1042L is now followed by 1043L. As files in this series seem to be lasting somewhat over three days in active new task distribution, this will likely get us through the weekend with new issue tasks being Turing-compatible.
If you have not been following the data file thread, possibly it may be news to you that Oliver Behnke has reported this excellent news regarding the Turing failures on Einstein:
"I could isolate the problem: it's an issue in the thread management where a specific local memory synchronization barrier isn't reached by all threads, so the process waits forever."
That is vastly more specific than "then Windows driver fails and restarts" or Exit status: 28 (0x0000001C) Unknown error code, or stderr showing "[CRITICAL]: ERROR: MAIN() returned with error '-36'"
1042L is now followed by
)
1042L is now followed by 1043L. As files in this series seem to be lasting somewhat over three days in active new task distribution, this will likely get us through the weekend with new issue tasks being Turing-compatible.
If you have not been following the data file thread, possibly it may be news to you that Oliver Behnke has reported this excellent news regarding the Turing failures on Einstein:
"I could isolate the problem: it's an issue in the thread management where a specific local memory synchronization barrier isn't reached by all threads, so the process waits forever."
That is vastly more specific than "then Windows driver fails and restarts" or Exit status: 28 (0x0000001C) Unknown error code, or stderr showing "[CRITICAL]: ERROR: MAIN() returned with error '-36'"