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.
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.
Is Apple proving how clueless it is about security by backing a method of replacing passwords with fingerprint readers?
Just days after a scandal where a South American hospital was staffed by phantom doctors who used silicon fingers of their colleagues to convince administrators’ finger print readers that they were working, Apple has decided that they are the perfect form of security.
Word on the street is that Apple is said to be planning to introduce an iPhone that can be unlocked by the owner’s fingerprint. Speculation about Apple’s plans for fingerprint recognition began last summer when the iPhone maker bought bio-metric security firm AuthenTec for $335 million.
It is believed that the iPhone 5S will have a fingerprint chip under the Home button, to “improve security and usability.” Meanwhile in an engineering journal, two Google security experts outlined plans for an ID ring or smartphone chip that could replace online passwords, which is a lot sexier than fingerprint scanning.
Richland is set to replace AMD’s Virgo platform, powered by Trinity processors, and this change will happen in June 2013, most likely coinciding with Computex 2013.
AMD has just launched the first batch of Richland mobile APUs and we still have to see some notebook designs hitting the market. We wrote about mobile Richland APUs.
As of late last year Desktop Richland was always set to launch in June 2013 and the fastest of them is the A10 6800K, clocked at 4.1GHz and 4.4 with Turbo. It also features Radeon HD 8670D graphics that run at 844 MHz. This is the fastest Richland part and it comes unlocked, ready to replace the current AMD A10 5800K. In Europe, the A10 5800K currently sells for 112, while in US the same CPU sells for $129.00 (boxed).
The alpha dog A10 6800K is followed by A10 6700, A8 6600K (Unlocked) and A8 6500. AMD has a mix of 100W and 65W quad-core Richland desktop SKUs. There will be a single A6 6400K (Unlocked) SKU and the A4 6300, both dual-cores with 65W TDP.
Production ready samples were churned out in late January, while volume production is scheduled for late March 2013. The announcement was always scheduled for June 2013 and Richland last through most of 2013, until Kaveri with 28nm Steamroller comes on line.
Researchers Nikita Tarakanov and Oleg Kupreev analyzed the security of 3G/4G USB modems obtained from Russian operators for the past several months. Their findings were presented Thursday at the Black Hat Europe 2013 security conference in Amsterdam.
Most 3G/4G modems used in Russia, Europe, and probably elsewhere in the world, are made by Chinese hardware manufacturers Huawei and ZTE, and are branded with the mobile operators’ logos and trademarks, Tarakanov said. Because of this, even if the research was done primarily on Huawei modems from Russian operators, the results should be relevant in other parts of the world as well, he said.
Tarakanov said that they weren’t able to test baseband attacks against the Qualcomm chips found inside the modems because it’s illegal in Russia to operate your own GSM base station if you’re not an intelligence agency or a telecom operator. “We’ll probably have to move to another country for a few months to do it,” he said.
There’s still a lot to investigate in terms of the hardware’s security. For example, the SoC (system on a chip) used in many modems has Bluetooth capability that is disabled from the firmware, but it might be possible to enable it, the researcher said.
For now, the researchers tested the software preloaded on the modems and found multiple ways to attack it or to use it in attacks.
For one, it’s easy to make an image of the USB modem’s file system, modify it and write it on the modem again. There’s a tool available from Huawei to do modem backup and restore, but there are also free tools that support modems from other manufacturers, Tarakanov said.
Malware running on the computer could detect the model and version of the active 3G modem and could write an image with malicious customizations to it using such tools. That modem would then compromise any computer it’s used on.
The researchers also found a possible mass attack vector. Once installed on a computer, the modem application — at least the one from Huawei — checks periodically for updates from a single server, Tarakanov said. Software branded for a specific operator searchers for updates in a server directory specific to that operator.
An attacker who manages to compromise this update server, can launch mass attacks against users from many operators, Tarakanov said. Huawei 3G modems from several different Russian operators used the same server, but there might be other update servers for other countries, he said.
Research in this area is just at the beginning and there’s more to investigate, Tarakanov said. Someone has to do it because many new laptops come with 3G/4G modems directly built in and people should know if they’re a security threat.
Intel is going to update its desktop Pentium family with several slightly faster Ivy Bridge-based processors.
According to CPU World the chips should hit the shops in the second quarter of 2013 which is a quarter after January’s refresh of budget desktop families, and one quarter before the launch of Haswell. The new chips have the original titles of Pentium G2030, G2030T, G2120T and G2140. They will have two cores, but lack Hyper-Threading technology, and can run two threads before getting all confused.
