STT-tensorflow/tensorflow/compiler/xla
David Majnemer 4fcfcbe2c6 [XLA] Refactor dot_operation_test's parameterization
PiperOrigin-RevId: 352483336
Change-Id: Ib5d3adf1e91a495fa7adb18d47ad99b94f99f9b4
2021-01-18 20:08:51 -08:00
..
client Enables per-host dummy args for TPUExecute (TF1) and adds XLA options. 2021-01-14 17:03:51 -08:00
experimental/xla_sharding PY2 removal cleanup 2021-01-15 16:48:57 -08:00
g3doc [XLA] Add AllGather documentation 2021-01-18 14:04:56 -08:00
pjrt Internal changes only. 2021-01-15 18:51:23 -08:00
python Move jax_jit functions to the jax namespace. 2021-01-16 15:12:36 -08:00
python_api PY2 removal cleanup 2021-01-15 16:48:57 -08:00
rpc
service Support 0-sized shape with dynamic reshapes. 2021-01-16 10:23:25 -08:00
tests [XLA] Refactor dot_operation_test's parameterization 2021-01-18 20:08:51 -08:00
tools Internal changes only. 2021-01-14 19:09:44 -08:00
.clang-format
array2d_test.cc Enable half precision convolution for the CPU and GPU backends. 2018-02-15 10:42:55 -08:00
array2d.h [TF] [XLA] Fix a number of compiler warnings on Mac OS X. 2018-11-19 13:19:32 -08:00
array3d_test.cc
array3d.h [XLA] FP16 Dot support for the CPU and GPU backends. 2018-02-28 12:59:55 -08:00
array4d_test.cc
array4d.h Add a default constructor to Array4D 2020-02-07 15:23:01 -08:00
array_test.cc
array.cc
array.h Fix C++14 build. 2020-08-08 13:12:15 -07:00
bit_cast_test.cc Remove absl::bit_casts of non-trivially-copyable Eigen types, and replace them with a new, extensible xla::BitCast call. The latter does everything absl::bit_cast does, but additionally can be specialized to support non-trivial types. 2019-06-14 02:44:19 -07:00
bit_cast.h Move bfloat16 header to tensorflow/core/platform. 2020-08-14 13:44:57 -07:00
BUILD Move llvm dependency from xla/util.h to xla/service/gpu/ir_emission_utils.h 2020-12-14 16:51:06 -08:00
comparison_util.cc
comparison_util.h
cpu_function_runtime.cc [XLA] Move tensorflow/compiler/tf2xla/cpu_function_runtime.h to tensorflow/compiler/xla/cpu_function_runtime.h 2019-04-01 09:27:18 -07:00
cpu_function_runtime.h [XLA:CPU] Reconsider alignment heuristics 2020-04-24 02:51:55 -07:00
debug_options_flags.cc [XLA:GPU] Add --xla_gpu_deterministic_ops to force run-to-run determinism. 2020-12-15 12:51:36 -08:00
debug_options_flags.h
debug_options_parsers_test.cc
debug_options_parsers.h
device_util.h
error_spec.h [XLA] Add ErrorSpec::fewer_infs_ok knob. 2019-01-24 16:53:05 -08:00
executable_run_options.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
executable_run_options.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
execution_options_util.cc
execution_options_util.h minor spelling tweaks 2019-12-09 18:21:12 +09:00
index_util_test.cc
index_util.cc
index_util.h Replace Shape with a C++ class in XLA. 2018-11-28 16:08:45 -08:00
iterator_util_test.cc
iterator_util.h
layout_test.cc [XLA] Remove unsupported sparse layout 2020-01-02 18:04:52 -08:00
layout_util_test.cc Add MakeAscendingLayout(). 2021-01-08 08:21:45 -08:00
layout_util.cc Add MakeAscendingLayout(). 2021-01-08 08:21:45 -08:00
layout_util.h Add MakeAscendingLayout(). 2021-01-08 08:21:45 -08:00
layout.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
layout.h [XLA] Remove unsupported sparse layout 2020-01-02 18:04:52 -08:00
literal_comparison.cc fix typos in compiler dir 2020-10-29 01:08:30 +03:00
literal_comparison.h Near comparison now works for non-fp types. Callback uses ShapeIndex parameter. 2019-06-05 16:01:58 -07:00
literal_test.cc [Resubmit] Dynamic literal support 2020-07-17 18:19:30 -07:00
literal_util.cc xla directory resolutions 2020-07-26 22:14:33 +00:00
literal_util.h Introduce a few new literal conversion functions for various floating point types 2020-01-27 07:47:30 -08:00
