CHANGELOG
=========
3bb6a48d8 - Fix bug atan2
14c847dc0 - Refactor special values test for pow, and add a similar test for atan2
462758e8a - Don'\''t use generic sign function for sign(complex) unless it is vectorizable
c0d6a7261 - Use pnegate(pzero(x)) as a generic way to generate -0.0. Some compiler do not handle the literal -0.0 properly in fastmath mode.
7846c7387 - Eigen/Sparse: fix warnings -Wunused-but-set-variable
316754487 - Handle NaN inputs to atan2.
72db3f0fa - Remove references to M_PI_2 and M_PI_4.
d6bc06259 - Remove reference to EIGEN_HAS_CXX11_MATH.
5ceed0d57 - Guard GCC-specific pragmas with "#ifdef EIGEN_COMP_GNUC"
528b68674 - [clang-format] Add a few macros to AttributeMacros
e95c4a837 - Simpler range reduction strategy for atan<float>().
80efbfded - Unconditionally enable CXX11 math.
e5794873c - Replace assert with eigen_assert.
7d6a9925c - Fix 4x4 inverse when compiling with -Ofast.
1414a76fa - Only vectorize atan<double> for Altivec if VSX is available.
c475228b2 - Vectorize atan() for double.
1e1848fdb - Add a vectorized implementation of atan2 to Eigen.

* Switch TensorFlow to using the new fast atan2 in Eigen.
* Get rid of local implementations since Eigen is now guaranteed to support C++11 math.

PiperOrigin-RevId: 481044760

http://github.com/tensorflow/runtime/commit/97d12a118984d820c14bdad0971704d95d99f411.

PiperOrigin-RevId: 481043847

Updates LLVM usage to match
[1fda6f6859aa](https://github.com/llvm/llvm-project/commit/1fda6f6859aa)

PiperOrigin-RevId: 481042584

PiperOrigin-RevId: 481042256

For tf.DivNoNan operators, the calibrator should NaN values since the lowered
form of TFLite will encounter NaN value by design.

PiperOrigin-RevId: 481039479

PiperOrigin-RevId: 481035658

PiperOrigin-RevId: 481034607

PiperOrigin-RevId: 481030210

Updating determinism check in svd op. Now the op works deterministically when enabled, except in the case that the input matrix has column size 1.

PiperOrigin-RevId: 481018683

PiperOrigin-RevId: 481016434

This CL introduces a new legalization pattern that rewrites sigmoid_grad
operation as a `grad = dy * y * (1 - y)`, where `y = sigmoid(x)`.

PiperOrigin-RevId: 481015565

JitExecutable is not required for AOT compilation, so XlaRuntimeCpuExecutable can own a runtime::Executable directly.

PiperOrigin-RevId: 481012743

PiperOrigin-RevId: 481010554

PiperOrigin-RevId: 481008739

PiperOrigin-RevId: 481007346

PiperOrigin-RevId: 481006537

PiperOrigin-RevId: 481006100

PiperOrigin-RevId: 481004699

PiperOrigin-RevId: 481001377

PiperOrigin-RevId: 480996400

PiperOrigin-RevId: 480996180

http://github.com/tensorflow/runtime/commit/36b7795640a99e44a9ab246c5495be5f99736c99.

PiperOrigin-RevId: 480985467

[lite] When constructing a subgraph, use control dependencies from the model's metadata, if present.

PiperOrigin-RevId: 480984280

PiperOrigin-RevId: 480983235

PiperOrigin-RevId: 480977676

PiperOrigin-RevId: 480974257

Use std::function objects rather than creating thousands of separate copies of
very large routines in shape_util.h

Refactored code to have an internal helper ForEachState struct, and to have
separate code for the parallel vs. non-parallel versions of the core
ForEachInternal functionality (compiler wasn't smart enough to track the
parallel bit through the std::optional object with the ThreadPool, and so
was emitting parallel code even for calls with the non-parallel variant,
and due to templatization, there were thousands of copies of these routines.

Avoid inlining some large routines in literal.h

Avoid inlining some automatically generated constructors for ShapeIndex, ProgramShape,
etc. in shape.{h,cc}

Avoid inlining large routines on non-OK paths in status_macros.h

Changes drop generated text size for a large binary by about 3.0 MB (~1.4%).

PiperOrigin-RevId: 480973483

Merge pull request #55780 from ROCmSoftwarePlatform:google_upstream_remove_rocm_build_flag_nextafter_op

PiperOrigin-RevId: 480973150

- Unify the code for handling operand->tuple sharding propagation when no
  sharding is present vs refining the existing sharding (and reuse the code
  to refine existing sharding).
- This also fixes an issue with handling empty tuple sub-elements, which are
  essentially not counted in the top-level tuple elements of the tuple sharding
  (since the code the refines existing sharding handles this correctly)

PiperOrigin-RevId: 480971521

PiperOrigin-RevId: 480968915

PiperOrigin-RevId: 480958124

 - consider collective communication operations with channel_id as side
   effecting only in non-spmd mode.
 - Also handle all collective operations in the function.
 - Change SPMD partitioning test to verify that any collective generated by
   partitioning does not have sharding.

PiperOrigin-RevId: 480953154

PiperOrigin-RevId: 480950049

PiperOrigin-RevId: 480949877

PiperOrigin-RevId: 480944931

Existing lowering missed cases where the width/height of
the input or output are 1. These cases were difficult to
address in the current implementation so they were cleaned
up. Then power-of-2 specific code was removed as it was
easier to just depend on GCD to do the right thing.

PiperOrigin-RevId: 480936509

These 2 tests cases are long running, because they test a cartesian product of dtypes * transpose * adjoint * shapes (2 * 4 * 4 * 3 = 96). These 2 test cases are the bottlenecks in the entire test suite finishing. By converting them into parameterized test cases, each of the case in the product becomes its own test case, and can run on different shards.

PiperOrigin-RevId: 480935083

PiperOrigin-RevId: 480932683

This creates a const op filled with [0, 1, 2...iotaSize] values, then tiles it to the iota result shape

PiperOrigin-RevId: 480930548

PiperOrigin-RevId: 480928553