Sign up for our Technology Newsletter 
TSMC And Imagination Team Up
TSMC and Imagination Technologies announced the next step in their tech collaboration in an effort to develop Imagination’s next generation PowerVR 6-series GPUs.
The new GPUs are still not ready for prime time, but they should be used in future SoC designs, including those stamped out using TSMC’s 16nm FinFET process. The two companies will work to create new reference system designs, utilizing high bandwidth memory standards and TSMC’s 3D IC technology.
As GPU muscle becomes more important for next generation SoCs, designers need more advanced and more complex processes, such as TSMC’s 16FinFET.
“Through advanced projects initiated under this partnership, Imagination and TSMC are working together to showcase how SoCs will transform the future of mobile and embedded products,” said Hossein Yassaie, CEO of Imagination.
TSMC VP Cliff Hou argued that the need for high performance mobile GPUs will drive silicon processes in the future, much in the same way CPU development pushed new processes in the nineties.
Are CUDA Applications Limited?
Acceleware said at Nvidia’s GPU Technology Conference (GTC) today that most algorithms that run on GPGPUs are bound by GPU memory size.
Acceleware is partly funded by Nvidia to provide developer training for CUDA to help sell the language to those that are used to traditional C and C++ programming. The firm said that most CUDA algorithms are now limited by GPU local memory size rather than GPU computational performance.
Both AMD and Nvidia provide general purpose GPU (GPGPU) accelerator parts that provide significantly faster computational processing than traditional CPUs, however they have only between 6GB and 8GB of local memory that constrains the size of the dataset the GPU can process. While developers can push more data from system main memory, the latency cost negates the raw performance benefit of the GPU.
Kelly Goss, training program manager at Acceleware, said that “most algorithms are memory bound rather than GPU bound” and “maximising memory usage is key” to optimising GPGPU performance.
She further said that developers need to understand and take advantage of the memory hierarchy of Nvidia’s Kepler GPU and look at ways of reducing the number of memory accesses for every line of GPU computing.
The point Goss was making is that GPU computing is relatively cheap in terms of clock cycles relative to the time it takes to fetch data from local memory, let alone loading GPU memory from system main memory.
Goss, talking to a room full of developers, proceeded to outline some of the performance characteristics of the memory hierarchy in Nvidia’s Kepler GPU architecture, showing the level of detail that CUDA programmers need to pay attention to if they want to extract the full performance potential from Nvidia’s GPGPU computing architecture.
Given Goss’s observation that algorithms running on Nvidia’s GPGPUs are often constrained by local memory size rather than by the GPU itself, the firm might want to look at simplifying the tiers of memory involved and increasing the amount of GPU local memory so that CUDA software developers can process larger datasets.
Will Tegra 4 Help nVidia’s Financials?
Comments Off on Will Tegra 4 Help nVidia’s Financials?
Trefis analysts believe Nvidia’s Tegra business is likely to grow over the next few years, although Nvidia won’t become a mobile chip company anytime soon.
In a note published a couple of days ago, Trefis concluded that Nvidia has managed to offset the impact of the PC slump thanks to mobile revenue. The PC market took a massive hit in 2012, and although things are looking up, Tegra could still come in handy.
Nvidia currently earns about 18 percent of its revenue from Tegra processors, which is not bad for a product that was on the drawing board just a few years ago.
“We estimate Tegra sales to grow at a CAGR of 17% until 2016. While we believe that Nvidia will manage to expand its footprint in mobile computing, we think that the increasing competition will keep its growth rate lower than the industry average,” said Trefis.
However, Trefis went on to conclude that Nvidia had more lack with tablets than smartphones. Last year it scored several big tablet design wins, but relatively few phone wins. The Tegra 4i, with integrated LTE, should lend a helping hand, but it won’t be ready for much of 2013. In addition, Nvidia is facing more pressure from Qualcomm and Samsung, while at the same time it was forced to push back the introduction of Tegra 4 due to technical issues.
Trefis believes Tegra’s contribution to Nvidia’s overall revenue could reach over 25 percent by 2019, which means the Tegra business won’t expand much in a mature smartphone market.
