Cloud Hosting

An explosion in cloud services is making chip design for the server market more challenging, more diverse, and much more competitive.

Unlike datacenter number crunching of the past, the cloud addresses a broad range of applications and data types. So while a server chip architecture may work well for one application, it may not be the optimal choice for another. And the more those tasks become segmented within a cloud operation, the greater that distinction becomes.

This has set off a scramble among chipmakers to position themselves to handle more applications using more configurations. Intel still rules the datacentera banner it wrestled awayfrom IBM with the introduction of commodity servers back in the 1990sbut increasingly the x86 architecture is being viewed as just one more option outside of its core number-crunching base. Cloud providers such as Amazon and Google already have started developing their own chip architectures. And ARM has been pushing for a slice of the server market based upon power efficient architectures.

ARMs push, in particular, is noteworthy because it is starting to gain traction in a number of vendors server plans. Microsoft said last month it would use ARM server chips in its Azure cloud business to cut costs. This seemed like dream just a couple years ago, but a lot of people are putting money into it big time right now, said Kam Kittrell, product management group director in the Digital & Signoff Group at Cadence. As time goes on, what well see is that is instead of just having a general-purpose server farm that runs at different frequencies but basically has a different chip in it (depending if its high performance or not), youre going to see a lot of different types of compute farms for the cloud.

Fig. 1: ARM-based server rack. Source: ARM

Whether ARM-based servers will succeed just because they use less power than an x86 chip for specific workloads isnt entirely clear. Unlike consumer devices, which typically run in cycles of a couple years, battles among server vendors tend to move in slow motionsometimes over a decade or more. But what is certain is that inside large datacenters, power expended for a given workload is a competitive metric. Powering and cooling thousands of server racks is expensive, and the ability to dial power up and down quickly and dynamically can save millions of dollars per year. Already, Google and Nvidia have publicly stated that a different architecture is required for machine learning and neural networking.

In looking at the power performance tradeoffs, and how to target the designs properly, there are two distinct things that cloud has accelerated in both the multicore and networking space. What is common between these chips is that they are pushing whatever the bleeding edge is of technology, such as 7nm, Kittrell said. Youve got to meet the performance, theres no question. But youve also got to take into account the dynamic power in the design. At 65nm we got used to power being dictated by leakage all the way through 28nm. At 28nm, which was the end of planar transistor, dynamic power became more dominant. So now youre having to study the workloads on these chips in order to understand the power. Even today, datacenters use 2% of the power in the United States, so they are a humongous consumer. And when it comes to power, its not just how much power the chip uses, its the HVAC in order to keep the datacenter cool. In essence, youve got to keep the dynamic power under target workloads under control, and the area has to be absolutely as small as possible. Once you start replicating these things, it can make a tremendous difference in the cost of the chip overall. The more switching nodes you put in there, the more power it consumes overall.

Slicing up the datacenter Changes have been quietly infiltrating datacenters for some time. While there are still racks of servers humming along in most major data centers, a closer look reveals that not all of them are the same. There are rack servers, networking servers, and storage servers, and even within those categories the choices are becoming more granular.

While there is still a need for enterprise data centers to have a general server/traditional server primarily based on Intel Xeon-core-based processors with a separate NIC card connecting to external networking where the switching and routing occur, we see in these large-scale cloud datacenters that they have a number of specific applications that they feel can be optimized for those applications within the cloud, within that data center, said Ron DiGiuseppe, senior strategic marketing manager in the Solutions Group at Synopsys.

As an example, DiGiuseppe pointed to Microsofts Project Olympus initiative under its Azure business, which defines a server that is targeting different applications such as web services. Microsoft is large scale they are estimating that 50% of their data center capacity is allocated to web server applications. And obviously, every cloud data center would be different. But they wanted to have servers that can be optimized for the web applications. They announced last month that they have five different configurations of servers targeting segment-optimized applications.

Another example would be database services, he said. This is very fast, and therefore low latency search and indexing for databases, such as for financial applications. With that in mind, the system architectures are being optimized for those applications, and the semiconductor suppliers are architecting their chips to have acceleration capabilities tied to the end applications. Therefore, you could optimize semiconductor adding features to support those different segmented applications.

