Jonah Alben, co-lead of GPU engineering at NVIDIA, knows something about patience — he’s spent the last four years working on the NVIDIA A100, which was announced this month during the GTC 2020 keynote.
A 23-year veteran of the company, Alben was an integral contributor to the creation of CUDA, the parallel programming platform and application programming interface model that harnesses GPU acceleration.
He’s also seen the origins and growth of modern AI.
Alben spoke with Rick Merritt, long-time journalist and NVIDIA staff writer, on the AI Podcast about the current state of AI, and how the computer industry is building even better computer, system and data center architectures as Moore’s law slows.
Key Points From This Episode:
- Alben’s role requires that he unite hardware, software and systems teams to build GPUs that surpass the capabilities of the previous generation — in the case of the NVIDIA A100 GPU, by an astounding 20x.
- With the NVIDIA A100 GPU’s 54 billion transistors — the world’s largest 7-nanometer processor — Alben’s team was challenged with ensuring that it didn’t outgrow its reticle, or size limit.
“We had a vision that when we put GPUs out in the world…that somewhere somebody out there in the world would find these GPUs and would use them for some new problem that we didn’t even know about” — Jonah Alben [4:38]
“We wanted to make sure we put everything that we could imagine into making a great chip for our customers” — Jonah Alben [14:37]
You Might Also Like
Speed of Light: SLAC’s Ryan Coffee Talks Ultrafast Science
Particle physicist Ryan Coffee, senior staff scientist at the SLAC National Accelerator Laboratory, explains how he and others in his field are putting deep learning to work.
Sort Circuit: How GPUs Helped One Man Conquer His Lego Pile
At some point in life, every man faces the same great challenge: sorting out his children’s Lego pile. Thanks to GPU-driven deep learning, Francisco “Paco” Garcia is one of the few men who can say they’ve conquered it. Listen in to hear how.
Take Your Fantasy Football Pals to the Cleaners with GPU Computing
Swish Analytics is using GPUs to apply the mathematical models used in the credit card industry to the sports betting market, providing real-time predictions and analysis for bettors and fantasy players alike.
Tune in to the AI Podcast
Get the AI Podcast through iTunes, Google Podcasts, Google Play, Castbox, DoggCatcher, Overcast, PlayerFM, Pocket Casts, Podbay, PodBean, PodCruncher, PodKicker, Soundcloud, Spotify, Stitcher and TuneIn. If your favorite isn’t listed here, drop us a note.
Make the AI Podcast Better
Have a few minutes to spare? Fill out this listener survey. Your answers will help us make a better podcast.