Re: Denial of denial of service

[prev] [thread] [next] [lurker] [Date index for 2007/01/29]

From: Peter da Silva
Subject: Re: Denial of denial of service
Date: 12:12 on 29 Jan 2007
> Let's make it simple: did you actually see it /done/? I tried it with 
> gcc 3.3.1 on x86 and exceptions do translate to overhead (I don't know 
> x86 assembly either, but I can see when 2 additional instructions are 
> emitted). Green Hills on ARM is worse, trust me. Let's say I don't 
> care for the monstrous inflation of data. Let's say I don't care that 
> the generated assembly code looks like dog vomit. Can you name a 
> platform where no extra instructions in the normal flow path are 
> generated when exceptions are enabled?

Why are you using C++ on hardware where you're coding that close to the 
performance edge anyway?

Even when I was doing railroad safety systems on the Z80 a few percent 
overhead in total execution time wasn't going to push me over the 
limit.

Your comment about ARM and automotive applications implies you're doing 
real-time work, and if you're running real-time code where that 
percentage of overhead will make you slip deadlines... well, I hope 
it's not safety-critical. Hell, if you're coding realtime in C++ I hope 
it's not safety-critical. :P

Generated at 23:01 on 06 Feb 2007 by mariachi 0.52