That could include a 64-bit ARM processor-based server chip or an Intel Xeon-based server chip in a database services application, where the database access is accelerated by adding very close non-volatile storage using SSDs or NAND Flash SSDs through PCI Express, which connects directly to the processor using NVMB protocol. The goal is to minimize latency and to be able to store and access commands.

Seeing through the fog While equipping the datacenters is one trajectory, a second one is reducing the amount of data that floods into a datacenter. There is increasing interest to be able to use the network fabric to do at least some of the signal processing, data processing, and DSP processing to extract patterns and information from the data. So rather than pushing all of this data up through the pipe into the cloud, the better option is to refine that data so only a portion needs to be processed in the cloud servers.

This requires looking at the compute equation from a local perspective, and it opens up even more opportunities for chipmakers. Warren Kurisu, director of product management in the embedded division at Mentor, a Siemens Business, said current engagements are focused on working with companies that build solutions for local processing, local data intelligence, and local analytics so that the cloud datacenters are not flooded with reams of data that clog up the pipes.

One of the key areas of focus here involves intelligent gateways for everything from car manufacturing to breakfast cereal and pool chemicals. It requires multicore processors in the gateway that can enable a lot of the fog processing, a lot of data processing in the gateway, he said. And that adds yet another element, which is security.

Security is the number one question, so we have made a very huge focus on being able to create a gateway that leverages hardware security built-in to the chip and the board and establish a complete software chain of trust so that anything that gets run and loaded onto that gateway any piece of software is authenticated and validated through cryptologythrough certificates and other things, Kurisu said. But you need some processing power to do just that sort of stuff. There needs to be some sort of hardware security available. One of our key demonstration platforms is on the NXP I.MX6 processor, which has a high-assurance boot feature in it. The high-insurance boot basically has a key burned into the silicon, and we can leverage that key to be able to establish that chain of trust. If there isnt that hardware mechanism enabled in the system, then we can leverage things like secure elements that might be on the board that would all do the same thing. There would be some sort of crypto element there or a key used to establish the whole chain of trust. A change in thinking The key to success comes down to thinking about these chip designs very holistically, Kurisu added, because when it comes to cloud in the datacenter, and if you think about Microsoft Azure or Amazon Web services or any of the others, the types of capabilities that are available from the cloud datacenter down to the actual embedded device, these things need to work in tandem. If you have a robot controller, and you need to do a firmware updateand you want to initiate that from the cloudhow that gets enabled on the end device is tied very explicitly into how the operation is invoked from the cloud side. What is your cloud solution? Thats going to drive what the embedded solution is. Youve got to think of it as a system, and in that way the stuff that happens in the datacenter is very closely related to the things that might seem very disconnected on the edge. But how the IoT strategy is implemented is somewhat tied together so it all has to be considered together.

It also could have an impact on chip designs within this market, and open doors for some new players that have never even considered tapping into this market in the past.

View original post here:
Cloud Computing Chips Changing - SemiEngineering

Larry Ellison, founder of Oracle, summed up on the concept of cloud computing very succinctly. All it is, is a computer attached to a network. Ellison and Oracle have gone on to embrace both open source and cloud technologies including OpenStack, but the basic premise that it starts with a physical server and a network still holds true.

The server industry is going through massive change, driven in the main part by advances in open source software, networking and automation. The days of monolithic on-site server rooms filled with rack-space, and blinking lights and buzzing air-con, are gone. However, the alluring simplicity of this concept is not quite how it works in the real world.

Organisations who want to run a private cloud on premises or a hybrid with public cloud must first master bare metal servers and networking and this is causing a major transition in the datacentre.

Instead, large organisations are deploying hybrid clouds, running on multiple smaller servers distributed across far-flung sites around the globe. These are being deployed and managed, as demand dictates, by robots, rather than IT administrators.

There is minimal human interaction, as the whole whirligig turns on slick IT automation, designed and directed by an IT technician on a dashboard on a laptop in any physical location.

