endian orderings will give different results. A copy from input buffer to output
buffer is made on BE machines when types are of different sizes in order to get
the same casting results as on LE machines.
  }];

  let arguments = (ins
    TF_NumberTensor:$input
  );

  let results = (outs
    TF_NumberTensor:$output
  );

    large_constant]`) into 32-bit arithmetic in SASS.

    As a result, these versions of `ptxas` miscompile most XLA programs which
    use more than 4GB of temp memory. This results in garbage results and/or
    `CUDA_ERROR_ILLEGAL_ADDRESS` failures.

    A fix in CUDA 9.1.121 is expected in late February 2018. We do not expect a

Class <org.gradle.api.internal.tasks.testing.results.DefaultTestResult> is not annotated (directly or via its package) with @org.gradle.api.NonNullApi in (DefaultTestResult.java:0)
Class <org.gradle.api.internal.tasks.testing.results.StateTrackingTestResultProcessor> is not annotated (directly or via its package) with @org.gradle.api.NonNullApi in (StateTrackingTestResultProcessor.java:0)