Andy Patrizio
Author Archives: Andy Patrizio
- Home → Author's archive:
Andy Patrizio
0
Marvell revs up Ethernet to 400Gbps with new ‘Alaska’ chips
Marvell Semiconductor is the first semiconductor to ship networking chips supporting the 802.3cd standard that will pump up Ethernet ports to 400Gbps max.The 802.3cd standard is designed to eventually replace the current physical Ethernet ports, which run at 25Gbps to 100Gpbs, with ports that will run at 50Gbps, 200Gbps, and 400Gbps.And Marvell is the first chip vendor out of the gate with support for the standard in its Alaska C 88X7120 transceivers. The chips aren’t fully cooked, but they are sampling to customers. Sampling is to semiconductors what beta testing is to software.To read this article in full, please click here
0
Marvell revs up Ethernet to 400Gbps with new ‘Alaska’ chips
Marvell Semiconductor is the first semiconductor to ship networking chips supporting the 802.3cd standard that will pump up Ethernet ports to 400Gbps max.The 802.3cd standard is designed to eventually replace the current physical Ethernet ports, which run at 25Gbps to 100Gpbs, with ports that will run at 50Gbps, 200Gbps, and 400Gbps.And Marvell is the first chip vendor out of the gate with support for the standard in its Alaska C 88X7120 transceivers. The chips aren’t fully cooked, but they are sampling to customers. Sampling is to semiconductors what beta testing is to software.To read this article in full, please click here
0
Why a bare-metal cloud provider might be just what you need
Cloud services, particularly infrastructure- and platform-as-a-service, are well established, but in some cases customers demand more – more control, more access to hardware, more performance, and the ability to pick their own operating environment.In those cases they are looking to bare-metal servcies, a niche that is growing fast.As the name implies, bare metal means no software just CPUs, memory, and storage. Customers provide all of the software from the operating system on up. That means a dedicated CPU, full access to the hardware, and freedom to run custom operating systems.According to a 2016 Markets and Markets report, the bare metal cloud market is expected to grow from $871.8 million in 2016 to $4.7 billion in 2021, at an estimated compound annual growth rate of 40.1%.To read this article in full, please click here
0
Why a bare-metal cloud provider might be just what you need
Cloud services, particularly infrastructure- and platform-as-a-service, are well established, but in some cases customers demand more – more control, more access to hardware, more performance, and the ability to pick their own operating environment.In those cases they are looking to bare-metal servcies, a niche that is growing fast.As the name implies, bare metal means no software just CPUs, memory, and storage. Customers provide all of the software from the operating system on up. That means a dedicated CPU, full access to the hardware, and freedom to run custom operating systems.According to a 2016 Markets and Markets report, the bare metal cloud market is expected to grow from $871.8 million in 2016 to $4.7 billion in 2021, at an estimated compound annual growth rate of 40.1%.To read this article in full, please click here
0
Why a bare-metal cloud provider might be just what you need
Cloud services, particularly infrastructure- and platform-as-a-service, are well established, but in some cases customers demand more — more control, more access to hardware, more performance, and the ability to pick their own operating environment.In those cases, they are looking to bare-metal services, a niche that is growing quickly.As the name implies, bare metal means no software, just CPUs, memory, and storage. Customers provide all of the software from the operating system on up. That means a dedicated CPU, full access to the hardware, and freedom to run custom operating systems.According to a 2016 Markets and Markets report, the bare-metal cloud market is expected to grow from $871.8 million in 2016 to $4.7 billion in 2021, at an estimated compound annual growth rate of 40.1 percent.To read this article in full, please click here
0
New Spectre derivative bug haunts Intel processors
Intel just can’t catch a break these days. Researchers at Ohio State University have found a way to use the Spectre design flaw to break into the SGX secure environment of an Intel CPU to steal information.SGX stands for Software Guard eXtensions. It was first introduced in 2014 and is a mechanism that allows applications to put a ring around sections of memory that blocks other programs, the operating system, or even a hypervisor from accessing it.To read this article in full, please click here
0
New Spectre derivative bug haunts Intel processors
Intel just can’t catch a break these days. Researchers at Ohio State University have found a way to use the Spectre design flaw to break into the SGX secure environment of an Intel CPU to steal information.SGX stands for Software Guard eXtensions. It was first introduced in 2014 and is a mechanism that allows applications to put a ring around sections of memory that blocks other programs, the operating system, or even a hypervisor from accessing it.To read this article in full, please click here
0
EdgeMicro announces 30-city edge-network deployment
