POSSIBLE HARDWARE FAILURE
If the message, "Possible hardware failure,
consult the readme file.", appears in the results
file, then prime95's error-checking has detected a problem. After waiting 5 minutes, the program will
continue testing from the last save file.
Could it be a software problem? If the error is ILLEGAL SUMOUT, then there
is a good chance that this is a software problem. A device driver or VxD may not be saving and restoring FPU state
correctly. The good news is that
prime95 recovers very well from ILLEGAL SUMOUT errors. Try seeing if the problem occurs only when a
specific device is active or a specific program is running.
The other two errors messages, SUMINP! = SUMOUT and
ROUND OFF > 0.40 are caused by one of two things:
1.
For reasons too complicated to go into here, the
program's error checking is not perfect.
Some errors can be missed and some correct results flagged as an
error. If you get the message
"Disregard last error..." upon continuing from the last save file,
then you may have found the rare case where a good result was flagged as an
error.
2.
A true hardware error.
If you do not get the "Disregard last
error..." message or this happens more than once, then your machine is a
good candidate for a torture test. See
the stress.txt file for more
information.
Running the program on a computer with hardware
problems may produce incorrect results.
This won't hurt the GIMPS project since all results will be
double-checked. However, you could be
wasting your CPU time. If you are
getting several errors during each primality test, then I recommend using your
machine to factor Mersenne numbers or run less strenuous distributed computing
projects at http://www.mersenne.org/projects.htm
.