Nvidia določa časovnico za GPU H100 – zdaj za HGX, naslednje leto za DGX

Splošni pogoji poslovanja Nvidia’s long-awaited Hopper H100 accelerators will begin shipping later next month in OEM-built HGX systems, the silicon giant said at its GPU Technology Conference (GTC) event today.

However, those waiting to get their hands on Nvidia’s DGX H100 systems will have to wait until sometime in Q1 next year. The DGX is Nvidia’s line of workstations and servers using its GPUs and interconnects, and HGX systems are partner-made servers again using Nv’s technology.

And while Nvidia is hyping its Hopper architecture in the datacenter, most of the enterprise kit announced this week won’t be getting the chip giant’s flagship architecture anytime soon.

Na robu se zdi, da je Nvidia zadovoljna s polnim življenjem svoje arhitekture Ampere.

Danes je Nvidia podrobno opisala novo generacijo platforme za umetno inteligenco in robotiko, ki jo imenuje IGX.

IGX is an “all-in-one computing platform to accelerate the deployment of real-time intelligent machines and medical devices,” Kimberly Powell, veep of healthcare at Nvidia, said. At its core, the system is essentially an expanded version of Nvidia’s previously announced Jetson AGX Orin module, announced this pomlad.

“IGX is a full system with the Nvidia Orin robotics processor, Ampere tensor-core GPU, the ConnectX streaming I/O processor, a functional safety island, and safety microcontroller unit because more and more robots and humans will be working in the same environment,” she added.

In terms of performance, there’s not much new here. We’re told the platform is based on an Orin industrial system on module with 64GB of memory that’s comparable in performance to the AGX Orin module launched earlier this year. That system featured 32GB of memory, an octacore Arm Cortex A78AE CPU and Ampere-based GPU.

IGX pridobi integrirano omrežno kartico ConnectX-7 za hitro povezljivost prek dveh vmesnikov 200 Gbps. Zdi se, da ima plošča tudi popoln nabor pomnilnika M.2, reže PCIe in vsaj eno podedovano režo PCI za razširitev.

Nvidia cilja na platformo IGX za različne robne primere uporabe umetne inteligence in robotike v zdravstvu, proizvodnji in logistiki, kjer so zaradi zaupnosti ali zakasnitve bolj centralizirani sistemi nepraktični.

Like the AGX Orin, the system is complimented by Nvidia’s AI Enterprise software suite and Fleet Command platform for deployment and management.

One of the first applications of the IGX platform will be using Nvidia’s robotics imaging platform.

“Nvidia Clara Holoscan is our application framework that sits on top of IGX for medical devices and imaging robotics pipelines,” Powell explained.

Trije prodajalci medicinskih pripomočkov – Activ Surgical, Moon Surgical in Proximinie – nameravajo uporabiti IGX in Clara Holoscan za napajanje svojih platform za kirurško robotiko in teleprisotnost. Kompleti za razvijalce IGX Orin naj bi bili dobavljeni v začetku naslednjega leta s proizvodnimi sistemi, ki so na voljo pri ADLink, Advantech, Dedicated Computing, Kontron, MBX in Onyx, če naštejemo le peščico.

Na temo Orina je Nvidia predstavila tudi svoje računalniške module Jetson Orin Nano. Orin Nano je ob lansiranju na voljo v dveh konfiguracijah, vključno z različico z 8 GB, ki omogoča 40 TOPS sklepanja z umetno inteligenco, in zmanjšano različico s 4 GB pomnilnika, ki omogoča 20 TOPS.

Like prior Jetson modules, the Orin Nano uses a pin-compatible edge connector reminiscent of that used for laptop SODIMM memory and consumes between 5W and 15W depending on application and SKU. Nvidia’s Jetson Orin Nano modules are available in January starting at $199.

Osvežitev OVX

Nvidia’s OVX servers, which are designed to run its Omniverse platform, won’t be running on Hopper either.

The company’s second-gen visualization and digital-twinning systems instead come equipped with eight L40 GPUs. The cards are based on the company’s next-generation Ada Lovelace architecture and feature Nvidia’s third-gen ray tracing cores and fourth-gen Tensor Cores.

Grafične procesorje spremlja par procesorjev Ice Lake Intel Xeon Platinum 8362 za skupno 128 procesorskih niti pri do 3.6 GHz.

The compute system is accompanied by three ConnectX-7 NICs, each capable of 400Gbps of throughput, and 16TB of NVMe storage. While the system is available as individual nodes, Nvidia envisions the system being deployed as part of what it calls an OVX SuperPod, which incorporates 32 systems connected using the company’s 51.2Tbps Spectrum-3 switches.

Sistemi druge generacije bodo od leta 2023 na voljo pri družbah Lenovo, Supermicro in Inspur. V prihodnosti namerava Nvidia razširiti razpoložljivost sistemov na dodatne partnerje.

Skočil sem na Drive Thor

The only bit of kit announced at GTC this week that is getting Nvidia’s Hopper architecture is the Drive Thor autonomous vehicle computer system.

Drive Thor replaces Nvidia’s Atlan platform on its 2025 roadmap and promises to deliver 2,000 TOPS of inferencing performance when it launches.

“Drive Thor comes packed with cutting-edge capabilities introduced in our Grace CPU, our Hopper GPU, and our next-generation GPU architecture,” Danny Shapiro, VP of Automotive at Nvidia, told a press briefing. He said Drive Thor is designed to unify the litany of computer systems that power modern automobiles into a single centralized platform.

“Look at today’s advanced driver-assistance systems – parking, driver monitoring, camera mirrors, digital instrument cluster, infotainment systems – they’re all on different computers distributed throughout the vehicle,” he said. “In 2025, however, these functions will no longer be separate computers. Rather, Drive Thor will enable manufacturers to efficiently consolidate these functions into a single system.”

Za obvladovanje vseh informacij, ki se pretakajo iz avtomobilskih senzorjev, ima čip izolacijo z več računalniškimi domenami, za katero Nvidia pravi, da omogoča, da čip izvaja sočasne kritične procese brez prekinitev.

The tech also allows the chip to run multiple operating systems simultaneously to suit the various vehicle applications. For example, the car’s core operating system might run on Linux, while the infotainment system might run QNX or Android.

However, it it is unknown when we might get to see the tech in action. As it stands, all three of Nvidia’s launch partners – Zeekr, Xpeng, and QCraft – are based in China. ®