AD1819 | AD7332 | ADSP-2106 | ADSP-21060 | ADSP-21065L | ADSP-2116 | ADSP-21160M | ADSP-2181 | ADSP-218x | ADSP-219 | ADSP-2199 | ADSP219 | BF531 | BF532 | BF533 | BF535 | Blackfin | FFT | JTAG | LDF | SDRAM | SHARC | SPORT | UART | VDSP++ | VisualDSP

Hi people, as usual, I never got a reply to the query below which I sent to the ADI hotline. Anybody have an idea? Regards, Andor > -----Ursprüngliche Nachricht----- > Von: Andor Bariska > Gesendet am: Dienstag, 22. Juni 1999 11:46 > An: ADI DSP Support > Betreff: 21065L Simulator > > Hi, > > using the VisualDSP Debugger V2.32 (dated March 18, 1999) to > simulate a program running on a 21065L, I noticed the > following oddity: > > When loading from 32bit dm memory into a register, the 40bit > extension in the register is not cleared, but appearently set > to some arbitrary value. For example, loading the value > 0xB7BFCC34 into R5 once yielded 0xB7BFCC34D9 and another time > 0xB7BFCC34C2. In my application, this results in two > identical FIRs with exactly the same values in the z buffers > having different output values (the processor is set to 40bit > arithmetic by executing "bit clr MODE1 RND32" at the start of > the program). > > Is this a fluke of the simulator, or will the 21065L actually > behave that way? > > Kind regards, > Andor Bariska > WEISS ENGINEERING LTD. - Professional Digital Audio Products > Florastrasse 42 8610 Uster Switzerland > phone: +41 1 940 20 06, fax: +41 1 940 22 14 > mailto: web: http://www.weiss.ch > You *can* afford the best

______________________________
New Code Sharing Section now Live on DSPRelated.com. Learn about the Reward Program for Contributors here.



(You need to be a member of adsp -- send a blank email to adsp-subscribe@yahoogroups.com )