Sign up for our Technology Newsletter 
AMD’s Richland Shows Up
Kaveri is coming in a few months, but before it ships AMD will apparently spice up the Richland line-up with a few low-power parts.
CPU World has come across an interesting listing, which points to two new 45W chips, the A8-6500T and the A10-6700T. Both are quads with 4MB of cache. The A8-6500T is clocked at 2.1GHz and can hit 3.1GHz on Turbo, while the A10-6700T’s base clock is 2.5GHz and it maxes out at 3500MHz.
The prices are $108 and $155 for the A8 and A10 respectively, which doesn’t sound too bad although they are still significantly pricier than regular FM2 parts.
AMD’s Kaveri Coming In Q4
AMD really needs to make up its mind and figure out how it interprets its own roadmaps. A few weeks ago the company said desktop Kaveri parts should hit the channel in mid-February 2014. The original plan called for a launch in late 2013, but AMD insists the chip was not delayed.
Now though, it told Computerbase.de that the first desktop chips will indeed appear in late 2013 rather than 2014, while mobile chips will be showcased at CES 2014 and they will launch in late Q1 or early Q2 2014.
As we reported earlier, the first FM2+ boards are already showing up on the market, but at this point it’s hard to say when Kaveri desktop APUs will actually be available. The most logical explanation is that they will be announced sometime in Q4, with retail availability coming some two months later.
Kaveri is a much bigger deal than Richland, which was basically Trinity done right. Kaveri is based on new Steamroller cores, it packs GCN graphics and it’s a 28nm part. It is expected to deliver a significant IPC boost over Piledriver-based chips, but we don’t have any exact numbers to report.
ARM & Oracel Optimize Java
ARM’s upcoming ARMv8 architecture will form the basis for several processors that will end up in servers. Now the firm has announced that it will work with Oracle to optimise Java SE for the architecture to squeeze out as much performance as possible.
ARM’s chip licensees are looking to the 64-bit ARMv8 architecture to make a splash in the low-power server market and go up against Intel’s Atom processors. However unlike Intel that can make use of software already optimised for x86, ARM and its vendors need to work with software firms to ensure that the new architecture will be supported at launch.
Oracle’s Java is a vital piece of software that is used by enterprise firms to run back-end systems, so poor performance from the Java virtual machine could be a serious problem for ARM and its licensees. To prevent that, ARM said it will work with Oracle to improve performance, boot-up performance and power efficiency, and optimize libraries.
Henrik Stahl, VP of Java Product Management at Oracle said, “The long-standing relationship between ARM and Oracle has enabled our mutual technologies to be deployed across a broad spectrum of products and applications.
“By working closely with ARM to enhance the JVM, adding support for 64-bit ARM technology and optimizing other aspects of the Java SE product for the ARM architecture, enterprise and embedded customers can reap the benefits of high-performance, energy-efficient platforms based on ARM technology.”
A number of ARM vendors including x86 stalwart AMD are expected to bring out 64-bit ARMv8 processors in 2014, though it is thought that Applied Micro will be the first to market with an ARMv8 processor chip later this year.
Will Qualcomm Be First?
We could not get the right timeframe for the launch of Qualcomm’s successor to the high-end Snapdragon 800, but there is no doubt that Qualcomm, Samsung, Nvidia and other ARM supporters are thinking about 20nm products where some of them will be based on Cortex A57.
Qualcomm has its own Krait core that can be adapted to 20nm and follow up the success of Snapdragon 600 and the soon to come Snapdragon 800. It turns out that it traditionally takes 18 to 24 months for the mobile industry to shift from one process to another and Qualcomm had its first 28nm part in April 2012, with the Snapdragon S4, used in the HTC One S. The first ever 28nm part from Qualcomm was the Snapdragon S4 MSM8260A that is now more than a year old and a relatively obsolete product.
Less than a year after the first 28nm product Qualcomm followed up with the Snapdragon 600 that is shipping in millions of high end devices right now. In a month or two it plans to release Snapdragon 800 based on new Krait 400 core and add a new core and get even better performance.
