Andy Patrizio
Author Archives: Andy Patrizio
- Home → Author's archive:
Andy Patrizio
0
Nvidia jumps into Zero Trust
Nvidia has announced a Zero Trust platform built around its BlueField data-processing units and Nvidia software.Zero Trust is an architecture that verifies every user and device that tries to access the network and enforces strict access control and identity management that limits authorized users to accessing only those resources they need to do their jobs.[Get regularly scheduled insights by signing up for Network World newsletters.] “You cannot just rely on the firewall on the outside, you have to assume that any application or any user inside your data center is a bad actor,” said Manuvir Das, head of enterprise computing at Nvidia. “Zero Trust basically just refers to the fact that you can't trust any application or user because there are bad actors.”To read this article in full, please click here
0
Nvidia jumps into Zero Trust
Nvidia has announced a Zero Trust platform built around its BlueField data-processing units and Nvidia software.Zero Trust is an architecture that verifies every user and device that tries to access the network and enforces strict access control and identity management that limits authorized users to accessing only those resources they need to do their jobs.[Get regularly scheduled insights by signing up for Network World newsletters.] “You cannot just rely on the firewall on the outside, you have to assume that any application or any user inside your data center is a bad actor,” said Manuvir Das, head of enterprise computing at Nvidia. “Zero Trust basically just refers to the fact that you can't trust any application or user because there are bad actors.”To read this article in full, please click here
0
AMD launches big data-center push vs. Intel, Nvidia
AMD has emerged from its long defensive crouch to taking the fight directly to Intel and Nvidia, a bold move but one backed by a company that's been racking up wins lately.Coming on the heels of a record-setting quarter, AMD announced new EPYC server CPUs, a new line of Instinct brand GPUs it says are faster in than Nvidia’s best, the next generation of its CPU architecture, and a deal with Meta, formerly known as Facebook.[Get regularly scheduled insights by signing up for Network World newsletters.] EPYC Milan-X CPU AMD CEO Lisa Su introduced the EPYC Milan-X processors, an iteration of its third-generation server processors with a 3D-stacked L3 cache called 3D V-Cache. One problem with increasing cache is you get transistor sprawl and the die gets progressively bigger. 3D stacking reduces the physical size while increasing density.To read this article in full, please click here
0
AMD launches big data-center push vs. Intel, Nvidia
AMD has emerged from its long defensive crouch to taking the fight directly to Intel and Nvidia, a bold move but one backed by a company that's been racking up wins lately.Coming on the heels of a record-setting quarter, AMD announced new EPYC server CPUs, a new line of Instinct brand GPUs it says are faster in than Nvidia’s best, the next generation of its CPU architecture, and a deal with Meta, formerly known as Facebook.[Get regularly scheduled insights by signing up for Network World newsletters.] EPYC Milan-X CPU AMD CEO Lisa Su introduced the EPYC Milan-X processors, an iteration of its third-generation server processors with a 3D-stacked L3 cache called 3D V-Cache. One problem with increasing cache is you get transistor sprawl and the die gets progressively bigger. 3D stacking reduces the physical size while increasing density.To read this article in full, please click here
0
ITRenew integrates Pluribus Networks software with its hyperscale servers
ITRenew, the reseller of slightly used hyperscalar servers, has partnered with Pluribus Networks to add Pluribus’s Netvisor ONE operating system and Adaptive Cloud Fabric controllerless SDN cloud networking software to its hardware.ITRenew resells servers it buys from hyperscalers like Amazon and Google that are retiring them, typically after a year or so. It refurbishes them, offers a warrantee, and sells them to enterprises for half the price of new hardware.ITRenew sells the servers under the Sesame brand, which will now include Pluribus’s open networking software with their hyperscale-grade compute, storage and networking infrastructure for a fully integrated hardware and software solution.To read this article in full, please click here
0
ITRenew integrates Pluribus Networks software with its hyperscale servers
ITRenew, the reseller of slightly used hyperscalar servers, has partnered with Pluribus Networks to add Pluribus’s Netvisor ONE operating system and Adaptive Cloud Fabric controllerless SDN cloud networking software to its hardware.ITRenew resells servers it buys from hyperscalers like Amazon and Google that are retiring them, typically after a year or so. It refurbishes them, offers a warrantee, and sells them to enterprises for half the price of new hardware.ITRenew sells the servers under the Sesame brand, which will now include Pluribus’s open networking software with their hyperscale-grade compute, storage and networking infrastructure for a fully integrated hardware and software solution.To read this article in full, please click here
0
Rockport Networks debuts the “switchless” network
A startup called Rockport Networks has exited stealth mode with an intriguing product: a switchless network. It claims the Rockport Switchless Network product can move data faster and with better latency than switched networks.In a Rockport Switchless Network, switching functionality has been reassigned to intelligent endpoint network cards where these devices (nodes) become the network. Each device has an FPGA and can connect up to 24 endpoints to a dedicated 1U SHFL (pronounced “shuffle”) optical device using passive cabling.[Get regularly scheduled insights by signing up for Network World newsletters.] SHFLs need no power or cooling and can be linked together to scale out the network. Ethernet and InfiniBand traffic can be carried over the Rockport network. The network cards are standard, low-profile half height, half length (HHHL) PCIe cards.To read this article in full, please click here
