Sign up for our Technology Newsletter 
AMD’s 8350 Clocked At 4.0GHz
We have got some information about AMD’s upcoming FX 8350.
However, today we learned that AMD will push this CPU from Q3 to early Q4 2012 as now it claims that it can launch this processor in late October. AMD FX 8350 is an eight-core with 16MB cache, Vishera based 32nm core with 4.0GHz default clock and ability to jump to 4.2GHz with turbo core automatic overclocking.
This is an impressive frequency jump as the AMD FX 8150 works at 3.6GHz default and with turbo gets to 4.2GHz. The FX 8350 is supposed to replace the 8150 as AMD’s flagship processor.
According to current schedule production ready samples are expected in roughly a month (early August). Mass production starts in early August, probably days after they finalize the clocks and give it a green light for mass production but the launch is pushed for late October 2012.
Will Chipmakers Make Cuts This Year?
Gartner is warning that worldwide wafer fab equipment spending is on pace to total $33 billion in 2012 which is a decline of 8.9 percent from 2011.
Gartner analysts warned that this is a sign of an industry in downturn and said the market will return to growth in 2013 with WFE spending projected to surpass $35.4 billion, a 7.4 percent increase from 2012. Bob Johnson, research vice president at Gartner said 2012 spending was strong at the beginning of the year, as foundries and other logic manufacturers ramped up sub-30-nm production.
Will More Win8 RT Hybrids Start Showing Up?
June 29, 2012 by admin
Filed under Uncategorized
Comments Off on Will More Win8 RT Hybrids Start Showing Up?
Rumour has it that Nvidia has the best drivers and might be close to fine tuning its Windows RT platform, but we are sure Qualcomm and Texas Instruments aren’t far behind.
The Asus Transformer series has set a new trend by providing tablet users with a keyboard dock with some extra ports and an additional battery. This is definitely the way to go as you get the best of both worlds in a single package Windows 8 RT is finally bringing Microsoft in the ARM market and needless to say there will be many systems to be ready for launch.
Nvidia with Tegra, Texas Instruments with OMAP and Qualcomm with S4 are getting ready to embrace tablets as well as hybrid notebooks based on Windows 8 RT. The Asus Transformer 600 is just the first of many to come and there will be at least a few more similar designs to launch this year with Windows 8 RT, so we have no doubt that we will see quite a few convertible Windows tablets.
AMD, ARM And Others Form HSA Chip Foundation
Comments Off on AMD, ARM And Others Form HSA Chip Foundation
AMD, ARM, Imagination Technologies, Mediatek and Texas Instruments have signed up to create the Heterogeneous System Architecture Foundation (HSAF).
AMD has been pushing its vision for heterogeneous computing, where CPUs and GPUs can share system resources such as memory allowing developers to treat any processing core as a black box. Now the firm has managed to rope in ARM, Imagination Technologies, Mediatek and Texas Instruments to create the non-profit HSAF.
According to AMD, HSAF will try to define a hardware specification for developers to standardise upon, which should make development quicker and easier.
Phil Rogers, HSAF president and AMD corporate fellow said, “HSA [heterogeneous system architecture] moves the industry beyond the constraints of the legacy system architecture of the past 25-plus years that is now stifling software innovations. By aiming HSA squarely at the needs of the software developer, we have designed a common hardware platform for high performance, energy efficient solutions. HSA is unlocking a new realm of possibilities across PCs, smartphones, tablets and ultrathin notebooks, as well as the innovative supercomputers and cloud services that define the modern computing experience.”
AMD has scored something of a coup by getting big names such as ARM, Imagination and Texas Instruments to back its vision of a heterogeneous system architecture. Although the company has been struggling in outright performance terms against Intel, the idea of a combining CPU and GPU resources and making them appear as one to the application is something that will help it leverage its GPU compute capability against Intel.
Microsoft Says Windows RT Best For ARM
Microsoft has said its upcoming Windows RT will be loaded on laptops and tablets, claiming it is the “most compatible” ARM operating system.
