Forums before death by AOL, social media and spammers... "We can't have nice things"
|    alt.os.development    |    Operating system development chatter    |    4,255 messages    |
[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]
|    Message 3,370 of 4,255    |
|    wolfgang kern to muta...@gmail.com    |
|    Re: segmentation    |
|    24 Oct 22 21:10:18    |
      From: nowhere@nevernet.at              On 23/10/2022 10:42, muta...@gmail.com wrote:       > On Sunday, October 23, 2022 at 4:39:10 PM UTC+8, muta...@gmail.com wrote:       >> On Sunday, October 23, 2022 at 3:55:06 PM UTC+8, Joe Monk wrote:       >>>> Opportunity for what, as far as segment shift is       >>>> concerned?       >>>>       >>> Not a power of 2.       >> 2 ** 5 is a power of 2.       >>       >> What more could possibly be required?       >       > Or are you saying that it is easier for a CPU to shift 4 bits than       > 5 bits because 4 is a power of 2?       >       > I'm not familiar with the hardware, so maybe that is true.       >       > But I am familiar with SHL and SHR, and I know those       > instructions take the same amount of time to execute       > regardless of whether you are shifting 4 bits or 5 bits.       >       > But segment shifting may be different.       >       > So maybe you're right.       >       > Please explain.              The CPU doesn't shift at all here.       these additional bits are hardwired to add:              C BA98 7654 3210 ;bit#        aaaa bbbb ;CS ie: FFFF        cccc dddd ;IP + 0010       __________________ ______       y xxxx xxxx xxxx ; 100000 aka HMA       y is the carryover aka A20              __       wolfgang              --- SoupGate-Win32 v1.05        * Origin: you cannot sedate... all the things you hate (1:229/2)    |
[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]
(c) 1994, bbs@darkrealms.ca