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.
ARM Seeing Growth
ARM and Vivante have achieved significant market share gains in the system-on-chip (SoC) GPU market while Imagination and Qualcomm have seen their market shares fall.
ARM has been aggressively pushing its Mali GPU design for the last two years, while Vivante has ridden the surge in Chinese tablet sales, and these factors have resulted in both firms increasing market shares. Analyst outfit Jon Peddie Research claimed that ARM and Vivante scored first half 2012 SoC GPU market shares of 12.9 percent and 9.8 percent, respectively, while the SoC GPU market share leaders Imagination and Qualcomm both suffered declines.
ARM more than doubled its market share from the same period a year ago while Vivante went even better by almost quadrupling its market share. Not only were both firms claiming large pieces of the pie, Jon Peddie Research claimed the SoC GPU market had increased by 91.3 percent, suggesting that Qualcomm and Imagination are having a harder time getting new business. Jon Peddie told The INQUIRER that new vendors are entering the market, typically with lower prices to earn customers.
Nvidia’s SoC GPU operations accounted for 2.5 percent of the total smartphone and tablet market, which given that the firm doesn’t license out its GPU designs is pretty impressive. Nvidia could see its market share increase if Microsoft’s Surface tablet sells well.
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 Confirms Trinity’s New Specs
AMD has confirmed the specifications of its Trinity accelerated processor units (APUs), with the majority being quad-core units with 4MB cache.
AMD launched its mobile Trinity APUs earlier this year in a bid to cash in on “back to school” sales and now it has detailed the specification of Trinity processors that will slot into desktop systems. The firm confirmed that Trinity has moved from Socket FM1 to Socket FM2 and save for two A4 and A6 SKUs the chips will all be quad-core parts with base frequencies over 3GHz.
AMD stuck with its A4, A6, A8 and A10 branding with the dual-core A4-5300, base clocked at 3.4GHz with turbo mode pushing that up to 3.6GHz and 128 graphics cores clocked at 723MHz at the foot of AMD’s APU line-up. Next up the firm has the unlocked dual-core A6-5400K, which not only bumps the CPU clock speed by 200MHz to 3.6GHz and 3.8GHz for base and turbo modes, respectively, but increases the number of graphics cores to 192 and their frequency to 760GHz.
While AMD’s A4 and A6 Trinity processors are dual-core, the four other chips in the range are all quad-core parts, with the A8-5500 and A8-5600K sporting base clock speeds of 3.2GHz and 3.6GHz, respectively, with turbo mode boosting those to 3.7GHz and 3.9GHz, respectively. The firm has kept the number of graphics cores on both chips the same at 356 and clocked them at 760MHz, however the higher frequency on the A8-5600K means that the firm bumped up the TDP to 100W, though given it is unlocked, the factory TDP is largely academic.
AMD’s A10 chips follow in the same vein as the A8 parts, with the 65W A10-5700 part clocked at 3.4GHz, boosted to 4GHz while the 100W A10-5800K part has its clocks set at 3.8GHz and boosted to 4.2GHz. AMD has given both processors 384 graphics cores clocked at 800MHz.
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 Cuts Radeon Prices
After the recent price cut back in July, that included a $50 price cut for HD 7970, HD 7950 and HD 7870 graphics cards, AMD has apparently decided to cut some of these prices even further taking the HD 7950 3GB graphics card down to $320, or just in line with Nvidia’s recently release GTX 660 Ti graphics card.
AMD has already dropped the HD 7970 from $479 to $429, HD 7950 from $399 to US $349 and the HD 7870 down from $349 to $299. The new price cut skips the HD 7970 graphics card but includes the HD 7950, HD 7870 as well as the 1 and 2GB versions of the HD 7850.
The most important is probably the price cut for the 3GB HD 7950 which battles it out with Nvidia’s recently released GTX 660 Ti. The HD 7950 3GB is, according to the report, will receive a $30 price cut placing it at $320. The HD 7870 2GB graphics card got another $50 price cut pushing it down to $250 which probably makes it one of the most interesting mid-range graphics cards on the market.
AMD also decided to drop price on 1 and 2GB version of the HD 7850 graphics card taking them down by $40 to $190 and $210, respectively.
Will ARM Get OpenCL Certification?
ARM has submitted its Mali-T604 GPU for OpenCL certification.
ARM’s Mali GPUs have so far shyed away from GPGPU support, however as smartphones and tablets are not expected to see an ever growing number of processor cores the cries for OpenCL support in its GPUs have been growing louder. Now ARM has submitted its Mali-T604 GPU to the Khronos consortium for full profile OpenCL certification.
The Khronos consortium oversees the development of OpenCL and the high-level language is supported by a number of firms including AMD, Nvidia and Intel on their latest GPUs. However until now there hasn’t been an OpenCL certified GPU that is used in smartphones, though firms such as Zii Labs also boast OpenCL support for their chips.
ARM said, “Building on a scalable multicore, multi-pipeline architecture design, the Mali-T600 Series GPU includes a number of advanced features. In particular, native scalar and vector operations for OpenCL’s integer and floating point data types (including 64-bit); support for static and dynamic compilation; hardware accelerated image and sampler data types; fast atomic operations and compliance to IEEE754-2008 precision requirements.
ARM Profits On The Rise
ARM has reported good second quarter financial results, with profit rising by 23 per cent to $102.97 million.
ARM has been riding high in the public consciousness thanks to firms such as Qualcomm, Texas Instruments and Nvidia pushing its chip architecture into smartphones and tablets. The firm announced it managed to take in $209.78 millio in revenue during the second quarter, a 15 per cent increase from the same period last year, while net income rose even faster by 23 per cent to $102.97 million.
ARM said two billion chips using the firm’s various design models were shipped during the quarter, which represented a nine per cent increase from last year. The firm revealed that its core money making operation, processor royalties, rose by 14 per cent.
Warren East, CEO of ARM said, “ARM’s royalty revenues continued to outperform the overall semiconductor industry as our customers gained market share within existing markets and launched products which are taking ARM technology into new markets.
“This quarter we have seen multiple market leaders announce exciting new products including computers and servers from Dell and Microsoft, and embedded applications from Freescale and Toshiba. In addition, ARM and TSMC announced a partnership to optimise next generation ARM processors and physical IP and TSMC’s FinFET process technology.”
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.