visibility
2020-12-17 10:52:08 -08:00
hlo_creation_utils_test.cc
…
hlo_creation_utils.cc
[XLA] Add an optional preferred_element_type argument to Dot/Conv builder methods to enable generating HLOs that has wider accumulation type than default shape inference result.
2020-11-20 13:16:56 -08:00
hlo_creation_utils.h
[XLA] Add an optional preferred_element_type argument to Dot/Conv builder methods to enable generating HLOs that has wider accumulation type than default shape inference result.
2020-11-20 13:16:56 -08:00
hlo_cse_test.cc
…
hlo_cse.cc
[XLA] Avoid hash collisions in CseHash.
2020-02-20 00:01:30 -08:00
hlo_cse.h
…
hlo_dataflow_analysis_test.cc
[XLA/GPU] Re-enable h-loop-fusion to share operands with users.
2021-02-24 15:34:18 -08:00
hlo_dataflow_analysis.cc
[XLA/GPU] Fix a bug in CanShareOperandBufferWithUser().
2021-02-24 15:34:29 -08:00
hlo_dataflow_analysis.h
Internal change
2020-09-24 10:22:25 -07:00
hlo_dce_test.cc
…
hlo_dce.cc
[XLA] Introducing AllGather HLO and a decomposition pass
2020-05-09 12:22:17 -07:00
hlo_dce.h
[XLA] Resubmit DCE change
2020-03-03 17:43:00 -08:00
hlo_domain_isolator.cc
…
hlo_domain_isolator.h
…
hlo_domain_map.cc
…
hlo_domain_map.h
…
hlo_domain_metadata.h
…
hlo_domain_remover.cc
minor spelling tweaks
2019-12-09 18:21:12 +09:00
hlo_domain_remover.h
Add interface for HLO passes which run on HloModuleGroup.
2018-09-19 08:16:42 -07:00
hlo_domain_test.cc
…
hlo_domain_verifier.cc
…
hlo_domain_verifier.h
…
hlo_element_type_converter_test.cc
…
hlo_element_type_converter.cc
…
hlo_element_type_converter.h
…
hlo_evaluator_test.cc
[XLA] Invert the meaning of xla::Permute, add an inverse xla::PermuteInverse().
2021-02-10 12:21:04 -08:00
hlo_evaluator_typed_visitor_bfloat16.cc
…
hlo_evaluator_typed_visitor_bool.cc
…
hlo_evaluator_typed_visitor_complex64.cc
…
hlo_evaluator_typed_visitor_complex128.cc
…
hlo_evaluator_typed_visitor_double.cc
…
hlo_evaluator_typed_visitor_float.cc
…
hlo_evaluator_typed_visitor_half.cc
…
hlo_evaluator_typed_visitor_int8.cc
…
hlo_evaluator_typed_visitor_int16.cc
…
hlo_evaluator_typed_visitor_int32.cc
…
hlo_evaluator_typed_visitor_int64.cc
…
hlo_evaluator_typed_visitor_uint8.cc
…
hlo_evaluator_typed_visitor_uint16.cc
…
hlo_evaluator_typed_visitor_uint32.cc
…
hlo_evaluator_typed_visitor_uint64.cc
…
hlo_evaluator_typed_visitor.h
[XLA] Add S16/U16 support for Map in the HLO evaluator
2020-11-22 16:26:00 -08:00
hlo_evaluator.cc
[XLA] Add support for C64 to the sort evaluator
2020-11-28 10:29:36 -08:00
hlo_evaluator.h
[XLA] Rollforward of Rolledback CL after fixing mistakes.
2020-11-03 12:07:01 -08:00
hlo_execution_profile_data.proto
…
hlo_execution_profile_test.cc
[XLA:Python] Drop and/or minimize some streamexecutor dependencies from the XLA:Python TPU driver code.
2021-01-20 08:42:02 -08:00
hlo_execution_profile.cc
[XLA/GPU] Make module parameter to GpuExecutable optional.
2020-12-29 14:33:16 -08:00
hlo_execution_profile.h
[XLA:Python] Drop and/or minimize some streamexecutor dependencies from the XLA:Python TPU driver code.
