Intel/Linux BUG (fwd)

James Simmons jsimmons at acsu.buffalo.edu
Sat Apr 1 10:03:00 EST 2000


---------- Forwarded message ----------
Date: Sat, 1 Apr 2000 09:32:46 -0500 (EST)
From: Richard B. Johnson <root at chaos.analogic.com>
To: Linux kernel <linux-kernel at vger.rutgers.edu>
Subject: Intel/Linux BUG


Boston, Massachusetts, April 1, 2000;

We all know that Intel has included the rdtsc instruction in their
processors for quite some time now. This is a count of the number
of CPU clocks that have occurred since the processor was started.

The length of the count (a long long) has always been assumed to
be 2^64. Nobody has questioned what the result will be when it
wraps.

Dr. Robert Mandl, a former mathematics professor at MIT, now working as an
independent consultant has found that when the timer wraps, the processor
will no longer recognize any `mov` instructions.

When questioned, an unnamed Intel spokesman stated; "The machine should
be shut down before this event can occur. No known operating system,
except Linux, would allow a CPU to run for such a long time anyway."

Because of this, this newly discovered Intel bug has been named the
"Linux BUG".


Cheers,
Dick Johnson

Penguin : Linux version 2.3.41 on an i686 machine (800.63 BogoMips).


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo at vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/



More information about the nflug mailing list