I’m writing this on the plane from Narita airport to Portland as I return from giving the plenary talk at the Solid State Devices and Materials conference (SSDM), in Sendai Japan. It is always exciting to visit these device conferences to see the myriad of new options that are being discussed for next generation transistors.
Before I get into the technical details, I have a few fun stories to share about my trip. I arrived a little early, so I could have the weekend to tour Tokyo. Much of my time in Tokyo was spent figuring out the subway/train system. In all the excitement, I managed to lose my wallet on the subway, and to my surprise and delight - it was returned a few hours later (with all the money intact). I was deeply impressed as I doubt that would happen in New York! Another adventure was with a Japanese toilet at Tokyo institute of technology. Japanese toilets are quite complicated (among other things, they play music) with a number of interesting features (which I will not describe here, you’ll need to go to Japan to check). This was one of the more complicated ones, and in looking for the flush button, I pushed a green button that looked reasonable. Well, it was an alarm button. A horn sounded, the lights turned on and off and so on and so on. Made me deeply suspicious of all buttons for the rest of the trip. At this point, I hoped my adventures were over, but no. I had a most interesting night on the 12th floor of the hotel when the typhoon Melor passed over (as a side note, I began to feel jinxed, because I ran into Melor a second time when in California a few days later after it had crossed the Pacific).
Anyway, enough of the light stuff, now let’s discuss the meat! SSDM is a big conference (~1000 people) where the various conference sessions include papers ranging from energy systems to organic semiconductors. Of the most interest to me were the sessions focusing on the various approaches for continued gate scaling through improved short channel control.
High-k metal gate is the primary path for improved short channel control. Intel leads the pack in this area, with its recent 32nm announcement demonstrating successful second-generation high-k metal gate (http://www.intel.com/technology/architecture-silicon/32nm/index.htm). Note that much of the industry is trying to “catch up” to Intel, with significant discussion industry-wide on the correct architecture for the gate (gate-first or replacement, one metal or two, and so on) with representative SSDM papers such as those presented by Drs. Ikeda, Kim and Fukutome. There is also significant research on gate materials, shown with papers such as those from Drs. Kadoshima and Inumiya. Another area of strong research is fundamental physics of the HiK-metal gate materials system, with SSDM papers such as those by Drs. Hsieh and Shimizu.
Advanced device architectures are another path for improved short channel control. This include ultra thin body (UTB) devices, vertical thin body devices (for example, trigate and Finfet), and lateral nanowire devices. UTB devices are the simplest of the new architectures, with short channel control offered by a thin body, and with fabrication being an extension of historical processing. An additional advantage of UTB devices is excellent random variation due to the undoped depleted body (several interesting SSDM papers in this area, including the papers of Drs. Andrieu and Lee). The problem is that UTB devices are expensive (SOI is NOT cheap), and quite sensitive to variation in the body thickness (changes in body thickness affect VT from quantum effects, and also impact DIBL and SS)). In addition, the thin body creates high external resistance and makes it extremely difficult to strain the devices.
Multiple gate (MuGFET) devices such as FinFETs or Trigates are a longer term path for improved short channel control. These devices mitigate many of the variation issues with UTB devices (because the desired fin width is greater than 2X of the equivalent body thickness in an UTB device.) HOWEVER, the non-planarity of these devices represents significant challenges in fabrication. Dr. Veloso’s paper nicely explored many of these challenges in some detail. Lateral nanowire devices are next in the logical sequence, again offering significant advantages for short channel control, but at the cost of challenging fabrication. While nanowires offer further short channel benefit, they have all the issues of FinFETs, along with a host of new issues, many of which were explored in papers from Drs. Chen, Seike, Lee and others.
I had a lot of fun, and learned some new things. As a wonderful closure for the trip, as we were leaving Narita airport (after pushback and just as the plane started to taxi on its own) all the line service folks (the people who fuel the plane etc.) lined up and waved and then bowed the plane off. “What a wonderful custom,” I thought, as I waved back.
Fantastic first day and night in San Francisco for the 2009 Web 2.0 Summit. Intel sponsored last night’s reception in the courtyard at the Westin, right before Carly Fiorina almost declared that she was running for the California Senate. John Battelle tried to coax the answer out of her to no avail.
Day 2 promises to hold some interesting technology topics on tomorrow’s web.
First up: Nokia on Social Location - Nokia OVI is a new platform based on GPS utilizing social location apps, currently shipping w/ many of its devices and mobile phones.
Nokia talked about how the ways of connecting people have changed. Users are increasingly connecting to different services, cloud objects, etc. in addition to the traditional direct dials/texts to individuals. Massive growth in Social Networking is a common prediction, now measured as the 4th most popular online activity. Mobile users will continue to demand more SNS (Social Networking Services), yet with Mobile, a entirely new usage model will need to evolve to satisfy unique mobile needs. The mobile and location-aware client is expanding the current SNS landscape.
