AMD’s decision to rename and split the Northern Islands family into two is starting to unravel itself. Polaris 10 (Ellesmere) and 11 (Baffin) are coming to market as low-power mainstream cards – Radeon RX460 (Polaris 11), RX470, RX480 4GB and RX480 8GB (all Polaris 1o). On the other side, Greenland i.e. Vega 10 will be the most advanced silicon AMD has ever produced. Featuring 14nm FinFET design by GlobalFoundries or Samsung, with SK.Hynix HBM2 memory modules on multi-chip-module, i.e. MCM (TSMC calls this CoWoS), Vega 10 is looking to offer equal or higher performance than the high-end GP100. You should expect the chip to land in between
Ever since we revealed the specifications of new PlayStation Neo console, rumors were about when SONY will pull the trigger and introduce the console. Our sources told us that the time of introduction is Tokyo Game Show – scheduled for September 15-17, 2016. As such, we’re afraid that the next week’s E3 will pass with perhaps just a teaser for the new console – or will be the biggest (silent) elephant in the room. In an interview with Financial Times, Andrew House, President and Global Chief Executive Offices at Sony Interactive Entertainment said that the high-end PlayStation 4 “Is intended to sit alongside and complement the standard PS4,
Even though we continuously hear rumors and statements that the pace of Moore’s Law is slowing down or stopping (last one came from Jen-Hsun Huang, co-founder and CEO Nvidia Corporation), the speed of progress in semiconductor industry isn’t slowing down. 14nm is getting traction not just by high-end chips from Intel, AMD, Nvidia, Apple, Samsung and other large players, but also by smaller companies which are moving to revolutionize the way how we build virtual reality glasses, cars, infotainment systems, TVs and many other. FinFET transistors are moving to replace Planar, resistive memory technologies such as ReRAM plan to succeed NAND Flash and SDRAM etc. Still, there is one major technology barrier we
Ten years, even five years ago Intel was the undisputed process leader, and if you wanted to see how the new process node would look like, you would wait to see a new processor coming from Intel architecture. That was the unwritten law of the semiconductor industry, with an occasional blimp when TSMC would introduce a half-node step, beating Intel’s 90/65/45/32nm with 80nm, 55nm, 40nm and 28nm GPUs for ATI and Nvidia. Today, Intel’s missed approach to mobile resulted in company loosing the process node advantage, and ultimately being forced to cancel the most of Atom product family. And now, to add insult to injury, DigiTimes (also known
Nvidia Pascal Editor’s Day is taking shape as select group of press, analysts and gaming VIPs are flying to Austin, the capitol of Texas, and then being driven to a W Hotel where the festivities will take place. We already know that Electronic Arts will reveal next installation of Battlefield franchise at 1PM Pacific, 10PM Central European Time while we can now deliver the news that the public part of Pascal Editor’s Day will take place at 6PM Pacific, Midnight Zulu i.e. GMT, and 2AM in Europe. Conveniently for Asian markets, the stream will take place in the morning hours on Saturday, i.e. weekend. Previous launches almost
According to multiple sources we managed to talk to during the last couple of industry conferences, and the story that just break today, Sony is rushing ahead towards introduction of “Playstation 4.5”, codenamed NEO. The company decided to update the console rather than performing a ‘simple’ die shrink, a tactic both Microsoft and Sony utilized over the lifetime of their Playstation 2 and 3, Xbox and 360 consoles. The original plan for NEO was to introduce a 14nm die-shrink of 8-core Jaguar processor and an update of a GCN-based graphics processor. However, a shift from 28nm to 14nm is significantly more complex due to the fact that 28nm process used
A technology rumor website recently published a story detailing the upcoming AMD Polaris 10 GPU, allegedly named “67DF:C4”. As it turns out, a bird sent us screenshots showing the details of the card. While we cannot go into more details in order to protect the source, we can confirm that AMD Polaris 10 engineering samples are varying in clock between 800 and 1050 MHz, depending on the partner. Our original Polaris 10 story is here. What we know so far is that Polaris 10 used to be known as Ellesmere, Baffin is Polaris 11 and Greenland is Vega 10. Apparently, the numbers 10, 11, 12 will not co-relate
It looks like 2016 is turning into a year of anticipation and redemption for AMD, not just to its consumers, but also to customers which purchased millions of dollars of AMD hardware in the past, and then felt left out. We all saw Oak Ridge National Laboratories, one of first Opteron adopters – ditching a decade old AMD collaboration for IBM+NVIDIA team up. Luckily for all involved, AMD seems to have finally “get their s*** together” and started a sales campaign which might be the most successful since Henri Richard led the sales team taking over more than 50% market share from Intel (albeit only in 4P and 8P
