AI is reshaping the world. The researchers gathered at this week’s Computer Vision and Pattern Recognition conference in Honolulu are reshaping AI.
That’s why NVIDIA CEO Jensen Huang chose to light up a meetup of elite deep learning researchers at CVPR to unveil theNVIDIA Tesla V100, our latest GPU, based on our Volta architecture, by presenting it to 15 participants in ourNVIDIA AI Labs program.
The audience of more than 150 top AI researchers — gathered for our NVAIL meetup — grabbed their smartphones to snap pictures of the moment.
“AI is the most powerful technology force that we have ever known,” said Jensen, clad in a short sleeve dress shirt, white jeans and vans, or what he called his “aloha uniform.”
“I’ve seen everything. I’ve seen the coming and going of the client-server revolution. I’ve seen the coming and going of the PC revolution. Absolutely nothing compares,” he said.
Tesla V100: Great Gear for Great AI Researchers
Jensen then presented representatives of each of the 15 attending research institutions with NVIDIA Tesla V100 GPU accelerators, each of which included his signature, along with an inscription on the accelerator’s box that read, “Do great AI!”
GPUs — along with the torrents of data unleashed by the internet — have played a key role in the deep learning boom led by researchers like the ones gathered at CVPR. It’s remaking every aspect of human endeavor.
One of the researchers, Silvio Savarese, an associate professor of computer science at Stanford University and director of the school’s SAIL-Toyota Center for AI Research , likened the signed V100 box to a bottle of fine wine.
Savarese’s research has broken ground in computer vision, robotic perception and machine learning. In recent years, he has received the Best Student Paper Award at CVPR 2016, the James R. Croes Medal in 2013, a TRW Automotive Endowed Research Award in 2012, an NSF Career Award in 2011 and a Google Research Award in 2010.
It was clear this moment meant something special to him.
“It’s exciting, especially to get Jensen’s signature,” Savarese said. “My students will be even more excited.”
He said the V100 would be used for new research on autonomous driving and virtual reality, among other areas.
“Everything is powered by deep learning,” said Savarese. “We can do things we’ve never done before.”
Breakthroughs made by researchers such as Savarese and others gathered at CVPR are unleashing technologies with superhuman capabilities.
So it’s fitting that the researchers in attendance will be among the first to put our latest technology to work.
Close Ties to AI Researchers
The surprise presentation is just the latest evidence of NVIDIA’s unique relationship with researchers, Saverese added.
“NVIDIA has a very unusual way of interacting with the community that’s not like any other company,” he said. “It’s a way to sustain the collaboration, and we look forward to more interactions.”
Volta, our seventh-generation GPU architecture, provides a 5x improvement in peak teraflops over its predecessor Pascal, and 15x over the Maxwell architecture, launched just two years ago. This performance surpasses by 4x the improvements that Moore’s law would have predicted.
The Tesla V100 GPU accelerator shatters the 100 teraflops barrier of deep learning performance.
The V100 features over 21 billion transistors, and includes 640 Tensor Cores, delivering 120 teraflops of deep learning performance; the latestNVLink high-speed interconnect technology; and 900 GB/sec HBM2 DRAM to achieve 50 percent more memory bandwidth than previous generation GPUs.
It’s all supported by Volta-optimized software, includingCUDA,cuDNN andTensorRT, which frameworks and applications can easily tap into to accelerate AI and research.
Researchers Relish the Moment
Audience members at the gathering busily captured the moment with photos and video as Jensen detailed the V100’s capabilities. While they were soaking in the moment, Jensen returned the favor by paying tribute to them.
“We’ve learned a great deal about the challenges of AI, and we’ve been adapting our GPUs to be better suited for AI,” he said. “I can’t imagine a better place and a better group of people to share the work we’ve been doing.”