Drut tackles disaggregation at a data centre scale

• Drut’s DynamicXcelerator supports up to 4,096 accelerators using optical switching and co-packaged optics. Four such clusters enable the scaling to reach 16,384 accelerators.
• The system costs less and is cheaper to run, has lower latency, and better uses the processors and memory.
• The system is an open design supporting CPUs and GPUs from different vendors. 
• DynamicXcelerator will ship in the second half of 2024.

Bill Koss (L) and Jitender Miglani.

Drut Technologies has detailed a system that links up to 4,096 accelerator chips. And further scaling, to 16,384 GPUs, is possible by combining four such systems in ‘availability zones’.

Click to read more ...

Broadcom's first Jericho3 takes on AI's networking challenge

Broadcom’s Jericho silicon has taken an exciting turn.

Oozie Parizer

The Jericho devices are used for edge and core routers.

But the first chip of Broadcom’s next-generation Jericho is aimed at artificial intelligence (AI); another indicator, if one is needed, of AI’s predominance.

Dubbed the Jericho3-AI, the device networks AI accelerator chips that run massive machine-learning workloads.

Click to read more ...

Enfabrica’s chip tackles AI supercomputing challenges

• Enfabrica’s accelerated compute fabric chip is designed to scale computing clusters comprising CPUs and specialist accelerator chips.
• The chip uses memory disaggregation and high-bandwidth networking for accelerator-based servers tackling artificial intelligence (AI) tasks.

Rochan Sankar

For over a decade, cloud players have packed their data centres with x86-based CPU servers linked using tiers of Ethernet switches.

“The reason why Ethernet networking has been at the core of the infrastructure is that it is incredibly resilient,” says Rochan Sankar, CEO and co-founder of Enfabrica.

But the rise of AI and machine learning is causing the traditional architecture to change.

What is required is a mix of processors: CPUs and accelerators. Accelerators are specialist processors such as graphics processing units (GPUs), programmable logic (FPGAs), and custom ASICs developed by the hyperscalers.

Click to read more ...

Data centre photonics - an ECOC report

• ECOC 2022 included talks on optical switching and co-packaged optics.
• Speakers discussed optical switching trends and Google's revelation that it has been using optical circuit switching in its data centres.
• Nvidia discussed its latest chips, how they are used to build high-performance computing systems, and why optical input-output will play a critical role.

Co-packaged optics and optical switching within the data centre were prominent topics at the recent ECOC 2022 conference and exhibition in Basel, Switzerland.

Click to read more ...

Telecoms' innovation problem and its wider cost

Imagine how useful 3D video calls would have been this last year.

The technologies needed - a light field display and digital compression techniques to send the resulting data across a network - do exist but practical holographic systems for communication remain years off.

Source: Accelerating Innovation in the Telecommunications Arena

But this is just the sort of application that telcos should be pursuing to benefit their businesses.

Click to read more ...

UK quantum algorithm start-up targets first opportunity

A UK start-up developing software for quantum computers has received £3.25 million ($4.1 million) in funding. 

Riverlane, based in Cambridge, is working with leading quantum computing hardware companies as well as large corporates interested in benefiting from the technology.

The start-up will use the funding to grow the company and has already identified the most promising applications for the technology.

“A lot of people are building hardware using various technologies such as iron trap or supercomputing qubits,” says Steve Brierley, CEO of Riverlane. “What we are trying to do is make that [hardware] useful as soon as possible.” A qubit is the shorthand term for a quantum bit.

Click to read more ...

Habana Labs unveils its AI processor plans

Start-up Habana Labs has developed a chip architecture that promises to speed up the execution of machine-learning tasks. 

The Israeli start-up came out of secrecy in September to announce two artificial intelligence (AI) processor chips. One, dubbed Gaudi, is designed to tackle the training of large-scale neural networks. The chip will be available in 2019. 

Eitan MedinaGoya, the start-up’s second device, is an inference processor that implements the optimised, trained neural network.

The Goya chip is already in prospective customers’ labs undergoing evaluation, says Eitan Medina, Habana’s chief business officer.

Habana has just raised $75 million in a second round of funding, led by Intel Capital. Overall, the start-up has raised a total of $120 million in funding. 

Click to read more ...