Both the G2000 and G2100 series CPUs support only basic features, like Intel 64 and Virtualization. They do integrate HD graphics which are clocked at 650 MHz and dual-channel memory controller, that supports DDR3-1333 on the G2030 and the G2030T, and up to DDR3-1600 on the G2120T and the G2140.
Pentium G2030T and G2120T are low-power models, replacing G2020T and G2100T but are clocked 100 MHz higher, that is at 2.6GHz and 2.7GHz respectively. However they still fit into 35 Watt thermal envelope. Pentium G2030 and G2140 mainstream microprocessors will be faster than “T” SKUs, and they will have 57 per cent higher TDP. Intel expects these to replace the G2020 and G2130 SKUs. The G2030 will run at 3 GHz. The G2140 will operate at 3.3 GHz. No word on prices yet.
The general consensus is that iOS apps tend to be somewhat safer than their Android counterparts. Apple goes to great lengths to have apps vetted and as a result far fewer iOS apps end up with malware or security issues.
However, a new report fresh out of Appthority claims iOS apps have their fair share of issues and in some respects then can pose an even greater security risk than Android apps. The report covered the top 50 apps from the Apple App Store and Google Play and found that iOS apps exhibited riskier behaviour.
“The majority of iOS apps track for location (60%), share data with advertising or analytics networks (60%) and have access to the user’s contact list (54%). A small percentage of iOS apps also had access to the user’s calendar (14%),” the report found.
However, Android fans shouldn’t be too happy since their platform is not far behind. Half of them share data with ad networks or analytics companies, while 42 percent tracked location. Slightly better, but nothing to be proud about.
One of the most worrying findings is that both Android and iOS apps don’t do much to prevent personal data from leaking from our devices. Not a single iOS app analyzed in the study used encryption to send and receive data, and neither did 92 percent of Android apps.
So while it might seem that Android is a somewhat better platform for users with privacy concerns, both Google and Apple are pants at that sort of thing.
y Bridge E, Intel’s ultra-high end chip that is set to replace the Core i7 3970X, has been delayed. It doesn’t look like it was anything major. Our sources tell us that the decision was made by Intel server guys who did not want to launch this chip in Q3 as originally indented.
Since Q3 starts in July, a relatively slow month for IT, the normal time to launch products is late August or September, but at this time there is no confirmation that this will happen at this time.
Sandy Bridge E, or Core i7 3960X, was launched in Q4 2011, November 14th to be precise. This can give you a clue on when to expect the successor.
Originally Ivy Bridge E was supposed to launch in Q3, one quarter after the launch of quad-core Desktop Haswell processors. Ivy Bridge E works in X79 motherboards but we do expect that a few key motherboard vendors will have their newer versions ready for the launch of the new $999 flagship processor.
If Intel continues at this pace, it will take quite a while before we see Haswell E in action.
Facebook has come up with a data cache which runs on flash memory instead of DRAM. Dubbed McDipper it saves money while still delivering higher performance than disk.
The system is a Facebook-built implementation of the popular memcached key-value store the only difference is that runs on flash memory rather than pricier DRAM. Memcached is the open-source key-value store that caches frequently accessed data in memory so applications can access and serve it faster than if it were stored on hard disks.
Facebook runs thousands of memcached servers to power its various applications. The only downside is that it is expensive. McDipper can handle working sets that had very large footprints but moderate to low request rates. It provides up to 20 times the capacity per server and still supports tens of thousands of operations per second.
According to Gigaom, Facebook has deployed McDipper for a handful of these workloads. This has reduced the total number of deployed servers in some pools by as much as 90 per cent while still delivering more than 90 per cent of get responses with sub-millisecond latencies.
There have been more than enough leaks dealing with Richland, AMD’s successor to the Trinity powered Virgo platform, and we even had a chance to see some leaks regarding its successor, codenamed Kaveri. As you may already know, Richland is planned to last through 2013 and it is clear that this is very important chip for AMD.
Based on the Piledriver architecture and built using 32nm technology, Richland will feature an integrated GPU that will be upgraded to Radeon HD 8000 series, a generation ahead of Trinity. As you know, there has been a lot of leaks regarding the Richland parts and the quad-core A10-6800K with Radeon HD 8670D graphics is expected to pack quite a punch. Best of all, Richland will still use the same FM2 socket.
According to our sources, the NDA will be lifted on 12th of March, 8am EST, and we are sure that we will see at least a couple of reviews as well as some additional info regarding the price and the availability date.
Sign up for our Technology Newsletter 
Comments