Suddenly, traditional IT infrastructure is less gargantuan, and less costly, if no less important. But servers remain a part of a bigger solution, residing in software. It is crucial CIOs also make use of their existing hardware to take full advantage of the opportunities the cloud offers, rather than just tearing it out, and ripping it up, and starting again.

It does not make sense to renew their infrastructure, at great expense; such squandering actions hinder progress, ultimately. New architectures and business models are emerging that will streamline the relationship between servers and software, and make cloud environments more affordable to deploy.

What do robots bring to the party?

The automation of data centres to do in minutes what a teams of IT administrators used to do in days does present a challenge to organisations.

Reducing human interaction could be linked to fear of job losses, but instead IT Directors and CIOs will find that they can redeploy the workforce to focus on higher value tasks, giving them more time back to interact with their infrastructures and enabling them to extract real value from their cloud architectures.

In addition, automation opens up the field to new and smaller players. Rather than requiring an organisation to spend a great deal of time and money on specialist IT consultancy, automation and modelling allows smaller organisations to take advantage of the opportunities offered by cloud, and offer their service more effectively.

For example, imagine you are a pharmaceutical company analysing medical trial data. Building a Hadoop big data cluster to analyse this data set could have previously taken ten working days. Through software modelling on bare metal, this workload can be reduced to minutes, allowing analysts to do what they need to do more quickly, finding the trends or results from a trial, and bringing new drugs to market faster.

Deployment and Expansion

The emergence of big data, big software, and the internet of things is changing how data centre operators design, deploy, and manage their servers and networks. Big software is a term we at Canonical have coined to describe a new era of cloud computing. Where applications were once primarily composed of a couple of components on a few machines, modern workloads like Cloud, Big Data & IoT are made up of multiple software components and integration points across thousands of physical and virtual machines.

The traditional practice of delivering scale on a limited number of very large machines is being replaced by a new methodology, where scale is achieved via the deployment of many servers across many environments.

This represents a major shift in how data centres are deployed today, and presents administrators with a more flexible way to drive value to cloud deployments, and also to reduce operational costs. A new era of software (web, Hadoop, Mongodb, ELK, NoSQL) is enabling them to make more of their existing hardware. Indeed, the tools available to CIOs for leveraging bare metal servers are frequently overlooked.

Beyond this, new software and faster networking is starting to allow IT departments to take advantage of new workload benefits from distributed, heterogeneous architectures. But we are at a tipping point, as much of the new server software and technology takes hold, and comes to light.

OpenStack has been established as a public cloud alternative for enterprises wishing to manage their IT operations as a cost-effective private or hybrid cloud environment. Containers have brought new efficiencies and functionality over traditional virtual machine (VM) models, and service modelling brings new flexibility and agility to both enterprises and service providers.

Meanwhile, existing hardware infrastructure can be leveraged to deliver application functionality more effectively. What happens from here, in the next three-to-five years, will determine how end-to-end solutions are architected for the next several decades.

Next Generation Solutions

Presently, each software application has different server demands and resource utilisation. Many IT organisations tend to over-build to compensate for peak-load, or else over-provision VMs to ensure enough capacity in the future. The next generation of hardware, using automated server provisioning, will ensure todays IT professionals dont have to perform capacity planning in five years time.

With the right provisioning tools, they can develop strategies for creating differently configured hardware and cloud archetypes to cover all classes of applications within their current environment and existing IT investments.

This way, it is possible for administrators to make the most of their hardware by having the ability to re-provision systems for the needs of the data centre for instance, a server being used for transcoding video 20-minutes ago is a Kubernetes worker node now, a Hadoop Mapreduce node later, and something else entirely after that.

These next generation solutions, affording a high degree of automation, bring new tools, efficiencies, and methods for deploying distributed systems in the cloud. The IT sector is in a transition period, between the traditional scale-up models of the past and the scale-out architecture of the future, where solutions are delivered on disparate clouds, servers, and environments simultaneously.

Mark Baker, OpenStack Product Manager, Canonical

Image Credit: Scanrail1 / Shutterstock

See original here:
How robots will retool the server industry - ITProPortal