I hate to do it.....

[BurntKooshie]

But I am here for a shameless self plug .

I wrote a long whopper of an article on multithreading, and I don't know if it's gonna get a lot of attention from the big sites (I write for systemlogic.net). I hope it does, but I'm not sure. While one of my other articles got /.ed, I think this one is even better, and it'd be really cool if I could get another one /.ed .


Guys, if you could please submit the article to slashdot, I might have a better chance of it getting posted, and getting some mad hit rates

And, believe it or not, I link back to these forums in the article, discussing a post I made (yes, about DC projects no less!), and if you think carefully, you should be able to see many other future applications of the technologies I discussed with respect to distrubuted computing

I really hate to be a self-promoter, but unfortunetly, if I don't, I'm not sure enough other people will for the article to "get noticed."

Thanks guys

Paul Mazzucco

(BK)

 

[Wiz]

cool BK, had to save it in my favs folder!
I have set up for others and am personally running multiproc systems myself - so I can relate so much to what you say from a 'user' point of view.
Thanks, good info!

 

[merlocka]

submitted

 

[IJump]

Sweet article. Told me more than I ever wanted to know about multithreading!

Submitted to /. Hope it helps.

 

[RaySun2Be]

BK,
Great article, well written. Just one point. If you are referring to Gene Amdahl in your Amdahl Law section, you have Amdahl misspelled twice. Once in the section title, and once in the paragraph following. Hopefully you can get that cleaned up before it gets to /.

Oh, you might find this interesting (you probably have already seen it though )

Reevaluating Amdahl's Law

 

[BurntKooshie]

:Q. Email's been sent to Dave...thanks for the heads up

Interesting link! I had not seen it before...wish I had though .

 

[Smoke]

3rd paragraph

The other thing "Bob" didn't realize is that for the vast majority of current consumer based applications, the multithreading support, if existent, does not often expedite the complete (shouldn't this be: completion) of a task proportionally with the number of processors in the system. This fact does not preclude an application from experiencing linear scaling with respect to the number of processors - nay, some applications can experience superlinear scaling, though these are few and far between.

If you do not need any further "proofing", let me know. I'm only through the 3rd paragraph. I did read the Amdahl's Law link provided by RaySun2be...did this guy do graduate work at the University of California - Berkeley?

 

[BurntKooshie]

Yep, there are still errors in it . It's been proofed a couple times, but it's so long it gets tiring . I'd say keep them coming, but then this thread would get so long with grammar errors that you'd not want to read the article thinking it was trash

 

[Smoke]

No more proofing.

Still reading. (off and on while watching the stock market)

 

[RaySun2Be]

Oops,
Sorry BK, my brain cell is on strike today. I should have PMd ya with the editing comments. if I find anymore, I'll email or PM ya. A few typos doesn't detract from it being a great article!

 

[Kilowatt]

Good read BK, I'm impressed WTG.

I submitted it to a dually site I know.

 

[Dale]

BurntKooshie .. well you made it.. now you're /....

liked your article also

_________________________

Bob Moore writes "SystemLogic has got a very thorough article on
multithreading. Deals with Amdalh's Law, Latencies and Bandwidth,
On-Chip Multiprocessing, Course-Grained Multithreading, Fine-Grained
Multithreading, Simultaneous Multithreading, and Applications Of
Multithreading. This is definately a good one."
__________________

..Dale

 

[Kilowatt]

Crongrats, you made 2cpu.com also! You're famous!

 

[BurntKooshie]

Hehe, thanks everybody. Apparently it wasn't so tough to get it /.ed....so which one of you is "Bob Moore"? (That wasn't my submission to /. ). Kinda funny how Hemos was the same guy that posted my last /.ed article....hehe.

Thanks for visiting, and helping to get our server run through hell (It was /.ed bad enough that it was down for a good 20 minutes before it was optimized for load rather than functionality).