Sign up for our Technology Newsletter 
AMD Goes Piledriver
AMD has released its Piledriver desktop
processors codenamed Vishera.
AMD showed off Vishera at IDF last month, an overclocked chip running at 5GHz. Now the company has taken the wraps off its eight-core Vishera chip, a processor that it hopes will finally bury memories of its disappointing Bulldozer Zambezi chip.
AMD’s Vishera processors will continue to use Socket AM3+, meaning it is a drop-in upgrade for those customers lumbered with Zambezi processors.
The firm announcing four models all branded with the FX moniker. The low-end Vishera chip is the quad-core FX-4300 clocked at 3.8GHz boosted up to 4.0GHz, with 4MB of Level 3 cache.
The firm has kept feature parity throughout its Vishera FX range aside from core count and total Level 3 cache. Therefore AMD’s six-core FX-6300 still sports the same 1MB of Level 2 cache per core but has a total Level 3 cache of 8MB and is clocked at 3.5GHz that can be boosted up to 4.1GHz.
AMD’s top two Vishera parts, the FX-8320 and FX-8350 sport eight cores and have 8MB of Level 3 cache. The difference between the two chips is their clock frequencies, with the FX-8320 running at 3.5GHz and boosted to 4.0GHz while the FX-8350 is clocked at 4.0GHz and is boosted to 4.2GHz.
The firm’s decision to clock its FX-8320 and FX-8350 so closely is largely academic, as all Vishera chips feature an unlocked multiplier. AMD even plays up the overclockability of Vishera and touts 5GHz as being reachable with water cooling. Insiders have even said it can reach 5GHz with strong air cooling.
As for AMD’s Piledriver architecture, the firm claims it offers improved branch prediction and improvements to Level 2 cache efficiency and scheduling. Overall the company is sticking to its longstanding line that Vishera is a 15 percent performance increase over Bulldozer, and while that might well be true, Bulldozer was so far behind its competition in single-threaded performance that a 15 percent gain is needed simply to achieve parity, let alone a lead.
AMD Makes Cuts
AMD has cut its third quarter revenue and gross margin forecasts citing weak demand.
AMD’s lacklustre Bulldozer processor line has left the firm desperately trying to compete with Intel in the desktop market while its more impressive accelerated processor unit (APU) range has been rebuffed by Intel’s multi-million dollar ultrabook marketing push. Now AMD has revised down its estimate of third quarter revenues, which it says will be around 10 percent lower than the previous quarter.
Even more worrying for AMD is its lower forecast for gross margin, the difference between selling an item and the cost to make it, down from 44 percent to 31 percent. Effectively AMD said its cost of doing business has risen considerably higher, although it laid most of the blame on an $100m inventory writedown.
AMD couldn’t avoid admitting the blindingly obvious and said that its writedown of inventory was due to “lower anticipated future demand for certain products”. The firm has suffered through a disappointing 2012, and earlier this year it announced a $580m loss back in April.
AMD Details Vishera
AMD will launch three eight-core processors led by the AMD FX 8350 but it also plans to launch two six-core processors for people who like to spend a bit less.
The AMD FX6350 is a 125W six-core with a 3.9GHz base clock and 4.2 maximum turbo core clock. It comes with 14MB of cache, supports DDR 3 1866 and comes in AM3+. Naturally this is a 32nm SOI product just as its predecessor as AMD is not ready for 22nm fun yet.
The runner up is a 3.5GHz clocked six core that turbos to 4.1GHz, all that while staying in 95W TDP envelope. The name is FX 6300 and these two boys should launch together. The rest of the specification is the same as with faster brother. These two processors will replace the Zambezi based FX 6120 and FX 6100. These parts as well as FX 6200 that is also a part of Zambezi legacy are all selling between $190 and $250 which is definitely not a lot of money for quite powerful processors.
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.
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.
AMD’s Trinity To Have Fewer Cores
AMD’s soon to launch A10 5800K is a 100W quad-core Trinity 32nm CPU with 3.8 GHz base clock and 4.2GHz maximal clock possible with AMD turbo core dynamic overclocking technology.
The A10 5800K has 4MB of L2 cache, supports DDR3 1866, dual graphics configurations as well as AMD’s new FM2 socket. The fun part is new HD 7660D GPU that works at 800MHz and comes with 384 shader units. The current APU market leader A8 3870K that works at 3GHz has HD 6550 graphics with 400 cores running at 600MHz.
AMD claims that new Radeon cores from Trinity CPU including A10 5800K are more efficient and this is the main reason why you have fewer cores that can deliver superior performance. The other reason is that with 800MHz core clock they can probably process more data, meaning that HD 7660D of A10 5800K should end up quite a bit faster than the Llano A8 3870K.
All these Radeon cores are a key feature of the Vision Engine that accelerates GPU enabled applications. AMD also tells the world that Trinity is DirectX 11 compatible, supports Direct compute and the new A series of processors, including the A10 5800K all the way to dual-core A4 5300, should not have any issues playing Blu-ray 3D. The GPU part of Trinity supports AMD V, UVD3 as well as Open CL acceleration.
Did AMD Want nVidia Instead of ATI?
While it is ancient history now, it seems that the story about the controversial buying of ATI by AMD was not an easy process.
Forbes has found a deep throat who has left AMD who has told it that AMD approached graphics processor designer Nvidia about an acquisition before snapping up Nvidia rival ATI in 2006. AMD leaders believed that shrinking transistors would create an opportunity to add new capabilities to the processors AMD and rival Intel designed for PCs and servers.
AMD Chief Executive Hector Ruiz decided to bet that AMD could get ahead of rival Intel by grabbing a piece of the market for GPUs. Fusing CPUs and GPUs would let AMD hit the PC market with something Intel wasn’t ready to offer. Initially AMD thought that Nvidia was the best bet but the deal was killed off because Nvidia Chief Executive Jen-Hsun Huang insisted on being chief executive of the combined company.
Ruiz decided it was better to buy Nvidia rival ATI in July of 2006 for $5.4 billion. Nvidia replied by unleashing several strong products, gobbling up market share. AMD has fought its way back, with a strong lineup of graphics processors, Nvidia pushed into mobile processors. Nvidia has a market capitalization of $9.7 billion.
Will AMD’s HD 7950 Debut Next Month?
AMD has decided to delay the launch of its HD 7950 graphics card to early February.
This comes after news that the HD 7970, which AMD ‘launched’ on 22 December, will not be available until 9 January. This wasn’t received too well by the media and customers as it does help to have some stock to sell on launch day.
To avoid another bashing for a ‘paper launch’ the firm will launch the HD 7950 in February when it will actually be available. Guru 3D had confirmed this but the article has since been taken down.
AMD has told us that it won’t comment on rumour, speculation or any unannounced products.
The upcoming HD 7950 graphics card will use the same 28nm Southern Islands Tahiti GPU as the HD 7970, with the latter the first to do so. According to AMD it has 4.3bn transistors, more on-chip cache and greater overclocking potential than previous cards.
.
Intel Gives Details On Their Xeon E5 Processors
Comments Off on Intel Gives Details On Their Xeon E5 Processors
Intel finally gave more details at the supercomputing conference SC2011 about its upcoming Xeon E5 processors and been showing off its Knights Corner many integrated core (MIC) solution.
We don’t expect to see the new Xeons until the first half of 2012, but Intel has has been shipping the new chips to “a small number of cloud and HPC customers” since September. The E5 family has the same core as the 3960X which Intel launched this week. So far though Intel does not seem to be keen to ramp up any mass production. Some of this might have something to do with problems in production which were rumoured earlier this year. However early benchmarks indicate that it could be a winner.
.
.