Samsung Semiconductor is on a roll of late. The company introduced FinFET transistors with the 14nm process last year for logic, beating Intel for the first time in history to to a new manufacturing node. 14nm process expanded from in-house Exynos SoC processors to customers such as Apple, Qualcomm and others, while Intel was trying to get Broadwell architecture out the door. This process was followed by the announcement of ultra-dense 15nm NAND Flash memory, and now the company announced mass-production of next-gen memory standard – HBM2. The company announced that it started mass production of High-Bandwidth Memory 2 chips using its 20nm process, which just got
AMD received a substantial coverage at VentureBeat recently, with Dean Takahashi interviewing key executives in succession. First off was an in-depth interview with Lisa Su (CEO and Chairman of AMD), followed by an interview with Raja Koduri, Head (CEO?) of Radeon Technologies Group. RTG is AMD’s spin-off which you can compare with the spin-off of manufacturing division you now know as GlobalFoundries, just without a strong sovereign wealth fund (like Mubadala Development Company)… for now. In order to execute on a huge market opportunity in the form of Virtual Reality, RTG wants to make sure all the basics are covered. For starters, one of more painful episodes from the company
Back in early December 2015, AMD invited their preferred media partners to brief them about the new company structure, where Radeon Technology Group (RTG, also known as ATI 2.0) will continue to bring products to market under the AMD banner until the (almost inevitable) spin-off occurs. In a run-up to CES 2016, which takes place in Las Vegas, NV, AMD made a formal announcement introducing the Polaris GPU architecture. In a video bewlo, Raja Koduri (head of RTG) spoke of innovation that was enabled by a logical transition from planar transistors (single-gate, i.e. 2-D) to multi-gate (i.e. 3-D) technology, with a variant of 3-D transistors being called FinFET. If
Couple of days ago, GlobalFoundries issued a press release stating that they ‘demonstrated silicon success on the first AMD (NASDAQ: AMD) products using GLOBALFOUNDRIES’ most advanced 14nm FinFET process technology.’ “FinFET technology is expected to play a critical foundational role across multiple AMD product lines, starting in 2016. GLOBALFOUNDRIES has worked tirelessly to reach this key milestone on its 14LPP process. We look forward to GLOBALFOUNDRIES’ continued progress towards full production readiness and expect to leverage the advanced 14LPP process technology across a broad set of our CPU, APU, and GPU products,” said Mark Papermaster, Senior Vice President and Chief Technology Officer at Advanced Micro Devices.
Since its inception, GlobalFoundries had a plan to become world’s leading semiconductor manufacturer. From starting as an AMD manufacturing spin-off, the company owners set a multi-decade plan which involved acquiring Chartered Semiconductor and recently, acquired IBM foundry business as well. The capacity grew from initial 60,000 300mm wafers in 2009 to almost quarter billion 300mm and 130+ million 200mm wafers in second quarter of 2015. While the absolute capacity numbers were even higher, the owners (Mubadala Development Company, Abu Dhabi) decided to re-address the capacity and increase volume in processes that make financial sense. In order to stay ahead the company kept on investing in SOI
A statement from Ultratech’s CEO appears to support rumors of a big delay from Samsung.
As Samsung seems to complete its move to a 20nm manufacturing process, TSMC is aiming to shift to a 10 nm process node by the end of 2015.
On Thursday (LON: ARM) and Taiwan Semiconductor Manufacturing Corporation (TPE: 2330) announced a plan to deliver ARM-based processors on TSMC 10FinFET process node. The two companies said that their roadmap would place the release of the 10nm chips in the fourth quarter of 2015. In the announcing press release, the companies said that the success of the transition from 20nm to 16FinFET influenced their decision to work together again on the deal. As announced at Computex in June, ARM is building a research and innovation center in Hsinchu, Taiwan home to the headquarters of TSMC and MediaTek. “ARM and TSMC are industry leaders in our
Today’s announcement from the well-known full service semiconductor company, Global Foundries and QuickLogic (NASDAQ:QUIK), will interest those looking for ultra low power (ULP) sensor hubs. The new ArcticLink 3 S2 is optimized for smartphones and the new wearable devices. QuickLogic is known as being an innovator of ultra low power programmable Customer Specific Standard Products — silicon platforms plus software solutions. Its next generation ArcticLink 3 S2 platform is sampling on Global Foundries own lower power 65 nanometer process technology. Global Foundries also prides itself on its 14nm FinFET leading edge technologies fashioned for high-volume, high-performance and power-efficient SoC applications. Sensor hubs like the 3 S2
Samsung and Globalfoundries have announced a partnership to collaborate on a global scale to deliver 14nm FinFET technology to their customers. This partnership is different from the already existing Common Platform Alliance which includes Globalfoundries, Samsung and IBM, but is likely a product of that relationship considering that IBM is mostly a research fab and doesn’t really produce many commercial wafers. This 14nm FinFET collaboration is an effort by both companies to build up enough fab capacity in order to satisfy the demand of their customers on this leading-edge technology. As you can see from the slide above Samsung and Globalfoundries’ partnership means that the