The oft quoted “Mobile is the next big thing” is true. However, the current SNS services will need to evolve to meet new mobile usage models, or fail to other future SNS that take better advantage of a mobile user base. Nokia is on the right path by opening up their API to a developer community, taking advantage of new location data in new apps.
My biggest question is w/ GPS itself. How can a 1970’s technology and 1.0 approach to connection serve us in the 2.0 and increasing 3.0 World? For one, indoors is potentially the biggest problem. Another is the focal point. It’s all about the (dumb) client. In other words, it is the “I’m here” technology, just like the 1970’s was the “Me” decade. Meaning these mobile devices only have “receive-only” location capabilities via broadcasted GPS positioning data.
When will location devices become 2.0? 2.0 devices that are able to share their location in a mesh architecture. I.e. my netbook communicating w/ my mobile device, with my keys and my car going 70mph in an urban canyon? And more importantly, the car next to me so I don’t crash!
Nokia’s looking at the Indoor problem w/ a-GPS and Wi-Fi mapping of nodes for location data. As are many other device and component manufacturers, that’s all fine and good. It’s the 2.0 lens that I’m craving. I want to know if my Facebook friends or Twitter followers are sitting behind me in this conference room. Or, if anyone on my plane is heading to the same hotel so we can share a cab. When will my devices know where they are in relation to each other? That’s when LBS and social location will really take off.
For now, Ovi by Nokia will be an interesting service to watch for Location Based Services.
Today, a small team of engineers will be recognized at the Computer History Museum for designing the world’s first programmable microprocessor in 1971, a 4-bit parallel CPU with 2,300 transistors. That project, from a fledgling integrated memory manufacturer barely 3 years old, was a significant achievement that one can honestly say changed the world.
The Intel 4004 was the first general purpose microprocessor that could be customized with software to perform different functions on different devices. The rest, as they say, is history. The 4004 spawned a new era in both hardware AND software, along with an unrelentless quest for silicon integration that continues to this day. That is why the team of Federigo Faggin, Ted Hoff, Stanley Mazor, and Masatoshi Shima are being recognized tonight at the Computer History Museum.
As Intel heralds its “rock star” engineers through the popular Sponsors of Tommorrow campaign, it’s worth noting that these guys were the original rock stars who defined innovation and integration nearly 40 years ago. Even the 4004 itself grew into something of a star over the years. There are multiple pages dedicated to it, including intel4004.com which focuses on Faggin’s role, an interesting digital archeology project done a few years ago with the Intel museum, fun facts, wiki pages, and more. It remains one of the hottest of semiconductor collectibles and can fetch hundreds of dollars on eBay. As part of the company’s 35th Anniversary, Intel even made the original schematics and mask designs available for non-commercial use. So as we fast forward into an era of hundreds of millions even billions of transistors on a single chip and more and more functionality being integrated directly on to the CPU, it’s worth taking a look back. To pause and say thank you to the original rock stars of the semiconductor world. Congratulations guys, you spawned an entire industry or two in the process of figuring out how to make a single chip do the task of many. For a calculator no less. Who knew?
I rarely write about topics with such vigour, but this latest video from a so-called documentary team is absolute and utter rubbish. There is no evidence whatsoever that the Intel Xeon 5500 processor can create the kind of data centre disruption witnessed in the documentary. In the spirit of openness, here is the video I am referring to:
Here is the text that accompanied the video:
**
Intel takes great pride in its new ‘Nehalem’ based Xeon Processors. They tout the fact that because of their incredible performance and power efficiency, the ROI benefit effectively makes them ‘Cash Machines’ for IT. See: http://www.tgdaily.com/content/view/44213/135/
But the truth is far darker, someone has to hold them accountable.
PBS-TV’s MotorWeek visited Intel headquarters recently. Steven Chupnick wanted to learn how the tiny, mighty Intel Atom processor can help automakers stay in step with consumer trends. He met with Staci Palmer, director of Intel’s In-Vehicle Infotainment, Embedded and Communications Group, who talked about how computer technology can connect autos to the Internet to bring information, entertainment and even maintenance services anywhere the auto goes.
Here’s a collection of photos that I used to create a quick video and photo slideshow of Steve shooting around the Intel Headquarters.
When Intel launched “Nehalem-EP,” more commonly known as the Intel Xeon 5500 Series processors back in March, we pointed out that their energy-efficient performance and other attributes lead to a very quick return on investment - as soon as eight months. Pat Gelsinger and Kirk Skaugen even referred to the new servers as literally becoming “Cash Machines for IT.”