Microsoft’s Windows 8 will be the first time the firm has launched a desktop operating system that supports the ARM architecture, albeit with the Windows RT branding. Now the firm has said that laptops and tablets will feature Windows RT and called it the most compatible ARM operating system.
Erwin Visser, senior director of Microsoft’s Windows Commercial Business Group said, “Windows RT devices in tablet and laptops will run all the apps from the Windows store. It will also include [Microsoft] Office components like Word, Excel, Powerpoint and Onenote and support a large amount of PC peripherals through in-box class drivers. Relative to other ARM offerings in the market, Windows RT will be the most compatible ARM offering on the market.”
When The INQUIRER asked Visser what he meant by “most compatible” Visser replied, “Taking into acount ARM is a completely new processor architecture and what we’re focused on is a couple of things to help enterprise customers embrace Windows RT. […] All the Windows 8 apps that run on x86 will also run on Windows RT.” Visser also cited inclusion of in-box drivers for PC hardware, something that is largely missing from both Android and IOS devices.
Visser also said users can side-load applications on Windows RT devices, meaning the Windows Store isn’t the only source of applications. When we asked whether this could be a security risk Visser said, “In the case of side-loading apps, the app will be certified through the enterprise IT organisation.”
As for why Microsoft will allow side-loading applications in Windows RT, apparently that is what big business wants. Visser said, “If you think about apps that are used internally, so not apps that are built by enterprises for their consumers or customers but apps that support internal processes, customers do not want to put those apps – because they always have some competitive advantage – in the Windows App Store, which is a public place. So they want to keep those apps within their own infrastructure and [with] side-loading they can still load them on Windows x86 and Windows RT systems.”
AMD Gives Opteron A Boost
AMD has shown there is a little life left in its Bulldozer Opterons by bumping up the clock speed of five Opteron models.
AMD launched its Bulldozer Opteron processors last November amid widespread anticipation that its brand new Bulldozer architecture would once again make it competitive with Intel. Its new architecture failed to impress, but the company has managed to eek out another 100MHz from five Opteron processors in what is likely to be a last hurrah before Piledriver Opterons make their appearance.
AMD bumped up the clocks by 100MHz on the 16-core Opteron 6284 SE and Opteron 6278 to 2.7GHz and 2.4GHz, respectively, while keeping TDPs the same as before, at 140W and 115W, respectively. The firm gave four Opteron 4200 series chips the same 100MHz bump, including the eight-core Opteron 4276HE to 2.6GHz, the six-core Opteron 4240 to 3.4GHz and the Opteron 4230 to 2.9GHz.
AMD was keen to point out that its speed bumped Opteron chips have been picked by Dell and by HP for 11 of its servers. Although the firm has not been able to compete with Intel’s Xeon chips on perfermance, its chips are considerably cheaper, a fact that AMD is using to win customers.
Although AMD’s 100MHz speed bump isn’t going to set the world on fire, every little bit of performance will help the firm as Intel ploughs on with its hugely impressive Sandy Bridge E and Ivy Bridge Xeon chips. AMD’s answer to Intel’s latest Xeon chips is expected to be the Piledriver Opterons.
AMD Officially Launches Trinity Mobile
AMD has finally and officially lifted an NDA veil off its mobile Trinity A-series APU lineup based on the 2nd-gen Bulldozer CPU core, aka Piledriver, and VLIW4 Northern Islands GPU squeezed together on a 32nm SOI die.
Architecture-wise, AMD’s Trinity combines two to four Piledriver x86 cores combined with up to 384 VLIW4 Radeon cores on a 32nm die which ends up as a 246mm2 chip with 1.303B transistors, slightly more than Llano’s 228mm2/1.178B. Since it is made in the same 32nm manufacturing process as Llano, the greatest win for Trinity are actual CPU and GPU performance improvements as well as impressive power consumption improvements when compared to Llano APUs.
Same as the FX-series desktop parts based on the Bulldozer architecture, AMD’s Trinity CPU part has a 2+1 integer/floating point design where you get two integer cores that share a single floating point scheduler. Although it appears to the OS as two cores, each Piledriver module actually has less resources than traditional core design. But with Piledriver, those Bulldozer kinks got ironed out as much as possible, improving IPC (instruction per cycle), reducing leakage, reducing CAC and giving it a slight frequency uplift.
