CULA R12 Highlight: Link Interface

by Dan

Today we’re very excited to talk about a key feature of CULA R12 that we’ve titled the “Link Interface”. The Link Interface is a link-compatible way of using CULA in your existing programs. That means that with no modifications to your code, you can use CULA’s GPU accelerated routines in your programs simply by changing the linking settings of your application. This is a true way to “swap” out your current package for a GPU accelerated one.

Within the Link Interface we’ve put a lot of work into ensuring that we support all of the needs of your program. Here is just a sampling of these capabilities:

  • GPU acceleration with a single code path. The link interface intercepts all LAPACK and BLAS calls and then dispatches them appropriately. If an accelerated version of a called function is available and the parameters are a sensible combination for GPU acceleration, then the CULA version is called. If not, or the user does not have a GPU, the function will run on the CPU.
  • All functions are available. The link interface provides definitions for all of the functions in LAPACK and BLAS. You don’t have to know which are GPU accelerated and which are not to use the interface because the link interface handles that for you (although we have options to show you if you do want to know).
  • Choose which functions are GPU accelerated and which are not. The link interface supports a configuration file with which you can override our defaults for determining which functions you would like to issue to the GPU and which to the CPU.
  • Accelerated level 3 BLAS is supported. In addition to LAPACK, our link interface provides GPU accelerated definitions for functions, such as matrix multiply, that can benefit from GPU acceleration.
  • Coexists peacefully with other packages. If you would like to use CULA for one part of your application but rely on other packages for different functionality, rest assured that CULA can coexist with other packages like MKL or ACML.

Having link compatibility is a stepping stone towards some amazing applications. For example, using our link interface, with nearly zero-effort you can use GPU accelerated functions in Matlab, a capability we’ll discuss in a future post.

Our main goal with this feature is to help those who have not tried adding GPU acceleration to their codes to do so with almost no work. As soon as CUDA 4 is released, look forward to a full announcement of our R12 release and all of the new capabilities it delivers!


Featured on CUDA Spotlight: John Humphrey

by Liana

John Humphrey, GPU Computing Team Leader

When Calisa Cole from NVIDA contacted me asking if she could feature John Humphrey on their CUDA Spotlight series, I got pretty excited.  "What a great opportunity for John to share about the work he and his team are doing on computational fluid dymanics for the NAVY," I thought.

Most people know us for CULA and our CUDA training program. We do so much more at EM Photonics!  I hope you will enjoy reading John's interview with Calisa, and learning more about this particular CFD-related project he is leading. Below is just a snapshot of how the interview went:

NVIDIA: One of your current projects is an aircraft carrier landing modeling system for the US Navy. Tell us about it.
John: The Navy has a strong desire for CFD (computational fluid dynamics) modeling for a number of reasons. Foremost among these is to be confident of the safety of both aircraft and pilot. For each vessel and aircraft pair, there are tables describing the difficulty of landings and takeoffs based on a large number of variables, such as light conditions, wind speed and direction, and approach angle.

We welcome you to read the entire interview and share your comments here!

Filed under: CULA Press No Comments

CULA Added to TSUBAME 2.0

by Liana

We are excited to share that the engineers in the TSUBAME 2.0 team have chosen to add our library CULA to their software stack!

Here is what Professor Satoshi Matsuoka, TSUBAME 2.0 project leader, had to say about it:

"The majority of the achievable FLOPS in TSUBAME2.0 is due to the power of the GPUs, so it is essential that we provide as comprehensive a software stack to utilize them to their fullest potential as possible. CULA will be an extremely valuable part of the portfolio, allowing our scientists to conduct large scale simulations at unprecedented speeds."

Tokyo Tech signed up for  a 4-year site license and this means that users of their supercomputer will rely on having access to the most current version of CULA.

We would like to recognize here Katsuya Nishi, CEO of Best Systems, who facilitated this effort with Tokyo Tech.  Best Systems is one of our major CULA resellers in Japan and we look forward to a long-lasting, mutually-beneficial relationship with their team and customers.

“I believe there is a large need for a GPU-optimized linear algebra library such as CULA in Japan,” said Katsuya Nishi, CEO of Best Systems.  “Tsubame 2.0 is a great example of how the Japanese scientific community has embraced GPGPU computing on a petaflop scale. The trend is for an even greater adoption of GPUs across all major segments, including industry, government and higher education. Having a comprehensive GPU library like CULA in our portfolio gives us a great competitive edge.”

If you'd like to read the full press release, please check out our news section. We will soon be making another announcement related to our partnerships in Japan, so... stay tuned for more.