Follow Slashdot stories on Twitter

 



Forgot your password?
typodupeerror
×
Programming

An Open Source Compiler From CUDA To X86-Multicore 71

Gregory Diamos writes "An open source project, Ocelot, has recently released a just-in-time compiler for CUDA, allowing the same programs to be run on NVIDIA GPUs or x86 CPUs and providing an alternative to OpenCL. A description of the compiler was recently posted on the NVIDIA forums. The compiler works by translating GPU instructions to LLVM and then generating native code for any LLVM target. It has been validated against over 100 CUDA applications. All of the code is available under the New BSD license."

Comment Re:All makes perfect sense, until (Score 1) 317

Also look up some less well-known names like Allengheny Technologies. You're trafficking in the usual truisms about what the US economy has evolved into. The reality (which I don't pretend to have a full handle on) is much more complex.

You may be aware of that business about how the US share of world manufacturing "value added" is still the highest and has in fact been quite stable since WWII.

As a start, for the US data alone, I found it, of all places, at http://www.census.gov/mcd/. I'm still trying to make sense of it all, but one thing I think I've determined is that the largest industry in the US in terms of 'value added' is ... Chemicals.

The industry classifications to be found in the Annual Survey of Manufactures (ASM) are an international standard and so those are comparable.

The thing that makes me most uncomfortable is exchange rates. But recently, I've developed the theory that while PPP is all the rage, it, in fact, applies only to domestic economies and that Nominal values are in fact the best current way to measure international trade. And therefore, in some sense, comparative advantage.

Information on OLAP Databases? 34

oh-lap asks: "One relatively new topic in computing that hasn't seen much mainstream press (yet) is OLAP or multidimensional databases. OLAP is based on the principle of organizing your data along a number of dimensions which can be pivoted and drilled into. OLAP sounds like a neat idea and represent an abstraction of several problems which I've seen tackled by custom coding jobs. The biggest problem with OLAP right now, seems to be a dire lack of expert knowledge in the area and no standardized API or query language for OLAP servers. But the lack of decent introductory reading material is particularly bothersome. If there are any experts (or even dabblers) in OLAP out there, what are the sources of information (books, websites, forums, webblogs, etc) that you go to for info about OLAP? The issues I'm interested in are wide ins scope and include everything from querying and data modeling to actual design of an OLAP server. Any pointers"

Slashdot Top Deals

"A car is just a big purse on wheels." -- Johanna Reynolds

Working...