There is quite a rush on to build out edge computing networks, that vital link between the massive amount of Internet of Things (IoT) devices and data centers. One of the companies involved is newcomer EdgeMicro, which announced plans to deploy micro-data centers in 30 cities around the U.S. for an unnamed cellular partner.EdgeMicro said “a leading North American mobile network operator” has begun verification tests of its technology. It did not name the operator, but if it’s a national operator covering 30 major cities, there are only four obvious candidates — Verizon Wireless, AT&T, Sprint, or T-Mobile.To read this article in full, please click here
0
EdgeMicro announces 30-city edge-network deployment
There is quite a rush on to build out edge computing networks, that vital link between the massive amount of Internet of Things (IoT) devices and data centers. One of the companies involved is newcomer EdgeMicro, which announced plans to deploy micro-data centers in 30 cities around the U.S. for an unnamed cellular partner.EdgeMicro said “a leading North American mobile network operator” has begun verification tests of its technology. It did not name the operator, but if it’s a national operator covering 30 major cities, there are only four obvious candidates — Verizon Wireless, AT&T, Sprint, or T-Mobile.To read this article in full, please click here
0
Startup ZincFive makes old battery technology new again
A startup called ZincFive is set to launch a modular uninterruptible power supply (UPS) for data center computers using the venerable nickel-zinc technology, which it claims is more efficient than lithium-ion.Nickel-zinc batteries were invented by Thomas Edison in 1901 but fell out of favor to newer designs due to their limitations, such as a low number of charge cycles and their inability to hold a charge for long.On the plus side, the batteries could hold a stronger charge and didn’t use toxic metals like other batteries that make them difficult to recycle. And they are not flammable, something lithium-ion batteries certainly can’t claim.To read this article in full, please click here
0
Startup ZincFive makes old battery technology new again
A startup called ZincFive is set to launch a modular uninterruptible power supply (UPS) for data center computers using the venerable nickel-zinc technology, which it claims is more efficient than lithium-ion.Nickel-zinc batteries were invented by Thomas Edison in 1901 but fell out of favor to newer designs due to their limitations, such as a low number of charge cycles and their inability to hold a charge for long.On the plus side, the batteries could hold a stronger charge and didn’t use toxic metals like other batteries that make them difficult to recycle. And they are not flammable, something lithium-ion batteries certainly can’t claim.To read this article in full, please click here
0
Memcached servers can be hijacked for massive DDoS attacks
A flaw in the implementation of the UDP protocol for Memcached servers can allow anyone to launch a massive Distributed Denial of Service (DDoS) attack with little effort.The problem was first discovered by security researchers at content delivery network (CDN) specialist Cloudflare. Since then, CDN specialist Akamai and security provider Arbor Networks have also published their findings.Also read: Getting the most out of your next-generation firewall Memcached is a Web-based massive memory cache for database-drive sites, such as websites, that caches the most frequently retrieved data and keeps it in memory rather than getting it from the hard disk over and over again. It is a combination of open-source software and standard server hardware that consists of memory, memory, and more memory.To read this article in full, please click here
0
Memcached servers can be hijacked for massive DDoS attacks
A flaw in the implementation of the UDP protocol for Memcached servers can allow anyone to launch a massive Distributed Denial of Service (DDoS) attack with little effort.The problem was first discovered by security researchers at content delivery network (CDN) specialist Cloudflare. Since then, CDN specialist Akamai and security provider Arbor Networks have also published their findings.Also read: Getting the most out of your next-generation firewall Memcached is a Web-based massive memory cache for database-drive sites, such as websites, that caches the most frequently retrieved data and keeps it in memory rather than getting it from the hard disk over and over again. It is a combination of open-source software and standard server hardware that consists of memory, memory, and more memory.To read this article in full, please click here
0
Startup Concertio offers AI-optimized server configuration
For about as long as there has been personal computers, there has been an aftermarket of system optimization software. Even MS-DOS, which was about as basic as an operating system gets, had QEMM to get the most out of your 640K of memory. These days, there is a healthy market of Windows optimization utilities to speed up your PC.For servers, though, it gets a little more complicated. Actually, it gets very complicated. Not only does each server have to operate at peak efficiency on its own, but it then has to interact with the network, with other servers, and potentially with a public cloud service provider.Also on Network World: What will AI mean to the traditional data center? And usage models change over time. There might be peak use times when certain processes are not run, such as backups, and slow times of day when other tasks can be run. So an optimal configuration at one point in the day is not optimal at a different time of the day.To read this article in full, please click here
0
Startup Concertio offers AI-optimized server configuration
