Items tagged with memory
Are you excited for NVIDIA's latest and greatest GPU, the GeForce GTX 1080? If so, imagine how the hard-working engineers at Micron feel, as their GDDR5X memory has become part of what makes NVIDIA's new Pascal-based cards perform at such a high level. As NVIDIA's co-founder and CEO Jen-Hsun Huang said at his company's launch event last week, "This memory is so fast. It is so fast... G5X, the fastest GDDR memory in the world." That might sound a bit redundant, but Huang wanted to drive the point home that Micron's cooperation with NVIDIA has helped its latest product become so impressive. At the same time, Micron is very pleased to have NVIDIA as a partner, because with the Pascal launch, the...
Read more...
Eventually we're going to see next-generation graphics cards outfitted with GDDR5X memory. It's a process getting to that point, and slowly but surely, things are moving along. To wit, JEDEC ratified the GDDR5X specification back in January of this year, and not even a full month later Micron announced that its GDDR5X program was in "full swing" with sampling to soon follow. Well, that time has come.We just got word straight from Micron that it has indeed started sampling GDDR5X memory to clients. That's a big deal because it's one of the last steps in the rather long process of introducing new technology into the consumer market. The next announcement you're likely to hear about GDDR5X memory...
Read more...
We have been hearing about the next iteration of DDR for graphics for the past handful of months, and now, the folks at JEDEC have made it official. Called GDDR5X (the full standard is called JESD232 GDDDR5X SGRAM), this memory is designed to be twice as fast as GDDR5 per clock, boasting total throughput rates of 14Gb/s per pin. With GDDR5, peak bandwidth was 8Gb/s, which required the memory to be run at 2GHz. NVIDIA's current top-end cards peak at 7Gb/s, with clock speeds of 1.75GHz. With GDDR5X, we can see performance of 10Gb/s - 2Gb/s better than the previous max - at 1.25GHz. That's 70% of the frequency for 125% of the performance - not too shabby. At the top end, GDDR5X can push 14Gb/s...
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...
This past summer, Intel and Micron jointly announced a new type of memory they call 3D XPoint. While new memory types seem to emerge all of the time, this one stood out based on the fact that it's being touted as 1,000x faster than NAND. It almost seems too good to be true, and I guess that's all it is until we begin to see production silicon trickle out onto the market. Nonetheless, Intel and Micron have just found themselves more competition with a duo involving SanDisk and HP. On the SanDisk side, the company has been tightly integrated into the memory and storage market for quite some time, and is one of the world's leaders in NAND production. To say it brings a lot to the partnership here...
Read more...
If you're planning to build a new system around one of Intel's new Skylake processors, you might as well go the distance and pick up a Z170-chipset motherboard that supports DDR4 memory. You'll find that there are plenty of memory kits to choose from, including Kingston Technology's brand new HyperX Savage. With a name like "Savage," you better bring fast speeds and aggressive timings, and that's exactly what Kingston does here. The HyperX Savage DDR4 line is available in speeds up to 3,000MHz with built-in XMP-ready profiles optimized for Intel Core i5 and Core i7 processors. "We are excited to present this new high speed, yet power efficient memory for those gamers and enthusiasts looking to...
Read more...
As smartphones equipped with 3 and 4GB of RAM begin to litter the market, developers need to figure out ways to take advantage of them. The same could be said for phones that have 8 CPU cores - we keep packing more and more horsepower into these mobile devices but largely fail to take advantage of it. Given the general use of such devices, I suppose that's not too much of a surprise. That reality doesn't matter to Samsung, though, as it's keen on keeping the train moving and always availing us more than what we need on the mobile front. In this particular case, that comes by way of brand-new 20nm 12Gb memory chips, ultimately making it possible for vendors to pack in a staggering 6GB of...
Read more...
With all the hype surrounding AMD's use of High Bandwidth Memory (HBM) for its Fury line of graphics card, you would be excused for thinking GDDR5 memory had died and become a footnote. You'd also be wrong. There's still more bandwidth to be squeezed out of GDDR5 memory, and that's what Micron has done. The Boise, Idaho-based memory maker announced today that the 8Gb (gigabit, not gigabyte) GDDR5 memory it was previously sampling to customers is now widely available. Compared to the current crop of 4Gb GDDR5 memory, the newly available 8Gb chips push the bandwidth ceiling from 7Gbps up to 8Gbps. The advancement also makes it possible to increase the frame buffer on graphics cards without jacking...
Read more...
"This is something many people thought was impossible," exclaimed Intel Senior Vice President Rob Crooke. During an invite-only press conference, Crooke along with Micron CEO Mark Durcan revealed a radically new class of storage and memory architecture called 3D XPoint (pronounced "Cross Point"). To say this is a game-changer would be the understatement of the year. Tangible products based on the technology will debut in 2016, but today's event was focused on the development partnership between Intel and Micron. Frankly, what they've accomplished is astounding. Even though we’re finally on the cusp of Solid State storage breaking into mainstream adoption (e.g. becoming more affordable and more...
Read more...
Researchers at MIT have come up with a new network design that exploits cheap, power-efficient flash memory without sacrificing the speed that supercomputing applications enjoy from Random Access Memory (RAM). What's appealing about the development is that flash memory is about ten times less expensive than RAM and consumes about a tenth as much power. The downside is that flash memory is only about a tenth as fast, though by utilizing MIT's new system, several common big data applications could use flash memory just as efficiently as conventional RAM. Not only that, the researchers presented evidence at the International Symposium on Computer Architecture that if servers executing a distributed...
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...
Depending on the "3D" we're talking about, it could either be amazing, or "meh". 3D gaming? Awesome. 3D movies? Meh. 3D memory? Incredible. Why? Because with 3D stacked memory technology instantly gives a hearty boost to both density and bandwidth. There's a reason both AMD and NVIDIA are going to be making use of 3D memory in their respective future graphics cards. To help put things into immediate perspective, take a look at the "gumstick" SSD in the shot above (the long card). Because of their 3D memory, Micron and Intel say that hitting 3.5TB on drives of this size will be possible. Meanwhile, our traditional 2.5-inch SSDs could surpass 10TB. This kind of storage is the kind of density you...
Read more...
Samsung announced today that it has begun volume production of its 8Gb LPDDR4 memory chips, with expected commercial shipments in 2015. The announcement is noteworthy for a number of reasons. First, one of the most important characteristics of a modern mobile device is its battery life, and moving to a new memory standard should significantly reduce the memory subsystem's power consumption. Second, however, there's the clock speed. Samsung is claiming that its LPDDR4 will hit 3.2GHz, and while bus widths on mobile parts are significantly smaller than the 64-bit channels that desktops use, the higher clock speed per chip will help close that gap. In fact, multiple vendors have predicted that LPDDR4...
Read more...
Every few months, some huge chipmaker comes out with yet another advancement in memory technology that makes it simpler to shove more and more memory into tighter and tighter spaces. That's what is happening this week with Samsung's announcement that it is "mass producing the industry’s most advanced 8-gigabit (Gb) DDR4 memory and 32-gigabyte (GB) module, both of which will be manufactured based on a new 20-nanometer (nm) process technology, for use in enterprise servers." With its new 8Gb DDR4, Samsung now offers a full line-up of 20nm-based DRAM to lead a new era of 20nm DRAM efficiency that also includes the 20nm 4Gb DDR3 for PCs and the 20nm 6Gb LPDDR3 for mobile devices. Using the...
Read more...
