Sign up for our Technology Newsletter 
Can MediaTek Take On Qualcomm?
While Qualcomm’s 20nm Snapdragon 810 SoC might be the star of upcoming flagship smartphones, it appears that MediaTek has its own horse for the race, the octa-core MT6795.
Spotted by GforGames site, in a GeekBench test results and running inside an unknown smartphone, MediaTek’s MT6795 managed to score 886 points in the single-core test and 4536 points in the multi-core test. These results were enough to put it neck to neck with the mighty Qualcomm Snapdragon 810 SoC tested in the LG G Flex 2, which scored 1144 points in the single-core and 4345 in the multi-core test. While it did outrun the MT6795 in the single-core test, the multi-core test was clearly not kind on the Snapdragon 810.
The unknown device was running on Android Lollipop OS and packed 3GB of RAM, which might gave the MT6795 an edge over the LG G Flex 2.
MediaTek’s octa-core MT6795 was announced last year and while we are yet to see some of the first design wins, recent rumors suggested that it could be powering Meizu’s MX5, HTC’s Desire A55 and some other high-end smartphones. The MediaTek MT6795 is a 64-bit octa-core SoC clocked at up to 2.2GHz, with four Cortex-A57 cores and four Cortex-A53 cores. It packs PowerVR G6200 graphics, supports LPDDR3 memory and can handle 2K displays at up to 120Hz.
As we are just a few days from Mobile World Congress (MWC) 2015 which will kick off in Barcelona on March 2nd, we are quite sure that we will see more info as well as more benchmarks as a single benchmark running on an unknown smartphone might not be the best representation of performance, it does show that MediaTek certainly has a good chip and can compete with Qualcomm and Samsung.
Intel Gives Exascale A Boost
Intel’s exascale computing efforts have received a boost with the extension of the company’s research collaboration with the Barcelona Supercomputing Center.
Begun in 2011 and now extended to September 2017, the Intel-BSC work is currently looking at scalability issues with parallel applications.
Karl Solchenbach, Intel’s director, Innovation Pathfinding Architecture Group in Europe said it was important to improve scalability of threaded applications on many core nodes through the OmpSs programming model.
The collaboration has developed a methodology to measure these effects separately. “An automatic tool not only provides a detailed analysis of performance inhibitors, but also it allows a projection to a higher number of nodes,” says Solchenbach.
BSC has been making HPC tools and given Intel an instrumentation package (Extrae), a performance data browser (Paraver), and a simulator (Dimemas) to play with.
Charlie Wuischpard, VP & GM High Performance Computing at Intel said that the Barcelona work is pretty big scale for Chipzilla.
“A major part of what we’re proposing going forward is work on many core architecture. Our roadmap is to continue to add more and more cores all the time.”
“Our Knights Landing product that is coming out will have 60 or more cores running at a slightly slower clock speed but give you vastly better performance,” he said.
AMD’s Carrizo Coming In The Second Quarter
Comments Off on AMD’s Carrizo Coming In The Second Quarter
AMD released its earnings today and one cool question came up about the upcoming Carrizo mobile APU.
Lisa SU, the new AMD President and CEO, told MKM Partners analyst Ian Ing that Carrizo is coming in Q2 2015.
This is a great news and AMD’s Senior VP and outgoing general manager of computing and graphics group John Byrne already shared a few details about his excitement about Carrizo.
There are two Carrizo parts, one for big notebooks and All in Ones called Carrizo and a scaled down version called Carrizo L. We expect that the slower Carrizo-L is first to come but, Lisa was not specific. Carrizo-L is based on Puma+ CPU cores with AMD Radeon R-Series GCN graphics is intended for mainstream configurations with Carrizo targeting the higher performance notebooks.
Usually when a company says that something is coming in Q2 2015 that points to a Computex launch and this Taipei based tradeshow starts on June 2 2015. We strongly believe that the first Carrizo products will showcased at or around this date.
Lisa also pointed out that AMD has “significantly improved performance in battery life in Carrizo.” This is definitely good news, as this was one of the main issues with AMD APUs in the notebook space.
Lisa also said that AMD expects Carrizo to be beneficial for embedded and other businesses as well. If only it could have come a bit earlier, so let’s hope AMD can get enough significant design wins with Carrizo. AMD has a lot of work to do in order to get its products faster to market, to catch up with Intel on power and performance or simply to come up with innovative devices that will define its future. This is what we think Lisa is there for but in chip design, it simply takes time.
AMD Headed To The Facial Recognition Space
Comments Off on AMD Headed To The Facial Recognition Space
AMD has developed facial recognition technology to enable users to organize and search video clips based on the people featured in them.
AMD executive Richard Gayle demonstrated to Tom’s Guide how AMD Content Manager, uses facial recognition to browse through a group of local videos to find specific faces.
There is an index that displays the people’s faces that have been detected throughout the video clips.
