The chip market is a house divided. On the smartphone and tablet front, virtually every device you use, manage, and love is powered by tiny system-on-a-chip (SoCs) designs, processors which present a fundamental leap in the old design paradigms of decades past. Meanwhile, servers and PCs, while offering terrific performance, are still holding on to dated design models.
Evolution in the mobile market has been defined by the rise of the IP core, licensed circuit designs. This flexible approach allows companies like Qualcomm to compete -- and win -- in the mobile space against veterans like Intel, which have vastly bigger research and development budgets. The key is teamwork and agility. With the IP core paradigm, licensers like MIPS Tech. (now owned by Imagination Technologies) or ARM Holdings release basic circuit designs, with all the fundamental logic blocks. This takes the basic design load off the implementer, who merely has to customize the chip with extras like I/O (think LTE modems, image processing, and so on).
By comparison, the server and workstation markets still follow a dinosaur of a chip design paradigm. Each OEM goes out and does the entire design process itself, producing monolithic chips. The approach is sort of the digital equivalent of Ayn Rand's objectivism -- in the sense that it is radically individualist.
But this age of radical individualism in the PC market is coming to a close.
IBM has been working closely with ARM since 2011 to develop a co-designed mobile SoC dubbed Cortex-M0, which will put nearly all the components of the smartphone -- RAM, wireless modems, CPU, GPU, power management circuitry, and possibly even the camera sensor, onto a single tightly wired CPU. While no official announcements have been made, it is a pretty safe bet that IBM will look to apply the lessons learned to its server chips.
AMD is following a single route. It's promoting a concept called "heterogeneous computing" and has also announced it will be offering ARM Opterons (64-bit) to the server market in 2014. It took me a while to wrap my brain around what exactly AMD means by
"heterogeneous" because the company is purposefully vague about the term.
But I believe it's not just buzz. Heterogeneous computing could arguably be defined as the practice of mixing co-designed GPU cores, larger CPU cores (think Power6, Ivy Bridge, or PileDriver), and smaller CPU cores (think smartphone ARM Cortex cores). Math-heavy loads will be shuffled to the GPU cores; lightweight virtualized loads can be shuffled to the small CPU cores; branched processing-intensive will be loaded onto the larger CPU cores.
To date, no one player has achieve this triple architecture. But it is coming, as each of these fundamental building blocks -- the graphics core (essentially, a parallel math coprocessor); the lightweight core; and the monolithic core -- each have a valuable and unique role.
Co-designed, customizable, mixed, triple-component core (CD-MTCC) chips will be perfectly suited for power savings and a highly virtualized datacenter. In the datacenter of the future, large hosting firms will be able to work with chipmakers to produce custom-fit cores. For example, there will likely be a subset of servers with more graphics core-heavy chips, capable of serving online gaming clients needs. There will be a subset of servers with lighter CPU core-heavy chips, which will support clients whose service is driven on lightweight transactions (e-commerce, for example). Finally, for web application clients, there will be larger CPU core-heavy chips. Each type of chip will have some of the other core kinds, to support the odd cases where more of the less typical kind of processing is needed.
Ultimately, this approach will kill the traditional monolithic core and conquer the server market. It will also likely necessitate a wholesale transition to RISC instruction sets, to support a modicum of code homogeneity between the three kinds of cores. I expect even Intel, which is already working to merge GPU IP cores with some of its chips, to adopt a similar MTCC SoC approach, even if it alone has the resources to buck the greater overarching co-design push.
RISC server SoCs will pop up in 2014. Expect the next arrival to be mature designs combining heterogeneous RISC CPU core sizes in the 2016 to 2020 timeframe. Users can simply sit back and enjoy the coming improvements, as this new hardware model should decrease costs and improve service. For those in the serving business and hardware front, however, a tough decade is coming up as the industry prepares to make this radical shift.
But the benefits will be great when the work is done.
— Jason Mick is senior news editor at the independent tech news site DailyTech.
One has to think at some point these heterogeneous chips will end up in the clouds. I keep thinking, can even graphics processing be done remotely and the results spooled out (over HDMI, or something) back to a wireless client. Heterogeneous design with everything tied together in a cloud, deciding where to put the app, or app service, sounds radically efficient. And I was calling for divergent rather than convergent paths for technology, oh, in 1993. We don't all have the same Swiss Army knife, and many of us host a silver service set in our home.