Nvidia has Tegra, AMD has consoles, so both outfits have something to fall back on in a slow PC market, at least for the time being.
Samsung Goes Star-ups
Samsung will put $1.1 billion towards venture capital funding of semiconductor firms.
The company said that it will commit the research and development funding through its Samsung Venture Americas branch and Catalyst Fund investment operations, according to multiple reports.
The investment is set to target semiconductor design and manufacturing. The company will look to fund startups that can assist its hardware units and will open a new R&D facility in Silicon Valley.
The announcement comes as Samsung is seeing its revenues hit record levels. The company reported quarterly profits of 7.5 billion to close out 2012 and sales from Samsung’s handset unit reached record levels.
Analysts believe that the company now controls nearly 23 percent of the smartphone market. The jump in hardware sales has brought with it a healthy appetite for components. Earlier this month Samsung passed Apple to become the world’s largest single user of semiconductor chips.
Samsung has recently stepped up its investment activities, with the firm buying storage vendor Nvelo and last week buying a small stake in Wacom, best known for its touchpad and stylus input technology. With the firm looking to invest in startups, it is perhaps looking to follow in Apple’s footsteps, which kickstarted its chip design efforts by buying PA Semiconductor and later Intrinsity, and invested in Imagination Technologies.
TSMC 20nm Processors In High Demand
TSMC believes demand for next-generation 20nm chips will be even higher than demand for current 28nm products.
Speaking in a conference call, TSMC CEO Morris Chang said the volume of 20nm SoCs built next year will be greater than 28nm volume in 2012 and by 2015 it should be greater than 28nm volume in 2013.
TSMC hopes to start 20nm production in the latter part of the year. The company is constructing two new facilities at Fab 15 and it hopes to start 20nm production in both simultaneously. We could be in for a quick ramp.
TSMC will offer only one version of the 20nm process, compared to four versions of the 28nm process. This should also allow it to ramp up volume production faster, reckons Xbit Labs.
Will Tegra 4 Launch In Q2?
Tegra 4 was supposed to be production ready in Q4 2012 and the general expectation was that CES 2013 would be marked by the launch of phones and tablets based on the new chipset.
It turns out that the chip needed another re-spin, something that usually creates a delay of roughly a quarter. We don’t know which part of the chip was to blame but our sources claim that Tegra 4 is a complex chip with a lot of components where many things can go wrong.
Nvidia dared to move to 28nm, change the core from A9 to A15 and find a way to make its LTE work. There were a lot of things that could go wrong and obviously some did.
This is why Intel first shrinks the core, for example from 32nm to 22nm, and then in its “tock” cycle goes for a newly designed core. Nvidia doesn’t have that luxury, as making a 28nm version of Tegra 3 would not be enough for the SoC market in 2013.
A few people at Nvidia have been telling us that the chip has been sampled to accounts and Nvidia is planning to have some designs announced at the Mobile World Congress. We managed to confirm this schedule with some Nvidia partners.
Will Tegra 4 Support USB 3.0?
Wayne, also known as Tegra 4 is coming out at CES 2013, or in some 10 days from now. Nvidia has an event planned days ahead of CES 2013 and the company will likely show some tablets and hybrids based on the new Tegra SoC. Let’s call Wayne Tegra 4 before it gets official.
Nvidia had Wayne ready to launch in Q4 2012 but it had to wait for partners to release the designs based on it, and most of them wanted to do it at CES 2013. European phones based on Wayne are going to show up in February, at the Mobile World Congress.
This is the first quad-core A15 design that will bring a significant performance increase over Tegra 3 and we are hearing that the four-plus-one core will deliver a bigger performance boost than Tegra 3 did over Tegra 2. Also, the fact that the new chip is 28nm and supports DDR3L also promises more efficiency.
USB 3.0 support is something that is getting us excited as usually it is quite slow to transfer anything onto tablets, phones and hybrids. USB 3.0 on tablets will significantly increase the data transfer speed and Tegra 4 will be among the first chips to feature USB 3.0 support, and many consumers will appreciate faster data transfer rates.
