Intel Corporation (INTC) Message Board

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Technology Stocks : Intel Corporation (INTC)

INTC 48.23

+2.3%

Feb 11 3:59 PM EST

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next

To: d[-_-]b who wrote (20603)	5/7/1997 6:26:00 PM
From: Martin Atkinson-Barr	of 186894

FIST & FISTP BUG MUCH WORSE THAN FIRST THOUGHT Thanks for making me look at the Intel docs. The situation is much worse than originally thought. The FIST & FISTP instructions apparently are not setting the OVERFLOW bit instead of the IE bit. They are setting the PRECISION BIT. Here's a description from an Intel manual of that bit: "If the result of an operation is not exactly representable in the destination format the FPU rounds the number and reports the precision exception. For example, the fraction 1/3 cannot be precisely represented in binary form. This exception occurs frequently and indicates that some (generally acceptable) accuracy has been lost; it is provided for applications that need to perform exact arithmetic only" Thus numeric software would always ignore this bit to check for errors unless it is highly specialized exact arithmetic (such as may be found in Mathematica). General scientific & engineering software ignores the loss of precision since it is using either float or double variables and the FPU calculates internally with 80-bit precision. This bug therefore masks an error and will frequently return the wrong answer.

Report TOU Violation

Share This Post

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next