The user can edit the names of the people as well as add keyword tags to help improve future searches for specific people.
For instance, if you are searching for videos that feature one person, you can click on his or her respective face to pull up the corresponding videos.
Additionally, if you want to narrow a search to a specific person combined with a keyword tag, you can drag the face icon and click on the desired keyword.
Once you click on the video you wish to view, a player appears in the right windowpane, along with a timeline displayed at the bottom with a list of all the people who appear in the video.
The timeline is separated into various coloured boxes to mark the exact moment in the video when each person first appears on screen, so you do not have to watch the entire video to see the bit you want.
The application also has facial recognition capabilities that allow users to do some basic editing, such as compiling a single montage video of any individual or individuals.
While this is pretty good technology, it probably does not have any major use yet on its own.
Gayle said it is unlikely that AMD will release Content Manager in its current form but will license it to OEMs that are able to rebrand the application before offering it on their respective systems.
He claimed that only AMD processors have sufficient power to operate the application, because of the processor’s ability to have the CPU, GPU and memory controller work closely together.
AMD’s Fiji GPU Goes High Bandwidth
New evidence coming from two LinkedIn profiles of AMD employees suggest that AMD’s upcoming Radeon R9 380X graphics card which is expected to be based on the Fiji GPU will actually use High-Bandwidth Memory.
Spotted by a member of 3D Center forums, the two LinkedIn profiles mention both the R9 380X by name as well as describe it as the world’s firts 300W 2.5D discrete GPU SoC using stacked die High-Bandwidth Memory and silicon interposer. While the source of the leak is quite strange, these are more reliable than just rumors.
The first in line is the profile of Ilana Shternshain, an ASIC Physical Design Engineer, which has been behind the Playstation 4 SoC, Radeon R9 290X and R9 380X, which is described as the “largest in ‘King of the hill’ line of products.”
The second LinkedIn profile is the one from AMD’s System Architect Manager, Linglan Zhang, which was involved in developing “the world’s first 300W 2.5D discrete GPU SOC using stacked die High Bandwidth Memory and silicon interposer.”
Earlier rumors suggest that AMD might launch the new graphics cards early this year as the company is under heavy pressure from Nvidia’s recently released, as well as the upcoming, Maxwell-based graphics cards.
nVidia Finally Goes 20nm
For much of the year we were under the impression that the second generation Maxwell will end up as a 20nm chip.
First-generation Maxwell ended up being branded as Geforce GTX 750 and GTX 750 TI and the second generation Maxwell launched a few days ago as the GTX 980 and Geforce GTX 970, with both cards based on the 28nm GM204 GPU.
This is actually quite good news as it turns out that Nvidia managed to optimize power and performance of the chip and make it one of the most efficient chips manufactured in 28nm.
Nvidia 20nm chips coming in 2015
Still, people keep asking about the transition to 20nm and it turns out that the first 20nm chip from Nvidia in 20nm will be a mobile SoC.
The first Nvidia 20nm chip will be a mobile part, most likely Erista a successor of Parker (Tegra K1).
Our sources didn’t mention the exact codename, but it turns out that Nvidia wants to launch a mobile chip first and then it plans to expand into 20nm with graphics.
Unfortunately we don’t have any specifics to report.
AMD 20nm SoC in 2015
AMD is doing the same thing as its first 20nm chip, codenamed Nolan, is an entry level APU targeting tablet and detachable markets.
There is a strong possibility that Apple and Qualcomm simply bought a lot of 20nm capacity for their mobile modem chips and what was left was simply too expensive to make economic sense for big GPUs.
20nm will drive the voltage down while it will allow higher clocks, more transistors per square millimeter and it will overall enable better chips.
Just remember Nvidia world’s first quad-core Tegra 3 in 40nm was rather hot and making a quad core in 28nm enabled higher performance and significantly better battery life. The same was true of other mobile chips of the era.
We expect similar leap from going down to 20nm in 2015 and Erista might be the first chip to make it to 20nm. A Maxwell derived architecture 20nm will deliver even more efficiency. Needless to say AMD plans to launch 20nm GPUs next year as well.
It looks like Nvidia’s 16nm FinFET Parker processor, based on the Denver CPU architecture and Maxwell graphics won’t appear before 2016.
Intel Discusses SoFIA
Intel has shed more light on its upcoming SoFIA SoC, which stands for Smart of Feature Phone with Intel Architecture. For SEO purposes we’ll just call it Sophie.
The SoFIA project is being spearheaded by Intel’s Singapore office and CNET had a chance to catch up with recent developments. The chip was announced back in December, but details were sketchy and to some extent they still are.
SoFIA is going after MediaTek and Qualcomm in the mainstream and entry level segments. It features a dual-core Silvermont processor on a 28nm die. This is where it gets interesting, as Intel simply doesn’t do 28nm. SoFIA will be manufactured by TSMC instead, but Intel is planning to build SoFIA chips in-house in the future. The company has already made it clear that it is moving to 14nm, so there is a good chance the next generation chip will be a 14nm design churned out by Intel fabs.
