10:58PM EDT – We’re back for day two of our live blog coverage of Computex
10:59PM EDT – Following AMD’s big, CPU-centric showcase, NVIDIA is on deck this evening to deliver what promises to be a varied keynote touching upon several aspects of NVIDIA’s business
11:00PM EDT – The untitled keynote is slated to run for an hour and features a who’s who of NVIDIA VPs, including Ian Buck (VP Accelerated Computing), Michael Kagan (CTO), and Jeff Fisher (SVP GeForce)
11:00PM EDT – So expect the keynote to cover everything from datacenters to gaming
11:01PM EDT – And here we go
11:02PM EDT – Starting with a quick promo video of the NVIDIA and the growth of their GPU business from gaming to AI and much more
11:03PM EDT – First up, Ian Buck
11:03PM EDT – Starting with AI
11:04PM EDT – This requires reimagining the datacenter itself
11:04PM EDT – AI is also enabling a new market for digital twins
11:04PM EDT – A potential $150B market
11:04PM EDT – And a further $100B market for cloud game streaming
11:05PM EDT – All of which NVIDIA’s partners can tap into by using NVIDIA’s hardware
11:05PM EDT – These tasks consume a lot of computing power – so energy efficiency is a big deal
11:06PM EDT – Of course, NVIDIA is also happy to argue that a lot of power can be saved by moving from using CPUs for compute tasks to GPUs
11:07PM EDT – And NVIDIA has a sizable collection of other hardware, including Grace CPUs and ex-Mellanox networking hardware
11:07PM EDT – Now recapping the H100 accelerator
11:08PM EDT – NVLink 4, Multi-Instance GPU, Confidential Computing, transformer accelerator, etc
11:08PM EDT – And NVLink switches for forming larger clusters of computers
11:10PM EDT – And a shout-out to NVIDIA’s Taiwanese partners for their part in building these new servers
11:10PM EDT – Current NVIDIA roadmap
11:11PM EDT – Two year rhythm on hardware. Interleaving between x86 and Arm
11:11PM EDT – Now on to Grace
11:11PM EDT – Grace is on track to ship next year
11:11PM EDT – Grace and Grace Hopper
11:12PM EDT – For CPU and CPU+GPU workloads respectively
11:12PM EDT – The Grace Superchip (dual Graces) has 144 cores. It has 1TB of LPDDR5X memory and consumes 500 Watts
11:13PM EDT – And reiterating NVIDIA’s plans to put NVLink in all of their silicon, so that it can be linked up to other NVIDIA and third party hardware with a high speed cache coherent interconnect
11:14PM EDT – NVIDIA has developed a large number of reference systems over the years, and they are now producing a new generation of them based on Grace
11:15PM EDT – New CGX, OVX, and GFX refrence designs using Grace and/or Grace Hopper
11:15PM EDT – Announcing HGX Grace and HGX Grace Hopper systems
11:15PM EDT – Both are specifically designed for OEM 2U chassis
11:16PM EDT – Can leverage their existing system architectures
11:16PM EDT – Grace systems will start shipping in the first half of 2023
11:17PM EDT – Now on to talking about Bluefield-3 NPUs
11:18PM EDT – NVIDIA is betting heavily on Bluefield and DPUs becoming essential for datacenters
11:18PM EDT – It is silicon-heavy and will be able to leverage NVIDIA’s GPUs for processing
11:19PM EDT – Or as NVIDIA likes to put it, this networking gear will be the backbone of AI systems
11:19PM EDT – Now on to NVIDIA’s enterprise software stack
11:20PM EDT – As a reminder, NVIDIA has more software engineers than hardware engineers. So at the enterprise level, software is even more of a differentiating factor for NV than hardware is
11:20PM EDT – The next wave of AI: robotics
11:21PM EDT – “We see a clear demand for automation”
11:22PM EDT – Recapping NVIDIA’s Isaac robotics platform
11:23PM EDT – And how Isaac interfaces with omniverse for simulation and robotic training
