Items tagged with hbm

We saw first generation High Bandwidth Memory (HBM) enter the enthusiast arena with the arrival of AMD’s Radeon R9 Fury lineup of graphics cards. HBM promised incredible performance with equally impressive low power consumption, and largely delivered on those claims. NVIDIA introduced us to HBM2 with its Tesla P100 accelerator, which includes up to 16GB of the good stuff onboard. While HBM2 isn’t even shipping in volume for mainstream (or even enthusiast-class) applications, that isn’t stopping Samsung from laying out its roadmap for HBM3. HBM3 is expected to hit production in the 2019 to 2020 time frame and take the “bigger, faster, stronger” approach compared to HBM2. Each die will now be capable... Read more...
The big news yesterday from the AMD camp was with the official announcement of the Radeon Pro Duo, which was previously known as the Radeon R9 Fury X2. The water-cooled graphics card features two R9 Fury GPU cores clocked at 1GHz all operating within a 350W power envelope. But of course, we’re always looking to see what’s right around the corner, and in AMD’s case, that means Polaris. Polaris is destined to arrive about mid-way through 2016 and will move from a 28nm to a 14nm FinFET (Global Foundries) manufacturing processes. The move to FinFET allows for a radical decrease in power consumption with a new roadmap that was shared with us yesterday. So just how efficient is Polaris? If we use AMD’s... Read more...
Most of us were introduced to High Bandwidth Memory (HBM) DRAM courtesy of AMD’s Fury family of graphics cards, each of which sports 4GB of HBM. HBM allows Fury GPUs to tout an impressive 512GB/sec of memory bandwidth, but perhaps that just isn’t enough to fuel the next generation of graphics cards in the pipeline.AMD's Fiji GPU With First Generation Stacked HBM Samsung is looking to make first generation HBM look decidedly old hat, and has announced that it has begun mass production of HBM2. Samsung’s 4GB HBM2 package is built on a 20 nanometer process (each package contains four 8-gigabit core dies built on top of a buffer die). Each 4GB package is capable of delivering 256GB/sec of bandwidth,... Read more...
Micron Technology, the memory maker headquartered in Boise, Idaho, is making waves today. First is the announcement that it's acquiring the remaining shares of Inotera for approximately $3.2 billion, and secondly Micron is talking about a next generation memory technology to rival the performance of High Bandwidth Memory (HBM). Starting with the latter, Micron's Kristopher Kido confirmed the company's plans to release its new memory next year. It will likely be called GDDR5X and offer speeds of 10Gbps to 14Gbps, up to double that of existing 7Gbps 4Gb GDDR5 memory chips. More capacious 8Gb density chips won't push speeds quite as much, though will still end up at 8Gbps. You'll find Micron's new... Read more...
Although NVIDIA revealed some high level information on its next generation Pascal GPU architecture earlier this year, the company revealed some more interesting details this week at NVIDIA’s GPU Technology Conference in Japan. NVIDIA announced that Pascal will have close to a 2x performance-per-watt improvement over the current Maxwell GPU architecture, which is built on a 28nm process. It’s also been revealed that Pascal will be produced using TSMC’s 16nm FinFET process, which will put it right up against AMD which is moving to use 14nm/16nm with two new Graphics Core Next (GCN) products in 2016. Other improvements including replacing PLX PCIe Gen3 bridging with NVLink, which enables bi-directional... Read more...
If there’s one constant in the tech industry, it’s change. Well-rounded and highly sought after executives come and go, either moving from between tech firms or departing the industry altogether to pursue other interests (ahem, Steve Ballmer). Even tech companies themselves go through a metamorphosis of sorts, as we’ve seen a once powerhouse in the graphics industry, 3Dfx, become swallowed up by its fiercest rival, NVIDIA. Chipmaker AMD would later go on to acquire ATI — a pairing at the time that seemed a bit odd to many industry observers. AMD has once again come to a crossroads with respect to its graphics division, and instead of throwing in the towel in the face of stiff competition from... Read more...
AMD announced new Radeon R9 300 series and R7 300 series graphics cards earlier this week, and while those graphics cards are interesting, there are nowhere as titillating as the Mack Daddy of AMD GPUs: Fiji. Fiji will find its way into three distinct products this summer: Radeon R9 Nano, Radeon R9 Fury, and the range-topping (and water-cooled) Radeon R9 Fury X. And we can’t forget other upcoming variants like this dual-Fiji board or the scrumptious Project Quantum. As we indicated previously, the water-cooled Radeon R9 Fury X will debut June 24 for $649, while the air-cooled Radeon R9 Fury will land on July 14 for $549.AMD Radeon R9 Fury X Although we can’t yet bring you our full review on Fiji... Read more...
Earlier this week, XFX sprung a leak which revealed its Radeon R9 390X graphics card to all. But as we all sit around eagerly awaiting the arrival of Fiji-based Radeons, this card unfortunately didn’t fit the bill. The R9 390X is little more than an R9 290X “Hawaii” re-badge with 8GB of GDDR5 memory. But for those of us that are still holding out hope for some fresh Fiji info, there’s an abundance of supposedly confirmed specifications for what will be AMD’s most powerful graphics card to date. Fiji will initially be available in both Pro and XT variants with the Fiji Pro dubbed “Fury” and Fiji XT being dubbed “Fury X.” To get a taste for how potent these news chips are, take a look at the alleged... Read more...
Over the past few months, a number of details regarding AMD’s next-generation Radeon 300-series graphics cards has trickled out, even though the cards aren’t due to launch for quite some time. While official details of the actual GPUs that will be used to power the cards are still scarce (though rumors abound), AMD has publicly disclosed details regarding the revolutionary High Bandwidth Memory (HBM) interface that will be used on some Radeon 300-series products, and potentially future APUs as well.High Bandwidth Memory is designed to address a number of limitations of current GDDR5 memory implementations. With many of today’s graphics cards, a relatively large number of GDDR5 chips... Read more...
AMD this afternoon kicked off is first Financial Analyst Day in three years. During the hiatus, AMD has had a change of leadership (former CEO Rory Reed parted ways and was replaced by Dr. Lisa Su) and the company has seen its market share erode in the processor and GPU markets — the downturn in the PC market has been especially tough for AMD. On the x86 side, AMD is pushing forward with the 2016 launch of processors based on its new Zen core. We briefly touched on Zen last week when slides leaked to the Internet, but AMD’s Mark Papermaster was on hand to give us some more juicy details on what to expect. For starters, Zen-based processors will bring with them a significant boost in absolute... Read more...