When IBM’s Summit supercomputer was officially unveiled in June, some hailed it as the first exascale system because of its peak performance in applications that made heavy use of GPU acceleration at low precision. …
Now that deep learning at traditional supercomputing centers is becoming a more pervasive combination, the infrastructure challenges of making both AI and simulations run efficiently on the same hardware and software stacks are emerging. …
It is safe to say that a little more than a decade ago, when the clone of Google’s MapReduce and Google File System distributed storage and computing platform was cloned at Yahoo and offered up to the world as a way to transform the nature of data analytics at scale, that we all had much higher hopes for the emergence of platforms centered around Hadoop that would change enterprise, not just webscale, computing. …
Many programs have a tough time spanning across high levels of concurrency, but if they are cleverly coded, databases can make great use of massively parallel compute based in hardware to radically speed up the time it takes to run complex queries against large datasets. …
Perhaps the most important decision that any company will ever make is how they intend to structure and store the information they will preserve to encapsulate the goods and services they provide to their customers. …
By definition, HPC is always at the cutting edge of computing, driving innovations in processor, system, and software design that eventually find their way into more mainstream computing systems. …
The ProLiant server is still the workhorse for plowing datacenters and sowing money at Hewlett Packard Enterprise, much as it was for the datacenter division at Compaq nearly two decades ago. …
There is a certain level of impatience in the IT industry to create truly composable infrastructure from disaggregated compute, storage, and networking. …
Newisys has been on the NVM-Express for several years, putting the high-profile interface in a growing number of server and storage platforms, including servers with NVM-Express directly attacked to the CPU, a system running NVM-Express over Fabrics (NVMe-oF) and a storage expansion flash array (JBOF, or Just a Bunch of Flash). …
The massive amounts of data being generated in enterprise datacenters and out there on the public clouds and the need to quickly access and analyze that data is putting a strain on traditional storage and memory architectures that typically inhabit these environments. …
All Content Copyright 2017 The Next Platform
