diff options
author | Amit Patankar <amitpatankar@google.com> | 2018-02-01 10:27:29 -0800 |
---|---|---|
committer | GitHub <noreply@github.com> | 2018-02-01 10:27:29 -0800 |
commit | 68c52b926eb8cba2b43a37cde4a9658654427e70 (patch) | |
tree | 8b3b1c5d09e3cbaee9814ae55b7d36131e77d5c9 | |
parent | 3e932b668daf1534679811c58b83478873bb9573 (diff) |
Adding the known bugs to 1.5 as well.
-rw-r--r-- | RELEASE.md | 21 |
1 files changed, 21 insertions, 0 deletions
diff --git a/RELEASE.md b/RELEASE.md index 728a840002..0fad3b5d41 100644 --- a/RELEASE.md +++ b/RELEASE.md @@ -214,6 +214,27 @@ Yoni Tsafir, yordun, Yuan (Terry) Tang, Yuxin Wu, zhengdi, Zhengsheng Wei, ç”°ä¼ * Minor refactor: move stats files from `stochastic` to `common` and remove `stochastic`. +## Known Bugs +* Using XLA:GPU with CUDA 9 and CUDA 9.1 results in garbage results and/or + `CUDA_ILLEGAL_ADDRESS` failures. + + Google discovered in mid-December 2017 that the PTX-to-SASS compiler in CUDA 9 + and CUDA 9.1 sometimes does not properly compute the carry bit when + decomposing 64-bit address calculations with large offsets (e.g. `load [x + + 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 + fix for CUDA 9.0.x. Until the fix is available, the only workaround is to + [downgrade](https://developer.nvidia.com/cuda-toolkit-archive) to CUDA 8.0.x + or disable XLA:GPU. + + TensorFlow will print a warning if you use XLA:GPU with a known-bad version of + CUDA; see e00ba24c4038e7644da417ddc639169b6ea59122. + ## Thanks to our Contributors This release contains contributions from many people at Google, as well as: |