2021-01-20 08:42:02 -08:00
hlo_get_dimension_size_rewriter.h
…
hlo_graph_dumper_test.cc
…
hlo_graph_dumper.cc
fix a typo. this shows up in GraphViewer's tooltip
2021-02-11 18:09:25 -08:00
hlo_graph_dumper.h
[XLA] Implement the fusion progress visualizer, which dumps out the HTML+JS page visualizing the fusion decisions for XLA:GPU
2021-01-25 17:35:11 -08:00
hlo_input_output_alias_config_test.cc
[XLA] Unify aliasing types
2020-07-07 16:07:00 -07:00
hlo_input_output_alias_config.cc
[Resubmit] If an input-output pair is configured to be must-alias(off by default), they must be aliased at runtime.
2020-08-07 14:06:08 -07:00
hlo_input_output_alias_config.h
Fix priting of input/output must/may aliasing.
2020-08-11 13:48:12 -07:00
hlo_instruction_test.cc
Merge pull request #45276 from Alfie-Edwards:relaxing-requirements-for-clonewithnewoperands-to-preserve-sharding-information
2021-02-02 04:18:59 -08:00
hlo_instruction.cc
Add a literal field to custom call instruction.
2021-02-17 12:28:55 -08:00
hlo_instruction.h
XLA value inference.
2021-03-03 14:17:48 -08:00
hlo_instructions.cc
Add a literal field to custom call instruction.
2021-02-17 12:28:55 -08:00
hlo_instructions.h
Add a literal field to custom call instruction.
2021-02-17 12:28:55 -08:00
hlo_lexer.cc
[XLA:SPMD] Define manual sharding, instead of using fake replication
2020-11-25 11:10:08 -08:00
hlo_lexer.h
[XLA:SPMD] Define manual sharding, instead of using fake replication
2020-11-25 11:10:08 -08:00
hlo_live_range_test.cc
[XLA] Unify aliasing types
2020-07-07 16:07:00 -07:00
hlo_live_range.cc
[XLA] Print live ranges by every moment.
2021-02-12 17:48:57 -08:00
hlo_live_range.h
…
hlo_liveness_analysis_test.cc
…
hlo_liveness_analysis.cc
…
hlo_liveness_analysis.h
…
hlo_matchers_test.cc
[XLA] Add an optional bool is_cross_program_prefetch field to kCopyStart HLOs.
2020-08-21 15:10:38 -07:00
hlo_matchers.cc
…
hlo_matchers.h
[XLA] Add a variant of WhileLoopInvariantCodeMotion pass to hoist groups of loop expensive invariant HLOs out of while if they are not size-inflating as a whole.
2021-02-08 13:13:32 -08:00
hlo_memory_scheduler_test.cc
[XLA] Use templates in heap simulator to allow opaque type to be different than HloValue (NFC)
2020-08-14 15:58:46 -07:00
hlo_memory_scheduler.cc
If an outfeed instruction has a config, schedule it early. If an infeed instruction has a config, schedule it late.
2020-06-03 22:15:37 -07:00
hlo_memory_scheduler.h
…
hlo_module_config.cc
Rename GenerateCubinForTfCode to GenerateGpuBinaryForTfCode and add ROCm support for it
2020-08-26 13:50:01 +00:00
hlo_module_config.h
Updates weight broadcast option to go through different proto.
2021-02-27 01:55:04 -08:00
hlo_module_dce_test.cc
Update HloModuleDCE to call DCE and WhileLoopSimplifier after removing dead tuple elements in while loops.
2020-10-27 07:58:09 -07:00
hlo_module_dce.cc
Update HloModuleDCE to call DCE and WhileLoopSimplifier after removing dead tuple elements in while loops.
2020-10-27 07:58:09 -07:00
hlo_module_dce.h
…
hlo_module_group_metadata.cc
…
hlo_module_group_metadata.h
…
hlo_module_group_test.cc
[XLA] Add metadata for HLO modules and passes.
2020-11-12 11:34:07 -08:00
hlo_module_group_util.cc
…
hlo_module_group_util.h
…
hlo_module_group.cc
[XLA] Add metadata for HLO modules and passes.
2020-11-12 11:34:07 -08:00
hlo_module_group.h
[XLA] Add option to print out hlo pass hash.
2020-02-27 14:54:06 -08:00
hlo_module_metadata_test.cc
[XLA] Add metadata for HLO modules and passes.
2020-11-12 11:34:07 -08:00
hlo_module_metadata.cc
[XLA] Add metadata for HLO modules and passes.
