Linked by David Adams on Mon 5th Mar 2012 22:45 UTC, submitted by gogothebee
Hardware, Embedded Systems "After struggling with this issue for well over a year and really pushing hard to track it down in the last two months I was finally able to come up with a test case running 'cc1' from gcc-4.4 in a loop and get it to fail in less than 60 seconds. Prior to finding this case it would take anywhere up to 2 days with 48 cores fully loaded to reproduce the failure. AMD confirms. '...it isn't every day that a guy like me gets to find an honest-to-god hardware bug in a major cpu!'"
Permalink for comment 509652
To read all comments associated with this story, please click here.
According to the post
by Poseidon on Tue 6th Mar 2012 05:21 UTC
Poseidon
Member since:
2009-10-31

According to the post, AMD confirmed it is a hardware bug. These I believe have been seen in the past, and the last one I remember (don't quote me on this) was actually fixed by disabling certain instructions so that the bug would not happen.

Reply Score: 1