Tweet
Any news on the front?
(I was away for some days, if I did not answer any question, please repeat it)
(I was away for some days, if I did not answer any question, please repeat it)
-
-
We fixed the problem testing memory ranges, but the fix isn't public as yet.
The initial problem you had it probably the same as this problem.
http://www.passmark.com/forum/showth...ails-at-Test-3
Since your initial post we purchased a new test machine with same specs as one that exhibited the problem (a Xeon E3). We were able to reproduce the problem with Test #3 on the new machine, but the root cause of the problem is elusive. Basically when multiple threads are running the CPU registers get corrupted. They appear to spontaneously become corrupted during the test. Causing a flood of errors. We don't know if this is a CPU errata, or a bug in the way multi-threading is setup or something more subtle.Comment
-
We implemented a work-around in the V4.3 release that should allow testing on machines that have this problem. The memory testing range bug was also fixed in this release.
See the post on the MemTest86 V4.3 release for more details.Comment
Comment