2020-11-12 11:34:07 -08:00
hlo_module_metadata.h
[XLA] Add creation_pass_id and dummy op_names to OpMetadata.
2020-12-11 17:48:13 -08:00
hlo_module_test.cc
Add method to retrieve a filtered list of computations in post-order.
2020-12-16 20:26:32 -08:00
hlo_module_util.cc
Deprecate broadcast-replicated-params option in xla::ExecutionOptions proto.
2021-02-18 12:50:44 -08:00
hlo_module_util.h
Move CreateModuleConfig to a new hlo_module_util header.
2020-12-14 15:14:29 -08:00
hlo_module.cc
Add a field in hlo proto to record if graph has dynamic shapes.
2021-02-22 21:37:05 -08:00
hlo_module.h
Add a field in hlo proto to record if graph has dynamic shapes.
2021-02-22 21:37:05 -08:00
hlo_op_metadata.cc
Add OpMetadata list to OpShardingProto/HloSharding.
2021-01-12 12:56:24 -08:00
hlo_op_metadata.h
Add OpMetadata list to OpShardingProto/HloSharding.
2021-01-12 12:56:24 -08:00
hlo_opcode_test.cc
[XLA] Add xla builder support for variadic reduce window op. This is the first CL leading to full support of variaduc reduce window.
2020-10-22 00:22:54 -07:00
hlo_opcode.cc
[XLA] Replace individual comparison HLO ops with a single compare op.
2019-03-07 14:05:30 -08:00
hlo_opcode.h
[XLA] Add xla builder support for variadic reduce window op. This is the first CL leading to full support of variaduc reduce window.
2020-10-22 00:22:54 -07:00
hlo_ordering_test.cc
[XLA] Automated g4 rollback of changelist 352846603.
2021-01-26 14:45:12 -08:00
hlo_ordering.cc
[XLA] Automated g4 rollback of changelist 352846603.
2021-01-26 14:45:12 -08:00
hlo_ordering.h
[XLA] Automated g4 rollback of changelist 352846603.
2021-01-26 14:45:12 -08:00
hlo_parser_test.cc
Add a literal field to custom call instruction.
2021-02-17 12:28:55 -08:00
hlo_parser.cc
Add a literal field to custom call instruction.
2021-02-17 12:28:55 -08:00
hlo_parser.h
…
hlo_pass_fix.h
Better warning. With that we can just to replay_computation directly for further analysis.
2020-10-06 11:01:41 -07:00
hlo_pass_interface.h
…
hlo_pass_pipeline_test.cc
[XLA] Fix timestamps in HLO pipeline test.
2020-11-16 11:48:23 -08:00
hlo_pass_pipeline.cc
[XLA] Add a space in a log statement
2021-02-12 12:40:41 -08:00
hlo_pass_pipeline.h
[XLA] Add metadata for HLO modules and passes.
2020-11-12 11:34:07 -08:00
hlo_phi_graph_test.cc
Properly support nest phi reduction in reverse order.
2020-06-17 18:47:22 -07:00
hlo_phi_graph.cc
Properly support nest phi reduction in reverse order.
2020-06-17 18:47:22 -07:00
hlo_phi_graph.h
a bit more
2020-10-29 18:16:19 +03:00
hlo_profile_printer_data.proto
…
hlo_profile_printer.cc
…
hlo_profile_printer.h
…
hlo_proto_util_test.cc
…
hlo_proto_util.cc
With other internal changes, extend the TF XLA interface to support running post-optimizations HLO modules. Also fix a few bugs in XLA related to saving and loading HLO from protobuf.
2020-11-04 12:25:32 -08:00
hlo_proto_util.h
With other internal changes, extend the TF XLA interface to support running post-optimizations HLO modules. Also fix a few bugs in XLA related to saving and loading HLO from protobuf.
2020-11-04 12:25:32 -08:00
hlo_query.cc
…
hlo_query.h
…
hlo_reachability_test.cc
…
hlo_reachability.cc
Adding support to identify a subset of possible auxiliary
2021-01-22 18:48:00 -08:00
hlo_reachability.h
Adding support to identify a subset of possible auxiliary
2021-01-22 18:48:00 -08:00
hlo_rematerialization_test_utils_test.cc
…
hlo_rematerialization_test_utils.h
…
hlo_rematerialization_test.cc
[XLA] Extend hlo_rematerialization pass to support rematerialization of tuple producing instrs.
