Computer Architecture

Texture units as a general function
Terje Mathisen wrote: It seems to be a bandwidth problem much more than a flops, i.e. using the texture units effectively was the key to the big wins. I am puzzled, torn, wondering about the texture units. There's texture memory, which is just a slightly funky form of cache/memory, with funky locality, a... 14 Dec 2009 10:58

Larrabee delayed: anyone know what's happening?
All I've come across is the announcement that Larrabee has been delayed, with the initial consumer version cancelled. Anyone know something more substantive? ... 13 Jan 2010 12:03

PEEEEEEP
Robert Myers wrote: Sometimes I wonder if you are just one of the most devious and convoluted trolls I have ever encountered, which is to say that everything you say is entirely fabricated with considerable insight as to how it would be viewed by others. There's too much detail, though. If this is a... 21 Dec 2009 21:20

Intel Investing Millions for Supercomputer Research in Europe
http://www.eweek.com/c/a/IT-Infrastructure/Intel-Investing-Millions-for-Supercomputer-Research-in-Europe-171707/ ... 1 Dec 2009 18:23

I love USB displays!
I love displays! I love looking at large numbers of pixels, relatively large pixels for my aging eyes. When encountering the various fanboyisms of my friends and coworkers - gaming, netbooks - I have often felt somewhat embarassed, since I'm really not that much into games, not that much into PCs of clamshell ... 1 Dec 2009 13:52

pipes/streams/channels for parallelism (was: Is C close ...)
Mayan Moudgill <mayan(a)bestweb.net> writes: Anton Ertl wrote: To avoid these overheads and to achieve load balancing, I have been thinking about an implementation that automatically switches between communicating between threads and using coroutining for efficient communication within a thread. Cur... 23 Nov 2009 17:29

MCMT in Bulldozer and SIMT in GPUs
Andy "Krazy" Glew wrote: Of course, AMD has undoubtedly changed and evolved MCMT in many ways since I first proposed it to them. For example, I called the set of an integer scheduler, integer execution units, and an L1 data cache a "cluster", and the whole thing, consisting of shared front end, shared ... 16 Nov 2009 16:53

Sequential consitency on X86_64 - implementation of a bust wait algo not working inspite of using mfences
jon wayne wrote: Hi I was trying to implement a flavor of barrier wait to synchronize pthreads( the machine's Xeon X5, running linux 2.6 and gcc 4.1.1). To ensure sequential conistency - i sprinkled my code with mfences - unfortunately i find the memory consistency being broken when i run this cod... 16 Nov 2009 12:22

first-class types (was: Go language)
Andrew Reilly <areilly---(a)bigpond.net.au> writes: On Sat, 14 Nov 2009 15:43:19 +0000, nmm1 wrote: Secondly, to count as "first-class", at the very least the language has to permit the arrays to be operated on as composite objects, and include at least the basic array-specific operations (such as subsectio... 29 Nov 2009 06:52

CFP (deadline extension): GROW'10 (2nd Workshop on GCC Research Opportunities)
The submission deadline is extended until the 22nd of November, 2009. Apologies if you receive multiple copies of this call. **************************************************************************** CALL FOR PAPERS 2nd Workshop on ... 14 Nov 2009 03:33