0
Rockport Networks debuts the “switchless” network
A startup called Rockport Networks has exited stealth mode with an intriguing product: a switchless network. It claims the Rockport Switchless Network product can move data faster and with better latency than switched networks.In a Rockport Switchless Network, switching functionality has been reassigned to intelligent endpoint network cards where these devices (nodes) become the network. Each device has an FPGA and can connect up to 24 endpoints to a dedicated 1U SHFL (pronounced “shuffle”) optical device using passive cabling.[Get regularly scheduled insights by signing up for Network World newsletters.] SHFLs need no power or cooling and can be linked together to scale out the network. Ethernet and InfiniBand traffic can be carried over the Rockport network. The network cards are standard, low-profile half height, half length (HHHL) PCIe cards.To read this article in full, please click here
0
NetApp overhauls cloud storage lineup
NetApp used its virtual NetApp Insight 2021 conference as the launchpad for several new technologies and enhancements to existing products, as well as to announce an acquisition. All are meant to bolster the on-prem storage supplier’s cloud offerings.First up, NetApp introduced ONTAP 9.10 Enterprise Data Management software, which includes upgrades that protect against ransomware and enhanced detection and recovery capabilities. The new software also features expanded data management capabilities and NVMe/TCP support.NVMe traditionally works over a network fabric, but there are bottlenecks – namely, you have to build the fabric. NVMe/TCP allows the same storage devices to be shared among data centers through the Internet protocol over the existing network.To read this article in full, please click here
0
Startup gives IT control of GPU pools to maximize their use
Among the greatest component shortages bedeviling everyone is that of GPUs, both from Nvidia and AMD. GPUs are used in Bitcoin farming, and with massive farms around the world gobbling up every GPU card, getting one is nigh impossible or prohibitively expense.So customers need to squeeze every last cycle out of the GPUs they have in service. An Israeli company called Run:AI claims it has a fix with a pair of technologies that pool GPU resources and maximize their use.The technologies are called Thin GPU Provisioning and Job Swapping. Not the most creative of names but they describe what the two do in tandem to automate the allocation and utilization of GPUs.To read this article in full, please click here
0
Startup gives IT control of GPU pools to maximize their use
Among the greatest component shortages bedeviling everyone is that of GPUs, both from Nvidia and AMD. GPUs are used in Bitcoin farming, and with massive farms around the world gobbling up every GPU card, getting one is nigh impossible or prohibitively expense.So customers need to squeeze every last cycle out of the GPUs they have in service. An Israeli company called Run:AI claims it has a fix with a pair of technologies that pool GPU resources and maximize their use.The technologies are called Thin GPU Provisioning and Job Swapping. Not the most creative of names but they describe what the two do in tandem to automate the allocation and utilization of GPUs.To read this article in full, please click here
0
Graphcore beefs up data center AI offerings
Graphcore, the British semiconductor company that develops accelerators for AI and machine learning, has greatly increased the performance of its massively parallel Intelligence Processing Unit (IPU) servers.Graphcore sells its AI-oriented chips in rack-mounted designs called IPU-PODs. Up until now, the maximum per cabinet has been 64 units (in the IPU-POD64). The newest racks are twice and four times as large: the IPU-POD128 and IPU-POD256. Read more: 10 of the world's fastest supercomputersTo read this article in full, please click here
0
Graphcore beefs up data center AI offerings
Graphcore, the British semiconductor company that develops accelerators for AI and machine learning, has greatly increased the performance of its massively parallel Intelligence Processing Unit (IPU) servers.Graphcore sells its AI-oriented chips in rack-mounted designs called IPU-PODs. Up until now, the maximum per cabinet has been 64 units (in the IPU-POD64). The newest racks are twice and four times as large: the IPU-POD128 and IPU-POD256. Read more: 10 of the world's fastest supercomputersTo read this article in full, please click here
0
Arm creates virtual IoT chips to accelerate development
It can take years for a CPU to go from design to silicon, so Arm is helping developers get a jump on things by putting virtual models of its chip designs in the cloud. The virtual models will allow developers to write and test applications before the actual silicon ships.Dubbed Arm Total Solutions for IoT, the project is a full-stack solution intended for Internet of Things applications and use cases. Arm says the early access for developers, OEMs and service providers, as well as the reduction in product design cycles, could accelerate deployments by up to two years.Arm doesn’t make chips the way Intel and AMD do. It makes designs and licenses them to more than 800 OEMs, which are responsible for everything from embedded devices to servers. Once Arm releases the basic chip design to its partners, the partners then add their own IP to differentiate from the competition, which takes time.To read this article in full, please click here
