- Joined
- Aug 19, 2017
- Messages
- 2,651 (0.99/day)
Today the Hot Chips program committee officially announced the August conference line-up, posted to hotchips.org. For this first-ever live-streamed Hot Chips Symposium, the program is better than ever!
In a session on deep learning training for data centers, we have a mix of talks from the internet giant Google showcasing their TPUv2 and TPUv3, and a talk from startup Cerebras on their 2nd gen wafer-scale AI solution, as well as ETH Zurich's 4096-core RISC-V based AI chip. And in deep learning inference, we have talks from several of China's biggest AI infrastructure companies: Baidu, Alibaba, and SenseTime. We also have some new startups that will showcase their interesting solutions—LightMatter talking about its optical computing solution, and TensTorrent giving a first-look at its new architecture for AI.
And you won't want to miss Microsoft speaking about the system architecture for its new gaming console. There will be talks on powerful networking solutions from Intel's Barefoot Networks group, the hot startup Pensando Systems, as well as China's giant Alibaba.
This year's talks on "big-iron" server processors feature Intel's new Xeon Scalable processor, IBM's POWER10 processor, and Marvell's ThunderX3 processor. There are also special sessions on reconfigurable computing, edge computing, and a session on GPUs and gaming as well.
All the companies presenting talks in the conference this year (listed in alphabetical order not counting Tutorials) are: Alibaba, AMD, Arm, Baidu, Cerebras, DeepMind, ETH Zurich, Etherwhere, Google, Harvard University, IBM, Intel, Lightmatter, Marvell, Microsoft, Nvidia, Pensando, SenseTime, Tenstorrent, and Xilinx.
And the keynotes are always a special treat, especially this year. The two headlining keynotes are: Jim Keller, senior vice president of Intel's Technology, Systems Architecture and Client Group (TSCG) and general manager of Intel's Silicon Engineering Group (SEG) speaking on August 17, and Dan Belov, Distinguished Engineer from DeepMind speaking on August 18.
The first day of Hot Chips is a Tutorial Day, split into two half-day tutorials which will deep-dive into the latest and hottest topics in chip design. The morning tutorial from Google and Nvidia is on the topic of machine learning scaling which will cover deep learning basics, system architectures, and best practices. And the afternoon tutorial focuses on quantum computing—the session will review applications, challenges and solutions, with lectures from University of California, Santa Barbara, Google, IBM, Intel, and Microsoft.
The conference will also feature technical posters and a group of corporate sponsors. In upcoming blog posts we'll review more about the program, the keynotes, the tutorials, the posters and of course, the generous sponsors.
Registration is already open at the website hotchips.org. You can follow us on twitter, linkedin or this blog for future updates, including some information about the conference sponsors. Meanwhile, we hope you stay safe and healthy.
View at TechPowerUp Main Site
In a session on deep learning training for data centers, we have a mix of talks from the internet giant Google showcasing their TPUv2 and TPUv3, and a talk from startup Cerebras on their 2nd gen wafer-scale AI solution, as well as ETH Zurich's 4096-core RISC-V based AI chip. And in deep learning inference, we have talks from several of China's biggest AI infrastructure companies: Baidu, Alibaba, and SenseTime. We also have some new startups that will showcase their interesting solutions—LightMatter talking about its optical computing solution, and TensTorrent giving a first-look at its new architecture for AI.
And you won't want to miss Microsoft speaking about the system architecture for its new gaming console. There will be talks on powerful networking solutions from Intel's Barefoot Networks group, the hot startup Pensando Systems, as well as China's giant Alibaba.
This year's talks on "big-iron" server processors feature Intel's new Xeon Scalable processor, IBM's POWER10 processor, and Marvell's ThunderX3 processor. There are also special sessions on reconfigurable computing, edge computing, and a session on GPUs and gaming as well.
All the companies presenting talks in the conference this year (listed in alphabetical order not counting Tutorials) are: Alibaba, AMD, Arm, Baidu, Cerebras, DeepMind, ETH Zurich, Etherwhere, Google, Harvard University, IBM, Intel, Lightmatter, Marvell, Microsoft, Nvidia, Pensando, SenseTime, Tenstorrent, and Xilinx.
And the keynotes are always a special treat, especially this year. The two headlining keynotes are: Jim Keller, senior vice president of Intel's Technology, Systems Architecture and Client Group (TSCG) and general manager of Intel's Silicon Engineering Group (SEG) speaking on August 17, and Dan Belov, Distinguished Engineer from DeepMind speaking on August 18.
The first day of Hot Chips is a Tutorial Day, split into two half-day tutorials which will deep-dive into the latest and hottest topics in chip design. The morning tutorial from Google and Nvidia is on the topic of machine learning scaling which will cover deep learning basics, system architectures, and best practices. And the afternoon tutorial focuses on quantum computing—the session will review applications, challenges and solutions, with lectures from University of California, Santa Barbara, Google, IBM, Intel, and Microsoft.
The conference will also feature technical posters and a group of corporate sponsors. In upcoming blog posts we'll review more about the program, the keynotes, the tutorials, the posters and of course, the generous sponsors.
Registration is already open at the website hotchips.org. You can follow us on twitter, linkedin or this blog for future updates, including some information about the conference sponsors. Meanwhile, we hope you stay safe and healthy.
View at TechPowerUp Main Site
