Commit 081758b0 authored by Mark Heffernan's avatar Mark Heffernan Committed by TensorFlower Gardener
Browse files

Do not reuse allocations which hold tuple logical buffers. This works around a... 

Do not reuse allocations which hold tuple logical buffers. This works around a GPU codegen issue which extended the live range of tuple buffers. This also addresses a potential latent bug where thread-local or custom call buffer might have been reused.
Change: 145561773
parent e521a3df
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