2021-01-19 17:45:46 -08:00
hlo_rematerialization.cc
[XLA] Extend hlo_rematerialization pass to support rematerialization of tuple producing instrs.
2021-01-19 17:45:46 -08:00
hlo_rematerialization.h
[XLA] Initialize fields of RematerializationSizes by default
2021-02-05 16:48:25 -08:00
hlo_replication_analysis_test.cc
[XLA] Use CollectiveOpGroup mode to drive some of the HLO verification
2021-02-23 10:15:41 -08:00
hlo_replication_analysis.cc
Support x64<->x32 instructions in hlo replication analysis.
2020-10-01 13:25:16 -07:00
hlo_replication_analysis.h
…
hlo_runner_interface.cc
Added support to visualise HloModule Protobufs
2021-01-08 02:06:03 -08:00
hlo_runner_interface.h
Add new data transfer support.
2021-03-04 14:21:05 -08:00
hlo_runner.cc
[XLA] Drop useless shape argument from TransferManager::TransferLiteralFromOutfeed.
2021-01-25 17:29:36 -08:00
hlo_runner.h
Add SPMD alternative implementations.
2021-01-29 18:34:22 -08:00
hlo_schedule_test.cc
…
hlo_schedule.cc
…
hlo_schedule.h
…
hlo_sharding_metadata.cc
…
hlo_sharding_metadata.h
…
hlo_sharding_test.cc
[XLA] Add option to propagate sharding metadata in Hlo sharding propagation pass.
2021-01-25 13:41:17 -08:00
hlo_sharding_util_test.cc
[XLA:SPMD] Improve resharding
2020-07-22 23:18:17 -07:00
hlo_sharding_util.cc
[XLA] Add support for concurrent partitioning of gather with multiple strategies.
2021-01-27 13:21:08 -08:00
hlo_sharding_util.h
[XLA] Add support for concurrent partitioning of gather with multiple strategies.
2021-01-27 13:21:08 -08:00
hlo_sharding.cc
[XLA] Make sure to return replicated sharding when all tiles are partially replicated
2021-01-28 17:33:01 -08:00
hlo_sharding.h
[XLA] Add option to propagate sharding metadata in Hlo sharding propagation pass.
2021-01-25 13:41:17 -08:00
hlo_subcomputation_unification_test.cc
…
hlo_subcomputation_unification.cc
…
hlo_subcomputation_unification.h
…
hlo_value.cc
[XLA] BufferValue::Color now type aliases int64.
2020-05-27 09:35:14 -07:00
hlo_value.h
[XLA] Add hash function to HloUse/HloPosition.
2020-07-29 23:27:09 -07:00
hlo_verifier_test.cc
[XLA] Extend CollectivePermute verification to check if source/target IDs are in range.
2021-02-26 12:19:15 -08:00
hlo_verifier.cc
[XLA] Extend CollectivePermute verification to check if source/target IDs are in range.
2021-02-26 12:19:15 -08:00
hlo_verifier.h
[XLA] Fix dot/conv in ShapeVerifier for !allow_mixed_precision
2021-02-09 15:48:16 -08:00
hlo.proto
Add a field in hlo proto to record if graph has dynamic shapes.
2021-02-22 21:37:05 -08:00
human_readable_profile_builder.cc
…
human_readable_profile_builder.h
…
indexed_array_analysis_test.cc
Remove 1 + "string" cases and undo -Wno-string-plus-int.
2020-02-05 16:58:37 -08:00
indexed_array_analysis.cc
…
indexed_array_analysis.h
…
instruction_fusion_test.cc
rng loop fusion
2020-06-05 10:34:16 -07:00
instruction_fusion.cc
* Add virtual function NotFusingInstruction to FusionQueue to get necessary information for some subclasses.
2021-02-16 10:38:49 -08:00
instruction_fusion.h
* Add virtual function NotFusingInstruction to FusionQueue to get necessary information for some subclasses.
