It was a banner year for graphics, both in terms of market strength and technology advancements. Gaming, virtual reality, crypto mining, and artificial intelligence fueled demand for GPUs in 2017. The market responded with a wide array of products: high-performance discrete PC graphics cards that let gamers run multiple 4K displays; game consoles and VR headsets; and workstation-class GPUs that can build the stunning effects we have all come to expect. And since these products are full of our GDDR5 or G5X memory, it was an exciting year for Micron's graphics team too. We had a record-breaking year in GDDR5 shipments and further solidified Micron's industry leadership in graphics memory with the launch of our 12 Gb/s G5X, the highest-performance mass production GDDR memory.

INNO3D, a leading manufacturer of awesome high-end multimedia components and various innovations enriching your life, introduces its new P104-100 Crypto-Mining Accelerator. The new range will be available in TWIN X2 edition. The P104-100 has been designed with no less than 40% more mining power than its predecessor allowing the miner to enhance ETH, ZEC, etc. number crunching to levels, that have never been seen before. The freshly forged radical comes packed with 11 Gbps GDDR5X memory, and 4GB memory for optimizing cryptocurrency calculations. By deploying the INNO3D P104-100, miners now enjoy the ultimate power and utilize best-in-class hash rate today.

NVIDIA could severely limit the overclocking capabilities of its upcoming "almost GTX 1080" performance-segment graphics card, the GeForce GTX 1070 Ti. The company will tightly control the non-reference clock-speeds at which its add-in card (AIC) partners ship their custom-design graphics cards; and there could even be tighter limits to which you can overclock these cards. NVIDIA is probably doing this to ensure it doesn't completely cannibalize its GeForce GTX 1080 graphics card, which has been recently refreshed with faster 11 Gbps GDDR5X memory.

The GTX 1070 Ti is based on a "GP104" Pascal silicon with a core-configuration that's vastly higher than the current GTX 1070, and too close to that of the GTX 1080. It features 2,432 CUDA cores, just 128 fewer than the GTX 1080, and core clock speed of 1608 MHz that's on-par with the pricier card, too. The GPU Boost frequency is set to 1683 MHz, which is lower than the 1733 MHz of the GTX 1080. It also features slower GDDR5 memory. The GTX 1070 Ti is expected to launch by the 26th of October, priced at $429.

NVIDIA's upcoming GeForce GTX 1070 Ti performance-segment graphics card, which could be launched toward the end of this month, with market-availability following in early-November; could feature 9 Gbps GDDR5 memory, and not the previously-thought 8 Gbps GDDR5. This "almost-GTX 1080" answer of NVIDIA to AMD's RX Vega 56 features 2,432 CUDA cores, 152 TMUs, 64 ROPs, and a 256-bit wide GDDR5 memory interface, holding 8 GB of memory. It will be available at a price-point competitive with AMD's RX Vega series, and could come in custom-designs by NVIDIA's add-in card partners.

The GTX 1070 Ti will be NVIDIA's second SKU to max-out the GDDR5 clock band. The company had, in late-2016, refreshed the mid-range GeForce GTX 1060 6 GB to feature 9 Gbps memory in an effort to compensate for its narrower 192-bit wide memory interface, improving its competitiveness against the Radeon RX 480 8 GB. The company had also, at the time, refreshed the GTX 1080 with faster 11 Gbps GDDR5X memory, which means the GTX 1080 cards with the SKU's original 10 Gbps GDDR5X memory clock could be phased out of the market. NVIDIA will ride into the crucial Holiday 2017 season with its existing GeForce "Pascal" family, bolstered by the new GTX 1070 Ti.

Make every gaming session an immersive and thrilling experience with PNY GTX 1070 XLR8 Gaming Overclocked Edition. PNY Technologies (PNY) considered one of the worldwide leaders in consumer electronics market and flash memory products, has launched the GeForce GTX 1070 8GB XLR8 graphics card that transforms your PC into a super-charged gaming computer.