As far as the GPU is concerned, we are looking at quite familiar Northern Islands VLIW4 part, a same one that was behind Cayman Radeon HD 6970 graphics card. Of course, the GPU has been cut down to up to 384 stream processors (organized in 6 SIMDs) with 24 texture units and 8 ROPs. The clocks have also gone down to 497MHz base clock that can “turbo” up to 686MHz.
Trinity Launching On Desktops This Summer
Comments Off on Trinity Launching On Desktops This Summer
AMD is expected to introduce its new mobile Trinity APU in a week or so and now we are hearing some timeframes for desktop parts as well.
According to Digitimes, desktop Trinity parts are coming in August, while Brazos 2.0 chips are expected in June. There is no word on Trinity ULV parts yet and we believe they will be the most interesting of the lot.
Is Moore’s Law Dead?
May 11, 2012 by admin
Filed under Uncategorized
Comments Off on Is Moore’s Law Dead?
Physicist Michio Kaku says that Moore’s law will be dead within about 10 years.
Kaku, professor of theoretical physics at City University of New York told BigThink.com that we are already seeing a slowing down of Moore’s Law. He said that computing power simply cannot maintain this rapid, exponential rise using standard silicon technology.
Kaku said that the latest CPUs from Intel, which use a unique three-dimensional design, do continue roughly doubling processors. But he points out that the new design is nonetheless proof that the Law is winding down.
The two basic problems are heat and leakage and that is why the age of silicon will eventually come to a close.
By continuing to shrink the parts that go into processors, heat becomes concentrated. At a point in the near future, the heat generated will be so intense that the chip will melt. You can literally fry an egg on top of the chip, and the chip itself begins to disintegrate, he said.
AMD Shows Off New Radeon Chips
AMD has now officially updated its HD 7000M lineup of mobile GPUs with HD 7700M, HD 7800M and HD 7900M GPUs that are all based on AMD’s 28nm GCN architecture. The first in line that should show up in notebooks is the flagship HD 7970M GPU.
As noted, the entire lineup is based on AMD’s 28nm GCN architecture, but as always, the naming scheme of the AMD mobile parts has nothing to do with the desktop ones. The HD 7900M, codename Wimbledon, is actually based on 28nm Pitcairn destkop GPU that features 1280 stream processors, 80 texture units, 32 ROPs and up to 2GB of GDDR5 memory paired up with a 256-bit memory interface.
The HD 7800M series, codename Heathrow and the Radeon HD 7700M series, codename Chelsea, are both based on Cape Verde desktop GPU but with a slight twist. While Heathrow, HD 7800M series features fully enabled Cape Verde GPU with 640 stream processors, 40 texture units and 16 ROPs, the Chelsea HD 7700M series is based on a “crippled” Cape Verde core with 512 stream processors and 32 texture units. Both the HD 7800M series and the HD 7700M series will feature up to 2GB of GDDR5 memory paired up with a 128-bit memory interface. Of course, we expect at least two SKUs for both HD 7700M and HD 7800M series.
AMD also decided to ditch the PCI-Express 3.0 support on the HD 7700M series mainly as this one is aimed at lower-performance platforms that are all about power saving, and performance gain was simply too low.
For now, AMD has only shed precise details regarding the HD 7970M GPU that is based on the fully enabled Pitcairn GPU with 1280 stream processors that will end up clocked at 850MHz for the GPU and 4.8GHz for 2GB of GDDR5 memory paired up with a 256-bit memory interface.
As you can notice, the HD 7970M has lower GPU clocks than its HD 7870 desktop counterpart, but AMD also decided to keep the memory at the same level resulting in 153.6GB/s of memory bandwidth. According to AMD slides, HD 7970M should end up to be anywhere between 30 and 60% faster than HD 6990M and anywhere between 16 and 76 percent when compared to Nvidia current high-end GTX 675M GPU.