2021-02-16 10:38:49 -08:00
layout_assignment_test.cc
[XLA] Add a test for dynamic shapes vs ComputationLayout
2021-02-16 13:11:38 -08:00
layout_assignment.cc
[XLA] Rollback layout assignment change
2021-02-25 19:40:25 -08:00
layout_assignment.h
Internal change
2020-08-21 13:30:52 -07:00
llvm_compiler.cc
- Fix PjRt GPU Client to allow num_partitions > 1
2021-02-01 12:33:28 -08:00
llvm_compiler.h
[XLA] Pack some parameters in xla::Compiler member functions into a struct. This is for later expanding for more parameters, like a thread pool for parallel compilation.
2020-12-08 01:54:36 -08:00
local_service.cc
Move CreateModuleConfig to a new hlo_module_util header.
2020-12-14 15:14:29 -08:00
local_service.h
…
logical_buffer_analysis.cc
[XLA] Avoid structured bindings.
2021-01-12 16:13:55 -08:00
logical_buffer_analysis.h
[XLA] Add missing custom-call aliasing-related changes in analysis passes
2021-01-12 13:57:06 -08:00
logical_buffer.cc
[XLA] BufferValue::Color now type aliases int64.
2020-05-27 09:35:14 -07:00
logical_buffer.h
…
logistic_expander_test.cc
[XLA] Add expander pass for kLogistic.
2020-06-24 22:32:37 -07:00
logistic_expander.cc
[XLA] Add expander pass for kLogistic.
2020-06-24 22:32:37 -07:00
logistic_expander.h
[XLA] Add expander pass for kLogistic.
2020-06-24 22:32:37 -07:00
loop_schedule_linearizer_test.cc
[XLA] Insert control edges from write to read instructions for same buffers inside loops
2020-10-26 17:30:57 -07:00
loop_schedule_linearizer.cc
[XLA] Insert control edges from write to read instructions for same buffers inside loops
2020-10-26 17:30:57 -07:00
loop_schedule_linearizer.h
[XLA] Insert control edges from write to read instructions for same buffers inside loops
2020-10-26 17:30:57 -07:00
map_inliner_test.cc
…
map_inliner.cc
Rename "Inliner" to "MapInliner".
2018-10-04 14:29:35 -07:00
map_inliner.h
…
maybe_owning_device_memory.cc
Make XRT CPU/GPU use MaybeOwning buffer interface, so the new copy protection CL won't break aliasing.
2020-06-22 12:32:43 -07:00
maybe_owning_device_memory.h
Make XRT CPU/GPU use MaybeOwning buffer interface, so the new copy protection CL won't break aliasing.
2020-06-22 12:32:43 -07:00
memory_space_assignment_best_fit_repacker_test.cc
[XLA] Implement a repacker that wraps heap simulator's best fit algorithm.
2020-08-18 09:21:37 -07:00
memory_space_assignment_best_fit_repacker.cc
[XLA] Implement a repacker that wraps heap simulator's best fit algorithm.
2020-08-18 09:21:37 -07:00
memory_space_assignment_best_fit_repacker.h
[XLA] Implement a repacker that wraps heap simulator's best fit algorithm.
2020-08-18 09:21:37 -07:00
memory_space_assignment_repacking.h
[XLA] Use templates in heap simulator to allow opaque type to be different than HloValue (NFC)
2020-08-14 15:58:46 -07:00
memory_space_assignment_test.cc
[XLA] Remove an overly pessimistic assertion from memory space assignment.
2020-12-30 13:02:28 -08:00
memory_space_assignment_utils.cc
Internal change
2020-09-24 10:22:25 -07:00
memory_space_assignment_utils.h
[XLA] Exposes the IsValueAllowedInAlternateMemory() for better reuse.
2020-08-18 14:26:53 -07:00
memory_space_assignment.cc
Delete dead code in memory space assignment
2021-02-12 12:02:58 -08:00
memory_space_assignment.h
Delete dead code in memory space assignment
2021-02-12 12:02:58 -08:00
memory_space_propagation_test.cc
[XLA] Bitcasts should define values when propagating memory spaces.
2021-02-23 15:27:16 -08:00
memory_space_propagation.cc
[XLA] Bitcasts should define values when propagating memory spaces.
2021-02-23 15:27:16 -08:00
memory_space_propagation.h
[XLA] Propagate memory spaces recursively inside nested fusions.
2020-06-18 13:49:23 -07:00
multi_output_fusion.cc
[XLA] Try committing DUS buffer sharing again with fixes.