For about as long as there has been personal computers, there has been an aftermarket of system optimization software. Even MS-DOS, which was about as basic as an operating system gets, had QEMM to get the most out of your 640K of memory. These days, there is a healthy market of Windows optimization utilities to speed up your PC.For servers, though, it gets a little more complicated. Actually, it gets very complicated. Not only does each server have to operate at peak efficiency on its own, but it then has to interact with the network, with other servers, and potentially with a public cloud service provider.Also on Network World: What will AI mean to the traditional data center? And usage models change over time. There might be peak use times when certain processes are not run, such as backups, and slow times of day when other tasks can be run. So an optimal configuration at one point in the day is not optimal at a different time of the day.To read this article in full, please click here
0
Lenovo introduces new water-cooled server technology
Lenovo has introduced a new high-density server “tray” for high-performance computing (HPC) environments with the newest generation of water cooling technology it co-developed with a German HPC firm.Unlike your typical water-cooled system, where the water is chilled almost to a drinkable state, the ThinkSystem SD650 high-density server tray — so called because of its design and shape — is designed to operate using warm water, up to 50°C, or 122°F.Read also: Data center cooling market set to explode in the coming years There is a mindset that CPUs have to be chilled as though they were cold cuts, when Intel says they can handle much higher temperatures. Xeons can handle temps of up to 75°C without becoming unstable or crashing.To read this article in full, please click here
0
Lenovo introduces new water-cooled server technology
Lenovo has introduced a new high-density server “tray” for high-performance computing (HPC) environments with the newest generation of water cooling technology it co-developed with a German HPC firm.Unlike your typical water-cooled system, where the water is chilled almost to a drinkable state, the ThinkSystem SD650 high-density server tray — so called because of its design and shape — is designed to operate using warm water, up to 50°C, or 122°F.Read also: Data center cooling market set to explode in the coming years There is a mindset that CPUs have to be chilled as though they were cold cuts, when Intel says they can handle much higher temperatures. Xeons can handle temps of up to 75°C without becoming unstable or crashing.To read this article in full, please click here
0
Micron sets its sights on quad-cell storage
Micron is the latest NAND flash memory maker to announce plans for quadruple-level cell (QLC) flash memory, following similar announcements from Toshiba and Western Digital. It's a very technical story with a very real impact.NAND flash memory stores data in one bit per cell, with billions of cells in the flash memory chips. For flash drives to gain capacity, there are two solutions: increase the number of chips in the drive, which has physical limitations, and increase the density per cell, which is limited by the laws of physics.Also read: Impact of Intel and Micron ending their NAND partnership is negligible | Sign up: Receive daily tech news updates The first single-level cell, with one bit per cell, first emerged in the late 1980s when flash drives first appeared for mainframes. In the late 1990s came multi-level cell (MLC) drives capable of storing two bits per cell. Triple-level cell (TLC) didn't come out until 2013 when Samsung introduced its 840 series of SSDs. So, these advances take a long time, although they are being sped up by a massive increase in R&D dollars in recent years.To read this article in full, please click here
0
Juniper Networks expands multi-cloud connectivity portfolio
Juniper Networks has announced an expanded portfolio of products for companies to become “multi-cloud ready,” unifying both the public cloud and on-premises computing resources.The new offerings don’t just connect the data center to the cloud; they also cover campus and branch offices, the latter of which can often be overlooked or forgotten due to being remote.Also on Network World: Cloud strategy: hybrid and multi cloud are not the same Companies are moving more workloads to the cloud to keep up for a variety of reasons, but a recent study from consulting giant PwC and commissioned by Juniper found that while a majority of enterprise workloads are going to move to the cloud in the next three years, the workload on premises will not diminish. If anything, it will need to keep up with the cloud.To read this article in full, please click here
0
Juniper Networks expands multi-cloud connectivity portfolio
Juniper Networks has announced an expanded portfolio of products for companies to become “multi-cloud ready,” unifying both the public cloud and on-premises computing resources.The new offerings don’t just connect the data center to the cloud; they also cover campus and branch offices, the latter of which can often be overlooked or forgotten due to being remote.Also on Network World: Cloud strategy: hybrid and multi cloud are not the same Companies are moving more workloads to the cloud to keep up for a variety of reasons, but a recent study from consulting giant PwC and commissioned by Juniper found that while a majority of enterprise workloads are going to move to the cloud in the next three years, the workload on premises will not diminish. If anything, it will need to keep up with the cloud.To read this article in full, please click here