11:24PM EDT – A big part of enabling this are NVIDIA’s pre-trained models available on NGC
11:25PM EDT – Which is another example of where NVIDIA is using software to build up their ecosystem
11:26PM EDT – Isaac Sim using Omniverse
11:26PM EDT – NVIDIA wants to close the sim-to-real gap
11:26PM EDT – Announcing Isaac Sim 2022.1 release
11:27PM EDT – Now rolling a demo of Isaac Sim
11:29PM EDT – Now on to NVIDIA’s hardware for robotics: Jetson
11:31PM EDT – NVIDIA’s Orin SoC is reportedly performing well in MLPerf benchmarks
11:31PM EDT – The Jetson AGX Orin dev kit is available now
11:32PM EDT – Production systems with Jetson Orin are available now, and many are being announced at Computex this week
11:33PM EDT – Isaac Nova Orin. A state-of-the-art architecture for autonomous mobile robots
11:34PM EDT – One more thing: Drive Hyperion
11:35PM EDT – Hyperion version 8 will start shipping in 2024
11:35PM EDT – And Hyperion 9 is in development for cars shipping starting in 2026
11:35PM EDT – Processes twice as much sensor data as Hyperion 8
11:36PM EDT – And NVIDIA has signed up additional supplier-partners for Hyperion
11:36PM EDT – And now on to gaming with Jeff Fisher
11:37PM EDT – “Taiwan is the birthplace of the PC ecosystem”
11:37PM EDT – Recapping NVIDIA’s current stack of hardware, including GeForce RTX series video cards, Max-Q laptops, and G-Sync monitors
11:38PM EDT – PC game hardware is expected to be a $67B market this year, with double digit growth over coming years
11:38PM EDT – Jeff is thanking NVIDIA’s partners for their products
11:39PM EDT – “[Ampere] is the world’s fastest GPU”
11:39PM EDT – Recapping Ampere family features such as RT cores, DLSS, and NVENC video encoder
11:40PM EDT – Now rolling a video on NVIDIA’s driver development process
11:41PM EDT – This appears to be the same (or similar) Game Ready development video they released a couple of weeks back
11:41PM EDT – “Our mission with drivers is to be invisible”
11:42PM EDT – There are now over 250 RTX games and applications
11:42PM EDT – Hitman 3 is getting an update with ray tracing and DLSS
11:43PM EDT – Also announcing that F1 22, which is launching in July, will also have RT and DLSS
11:44PM EDT – Now on to NVIDIA Reflex
11:44PM EDT – “Low system latency helps all gamers”
11:44PM EDT – NVIDIA recently conducted a study on how system latency impacts aim accuracy
11:44PM EDT – Kovaak’s system latency challenge
11:45PM EDT – Running another promo video, this time on Reflex
11:45PM EDT – Talking about reducing system latency with Reflex
11:46PM EDT – Reflex is even a plugin in Unreal Engine these days
11:46PM EDT – Currently up to 38 games and 22 monitors
11:47PM EDT – Introducing a new Reflex-capable display
11:47PM EDT – A new 500Hz 1080p 24-inch Asus monitor
11:47PM EDT – TN panel
11:47PM EDT – Includes the Reflex Analyzer
11:48PM EDT – Now on to GeForce laptops with Max-Q
11:48PM EDT – Recapping the Max-Q feature set
11:49PM EDT – New gaming laptops at Computex from MSI, Asus, Gigabyte, and others
11:49PM EDT – Now on to NVIDIA Studio
11:49PM EDT – NVIDIA’s creation-focused platform
11:50PM EDT – Now over 200 Studio accelerated applications
11:51PM EDT – And how Omniverse will also help game developers and content creators
11:51PM EDT – Seen a 10x increase in Omniverse downloads
11:51PM EDT – Omniverse is being updated with new features as well, such as Omniverse Cloud and Audio2Face
11:53PM EDT – Now recapping the gaming segment of this keynote and the state of NVIDIA’s gaming ecosystem
11:53PM EDT – And Jeff thanks NVIDIA’s partners one last time
11:54PM EDT – And by signing off with Toy Jensen, that’s a wrap. Thanks for joining us.