Designed specifically to support next-generation PC games, the GeForce provides real-time 4K graphics powered by the new NVIDIA Pascal architecture. The GeForce GTX 1070 is built with 8 GB GDDR5 memory clocked at 8 Gbps with data transfer rate of 256 GB/s and 256-bit wide memory bus which provides ultra-graphics settings for an outstanding performance and gaming experience. Enjoy smooth gameplay while playing the most challenging, graphics-intensive games without any interruption or glitches.

NVIDIA is readying a new GeForce GTX 1070 refresh graphics card, according to well-placed sources. Positioned between the current GTX 1070 and the GTX 1080 11 Gbps in performance, the refreshed GTX 1070 could at least displace the current GTX 1070 from its price-point, if not replace it. NVIDIA could carve the new chip out of the latest stepping of the GP104 silicon, and give it more CUDA cores, likely 2,048 (on par with GTX 1070 Mobile), if not higher. It could also get faster memory, likely 9 Gbps GDDR5 or even 10 Gbps GDDR5X. Its core and GPU Boost clock speeds could even be dialed up a little.

NVIDIA's objective here appears to be convincingly outperforming AMD Radeon RX Vega 56, at a lower power-draw. There's a 20 percent performance gap between the current desktop GTX 1070 and GTX 1080, and the new GTX 1070 refresh could find a price-performance equation somewhere in the middle. As NVIDIA's product-stack currently stands, the GTX 1080, which was refreshed with faster 11 Gbps GDDR5X memory, has a wider performance gap with the GTX 1070, creating room for a GTX 1070 refresh SKU somewhere in the middle, which could perform within the 90th percentile of the original GTX 1080 with 10 Gbps memory. What NVIDIA could name the SKU is anybody's guess. Historically, NVIDIA has updated SKU specifications without changing the name. The GTX 1080 and GTX 1060 6 GB were refreshed with faster memory, by simply prominently mentioning the memory clock below the SKU branding, there's also the remote possibility of the GTX 1070 Ti branding to combat the "grandeur" of AMD's RX Vega branding. NVIDIA could have the new GeForce GTX 1070 refresh SKU out in time for Holiday.

The DRAM industry is experiencing an acute shortage of various classes of GDDR memory (graphics DDR), which could affect graphics card prices come Holiday. Supplier quotes for various graphics memory components have risen by as much as 30.8% in August, from an average of USD $6.50 in July, to $8.50. Top graphics memory suppliers Samsung and SK Hynix have committed a bulk of their inventories to manufacturers of servers and mobile handsets, which triggered the price rally. Samsung is the largest supplier of graphics memory, with a 55 percent market-share, followed by SK Hynix at 35 percent, and Micron Technology at 10 percent.

Ah mining. The revival of an old craze. Who doesn't want to make their room's temperature increase to insane levels over the summer in order to cash in on the mining wagon? Who doesn't want to pull their hardware by the ankles and wrists, stretching it in utilization so as to maintain the PoW (proof of Work) cryptographic security in cryptocurrencies? Apparently, a not insignificant number of users and would-be miners does want that. That has, in turn, placed a whole lot of pressure on the graphics card market from both AMD and NVIDIA, with prices climbing and skyrocketing for graphics cards in the $200-$400 price ranges, as you know. It remains to be seen whether the flow of new miners decreases somewhat now, considering the recent market correction (read: dip) in the cryptocurrency market value (down around 42% from the all-time high of 357€ [~$400] of June 12th.)

After ASUS, it would seem like it's Sapphire's time to try and sway miners from their consumer-oriented, gaming graphics cards, through the launch of five different graphics cards models especially geared for mining. These are currently available for pre-order on Overclockers UK, and there are five different products in total, one based of RX 560 silicon, and four different takes on the RX 470 silicon (no, that's not a typo; it really is the 400 series.)

