Timothy Prickett Morgan
Author Archives: Timothy Prickett Morgan
- Home → Author's archive:
Timothy Prickett Morgan
“Milan-X” 3D Vertical Cache Yields Epyc HPC Bang For The Buck Boost
Last fall ahead of the SC21 supercomputing conference, AMD said it was going to be the first of the major compute engine makers to add 3D vertical L3 cache to its chips, in this case to variants of the “Milan” Epyc 7003 series of processors that debuted in March 2021 called the “Milan-X” chips. …
“Milan-X” 3D Vertical Cache Yields Epyc HPC Bang For The Buck Boost was written by Timothy Prickett Morgan at The Next Platform.
Why Nvidia Should Acquire SUSE
Here we are, on the Friday before the flagship GPU Technology Conference hosted by Nvidia is set to kick off. …
Why Nvidia Should Acquire SUSE was written by Timothy Prickett Morgan at The Next Platform.
Liqid Launches Its Own Systems, Chases AI And HPC
To hardware or not to hardware, that is a real question for vendors peddling all kinds of software in the datacenter. …
Liqid Launches Its Own Systems, Chases AI And HPC was written by Timothy Prickett Morgan at The Next Platform.
Burning Cash Like Rocket Fuel To Get Hashi Stack To The Next Stage
Creating a platform is a massive technical challenge. We have seen many technically elegant ones in recent years – Cloud Foundry, Engine Yard, the original OpenShift, Photon Platform, Mesos, OpenStack come immediately to mind – that didn’t quite make it, and importantly did not rise to the economic challenge of making enough money to sustain the continued development and support of that platform to have to reach tens of thousands, to hundreds of thousands, to millions of customers. …
Burning Cash Like Rocket Fuel To Get Hashi Stack To The Next Stage was written by Timothy Prickett Morgan at The Next Platform.
Teaching Kubernetes To Do Fractions And Multiplication On GPUs
When any new abstraction layer comes to compute, it can only think in integers at first, and then it learns to do fractions and finally, if we are lucky – and we are not always lucky – that abstraction layer learns to do multiplication and scale out across multiple nodes as well as scaling in – slicing itself into pieces – within a single node. …
Teaching Kubernetes To Do Fractions And Multiplication On GPUs was written by Timothy Prickett Morgan at The Next Platform.
Ethernet Switching Keeps Rising Despite Supply Chain Woes
Whenever demand exceeds supply, inflation is inevitable. And it is not at all surprising to find that in certain sectors of the networking space, the cost of bandwidth is flattening out instead of decreasing and in some cases is on the rise. …
Ethernet Switching Keeps Rising Despite Supply Chain Woes was written by Timothy Prickett Morgan at The Next Platform.
How China Made An Exascale Supercomputer Out Of Old 14 Nanometer Tech
If you need any proof that it doesn’t take the most advanced chip manufacturing processes to create an exascale-class supercomputer, you need look no further than the Sunway “OceanLight” system housed at the National Supercomputing Center in Wuxi, China. …
How China Made An Exascale Supercomputer Out Of Old 14 Nanometer Tech was written by Timothy Prickett Morgan at The Next Platform.
Talking Silicon Photonics Signal And Noise With Andy Bechtolsheim
There is a lot of chatter this week about optical communications with the OFC2022 conference being held in San Diego. …
Talking Silicon Photonics Signal And Noise With Andy Bechtolsheim was written by Timothy Prickett Morgan at The Next Platform.
Will HPC Be Eaten By Hyperscalers And Clouds?
Some of the most important luminaries in the HPC sector have spoken from on high, and their conclusions about the future of the HPC market are probably going to shock a lot of people. …
Will HPC Be Eaten By Hyperscalers And Clouds? was written by Timothy Prickett Morgan at The Next Platform.