To celebrate the launch of our new family of Intel® Core™ i7 and Core™ i5 processors, Intel is challenging the world’s best mod enthusiasts to rock the world in the Intel® Core™ i7 Custom Desktop Challenge.
Submissions need to be recieved by November 16, 2009 (11:59 p.m. PDT). Winners will be selected on or about December 14, 2009 and announced on or about December 14, 2009.
The world of mobile entertainment along with always-on Internet is exploding, as consumers and road warriors demand greater connected experiences on the go. Mobile Internet Devices (MIDs) and smartphones are paving the way with advanced and highly efficient audio, video, camera and imaging usages, along with premium content delivery. Driving this effort, is the Intel® Atom™ processor-the world’s smallest processor. And the next-generation is coming to us in 45nm high-k system-on-a-chip (SoC) process technology, codenamed Moorestown.
At this year’s Intel Developer Forum in San Francisco, Intel Fellow and Chief Platform Architect for the Ultra Mobility Group, Shreekant (Ticky) Thakkar discussed the various usage models surrounding this exceptional, low-power processor that is effectively creating a big computer experience in a small and pocketable device. In volume, MIDs, handheld productivity devices, portable media players, game consoles, navigation devices, along with high-end smartphones will see an influx in the growing mobile landscape as Moorestown enables immersive experiences, such as:
Live video streaming
Video chat and video conferencing
Quality picture and video clip captures along with editing capabilities
Instant upload of pictures, video clips, blogs, and more to the Internet
Mobile TV and video services
Streaming audio
Voice memo recording
3G, WiFi, and WiMAX options for always-on, always connected (AOAC)
Moorestown SoC process technology offers hardware accelerated HD video playback, allowing users to render video on local or external displays. Moorestown also offers support for key codecs and file containers, enabling DRM protected video playback and media frameworks with hardware acceleration. And with a strong MIDs ecosystem in place supporting Moorestown, users will encounter compelling, connected experiences with additional enabling software including Linux, Real, Adobe, Eyecon, Move Networks, Inc., Discretix, and LiveCast.
For more on Ticky Thakkar’s presentation at IDF, download the presentation (PDF 1.75MB). Moorestown_IDF.pdf
Revolutionizing the ultra-mobile segment of Mobile Internet Devices (MIDs) and the future of smart phones, Intel’s next-generation Intel® Atom™ processor, codenamed Moorestown, made a larger-than-life splash at this year’s Intel Developer Forum (IDF) in San Francisco.
Intel Fellow and Chief Platform Architect for the Ultra Mobility Group, Shreekant (Ticky) Thakkar showcased the technology’s highlights including:
Extended battery life, running the full Internet with ultra-low power designs
Access to the full Internet
Always-on connectivity
Supporting a host of mobile devices, Intel’s Moorestown offers 3G, WiFi, and WiMAX options-100% compatibility at the application level with Linux for PC-exceptional media performance-while enabling smartphone form factors. And Moorestown reduced its board size at least 2x from previous generation Menlow, while decreasing its standby power up to 50%. With an idle power similar to current smartphone levels, this generation is offering serious computing power in the palm of your hand.
Based on 45nm high-k SoC process technology, Moorestown incorporates Intel® Hyper-Threading Technology (Intel® HT Technology) for high performance along with OpenGL ES 2.0 and OpenVG 1.0 graphics, making it an incredibly robust platform for mobile devices. Moorestown also offers Intel® Burst Performance Technology (Intel® BPT) for additional performance, taking advantage of thermal headroom and reduced system frequency, while saving consumed CPU and platform energy.
For more on Ticky Thakkar’s presentation at IDF, download the presentation (PDF 1.75MB) Moorestown_IDF.pdf
Intel Senior Fellow Stephen Pawlowski delivered a session at this week’s Intel Developer Forum (IDF) on Intel’s latest industry-standard, mission-critical platform codenamed Nehalem-EX. And one of the key topics of discussion? Intel® Virtualization Technology (Intel® VT).
Nehalem-EX offers scalability along with world-record virtualization performance, enabling the highest consolidation ratios of any industry-standard server. And as IT departments across the board move to lower costs while increasing hardware utilization, Intel has responded to their needs by improving and enhancing its hardware-based virtualization technology.
With Nehalem-EX, Intel has created a feature that enables data packets to come in and be tagged to the appropriate virtual machine (VM). The hardware then places those packets into hardware queues that are focused on a particular Virtual Machine Manager (VMM). Once packets arrive, they are delivered to the appropriate VM in packet order and are re-packetized and put in the appropriate VM queue before they get sent to the virtual machine. It’s Intel’s hardware that is making virtualization software perform even better.
Including broad industry support for an era that is increasingly moving towards the cloud, virtualization technology combined with energy-efficient performance and RAS-rich environments provide a reliable, scalable environment that IT departments can bank on.
del.icio.us