Design Automation Conference 2009

I had the opportunity to visit DAC 2009 this year in San Francisco. DAC is an EDA conference which showcases tools and processes that perform simulation, logic synthesis, design verification, and timing analysis.  The work we do in linear algebra has direct applicability in this space, and we are eager to expand our reach in the EDA market. The show itself was well attended and there were approximately 200 exhibitors. It was great to catch up with our customers and reach out to some new ones.

DAC 2009

One highlight of the show was the keynote presentation delivered by Bill Dally, the Chief Science Officer of NVIDIA. I was particularly interested in a section of Bill’s talk titled The End of Denial Architecture [Part II] – you will have to scroll down to get to that topic. 
Bill comments:

“We [are] entering the era of throughput computing. We enter the era where what matters now is not how fast we run a single thread, because that’s not where the value is being delivered to our end users.”

This statement is completely aligned with our objectives at Acceleware. While the CPU will continue to eke out performance on a single thread, the real value will come from parallelizing the problems we are working on and improving the throughput for our end users.

“It is time to come out of the closet! It is time to think parallel!”

We couldn’t agree more. For the past 5 years, we have seen software designers migrate their applications to multi-core CPU architectures to realize performance gains that have traditionally been realized by upgrading to the latest PC hardware. Today, the next logical step for parallel programming is the GPU, especially given the platform’s compelling price performance ratio. While CPU performance is becoming somewhat saturated (see Bill’s slide on CPU Scaling Ending), the GPU roadmap shows scaling to 2015 and beyond.

I was pleased to see that Acceleware was shown in Bill’s presentation in a couple of places including the CUDA Ecosystem and a large slide on Synopsys TCAD Sentaurus. It is exciting to be at the forefront of a revolutionary change in software design and parallel hardware architectures.

DAC 2009 was a great experience for me to be a part of, especially given this year’s focus on parallel and GPU computing.