A Cornucopia Of Memory And Bandwidth In The Agilex-M FPGA
When it comes to memory for compute engines, FPGAs – or rather what we have started calling hybrid FPGAs because they have all kinds of hard coded logic as well as the FPGA programmable logic on a single package – have the broadest selection of memory types of any kind of device out there. …
A Cornucopia Of Memory And Bandwidth In The Agilex-M FPGA was written by Timothy Prickett Morgan at The Next Platform.
With ROCm Software And Instinct MI200 GPUs, AMD Has Ecosystem Critical Mass
Paid Feature Great hardware is the foundation of any compute platform. …
With ROCm Software And Instinct MI200 GPUs, AMD Has Ecosystem Critical Mass was written by Timothy Prickett Morgan at The Next Platform.
With Excelero Storage, Nvidia Owns A Nearly Complete HPC/AI Stack
In case it is not immediately obvious, over the past decade Nvidia has been transforming itself from a component supplier into a complete platform provider. …
With Excelero Storage, Nvidia Owns A Nearly Complete HPC/AI Stack was written by Timothy Prickett Morgan at The Next Platform.
With Systems, HPE Walks The Line Between Demand And Supply
It is a tough environment for a lot of enterprises right now, and has been since the advent of the coronavirus pandemic more than two years ago. …
With Systems, HPE Walks The Line Between Demand And Supply was written by Timothy Prickett Morgan at The Next Platform.
GraphCore Goes 3D With AI Chips, Architects 10 Exaflops Ultra-Intelligent Machine
The 3D stacking of chips has been the subject of much speculation and innovation in the past decade, and we will be the first to admit that we have been mostly thinking about this as a way to cram more capacity into a given compute engine while at the same time getting components closer together along the Z axis and not just working in 2D anymore down on the X and Y axes. …
GraphCore Goes 3D With AI Chips, Architects 10 Exaflops Ultra-Intelligent Machine was written by Timothy Prickett Morgan at The Next Platform.
Cerebras Shows Off Scale Up AI Performance For Big Pharma And Big Oil
Historically, the largest organizations in the world – the Global 2000 plus the biggest national government and academic research institutions – have always had the most complex data processing needs. …
Cerebras Shows Off Scale Up AI Performance For Big Pharma And Big Oil was written by Timothy Prickett Morgan at The Next Platform.
Industry Behemoths Back Intel’s Universal Chiplet Interconnect
When the hyperscalers, the major datacenter compute engine suppliers, and the three remaining foundries with advanced node manufacturing capabilities launch a standard together on Day One, this is an unusual, significant, and pleasant surprise. …
Industry Behemoths Back Intel’s Universal Chiplet Interconnect was written by Timothy Prickett Morgan at The Next Platform.
Groq Buys Maxeler For Its HPC And AI Dataflow Expertise
When it comes to application acceleration, having a deep understanding of the complex algorithms that underly most HPC and AI applications is perhaps the most important thing that can be brought to bear. …
Groq Buys Maxeler For Its HPC And AI Dataflow Expertise was written by Timothy Prickett Morgan at The Next Platform.
Aurora In A Socket: What Intel’s “Falcon Shores” XPU Might Do
We are still chewing through some of the announcements that came out of Intel Investor Day and the ISSCC 2022 chip conference, and one of the things we want to circle back on is the “Falcon Shores” hybrid CPU-GPU that Intel is working on for future servers. …
Aurora In A Socket: What Intel’s “Falcon Shores” XPU Might Do was written by Timothy Prickett Morgan at The Next Platform.
SysMoore: The Next 10 Years, The Next 1,000X In Performance
What is the most important product that comes out of the semiconductor industry? …
SysMoore: The Next 10 Years, The Next 1,000X In Performance was written by Timothy Prickett Morgan at The Next Platform.
HPE Taps Ayar Labs To Add Silicon Photonics To Slingshot Interconnect
There are so many barriers to capacity increases in high performance computing systems that it would take a long time to rattle them off. …
HPE Taps Ayar Labs To Add Silicon Photonics To Slingshot Interconnect was written by Timothy Prickett Morgan at The Next Platform.