2020-09-17 09:20:11 -07:00
multi_output_fusion.h
[Resubmit] Fix several issues of multi output fusion.
2020-02-18 20:50:32 -08:00
name_uniquer_test.cc
…
name_uniquer.cc
[-Wsign-compare] warning fixes batch 4
2020-06-24 21:58:00 +00:00
name_uniquer.h
…
op_expander_pass.cc
…
op_expander_pass.h
…
operand_upcaster_test.cc
[XLA] IntegralUpcaster->OperandUpcaster to allow auto upcasting floating point types.
2020-12-29 11:14:04 -08:00
operand_upcaster.cc
[XLA] IntegralUpcaster->OperandUpcaster to allow auto upcasting floating point types.
2020-12-29 11:14:04 -08:00
operand_upcaster.h
[XLA] IntegralUpcaster->OperandUpcaster to allow auto upcasting floating point types.
2020-12-29 11:14:04 -08:00
optimize_input_output_buffer_alias_test.cc
Automated rollback of commit afd980b3ce068c30bd3a43d54929e2590be8bd29
2020-02-12 14:31:05 -08:00
optimize_input_output_buffer_alias.cc
[XLA] Unify aliasing types
2020-07-07 16:07:00 -07:00
optimize_input_output_buffer_alias.h
Automated rollback of commit afd980b3ce068c30bd3a43d54929e2590be8bd29
2020-02-12 14:31:05 -08:00
pattern_matcher_gmock_test.cc
…
pattern_matcher_gmock.h
…
pattern_matcher_test.cc
…
pattern_matcher.h
Virtualize the AddCopiesOnConditional function on copy insertion.
2021-02-02 10:01:15 -08:00
platform_util.cc
…
platform_util.h
…
qr_expander.cc
[XLA] Fix underflow in norm calculation in Householder reflection for complex inputs.
2021-02-23 18:24:36 -08:00
qr_expander.h
[XLA] Split QR decomposition along the same lines as LAPACK xGEQRf/xORGQR.
2021-02-23 14:13:25 -08:00
reshape_mover_test.cc
…
reshape_mover.cc
[XLA] Split permutation utilities from xla/util.* into a new xla/permutation_util.*
2021-02-09 17:01:49 -08:00
reshape_mover.h
Add interface for HLO passes which run on HloModuleGroup.
2018-09-19 08:16:42 -07:00
rng_bit_generator_expander.cc
Rewrite output state to match the input.
2020-04-29 15:51:55 -07:00
rng_bit_generator_expander.h
Introduce new RngBitGenerator HLO
2020-02-06 05:06:44 -08:00
rng_expander.cc
Introduce new RngBitGenerator HLO
2020-02-06 05:06:44 -08:00
rng_expander.h
…
root_instruction_sinker_test.cc
[XLA] Add a RootInstructionSinker pass.
2020-04-22 14:46:15 -07:00
root_instruction_sinker.cc
[XLA] Add a RootInstructionSinker pass.
2020-04-22 14:46:15 -07:00
root_instruction_sinker.h
[XLA] Add a RootInstructionSinker pass.
2020-04-22 14:46:15 -07:00
scatter_expander_test.cc
[XLA] Expand simple scatter operations into dynamic-update-slice.
2020-08-18 13:21:28 -07:00
scatter_expander.cc
[XLA] Expand simple scatter operations into dynamic-update-slice.
2020-08-18 13:21:28 -07:00
scatter_expander.h
[XLA] Expand simple scatter operations into dynamic-update-slice.
2020-08-18 13:21:28 -07:00
service_executable_run_options.h
…
service.cc
[XLA] Drop useless shape argument from TransferManager::TransferLiteralFromOutfeed.
2021-01-25 17:29:36 -08:00
service.h
[XLA/GPU] Add parallel compilation for LLVM and ptxas.
2020-12-08 09:22:49 -08:00
shape_inference_test.cc
[XLA] Be more consistent about inferring mixed operand shapes
2021-01-12 13:29:04 -08:00
shape_inference.cc
Support more cases for strided_slice gradient.
2021-02-17 12:18:39 -08:00
shape_inference.h
[XLA] Add an optional preferred_element_type argument to Dot/Conv builder methods to enable generating HLOs that has wider accumulation type than default shape inference result.
2020-11-20 13:16:56 -08:00
shaped_buffer_test.cc
Internal tests cleanup.
