Author's Blogs

"A View From Berkeley" Report on Parallelism
By Clay Breshears (Intel)Posted 03/07/20070
Two items in HPCWire (the article "Our Manycore Future" and the interview transcript "Confronting Parallelism") are touting a recent UC Berkeley EECS Department technical report: The Landscape of Parallel Computing Research: A View From Berkeley. The HCPWire article claims that this report is imp...
Developing New Apps: In Parallel or Serial?
By Clay Breshears (Intel)Posted 03/05/20072
With all the legacy code we have around (seems kinda funny to think about C++ apps as "legacy" code), we'll be converting serial applications to parallel versions in order for those applications to run effectively on multi-core platforms. We can add explicit threads, OpenMP pragmas, or threading ...
What's Not Parallel? (#4)
By Clay Breshears (Intel)Posted 02/27/20070
Previously on "What's not Parallel?": Julie had caught Dillon and Becky in a compromising position; Tyler was preparing to make his debut in New York; Copernicus had finally decided to publish De Revolutionibus; and Carol, having drawn the eight of hearts, was just about to go "all in" when the d...
Do We Need A(nother) Parallel Programming Language?
By Clay Breshears (Intel)Posted 02/23/200713
There seems to be a lot of buzz  that has been generated by the article "The Problem with Threads," by UC Berkeley Professor Edward A. Lee, which appeared in the May 2006 issue of IEEE Computer.  After reading the article, this Thread Monkey agrees with the conclusions, but he's not sure how soon...
Hold on Tight! It's Going to be a Bumpy Ride
By Clay Breshears (Intel)Posted 02/22/20071
John Hennessy and David Patterson are best known for their book Computer Architecture: A Quantitative Approach(4th Edition, Morgan Kaufmann, 2006).  At least they are in the circles that I travel. The ACM publication Queue has published an interview with these CS pioneers.  There is also an MP3 v...
Memory and elephants are playing in the band
By Clay Breshears (Intel)Posted 02/15/20072
Ever since the official introduction of the Intel Teraflop chip with 80 cores (octaginta-core?), I've been wondering about how you keep all those cores fed with data. It's not such a trick to imagine what you can do with 80 cores or dream about new kinds of applications that could be brought to t...
What's the next number in this sequence: 1, 2, 4, ?
By Clay Breshears (Intel)Posted 02/12/20071
It's looking like it may be 80. Cores, that is. The New York Times has an article about the upcoming announcement of the Intel Teraflop Chip with 80 cores. The article notes that there are other (specialized) chips with more cores, but this chip would seem to have the most cores for a general pur...
Multiprocessing: What's in it for me?
By Clay Breshears (Intel)Posted 02/11/20074
There has been a shift in the responsibility for delivering faster performing applications. In the past, chip makers have been delivering increases in the clock speed of processors. By doing nothing, ISVs got a performance increase since the CPU executed the same instructions in a shorter amount ...
Money for Nothing, Chicks for Free
By Clay Breshears (Intel)Posted 02/05/200711
I was reading about contests between mathematicians in the 16th Century. Specifically, I was reading about a public problem-solving contest in 1535 where Antonio Maria Fiore challenged NiccolಠTartaglia to solve 30 problems (each devised the problems to be solved by the other contestant) within ...
What's Not Parallel? (#3)
By Clay Breshears (Intel)Posted 01/29/20071
Induction variables are incremented on each trip through a loop. Most likely these are index variables that do not have a one-to-one relation with the value of the loop index variable. For example, consider the following code segment: i1 = 4; i2 = 0; for (k = 1; k < N; k++) { B[i1++] = functio...