Commit 34c98a6d authored by A. Unique TensorFlower's avatar A. Unique TensorFlower Committed by Gunhan Gulsoy
Browse files

[XLA] Handle domain instructions in dataflow analysis. 

Without domain propagation in dataflow analysis we end up in inconsistent domain instructions with BF16 as output and F32 as input. In case of tuple shapes these are not fixed by bfloat16_normalization, and later on they cause asserts once the domain instructions are removed.

PiperOrigin-RevId: 202442786
parent 406a3609
Show whitespace changes
Inline Side-by-side
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please to comment