Martin Heller
Contributing Writer

CUDA SDK is impressive

analysis
Mar 13, 20092 mins

Massively parallel GPU computing using the Nvidia tools is no harder than it needs to be.

When I wrote GPU computing is about massive data parallelism way back in January, I hoped to have a CUDA-capable machine set up quickly. It took a bit longer than I thought, but I’m finally ready to tell you about the CUDA SDK.

On Windows, the CUDA SDK integrates with Visual Studio. The documentation is good enough to get you started, although it wasn’t completely up to date when I did the download, and the installation has some manual steps. As you can see, when it’s all complete you get syntax-coloring for CUDA keywords and types. You can click this image to see a higher-resolution version.

I’m looking at the Mandelbrot sample provided in the CUDA SDK; it was contributed by Mark Granger of NewTek. In fact, the SDK comes with a sample browser, in case you just want to play with the applications provided.

Here’s the full Mandelbrot set. Note the frame rate:

And here’s a zoomed-in section of the set, with double-precision turned on and the iterations bumped to 4096 for high detail:

If we were running this with the CPU, that frame rate would not be in frames per second, it would be much slower, perhaps frames per hour. Color me impressed.

Martin Heller

Martin Heller is a contributing writer at InfoWorld. Formerly a web and Windows programming consultant, he developed databases, software, and websites from his office in Andover, Massachusetts, from 1986 to 2010. From 2010 to August of 2012, Martin was vice president of technology and education at Alpha Software. From March 2013 to January 2014, he was chairman of Tubifi, maker of a cloud-based video editor, having previously served as CEO.

Martin is the author or co-author of nearly a dozen PC software packages and half a dozen Web applications. He is also the author of several books on Windows programming. As a consultant, Martin has worked with companies of all sizes to design, develop, improve, and/or debug Windows, web, and database applications, and has performed strategic business consulting for high-tech corporations ranging from tiny to Fortune 100 and from local to multinational.

Martin’s specialties include programming languages C++, Python, C#, JavaScript, and SQL, and databases PostgreSQL, MySQL, Microsoft SQL Server, Oracle Database, Google Cloud Spanner, CockroachDB, MongoDB, Cassandra, and Couchbase. He writes about software development, data management, analytics, AI, and machine learning, contributing technology analyses, explainers, how-to articles, and hands-on reviews of software development tools, data platforms, AI models, machine learning libraries, and much more.

More from this author