literal.cc Add several fixes for s390x architecture and other Big-Endian systems 2020-10-28 11:14:47 -04:00
literal.h [Resubmit] Dynamic literal support 2020-07-17 18:19:30 -07:00
map_util.h
metric_table_report.cc
metric_table_report.h
overflow_util.h
packed_literal_reader.cc Replace Layout and Tile protos with C++ classes in XLA. 2018-12-11 21:00:21 -08:00
packed_literal_reader.h Global de-std::unique_ptr cleanup for xla::Literal. 2018-09-10 12:38:19 -07:00
parse_flags_from_env_test.cc Crash if XLA flags are to be read from a file but we could not open the file 2020-12-30 14:23:16 -08:00
parse_flags_from_env.cc Crash if XLA flags are to be read from a file but we could not open the file 2020-12-30 14:23:16 -08:00
parse_flags_from_env.h minor spelling tweaks 2019-12-09 18:21:12 +09:00
primitive_util_test.cc [XLA] Be more consistent about inferring mixed operand shapes 2021-01-12 13:29:04 -08:00
primitive_util.cc [XLA] Be more consistent about inferring mixed operand shapes 2021-01-12 13:29:04 -08:00
primitive_util.h [XLA] Be more consistent about inferring mixed operand shapes 2021-01-12 13:29:04 -08:00
protobuf_util.cc
protobuf_util.h
README.md
refcounting_hash_map_test.cc Added RefCountingHashMap::GetOrTryCreateIfAbsent to allow for factory methods that may fail. 2020-11-26 06:10:04 -08:00
refcounting_hash_map.h [XLA] Fix race condition in RefcountingHashMap that could lead to a use-after-free segfault. 2020-12-15 12:11:48 -08:00
reference_util_test.cc
reference_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
reference_util.h
service_interface.h [XLA] Split ExecuteGraph into Compile and Execute. 2018-11-07 19:20:01 -08:00
shape_layout.cc
shape_layout.h
shape_test.cc
shape_tree_test.cc Internal tests cleanup. 2020-10-28 07:40:36 -07:00
shape_tree.h
shape_util_test.cc Speed up Shape creation by avoiding unnecessary validations. 2020-11-22 20:40:07 -08:00
shape_util.cc Log error before failing 2021-01-11 17:59:46 -08:00
shape_util.h [XLA] Be more consistent about inferring mixed operand shapes 2021-01-12 13:29:04 -08:00
shape.cc
shape.h [libtpu] Reimplement XLA_Shape in C API for performance. 2020-10-19 14:17:22 -07:00
status_macros_test.cc minor spelling tweaks 2019-12-09 18:21:12 +09:00
status_macros.cc [TF:XLA] Add error message about the non-strict XLA jit. 2019-02-07 02:40:43 -08:00
status_macros.h Multiple blocks of code in StreamExecutor can be simplified using the 2019-05-22 12:00:46 -07:00
status.h
statusor.h
test_helpers.h
test.h
text_literal_reader_test.cc Global de-std::unique_ptr cleanup for xla::Literal. 2018-09-10 12:38:19 -07:00
text_literal_reader.cc Change Shape parsing from regexp matcher to parser. 2018-12-14 08:37:21 -08:00
text_literal_reader.h
text_literal_writer_test.cc Use Env::LocalTempFilename for a temp filename. 2020-02-19 17:30:20 -08:00
text_literal_writer.cc Remove unused inclusions and add missing inclusions 2019-02-05 14:06:22 -08:00
text_literal_writer.h [XLA] Use absl string types and functions instead of the TF versions. 2018-08-23 10:27:38 -07:00
types.h
union_find.h
util_test.cc Support 0-sized shape with dynamic reshapes. 2021-01-16 10:23:25 -08:00
util.cc Support 0-sized shape with dynamic reshapes. 2021-01-16 10:23:25 -08:00
util.h Support 0-sized shape with dynamic reshapes. 2021-01-16 10:23:25 -08:00
window_util_test.cc
window_util.cc
window_util.h
xla_data.proto Add OpMetadata list to OpShardingProto/HloSharding. 2021-01-12 12:56:24 -08:00
xla.bzl
xla.proto Enables per-host dummy args for TPUExecute (TF1) and adds XLA options. 2021-01-14 17:03:51 -08:00

XLA (Accelerated Linear Algebra) is a domain-specific compiler for linear algebra that optimizes TensorFlow computations. See the documentation.