The lid was taken from Microsoft's Project Scorpio console last weekend. Commercially named the Xbox One X, the new Xbox console will join the "Xbox family of devices" with much higher power envelope than any other console currently in the market, at 6 TFLOPs of computing power. At that rate, Microsoft says (and has demonstrated) that its new console will be able to power premium, true 4K experiences. However, some analysts say that the $499 price point will be too high for consumers, which usually look to purchase consoles in the $249, $349 price band.

That said, the question could be put to Microsoft whether or not the company could have decreased their new console's pricing even further, by taking a cut from the hardware selling profits. When asked whether Microsoft was making any profit at all from the Xbox One X's retail pricing, Phil Spencer answered with a pretty frontal "No". So Microsoft really isn't profiting from the sale of any Xbox One X console, which may look somewhat unbelievable considering its steep price point (relatively; we have to keep in mind this console Can actually power 4K experiences.) However, this is nothing new: in fact, most gaming consoles ever released barely made any amount of money on hardware sales at the moment of their introduction to market. Manufacturers such as Microsoft and Sony instead usually choose to subsidize console purchases by bringing their profit margin to zero (and sometimes even below zero, as in, the consoles cost more to manufacture than their selling point) so as to allow a greater number of customers to purchase the hardware. Software, and more recently DLC, is where the money is to be made in consoles.

AMD has recently added two new offerings to their WX series of professional, workstation-oriented graphics cards. The WX 2100 and WX 3100 are entry-level offerings for the professional market, with 512 stream processors running at 1,219 MHz on a 14 nm graphics processor based on the Polaris architecture. The RX 2100 features 2GB of GDDR5 memory on a 64-bit interface; the RX 3100 doubles those figures to 4GB of memory on a 128-bit interface.

On performance, AMD said that the soon to be released WX 2100 and WX 3100 deliver up to 2x the performance of previous entry-level professional AMD graphics, and up to 28% faster performance than competing NVIDIA offerings. The WX 2100 is expected to cost $149, while the WX 3100 is expected to go for $199. AMD said the Radeon Pro WX 2100 and WX 3100 are both expected to launch in June; an exact date wasn't provided. The company also said both cards are covered by 24/7 customer support and a three-year limited warranty that can be extended up to seven years.

Micron, who has been at the forefront in graphics memory production, has recently announced in a blog post their commitment to achieving ever increasing speeds and performance gains with their products (which isn't all that uncommon.) What this announcement has that better carves it as different and newsworthy, though, is that the company has seemingly achieved 16 Gbps speeds on GDDR5X memory - which up to now, ticked at up to 12Gbps. Some NVIDIA cards you probably know about actually had their GDDR5X memory clocked up to 12.4 Gbps.

The new achievements under GDDR5X will aid the company in better executing their vision for GDDR6 and its speed goals. Micron expects to have functional silicon of their G6 program very soon, being confident they can push products to market on early 2018. GDDR6 will bring some specific differences in regards to GDDR5X, such as dual-channel memory (GDDR5X is single-channel) and the introduction of a FBGA180 ball package with increased pitch, to accommodate these fundamental differences.

Colorful Technology Company Limited, professional manufacturer of graphics cards and motherboards, announces its latest addition to the Colorful family of graphics cards with the COLORFUL GT1030 2G graphics card suited for office/home use.

The Colorful GT1030 2G ships with 384 Streaming Multiprocessors (SMs), and runs at a base clock frequency of 1227 MHz while the GPU Boost clock speed is rated for 1468 MHz and is based on the Pascal GP108 silicone. This card has been outfitted with GDDR5 memory at 2GB capacity and is wired to a 64-bit bus. The GPU has 24 TMUs, 8 ROPs and has a rated draw of 30 watts power consumption making the card a highly efficient choice. With an all-solid-state capacitor power delivery design, COLORFUL provides customers better and more stability while maintaining excellent performance. It has a 90mm fan and a solid cooler featuring compact thermal fins keeping the card cool even under extreme loads. No pricing information was disclosed at the time.

