Slashdot Mirror

← Back to Stories (view on slashdot.org)

AMD Confirms CPU Bug Found By DragonFly BSD's Matt Dillon

Posted by Soulskill on from the it's-not-me-it's-you dept.

An anonymous reader writes "Matt Dillon of DragonFly BSD just announced that AMD confirmed a CPU bug he found. Matt quotes part of the mail exchange and it looks like 'consecutive back-to-back pops and (near) return instructions can create a condition where the processor incorrectly updates the stack pointer.' The specific manifestations in DragonFly were random segmentation faults under heavy load."

3 of 292 comments (clear)

  1. Kudos by Mannfred · · Score: 5, Insightful

    I can only imagine the time and effort spent on tracking down this problem - a rare CPU condition is exponentially more difficult to narrow down than most programming mistakes. A lot of progress in IT depends on engineers like this, who obsessively solve problems even when it's much easier to just ignore them, try to hack around them or pass the buck around. Kudos.

  2. Re:This isn't nearly as bad as the division bug by Anonymous Coward · · Score: 5, Insightful

    Floating point operations are never fully precise. Simple numbers such as 4.0 would be represented as 4.0000000000000213 or 3.99999999999973 if you arrive at this after doing a bunch of calculations.

    This is an inherent limitation of how floating point works, and not something that has been "fixed". Programmers still have to worry about this.

  3. Re:This isn't nearly as bad as the division bug by sjames · · Score: 5, Insightful

    Imagine, there is a tiny bug that makes your floating point results just slightly wrong once in 1000 times. You run an iterative dynamic simulation of a bridge under load that runs for a million cycles. The results LOOK right...