April 28th, 2010 11:24 PM
I can't add anything except to repeat the old saw: Don't reinvent the wheel. I find that (practically) every time I ask myself "Why hasn't anyone ever thought of this?", invariably someone has...
April 28th, 2010 11:13 PM
Codeplug - I'll take a look at the references.
dvyukov - Sounds simple enough.
April 28th, 2010 11:09 PM
What kind of synchronization do you want done by the thread? Are you looking to have it resume processing or stop processing (the current frame) and go on to something else?
(I'm no expert on...
April 23rd, 2010 11:54 AM
I was reading the Kode Vicious column in the April 2010 issue of Communications of the ACM. He was discussing data structures as the canon of computer science, like elementary equations are the...
April 22nd, 2010 03:54 PM
As I see it, automatic parallelization is a dead end. There hasn't been a significant breakthrough since I first heard about the idea many, many years ago. The problem is that auto-parallelizers...
April 21st, 2010 12:53 PM
I think you're describing what I call functional parallelism (or decomposition). Separate (heterogeneous), independent functions are each assigned to a thread in order to simplify the code and logic...
April 21st, 2010 12:22 PM
I don't consider myself any kind of expert in this area, but I would recommend a different keyword. For something that has been established for so long, additional usage will be confusing. And, if...
April 21st, 2010 12:14 PM
Chris -
Excellent questions. I wish I had some brilliant and excellent answers for them.
I've found that the platform being used rather than the computations to be done may have more influence...
April 21st, 2010 11:46 AM
HanneS - What dvyukov said.
I don't know about VB, but if you're using the C Runtime Library (CRT), _beginthreadex does a better job at initializations when starting threads. If you skip those...
April 21st, 2010 11:35 AM
"IO bound" applications were never the purview of TBB. The design was directed toward loop-level parallelism. I was trying to find a quote to that effect, but can't locate one.
A library that...
April 21st, 2010 11:21 AM
I don't think we have any insight about what developers are using except what someone might report from a poll (and I've not seen one like this).
The ability to perform and monitor asynchronous...
April 20th, 2010 12:56 PM
If you think the iterations of a loop are independent, but you're not sure, run the loop in reverse (in serial) and check to see if you get the same answer. For example, if your for-loop goes from 0...
April 20th, 2010 12:49 PM
As for what came first or who had the idea that was copied by the other, I think we're talking a chicken and egg question. In most cases, after an idea has been vetted as being something useful,...
April 19th, 2010 09:42 AM
The 2.2 version of Intel Threading Building Blocks (available now) has several new parallel algorithms. These include parallel_for_each and parallel_invoke. Support for C++0X lambda functions has...
April 19th, 2010 09:21 AM
Hello, hello.
I'm Clay Breshears and I've been doing parallel, concurrent, and multithreaded programming for over 25 years. I've been with Intel for almost ten of those, starting as a Senior...
April 12th, 2010 06:35 PM
Getting closer, then
--clay
April 12th, 2010 09:53 AM
Here's the code for the SyncQueue constructor.
SyncQueue<NodeType>::SyncQueue()
{
Node<NodeType> *dummy = new Node<NodeType>; // Set up initial dummy node on empty queue
head = dummy;...