Remember that MX150 mobile graphics card we covered recently? NVIDIA has just let the cat out of the bag, with an announcement that seemingly confirms the specs we were expecting. NVIDIA is selling this mobile GPU's space as the expected IGP-upgrade, citing up to 3x superior performance-per-Watt compared to previous-generation Maxwell-based GeForce 940MX laptops. In other words, GeForce MX150 enables thinner laptops that run applications faster while sipping less power.

NVIDIA has quietly added a new product to its mobile catalog, the MX150. This tiny GPU is apparently based on the company's desktop GP108-based GT 1030, which has been recently launched in a bid to bridge the gap between IGP solutions and discrete-class graphics processors. In fact, this product looks to serve the ultrabook market with its modest power requirements, offering system integrators a new GPU which packs a lot more "oomph" than Intel's integrated graphics chips, while ensuring a considerable battery life.

This means that the MX150 is being geared not towards gamers (as the lack of a GeForce moniker already implies), but media consumption enthusiasts who demand more flexibility from their graphics adapters. For now, the only confirmed spec is a 2 GB GDDR5 memory pool, which is in line with the desktop GT 1030.

We got whiff of NVIDIA working on the GeForce GT 1030 close to a month ago. The smallest implementation of the "Pascal" GPU architecture is NVIDIA's answer to the AMD Radeon RX 550, and targets the entry-level graphics segment. It looks like product launches of the GeForce GT 1030 are just around the corner as pictures and specifications of various GT 1030 cards were leaked to the web. Below you'll see pictures of a selection of GIGABYTE and MSI GT 1030 graphics cards.

According to VideoCardz, the GT 1030 are based on the GP108-300 ASIC, featuring 384 CUDA cores, 24 TMUs, 8 ROPs, and 2 GB of GDDR5 memory across a 64-bit wide memory bus. With a TDP of just 35W, the GPU can power low-profile and completely fanless graphics cards, although for those who prefer their cards with elaborate fan-heatsink cooling solutions, there will be full-height cards as well.

ASUS has announced its take on the RX 550, the graphics card that is meant to bridge the gap between IGPs and the power reserved to discrete GPUs. Not much differs from other AIB offerings, since this is the same GPU paired with either 2 or 4 GB of GDDR5 memory ticking at 7,000 MHz over a 128-bit memory bus, but ASUS dis manage to add an IP5X-certified dust-proof fan. According to ASUS, this fan design extends the lifespan of the graphics card by 25% through increased dust and particle resistance, as well as efficient heat dissipation. The cards will come clocked at 1,100 MHz stock, and 1,183MHz boost clocks, with no auxiliary power connectors.

The ASUS Radeon RX 550 is a dual-slot design measuring 182 (length) x 112 (height) x 43mm (width), which delivers 1x Dual-Link DVI-D, 1x HDMI, and 1x DisplayPort connectors. These cards are produced using ASUS' Auto-Extreme manufacturing technology, which fully automates every step of PCB manufacturing and dispenses with human intervention. ASUS also bundles its GPU Tweak II and Xsplit Gamecaster software suites with the Radeon RX 550. These include the new "Gaming Booster"for automated overclocking, while XSplit Gamecaster lets gamers stream or record gameplay right from the in-game overlay. The ASUS Radeon RX 550 2GB / 4GB are available now from a variety of retailers for $90 / $100, respectively.

AIB partner for NVIDIA KFA2 is renowned for the design (often polarizing) of its graphics cards, and the company seems to carry white quite close to its heart (something I don't have a problem with, actually.) Now, the company has seemingly confirmed incoming retail availability of NVIDIA's leaked GT 1030 graphics cards, with an EXOC edition of the card in question.