0
Intel’s 2nd-gen neuromorphic chip is 10x smarter than the first
Four years after Intel first introduced Loihi, the company’s first neuromorphic chip, the company has released its second generation processor, which Intel says will provide faster processing, greater resource density, and improved power efficiency.CPUs are often called the brains of the computer but aren’t, really, since they process only a handful of tasks at once in a serial manner, nothing like what the brain does automatically to keep you alive. Neuromorphic computing attempts to replicate the functions of the brain by performing numerous tasks simultaneously, with emphasis on perception and decision makingChip shortage will hit hardware buyers for months to years Neuromorphic chips mimic neurological functions through computational “neurons” that communicate with one another. The first generation of Loihi chips had around 128,000 of those digital neurons; the Loihi 2 has more than a million.To read this article in full, please click here
0
Intel’s second-generation neuromorphic chip is 10x smarter than the first
Four years after Intel first introduced Loihi, the company’s first neuromorphic chip, the company has released its second generation processor, which Intel says will provide faster processing, greater resource density, and improved power efficiency.CPUs are often called the brains of the computer but aren’t, really, since they process only a handful of tasks at once in a serial manner, nothing like what the brain does automatically to keep you alive. Neuromorphic computing attempts to replicate the functions of the brain by performing numerous tasks simultaneously, with emphasis on perception and decision makingChip shortage will hit hardware buyers for months to years Neuromorphic chips mimic neurological functions through computational “neurons” that communicate with one another. The first generation of Loihi chips had around 128,000 of those digital neurons; the Loihi 2 has more than a million.To read this article in full, please click here
0
A dive into Kyndryl, IBM’s managed-services spin-off
Thanks to a US Securities and Exchange Commission filing new details have emerged about Kyndryl, the IBM spin-off of its managed-infrastructure services unit into a separately traded public company.Kyndryl does exactly what the managed-infrastructure services unit of IBM’s Global Technology Services segment does: manage enterprises IT infrastructure, whether it comes from IBM or another vendor. That’s a challenge for Kyndryl because it has to deal with the trend toward cloud services and against on-premises infrastructure.The split is expected to be complete by the end of 2021, and when it was announced last year, IBM CEO Arvind Krishna said IBM will focus on open hybrid-cloud and AI capabilities while Kyndryl would focus on modernizing customer infrastructure.To read this article in full, please click here
0
Marvell announces some very smart SmartNIC processors
Marvell has begun to sample the Octeon 10, a server microprocessor aimed at intelligent network management that has up to 24 Arm-compatible cores, making it as powerful as any server processor.Marvell refers to the Octeon processor line as data processing units (DPUs). They are designed to run high-throughput data in the cloud and on-premises. The DPU is more commonly called the SmartNIC because it can offload non-computational tasks from the CPU like network packet processing, data encryption and compression. That frees up CPU cores to run general-purpose applications.The Octeon 10 has a few firsts. It's the first processor made by TSMCs 5nm manufacturing process and the first processor to feature Arm’s Neoverse N2 core. The N2 core uses the new Armv9 architecture that the company claims can deliver 40% more single-threaded performance for a variety of workloads vs. the N1, but still retains the same level of power and area efficiency as N1.To read this article in full, please click here
0
The Dell/VMware relationship remains strong despite split
VMware is in the process of spinning out from Dell Technologies, but the working relationship remains as strong as ever with a bunch of announcements from VMworld.All told, the pair made four significant announcements at the show, the first being that VMware Cloud will be sold on systems acquired through Dell's Apex pay-as-you-go program. The new Apex offering gives customers the ability to move workloads across multiple cloud environments and scale resources quickly with predictable pricing and costs.The new offering combines Dell’s hyperconverged infrastructure VxRail with VMware Cloud, VMware Tanzu for building cloud-native applications, and VMware HCX for application migration. Businesses can deploy the offering in their data center, at an edge location or a colocation facility with partners like Equinix.To read this article in full, please click here
0
The Dell/VMware relationship remains strong despite split
VMware is in the process of spinning out from Dell Technologies, but the working relationship remains as strong as ever with a bunch of announcements from VMworld.All told, the pair made four significant announcements at the show, the first being that VMware Cloud will be sold on systems acquired through Dell's Apex pay-as-you-go program. The new Apex offering gives customers the ability to move workloads across multiple cloud environments and scale resources quickly with predictable pricing and costs.The new offering combines Dell’s hyperconverged infrastructure VxRail with VMware Cloud, VMware Tanzu for building cloud-native applications, and VMware HCX for application migration. Businesses can deploy the offering in their data center, at an edge location or a colocation facility with partners like Equinix.To read this article in full, please click here