A few years ago a company called Ohio Scientific came up with a 'one size fits all' solution that incorporated three families of microprocessors on one board. The idea was that no matter what program you pulled in, you'd be able to run it on this versatile system board.
A bit of googling helped me find this description:
Model 510 CPU board (C3) (C) 1979 ------------------- 3 CPUs: 6502A, 6800, Z-80, ACIA, PIA, 3 1702A PROMS for 6502 (256x8), 1 1702A PROM for 6800 Address decoding for up to 1MB memory 6502 Proms at $FDxx, $FExx, $FFxx 6800 Prom at $FFxx Processor selection manual or connected to PIA PA6, PA7 (01 = Z80, 10=6800, 11=6502) PIA PA0-PA3 -> A16 -A19. PA4 ->ROM/RAM sel, PA5 ->Processor Switch Also configured as 2 CPU system board with 6502A & Z-80-4, 68B50, 6821, 6810 & 2716 DMon EPROM labeled OSI CP-1
I never had the opportunity to play with one; at the time I was fooling around with the Exidy Sorceror as well as an old PDP-8 that I got conned into buying. But that's another story.
Thanks for sharing this article, Jason. Very informative and good news in the right direction. I am looking for those days that we can buy any device and run any app we want and do not deal with different chips or incompatibility coming from them. It can be done, big players can easily come up with a plan and make it happen if they really want.
I'm wondering when (if ever) a time will come when quality hardware isn't proprietary. Why do I need my refrigerator to run a closed platform? Will there ever be a fully open graphing calculator? The chip design doesn't seem like the hard part nowadays... Will Dell ever sell PCs based on processors designed by the crowd?
True, but I think there is an industry-wide shift towards tighter integration/on-die component unification. Intel, as I recall, has said Haswell will be largely BGA. The days of being able to build and modify servers may be waning, although on a component scale you'll always be able to "upgrade" by adding new nodes.
However, server-wise the main shift will likely be more of a diversification of kinds of processors (e.g. lightweight cores for virtualization); there will still be a lot of pushback towards shifting solely to SoCs, as your comment alludes to.
The chief reason for mentioning the whole SoC trend is not to suggest that it will drive out traditional server chips directly; while it will likely catch on for certain server form factors (e.g. low-power servers), socket chips will likely continue to sell strong. However, the SoC work is important as the lessons-learned from a heterogeneous processor architecture perspective will likely be applied to socket chips in traditional servers, which still will be radically different from the homogeneous core-type chips that today are primarily used.
In that regard even the "traditional" socket chips will mirror, to some extent, the shift in processing that is occuring on the mobility side, moving from homogeneous computing units to heterogeneous "specialist" units.
IBM has been working closely with ARM since 2011 to develop a co-designed mobile SoC dubbed Cortex-M0, which will put nearly all the components of the smartphone -- RAM, wireless modems, CPU, GPU, power management circuitry, and possibly even the camera sensor, onto a single tightly wired CPU. While no official announcements have been made, it is a pretty safe bet that IBM will look to apply the lessons learned to its server chips.
The compromise is that you have to accept what is given, no or very little alteration will be allowed.
It does not sound to me like this is a "one sized fits all" proposition. In contrast, this is going to change the sever market. Instead of just being concerned about hardware specs, these triple architecture designs will allow servers to do exactly what they need to - no more, no less. That's more efficient than current designs, and will translate into cost effectiveness.
Plus, the server market is in need of some sort of upheaval. With cloud services dominating the headlines, something has to change in the bare metal.
The ThinkerNet does not reflect the views of TechWeb. The ThinkerNet is an informal means of communication to members and visitors of the Internet Evolution site. Individual authors are chosen by Internet Evolution to blog. Neither Internet Evolution nor TechWeb assume responsibility for comments, claims, or opinions made by authors and ThinkerNet bloggers. They are no substitute for your own research and should not be relied upon for trading or any other purpose.
The US National Security Agency learned the hard way that it can be dangerous to give a contractor too much money and access, with too little scrutiny. The NSA and other government agencies hire tens of thousands of contractors
a year to analyze data. Edward Snowden -- who revealed himself as the NSA leaker after fleeing the country -- was one such contractor, reportedly holding a $122,000 salaried position at Booz Allen Hamilton at the time of his departure.