The next step is the 20nm core that should start shipping before the end of 1H 2014. We would not be surprised to see 20nm Krait demoed at CES 2014 already in January, see more of it at the Mobile World Congress in February and the volume shipment to follow in early Q2 2014. This is the expected schedule and not something we got from Qualcomm.
The only official world we got is that the new generation traditionally comes 18 to 24 months after the first iteration of a current one. This can give you an idea that Tegra 5, codenamed Logan, should show up at a similar time, along with Samsung’s 20nm Exynos.
AMC Goes To The Clouds
Applied Micro Circuits has released its cloud chip which takes networking and computing and crams it all onto one SoC.
The X-Gene server on a chip, is being billed as the first 64-bit-capable ARM-based server in existence. According to the company it is the first chip to contain a software-defined network (SDN) controller on the die that will offer network services such as load balancing and ensuring service-level agreements on the chip.
Paramesh Gopi, president and CEO of Applied Micro, said that these new chips have now made it past the prototype stage and are being used by Dell and Red Hat. Gopi expects physical servers containing the X-Gene to hit the market by the end of this year.
The chip is manufactured at 40 nanometers and has eight 2.4 GHz ARM cores, four smaller ARM Cortex A5 cores running the SDN controller software, four 10-gigabit ethernet ports, and various ports that can support more Ethernet, SSDs, accelerator cards such as those from Fusion-io or SATA drives.
The cost of ownership, which includes power requirements are about half of that of a comparable x86 product, but wouldn’t discuss actual power consumption, the company claims.
TSMC Testing ARM’s Cortex A57
ARM and TSMC have manufactured the first Cortex A57 processor based on ARM’s next-gen 64-bit ARMv8 architecture.
The all new chip was fabricated on TSMC’s equally new FinFET 16nm process. The 57 is ARM’s fastest chip to date and it will go after high end tablets, and eventually it will find its place in some PCs and servers as well.
Furthermore the A57 can be coupled with frugal Cortex A53 cores in a big.LITTLE configuration. This should allow it to deliver relatively low power consumption, which is a must for tablets and smartphones. However, bear in mind that A15 cores are only now showing up in consumer products, so it might be a while before we see any devices based on the A57.
In terms of performance, ARM claims the A57 can deliver a “full laptop experience,” even when used in a smartphone connected to a screen, keyboard and mouse wirelessly. It is said to be more power efficient than the A15 and browser performance should be doubled on the A57.
It is still unclear when we’ll get to see the first A57 devices, but it seems highly unlikely that any of them will show up this year. Our best bet is mid-2014, and we are incorrigible optimists. The next big step in ARM evolution will be 20nm A15 cores with next-generation graphics, and they sound pretty exciting as well.
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.
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.
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.
ARM Goes High-End
Nvidia is itself an ARM chip licensee that has seen significant design wins with its Tegra 3 system-on-chip (SoC) processor, however the firm doesn’t see ARM based servers being able to do heavy lifting in server tasks for two years. Sumit Gupta, GM of Nvidia’s Tesla Accelerated Computing business unit said that even with GPGPUs, ARM based servers are not yet able to provide the computing power needed to drive high performance servers.
Gupta said, “Performance of these ARM cores is still not where it needs to be for servers. It is getting there; the new ARM64 [processor] is going to get it part of the way.” However he did say that eventually ARM SoCs could hit X86-like performance levels. “One day I think ARM will at least get to similar performance levels as X86 performance. The belief is that over the next one or two years these ARM SoCs will be good enough for cloud applications and web serving. I think it will take some more time to be good enough for accelerated computing.”
As for Nvidia using its Tegra chips to push work to the firm’s GPGPUs, a scenario that would make the firm’s accountants very happy, Gupta said he was surprised at the level of interest from developers and questioned the need for powerful CPUs. “We did a small development kit called Karma that has a Tegra 3 and a Nvidia GPU, [and] I was shocked by the number of those kits that have been sold. The interest in this ARM plus GPU is far larger than even I expected. If the GPU can do dynamic parallelism, it becomes more independent than how powerful CPUs do you need? I believe the first thing that will happen is that people will start using lower performing [Intel] Xeons […] then at some point when these Atom based processors become available they might use that, and when ARM64 is available they’ll use that.”