Celestial AI Wants To Break The Memory Wall, Fuse HBM With DDR5

In 2024, there is no shortage of interconnects if you need to stitch tens, hundreds, thousands, or even tens of thousands of accelerators together. …

Celestial AI Wants To Break The Memory Wall, Fuse HBM With DDR5 was written by Tobias Mann at The Next Platform.

Lambda Snags $320 Million To Grow Its Rent-A-GPU Cloud

Riding high on the AI hype cycle, Lambda – formerly known as Lambda Labs and well known to readers of The Next Platform – has received a $320 million cash infusion to expand its GPU cloud to support training clusters spanning thousands of Nvidia’s top specced accelerators. …

Lambda Snags $320 Million To Grow Its Rent-A-GPU Cloud was written by Tobias Mann at The Next Platform.

Cerebras To Ride The AI Wave To An IPO This Year?

Having commercialized its waferscale AI computing platform to a certain extent over the past several year, Cerebras Systems reportedly wants to get an initial public offering done before the AI hype peaks. …

Cerebras To Ride The AI Wave To An IPO This Year? was written by Tobias Mann at The Next Platform.

Expect Datacenters To Get Denser, Hotter, And Smarter

The datacenter industry today looks very different than it did a decade ago. …

Expect Datacenters To Get Denser, Hotter, And Smarter was written by Tobias Mann at The Next Platform.

Combining AI With HPC To Find Better Battery Designs

The melding of low and high precision mathematics to accelerate the pace of scientific discovery has been a topic of discussion for some time now. …

Combining AI With HPC To Find Better Battery Designs was written by Tobias Mann at The Next Platform.

Sometimes The Best AI Accelerator Is The 37,888 GPUs You Already Have

For traditional HPC workloads, AMD’s MI250X is still a powerhouse when it comes to double precision floating point grunt. …

The post Sometimes The Best AI Accelerator Is The 37,888 GPUs You Already Have first appeared on The Next Platform.

Sometimes The Best AI Accelerator Is The 37,888 GPUs You Already Have was written by Tobias Mann at The Next Platform.

How Lightmatter Breaks Bandwidth Bottlenecks With Silicon Photonics

Without question, the biggest bottleneck in artificial intelligence and for a lot of HPC workloads today is bandwidth. …

The post How Lightmatter Breaks Bandwidth Bottlenecks With Silicon Photonics first appeared on The Next Platform.

How Lightmatter Breaks Bandwidth Bottlenecks With Silicon Photonics was written by Tobias Mann at The Next Platform.

HPC Pioneers Pave The Way For A Flood Of Arm Supercomputers

Over the past few years, the Arm architecture has made steady gains, particularly among the hyperscalers and cloud builders. …

The post HPC Pioneers Pave The Way For A Flood Of Arm Supercomputers first appeared on The Next Platform.

HPC Pioneers Pave The Way For A Flood Of Arm Supercomputers was written by Tobias Mann at The Next Platform.

Where To Park Your AI Cluster Is As Important As Procuring It

When we think about high performance computing, it is often in the context of liquid-cooled systems deployed in facilities specifically designed to accommodate their power and thermal requirements. …

The post Where To Park Your AI Cluster Is As Important As Procuring It first appeared on The Next Platform.

Where To Park Your AI Cluster Is As Important As Procuring It was written by Tobias Mann at The Next Platform.

Hammering Out A Logical File System And A DNS For Data

Data is by its nature a messy beast, and it has only become more so as workloads have found their way out of the datacenter and into the cloud and even all the way out to the edge. …

The post Hammering Out A Logical File System And A DNS For Data first appeared on The Next Platform.

Hammering Out A Logical File System And A DNS For Data was written by Tobias Mann at The Next Platform.

Photonics To Make Celestial HBM3 Memory Fabric

There is no shortage of silicon photonics technologies under development, and every few months it seems like another startup crops up promising massive bandwidth, over longer distances, while using less power than copper interconnects. …

Photonics To Make Celestial HBM3 Memory Fabric was written by Tobias Mann at The Next Platform.

Move Over X86, Amazon’s Arm HPC instances Are Live

When it comes to deploying Arm in the cloud, a lot of the talk of late has centered on things like efficiency, core density, or predictability of performance. …

Move Over X86, Amazon’s Arm HPC instances Are Live was written by Tobias Mann at The Next Platform.

Los Alamos Taps Seagate To Put Compute On Spinning Rust

High performance computing workloads simulating all manner of things can produce a veritable mountain of data that has to be sifted through. …

Los Alamos Taps Seagate To Put Compute On Spinning Rust was written by Tobias Mann at The Next Platform.

More CPU Cores Isn’t Always Better, Especially In HPC

If a few cores are good, then a lot of cores ought to be better. …

More CPU Cores Isn’t Always Better, Especially In HPC was written by Tobias Mann at The Next Platform.

Gigabyte Spins Off Server Division To Chase Datacenter Business

Gigabyte Technology’s enterprise server division has been spun off under a new logo: Giga Computing. …

Gigabyte Spins Off Server Division To Chase Datacenter Business was written by Tobias Mann at The Next Platform.

Supermicro Throws Its Weight Behind Arm Servers

Supermicro has become the latest of the big OEMs to add Arm-based systems to its portfolio, with the launch of its Mt. …

Supermicro Throws Its Weight Behind Arm Servers was written by Tobias Mann at The Next Platform.

Just How Bad Is CXL Memory Latency?

Conventional wisdom says that trying to attach system memory to the PCI-Express bus is a bad idea if you care at all about latency. …

Just How Bad Is CXL Memory Latency? was written by Tobias Mann at The Next Platform.

SQUIP Side Channel Attack Rattles AMD’s Zen Cores

The majority of AMD’s CPU lineup – essentially any processor using Zen 1, Zen 2, or Zen 3 cores with simultaneous multithreading (SMT) enabled – is vulnerable to a newly disclosed side channel attack. …

SQUIP Side Channel Attack Rattles AMD’s Zen Cores was written by Tobias Mann at The Next Platform.

Solving Society’s Big Problems Means Funding More Than Supercomputers

Data science, AI/ML, and HPC have been influential in tackling complex issues like the coronavirus pandemic. …

Solving Society’s Big Problems Means Funding More Than Supercomputers was written by Tobias Mann at The Next Platform.

Marvell Throws Hat Into Intel’s Universal Chiplet Interconnect Ring

Marvell Technology is the latest chipmaker to join the emerging Universal Chiplet Interconnect Express (UCI-Express) consortium, which is working toward an open interconnect standard for chiplet architectures. …

Marvell Throws Hat Into Intel’s Universal Chiplet Interconnect Ring was written by Tobias Mann at The Next Platform.