The EXOC white edition by KFA2 is factory overclocked out of the box, and the packaging confirms its a 2GB GDDR5 model with 64-bit memory bus. According to the source, El Chapuzas Informatico, this card is equipped with a 16nm GP108 GPU with 384 CUDA cores (not the 512 we previously reported.) This makes sense, however, as this means NVIDIA can easily carve a GT 1040 SKU from the supposed 512 CUDA-cores base design of the GP108 chip. The base clock for the KFA2 GT 1030 EXOC is 1252 MHz, with a 1506 MHz boost clock. This card is expected to go on sale for around 80€ ($87 direct conversion, but more likely a $69 price-tag.)

Today AMD (NASDAQ: AMD) announced the world's first dual-GPU graphics card designed for professionals: the Polaris-architecture-based Radeon Pro Duo. Built on the capabilities of the Radeon Pro WX 7100, the Radeon Pro Duo professional graphics card is designed to excel at media and entertainment, broadcast, and design and manufacturing workflows, delivering outstanding performance and superior flexibility that today's creative professionals demand.

The Radeon Pro Duo is equipped with 32GB of ultra-fast GDDR5 memory to handle larger data sets, more intricate 3D models, higher resolution videos, and complex assemblies with ease. Operating at a max power of 250W, the Radeon Pro Duo harnesses a total of 72 compute units (4608 stream processors) for a combined performance of up to 11.45 TFLOPS of single-precision compute performance on one board, and twice the geometry throughput of the Radeon Pro WX 7100. The Radeon Pro Duo enables professionals to work up to four 4K monitors at 60Hz, drive the latest 8K single monitor display at 30Hz using a single cable, or drive an 8K display at 60Hz using a dual cable solution.

XFX has launched three variants of the RX 550 graphics cards, the tiny GPU that could, which AMD launched so as to bridge the enormous gap between IGP and its previous entry-line RX 460 (now RX 560) series of graphics cards. There are two low-profile versions of the RX 550, packing either 2GB or 4 GB of memory (whose amounts can be justified or not,) both with boost clocks set at 1203 MHz and 7000 MHz GDDR5 memory over a 128-bit bus. There is also a full-profile, dual slot RX 550, dubbed the Core Edition, and another Core Edition, though this one is a full-profile, single-slot solution.

All of these pack the same 1203 MHz boost clocks, so XFX is basically telling you to pick and choose the size of the graphics cards that best fits your use case, with improvements on cooling and sound profile that come with the larger, beefier cooling solutions. Display outputs stand the same among all the different cards, with 1x DVI-I Dual-Link, 1x DisplayPort, and 1x HDMI 2.0.

So, it would appear that rumors and leaks about the RX 500 series being simple rebrands of AMD's RX 400 line were true. Recent leaks point to no more changes and performance increases than those achieved through higher base clock speeds on the graphics cards' GPU and memory. The architecture is the same, and the process seems to have followed the same path - as of yet, no confirmation regarding whether or not these cards do use a newer, leaner LPP process for higher clocks and less power consumption.

ASUS today introduced revised versions of its GeForce GTX 1080 (non-Ti) STRIX and 6 GB GTX 1060 STRIX OC Edition graphics cards, featuring faster memory, as promised by NVIDIA during its GTX 1080 Ti launch. The GTX 1080 STRIX OC now comes with 11 Gbps GDDR5X memory and the 6 GB GTX 1060 STRIX OC with 9 Gbps GDDR5. To avoid bait-and-switch complaints from the retail market, these cards are clearly designated from their 10 Gbps and 8 Gbps siblings, in the model numbers, and in the prominent GPU SKU branding. The GTX 1080 STRIX OC is labelled "ROG-STRIX-GTX1080-O8G-11GBPS," and the GTX 1060 6 GB STRIX OC "GTX1060-O6G-9GBPS."

The two cards use revised GDDR5X and GDDR5 memory chips that can sustain their memory chips thanks to improvements in the memory controller end by NVIDIA. At 11 Gbps, the GTX 1080 now has a memory bandwidth of 352 GB/s, while the GTX 1060 has 216 GB/s bandwidth with 9 Gbps memory over its 192-bit wide memory bus. The new GTX 1080 STRIX OC also comes with "max-contact" heatsink base the company introduced with its GTX 1080 Ti STRIX. The company didn't reveal pricing.