Civil libertarians are outraged at the revelation the NSA is reportedly spying on more than one-third of Americans -- obtaining phone records from phone companies, in case it might need them for later use. Edward Snowden, the man who leaked details of that program, also revealed a second effort dubbed “Prism,” which represented a more aggressive grab of email and other communications. (See: Prism Exposes Unwritten Privacy Rules.)
While outsourcing can initially appear to deliver massive cost savings, some firms are starting to wake up to its hidden costs -- shipping, production latency, and quality control. But perhaps the biggest hidden cost of outsourcing is intellectual property (IP) theft.
The version of Windows 8.1 that Microsoft previewed this week is a step in the right direction, but it shows that Microsoft is still missing the boat in some ways.
Whether you’re an engineering firm that uses CAD for parts design, or an e-business that leverages Photoshop for user-interface graphics, you likely require a modest graphics-processing unit. In the old days, this was a daunting hurdle to innovation, but today, the situation has improved thanks to technologies like NVIDIA’s GRID and Microsoft’s RemoteFX. Such virtualized graphics protocols allow you to load-balance graphics-intensive workloads from virtual desktops on a server-side graphics card.
Cisco's rumored sale of Linksys suggests we may have problem with innovation and profit at the edge of our Internet, and that could be critical to the evolution of many Internet-delivered services.
A survey by JD Powers found that customer interest in product features is lessening as phones evolve. Rather than features, price is driving purchases, and that change could have a dramatic impact on how IT departments secure these devices.
The bring-your-own-device approach isn’t suited to monitoring of enterprise equipment and processes. In these cases, it is up to IT to come forward with gear suited to the task.
The very low-tech "scrum" project technique introduces "crowd talking" to projects and also sets the entire crowd to problem solving. So far, these new social-media-style meetings appear to have supercharged project execution.
Videoconferencing systems now are quite static. Users set up a camera, and it stays focused on the target regardless of whether or not the user moves during the presentation. NTT is developing a system that moves with the speaker, providing a feel similar to a face-to-face conversation.
With 24/7 processing and business continuation paramount, more organizations are considering having three datacenters, where primary and secondary datacenters are in their immediate region and a third is in a remote geography. Why? To avoid repercussions of a major disaster that could hit every IT resource in a specific region.
Big-data and analytics tools enable marketers to understand customers as individuals, identifying unmet needs and addressing each customer as a "segment of one," says John Kennedy, VP corporate marketing, IBM.
New York's Metropolitan Transit Authority is conducting a pilot test of digital kiosks to guide subway users to where they want to go more efficiently and at lower cost.
The whole Amazon.reader debate is a double-stupid. It's stupid to think that there's any e-book buyer who doesn't know Amazon's URL, and it was stupider to let ICANN launch the whole free-form TLD initiative to start with.
While NFC's original goal was to enhance mobile commerce applications, it is finding its way into a number of other uses, which is creating both opportunity as well as challenges for IT departments.
Enterprises would like to move to cloud computing but are hesitant because they are concerned about providers’ ability to secure company data. Here are some tips that help to ensure that if breaches occur, the business is not left holding the bag.
Edmunds separates customers into segments based on the info it collects on its site and from partners, and uses that to push out custom content, said Brian Baron, director of business analytics for Edmunds.com, at Predictive Analytics Innovation Summit.
The IBM Smarter Commerce Global Summit in Monaco kicked into high gear today, and we've already begun to see news emerging from that lovely city-state by the sea.
Expert Integrated Systems: Changing the Experience & Economics of IT In this e-book, we take an in-depth look at these expert integrated systems -- what they are, how they work, and how they have the potential to help CIOs achieve dramatic savings while restoring IT's role as business innovator. READ THIS eBOOK
your weekly update of news, analysis, and
opinion from Internet Evolution - FREE! REGISTER HERE
Wanted! Site Moderators Internet Evolution is looking for a handful of readers to help moderate the message boards on our site – as well as engaging in high-IQ conversation with the industry mavens on our thinkerNet blogosphere. The job comes with various perks, bags of kudos, and GIANT bragging rights. Interested?
To save this item to your list of favorite Internet Evolution content so you can find it later in your Profile page, click the "Save It" button next to the item.
Email This
