Beefy Boxes and Bandwidth Generously Provided by pair Networks
XP is just a number
 
PerlMonks  

Re^6: [OT] The interesting problem of comparing bit-strings.

by BrowserUk (Patriarch)
on Mar 25, 2015 at 14:01 UTC ( [id://1121306]=note: print w/replies, xml ) Need Help??


in reply to Re^5: [OT] The interesting problem of comparing bit-strings.
in thread [OT] The interesting problem of comparing bit-strings.

You spend far too much time making knee-jerk reactions to my posts,

I did not "knee-jerk". I read it and despaired for your sanity.

on the assumption that I don’t know what I am about

You don't!. You've proved that beyond a shadow of a doubt; over and over; and you're about to do it again.

and am speaking to hear my head rattle.

That's as good an explanation for it as any I suppose.

Now, step back and read my post again, starting with SCASD. You do not approach this thing “byte-wise.” Instead, you search through 64 bits at a time ... a quadword, I believe it is called.

Now you step back an read what I replied: "You cannot search for bits using byte(nor word, nor double-word)-wise instructions unless your happy to miss 75%(87%,94%) of possible hits."

Instead, you search through 64 bits at a time ... a quadword, I believe it is called.

SCASD is a Double word --ie. 32-bits -- you twonk!

(You just read my use of the term throughout this thread; and now your regurgitating your screen-reflected knowledge back at me? You utter twonk!)

There is a quadword version, but it's not x86 as you suggested above, but x64; and its a SCAS instruction no suffix, and requires a REX.W prefix; all of which will go completely over your rattling head.

But even that is completely useless for a bitstring search -- even more useless than SCASB/W/D.

Because it would require that you make 64 complete passes of the entire (1/4GB) haystack to detect that what you are looking for doesn't exist; and upto 63 complete passes to find it, even if it was right there at the very beginning. Everything you said in the first post was wrong; and with this rehashed, regurgitated, reiteration, it continues to be wrong! You total and utter twonk!

For an explanation (that you won't understand), read: Re^6: [OT] The interesting problem of comparing bit-strings. & Re^8: [OT] The interesting problem of comparing bit-strings..

You cannot do efficient bit-string searches using byte/word/double word or quadword string-scan instructions. Full stop. Now please STFU.


With the rise and rise of 'Social' network sites: 'Computers are making people easier to use everyday'
Examine what is said, not who speaks -- Silence betokens consent -- Love the truth but pardon error.
"Science is about questioning the status quo. Questioning authority". I'm with torvalds on this
In the absence of evidence, opinion is indistinguishable from prejudice. Agile (and TDD) debunked
  • Comment on Re^6: [OT] The interesting problem of comparing bit-strings.

Log In?
Username:
Password:

What's my password?
Create A New User
Domain Nodelet?
Node Status?
node history
Node Type: note [id://1121306]
help
Chatterbox?
and the web crawler heard nothing...

How do I use this?Last hourOther CB clients
Other Users?
Others studying the Monastery: (7)
As of 2024-04-19 09:35 GMT
Sections?
Information?
Find Nodes?
Leftovers?
    Voting Booth?

    No recent polls found