The other thing that got our attention is dual display support and you will be able to have two independent screens. On Tegra 3 based devices, you can only mirror the output, not display two independent screens. It could be a very interesting feature for dockable devices.
nVidia’s Tegra 4 Specs Spotted
Here is an interesting leak, just what the doctor ordered to spice up a rather slow news cycle. Chiphell has posted a slide containing a few Tegra 4 specs, but we still don’t know the clocks or a few other interesting details. Of course, the leak should be taken with a grain of salt, but the specs are more or less in line with what we were expecting all along.
Tegra 4, codenamed Wayne, is a 28nm part with revamped graphics and new ARM cores. Although the slide does not directly point to the type of ARM cores used in the design, the new chip is based on ARM’s latest A15 core. Like the Tegra 3, the new chip will also feature an additional companion core to improve energy efficiency. No surprises here really.
In terms of GPU performance, Nvidia promises to deliver a six-fold improvement over the Tegra 3 and a 20x improvement over Tegra 2 chips. Oddly enough, in spite of Nvidia’s graphics prowess, Tegra chips never featured world-beating graphics. This time around they could, thanks to the new 72-core GPU. The GPU will be able to cope with 2560×1600 screens at 120Hz, but it could also take on 4K resolutions, although details are still sketchy. At this point 4K support could only be relevant for next-generation smart TVs, with a huge price tag.
As far as other features go, Tegra 4 brings support for USB 3.0 and DDR3L dual-channel memory. The leak does not mention LTE support.
Tegra 4 will have to take on the likes of Samsung’s upcoming Exynos 5440, which should also debut in early 2013. Nvidia was first to market with a quad-core A9 chip, but this time around it will have to face off against the new Exynos and A15 quad-cores from other vendors.
Nvidia is expected to showcase the new chip at CES and we’ll be there to check it out.
Raspberry Pi Gets A Store
Raspberry Pi Foundation has opened a store to enable users to easily download applications that run on the credit-card sized computer.
The Raspberry Pi Foundation said it partnered with Indiecity and Velocix to create a store for applications that run on the Raspberry Pi computer. The Foundation said that the store itself is an application that runs under its Raspbian Linux distribution and at launch has 23 applications available for download.
The Raspberry Pi Store contains games such as Freeciv alongside applications such as Libreoffice and Asterisk. The Raspberry Pi Foundation said its store accepts compiled binaries, Python code, images, audio and video.
The Raspberry Pi Store will allow developers to charge for applications, with the Foundation saying that it hopes to see a mix of hobbyist and commercial software. The Foundation also asked users that download applications to review them in order to improve the results put out by its recommendations system.
While the Raspberry Pi was initially intended to help teach people how to program, the device has gained wider popularity due to the fact that its hardware can run many typical PC desktop applications. The Foundation’s Raspberry Pi Store will make it easier for users to find and install applications on the device, which can only be a good thing for the Raspberry Pi Foundation and Linux adoption.
TSMC To Boost 28nm Production
TSMC is able to make chips using 28nm process technology at a speedier pace that it originally anticipated. This means that the chipmaker will likely be able to meet demand for existing orders and start accepting new designs.
TSMC promised to increase its 28nm capacity to 68 thousand 300mm wafers per month by the end of the year. It did this by ramping up fab 15/phase 2 to 50,000 300mm wafers a month. According to the Taiwan Economic News it looks like the outfit managed to beat its own projections, which should be good news for customers like AMD, Nvidia and Qualcomm. Well not AMD of course. It just told Globalfoundries to stop making so many of its chips so it can save a bit of money.
But it looks like TSMC is flat out. In November the fab 15/phase 2 processed 52,000 wafers. When combined with fab 15/phase 1, TSMC should be able to process 75 – 80, 000 300mm wafers using 28nm process technologies this month. TSMC produces the majority of 28nm chips at fab 15, which will have capacity of more than 100,000 300mm wafers per month when fully operational.