Reports are going around that AMD's smallest-ever Polaris chip has been seen on the OpenCL pages of CompuBench. Based on a new Polaris 12 GPU (or should it be Polaris 22?), this is a chip which is likely to power an even lower-end of the spectrum than what AMD's RX 460 (and upcoming RX 560 rebrands) already does.

Polaris 12 apparently features 10 Compute Units, which amounts to 640 Stream Processors. Remember that AMD's Polaris 11 chip which powers the RX 460 actually has 1024 stream processors, though only 896 are available for access on retail versions of the card (though some magickery can unlock those latent stream processors.) This means that Polaris 12 essentially packs half as many shaders as Polaris 11 does. The 640 Stream Processors are expected to be clocked at 1302 MHz, and the cards will reportedly ship with up to 4 GB of GDDR5 memory. Expect cards based on this GPU to sell below the RX 460's $99.

At their GDC event yesterday, NVIDIA announced a change to how partners are able to outfit their GTX 1080 and GTX 1060 6 GB models in regards to video memory. Due to improvements in process and scaled-down costs, NVIDIA has decided to allow partners to purchase 11 Gbps GDDR5X (up from 10 Gbps) and 9Gbps (up from 8 Gbps) GDDR5 memory from them, to pair with the GTX 1080 and GTX 1060 6 GB, respectively. These are to be sold by NVIDIA's AIB partners as overclocked cards, and don't represent a change to the official specifications on either graphics card. With this move, NVIDIA aims to give partners more flexibility in choosing memory speeds and carving different models of the same graphics card, with varying degrees of overclock, something which was particularly hard to do on conventional 10 Gbps-equipped GTX 1080's, which showed atypically low memory overclocking headroom.

After finally reaching mature yields (comparable to those of planar NAND processes), Micron's 32-layer first generation 3D NAND has grown increasingly prominent in the company's NAND output. Now, the company is looking to ramp-up production of their (currently sampling) 64-layer 3D NAND, promising "meaningful output" by the end of December 2017, looking for an 80% increase in total GB per wafer and a 30% decrease in production costs.

When it comes to the graphics subsystem memory, Micron is looking to transition their 20nm production to a "1x nm" (most likely 16nm) node, in a bid to improve cost per GB by around $20, with introduction of 16nm GDDR5 memory to be introduced later this year. However, GDDR5X volume is expected to grow significantly, in a bid to satisfy bandwidth-hungry uses through GPUs (like NVIDIA's GTX 1080 and potentially the upcoming 1080 Ti) and networking, with GDDR6 memory being introduced by the end of 2017 or early 2018. The company is still mum on actual consumer products based on their interpretation of the 3D XPoint products through their QuantX brand, though work is already under way on the second and third generation specifications of this memory, with Micron planning an hitherto unknown (in significance and product type) presence in the consumer market by the end of this year.

Joining in on other manufacturer's offerings for low-profile graphics solutions for HTPCs and other small fomr factor PCs, GALAX has recently announced that they too will be offering low-profile variants of the GTX 1050 and GTX 1050 Ti graphics cards. With 2 GB and 4 GB of GDDR5 at 7 Gbps respectively, both over a 128 bit bus, both cards make do without any additional power connectors, making do with exclusive power delivery from the PCIe socket.

The core clocks are set at 1303 MHz and 1366 MHz base clocks for the 1050 and the 1060 Ti respectively, with boost clocks seeing a healthy (but somewhat traditional)n uplift to 1417 Mhz and 1468 Mhz. As to connectors, both cards carry 1x DisplayPort 1.4, 1x DVI-D, and 1x HDMI 2.0b. Considering the cards' characteristics, they probably won't be sold much higher than NVIDIA's reference MSRP for both cards: $139 for the GTX 1050 Ti and $109 for the GTX 1050.