2020-10-28 07:40:36 -07:00
shaped_buffer.cc
Remove platform field from shaped buffer.
2020-10-30 14:26:55 -07:00
shaped_buffer.h
Remove platform field from shaped buffer.
2020-10-30 14:26:55 -07:00
sharding_propagation_test.cc
Allow more sharding propagation from broadcast operands
2021-02-08 16:13:46 -08:00
sharding_propagation.cc
Allow more sharding propagation from broadcast operands
2021-02-08 16:13:46 -08:00
sharding_propagation.h
[XLA] Add option to propagate sharding metadata in Hlo sharding propagation pass.
2021-01-25 13:41:17 -08:00
slice_sinker_test.cc
…
slice_sinker.cc
…
slice_sinker.h
…
slow_operation_alarm.cc
Print HLO module name on slow compile
2020-12-10 23:19:52 -08:00
slow_operation_alarm.h
Print HLO module name on slow compile
2020-12-10 23:19:52 -08:00
sort_simplifier_test.cc
…
sort_simplifier.cc
…
sort_simplifier.h
…
source_map_util.h
…
space_to_batch_converter_test.cc
Skip space-to-batch optimization on convs that are used by a different rank reduce-window or select-and-scatter.
2021-03-04 19:12:55 -08:00
space_to_batch_converter.cc
Skip space-to-batch optimization on convs that are used by a different rank reduce-window or select-and-scatter.
2021-03-04 19:12:55 -08:00
space_to_batch_converter.h
Extend space to batch to apply to larger batch sizes
2020-10-06 09:56:50 -07:00
stable_sort_expander_test.cc
…
stable_sort_expander.cc
…
stable_sort_expander.h
…
stream_pool_test.cc
…
stream_pool.cc
…
stream_pool.h
Prefixing TensorFlow thread annotation macros with TF_.
2020-03-05 08:42:01 -08:00
topk_rewriter_test.cc
[XLA] Rewrite 1d sort to TopK
2020-08-05 02:40:46 -07:00
topk_rewriter.cc
[XLA] Rewrite 1d sort to TopK
2020-08-05 02:40:46 -07:00
topk_rewriter.h
[XLA] Add TopK rewriter pass
2020-08-05 01:44:08 -07:00
tpu_computation_placer.cc
Extract tpu_platform_id initialization to its own package.
2021-01-22 13:43:22 -08:00
tpu_computation_placer.h
[TPU] Colocate tpu_computation_placer with other registration in compiler/xla
2021-01-21 16:15:24 -08:00
transfer_manager.cc
Remove the use of host shape in TransferManager::ReadDynamicShapes.
2020-11-17 13:46:04 -08:00
transfer_manager.h
[XLA] Drop useless shape argument from TransferManager::TransferLiteralFromOutfeed.
2021-01-25 17:29:36 -08:00
transpose_folding_test.cc
[XLA] Add an optional preferred_element_type argument to Dot/Conv builder methods to enable generating HLOs that has wider accumulation type than default shape inference result.
2020-11-20 13:16:56 -08:00
transpose_folding.cc
[XLA] Teach TransposeFolding to fold dots with batch dimensions
2020-10-08 09:13:33 -07:00
transpose_folding.h
[XLA] Add the ability to disable the Reduce(Reshape(X)) to Reduce(X) rewrite and have TransposeFolding default to folding all operands of Convolution and Dot
2020-03-07 00:36:17 -08:00
tree_reduction_rewriter.cc
…
tree_reduction_rewriter.h
…
triangular_solve_expander_test.cc
Merge pull request #39690 from whoozle:triangular-solve-expander-block-size
2020-07-15 06:57:41 -07:00
triangular_solve_expander.cc
[XLA] Fix bug in triangular solve expander.
2020-11-04 10:32:06 -08:00
triangular_solve_expander.h
[XLA] Add an HLO implementation of a direct triangular solve, and use it for small matrices (n<32) with large batches (>8).
2020-11-02 17:14:35 -08:00
tuple_points_to_analysis_test.cc
[XLA] Add missing custom-call aliasing-related changes in analysis passes
2021-01-12 13:57:06 -08:00
tuple_points_to_analysis.cc
[XLA] Avoid structured bindings.
