Talk:Task parallelism

I think the example section could use a little work, but I'm not an expert enough to say whether it's actually wrong or not so I've left it the way it is. The problem I see is in the pseudocode:

• According to the example, "a" is executed as the first part of the if-block. "b" is part of the same block and is executed if the "else if" statement is true.
• In my opinion, "b" would never be executed because "a" evaluates as true, so the rest of the statements in that if-block are skipped. All the languages I'm familiar with evaluate each if-statement until they find one that's true and then skip the remaining else-statements, if any. Or is this ideosyncratic? AFAIK, C, C++, Python, Java and Scala all follow this convention.

Daniel Lee (talk) 08:55, 25 March 2013 (UTC)

Task parallelism = MIMD? --Abdull (talk) 09:00, 24 September 2009 (UTC)

The JVM example is confusing, and looks like spam. Furthermore, it adds little to the content of the article. — Preceding unsigned comment added by 85.247.160.254 (talk) 20:16, 6 November 2013 (UTC)

Contrast with data parallelism

[T]ask parallelism is achieved when each processor executes a different thread (or process) on the same or different data. The threads may execute the same or different code.

I'd don't really see the promised contrast with data parallelism materializing here. It looks like data parallelism is a special case of task parallelism (different data, same code). I'm not sure if that's intended. QVVERTYVS (hm?) 22:13, 28 December 2014 (UTC)

thread-level parallelism

I see that thread-level parallelism is now a redirect to this task parallelism article.

In another article, I see that someone recently changed[1] every instance of "thread-level parallelism" (TLP) to "task-level parallelism" (TLP).

Is there a difference between "thread-level parallelism" vs "task-level parallelism"? If so, what is the difference? --DavidCary (talk) 16:45, 19 November 2015 (UTC)