SoFIA has an integrated 3G modem, but a 4G version is coming later. Bluetooth and WiFi are on other chips. Lack of 4G connectivity might not be a big deal for potential SoFIA customers, as the chip is supposed to go after entry level smartphone designs. Intel told CNET that SoFIA could pave the way to $50 smartphones in Asian markets and realistically nobody expects a $50 phone to feature 4G connectivity.
It is hard to say anything about SoFIA’s real-world performance. Quad-core tablet processors based on the Silvermont architecture can still hold their ground against many high-end ARM SoCs, so a dual-core version optimised for smartphones should have no trouble keeping up with lesser ARM parts.
AMD’s Carrizo Goes Mobile Only
AMD’s upcoming Carrizo APU might not make it to the desktop market at all.
According to Italian tech site bitsandchips.it, citing industry sources, AMD plans to limit Carrizo to mobile parts. Furthermore the source claims Carrizo will not support DDR4 memory. We cannot confirm or deny the report at this time.
If the rumours turn out to be true, AMD will not have a new desktop platform next year. Bear in mind that Intel is doing the exact same thing by bringing 14nm silicon to mobile rather than desktop. AMD’s roadmap previously pointed to a desktop Carrizo launch in 2015.
AMD’s FM2+ socket and Kaveri derivatives would have to hold the line until 2016. The same goes for the AM3+ platform, which should also last until 2016.
Not much is known about Carrizo at the moment, hence we are not in a position to say much about the latest rumours. AMD’s first 20nm APU will be Nolan, but Carrizo will be the first 20nm big core. AMD confirmed a number of delays in a roadmap leaked last August.
The company recently confirmed its first 20nm products are coming next year. In all likelihood AMD will be selling 32nm, 28nm and 20nm parts next year.
ARM Launches Juno
ARM has announced two programs to assist Android’s ascent into the 64-bit architecture market.
The first of those is Linaro, a port of the Android Open Source Project to the 64-bit ARMv8-A architecture. ARM said the port was done on a development board codenamed “Juno”, which is the second initiative to help Android reach the 64-bit market.
The Juno hardware development platform includes a system on chip (SoC) powered by a quad-core ARM Cortex-A53 CPU and dual-core ARM Cortex-A57 CPU in an ARM big.little processing configuration.
Juno is said to be an “open, vendor neutral ARMv8 development platform” that will also feature an ARM Mali-T624 graphics processor.
Alongside the news of the 64-bit initiatives, ARM also announced that Actions Semiconductor of China signed a license agreement for the 64-bit ARM Cortex-A50 processor family.
“Actions provides SoC solutions for portable consumer electronics,” ARM said. “With this IP license, Actions will develop 64-bit SoC solutions targeting the tablet and over-the-counter (OTT) set top box markets.”
The announcements from ARM come at an appropriate time, as it was only last week that Google announced the latest version of its Android mobile operating system, Android L, which comes with support for 64-bit processors. ARM’s latest developments mean that Android developers are likely to take advantage of them in the push to take Android to the 64-bit market.
Despite speculation that it would launch as Android 5.0 Lollipop, Google outed its next software iteration on Wednesday last week as simply Android L, touting the oddly-named iteration as “the largest update to the operating system yet”.
Intel Links Up With Rockchip
Intel has joined forces with Chinese chip design firm Rockchip to develop next generation processors for the tablet market based on Intel Atom core technology and integrating 3G broadband communications.
Under the terms of the agreement, Intel and Fuzhou Rockchip Electronics (Rockchip) will work together on an Intel branded mobile system on chip (SoC) processor with the intention of enabling a range of entry-level Android tablets.
The chip is expected to ship in the first half of 2015, according to Intel, and will be based on a quad-core Atom processor design integrated with Intel’s 3G modem technology, which the firm gained through its acquisition of Infineon Technologies in 2010.
Rockchip, which is expected to contribute to the integrated graphics technology, will also help Intel bring the product to market faster than might otherwise be the case. The firm is a leading fabless semiconductor design company and already develops mobile SoCs, although its present designs are largely focused around the ARM architecture.
The agreement builds on announcements Intel made at an investor relations day last year, where chief executive Brian Krzanich disclosed the Intel Sofia family, of which the latest chip will form part, and conceded that the chipmaker needed to become more agile in order to gain traction in entry-level markets.
“The strategic agreement with Rockchip is an example of Intel’s commitment to take pragmatic and different approaches to grow our presence in the global mobile market by more quickly delivering a broader portfolio of Intel architecture and communications technology solutions,” Krzanich said.
With this announcement, the Intel Sofia family comprises three products, which are not shipping yet.
A dual-core 3G version is slated for the fourth quarter this year, the quad-core 3G version is due in the first half of 2015, and a version with 4G/LTE communication is also due in the first half of next year.