2021-01-12 16:13:55 -08:00
tuple_points_to_analysis.h
[XLA] Add missing custom-call aliasing-related changes in analysis passes
2021-01-12 13:57:06 -08:00
tuple_simplifier_test.cc
…
tuple_simplifier.cc
[XLA:HLO] Small refactoring and more comments in tuple_simplifier.
2020-06-08 11:52:07 -07:00
tuple_simplifier.h
[XLA:HLO] Small refactoring and more comments in tuple_simplifier.
2020-06-08 11:52:07 -07:00
tuple_util_test.cc
…
tuple_util.cc
…
tuple_util.h
[XLA] Add a RootInstructionSinker pass.
2020-04-22 14:46:15 -07:00
while_loop_all_reduce_code_motion_test.cc
Rolling forward after fixing C++ version problems.
2020-12-30 13:24:09 -08:00
while_loop_all_reduce_code_motion.cc
[XLA] Rollback layout assignment change
2021-02-25 19:40:25 -08:00
while_loop_all_reduce_code_motion.h
Rolling forward after fixing C++ version problems.
2020-12-30 13:24:09 -08:00
while_loop_analysis_test.cc
Adding support to identify a subset of possible auxiliary
2021-01-22 18:48:00 -08:00
while_loop_analysis.cc
[XLA] Rollback layout assignment change
2021-02-25 19:40:25 -08:00
while_loop_analysis.h
Adding support to identify a subset of possible auxiliary
2021-01-22 18:48:00 -08:00
while_loop_constant_sinking_test.cc
…
while_loop_constant_sinking.cc
…
while_loop_constant_sinking.h
…
while_loop_expensive_invariant_code_motion_test.cc
[XLA] Add a variant of WhileLoopInvariantCodeMotion pass to hoist groups of loop expensive invariant HLOs out of while if they are not size-inflating as a whole.
2021-02-08 13:13:32 -08:00
while_loop_expensive_invariant_code_motion.cc
[XLA] Add a variant of WhileLoopInvariantCodeMotion pass to hoist groups of loop expensive invariant HLOs out of while if they are not size-inflating as a whole.
2021-02-08 13:13:32 -08:00
while_loop_expensive_invariant_code_motion.h
[XLA] Add a variant of WhileLoopInvariantCodeMotion pass to hoist groups of loop expensive invariant HLOs out of while if they are not size-inflating as a whole.
2021-02-08 13:13:32 -08:00
while_loop_invariant_code_motion_test.cc
…
while_loop_invariant_code_motion.cc
[XLA] Correct WhileLoopInvariantCodeMotion log messages.
2020-05-07 13:35:38 -07:00
while_loop_invariant_code_motion.h
…
while_loop_simplifier_test.cc
[XLA] Remove tuple elements in while loop if unused both inside or outside loop.
2021-02-22 19:53:24 -08:00
while_loop_simplifier.cc
[XLA] Remove tuple elements in while loop if unused both inside or outside loop.
2021-02-22 19:53:24 -08:00
while_loop_simplifier.h
…
while_loop_trip_count_annotator_test.cc
…
while_loop_trip_count_annotator.cc
…
while_loop_trip_count_annotator.h
…
while_util_test.cc
…
while_util.cc
[XLA][TF2XLA] Support tensor list with dynamic dimension.
2020-04-22 14:37:18 -07:00
while_util.h
[XLA][TF2XLA] Support tensor list with dynamic dimension.
2020-04-22 14:37:18 -07:00
xla_debug_info_manager_test.cc
move singleton xla::gpu::GPUDebugInfoManager to xla::XlaDebugInfoManager. in hope that it can be reused by XLA/CPU.
2021-02-09 10:28:57 -08:00
xla_debug_info_manager.cc
move singleton xla::gpu::GPUDebugInfoManager to xla::XlaDebugInfoManager. in hope that it can be reused by XLA/CPU.
2021-02-09 10:28:57 -08:00
xla_debug_info_manager.h
move singleton xla::gpu::GPUDebugInfoManager to xla::XlaDebugInfoManager. in hope that it can be reused by XLA/CPU.
2021-02-09 10:28:57 -08:00
zero_sized_hlo_elimination_test.cc
…
zero_sized_hlo_elimination.cc
Support 0-sized shape with dynamic reshapes.
2021-01-16 10:23:25 -08:00
zero_sized_hlo_elimination.h
…