NVIDIA's more economically significant graphics card based on the "Pascal" architecture, the GeForce GTX 1070, goes on sale from today (10/06). The card starts at US $379, with NVIDIA selling the reference-design board for a $70 premium, as the GTX 1070 Founders Edition, priced at $449. With NVIDIA claiming performance levels higher than the previous-generation $999 GeForce GTX Titan X, the GTX 1070 could prove to be the gateway to 4K Ultra HD gaming with reasonably high eye-candy.

Based on the 16 nm "GP104" silicon, the GeForce GTX 1070 features 1,920 CUDA cores, 120 TMUs, 64 ROPs, and a 256-bit GDDR5 memory interface, holding 8 GB of memory. The core ticks at 1506 MHz, with a GPU Boost frequency of 1683 MHz, while the memory runs at 2000 MHz (actual), 8 GHz (GDDR5-effective), yielding a memory bandwidth of 256 GB/s. Display outputs include three DisplayPort 1.4, one HDMI 2.0b, and a dual-link DVI-D.

NVIDIA's upcoming GeForce GTX 1070 graphics card, which NVIDIA is pinning its summer upgrade revenue on, is shaping up to be faster than the previous-generation enthusiast GeForce GTX TITAN X. 3DMark FireStrike numbers scored by VideoCardz reveal that averaged across three popular resolutions - 1080p (FireStrike standard), 1440p (FireStrike Advanced), and 4K (FireStrike Ultra), the GTX 1070 is about 3 percent faster than the GTX TITAN X.

At FireStrike (standard), the GTX 1070 scored 17557 points, versus 17396 points of the GTX TITAN X; 8327 points at FireStrike Advanced against 7989; and 4078 points at FireStrike Ultra against 3862, respectively. The performance lead is highest at 4K Ultra HD. Based on the 16 nm GP104 silicon, the GeForce GTX 1070 features 1,920 CUDA cores, 120 TMUs, and 8 GB of GDDR5 memory clocked at 8.00 GHz (256 GB/s). The MSRP for this SKU is set at $379, although its reference design board will be sold at a $70 premium, for $449, when the card goes on sale this 10th June.

Here are some of the first pictures of the reference GeForce GTX 1080 PCB. NVIDIA is selling the reference-design card at a $100 premium, branded as "Founders Edition." Pictures reveal the PCB to be less crowded than the GTX 980 reference PCB. The PCB appears to feature a 6-phase VRM with DrMOS chips, drawing power from a single 8-pin PCIe power connector; the 16 nm GP104 ASIC, with a smaller die than the one featured on the 28 nm GM204, neighbored by eight 8 Gbit GDDR5X memory chips, which feature smaller packages than the ones GDDR5 chips usually come in. We wish someone zoomed in on its VRM controller.

After launching its shockingly fast (claimed) GeForce GTX 1080 and GTX 1070 graphics cards, NVIDIA posted specifications of the former. The two are based on NVIDIA's swanky new 16 nm "GP104" silicon, derived from its "Pascal" GPU architecture. The architecture is detailed in our older article, here. The GeForce GTX 1080 leads the pack, featuring four graphics processing clusters, holding 2,560 CUDA cores. The core runs at a scorching 1607 MHz, with a GPU Boost frequency of 1733 MHz. In one of its demos, NVIDIA overclocked this chip to over 2100 MHz, on its reference air cooling, and the GPU barely scraped 67 °C under stress. The GTX 1080 features a 256-bit wide GDDR5X memory interface, holding 8 GB of memory. The memory is clocked at 2500 MHz (10 GHz effective), working out to a memory bandwidth of 320 GB/s.

API support includes DirectX 12 (feature-level 12_1), OpenGL 4.5, and Vulkan. Display outputs include three DisplayPort 1.4 connectors, one HDMI 2.0b, and one dual-link DVI. The reference-design card is 10.5-inch long, and double-slot. It draws power from a single 8-pin PCIe power connector, and its typical board power is rated at 180W. With the GeForce "Pascal" family, instead of caving in to DirectX 12 native multi-GPU, NVIDIA developed its SLI technology further, with the new SLI HB (high-bandwidth) bridge standard. It's essentially a 2-way bridge in which both SLI fingers of the card are used. This doubles bandwidth between the two cards, allowing higher display resolutions, and multi-display setups between high-resolution monitors. The GeForce GTX 1080 will be available from May 27, 2016, starting at US $599. The $379 GTX 1070 specifications will be revealed closer to its June 10, 2016 market availability.

Hot on the heels of the GeForce GTX 1080, the company also announced its second fastest GPU, the GeForce GTX 1070. Based on the same 16 nm GP104 silicon as the GTX 1080, the GTX 1070 features 8 GB of GDDR5 memory, and has 3 quarters the single precision performance (6.5 TFLOP/s vs. 9 TFLOP/s) of the GTX 1080. NVIDIA claims that just as the GTX 1080 is faster than the GTX 980 SLI, the GTX 1070 is faster than the GTX TITAN X, making it the second fastest GPU in existence. Available on June 10, the GTX 1070 will be priced at US $379, with a "founder's edition" (reference-design) card going for $449.

NVIDIA announced its next-generation GeForce GTX 1080 graphics card. Based on the "Pascal" architecture, this chip is built on the 16 nm FinFET process. It uses GDDR5X memory at 10 GHz (GDDR5-effective) clock speed. NVIDIA announced major improvements to the VRM that drives graphics cards, that increases switching efficiency. NVIDIA announced that the GeForce GTX 1080 is faster than a GeForce GTX 980 SLI, and a GeForce GTX TITAN X. The air-cooled GTX 1080 runs at a very high clock speed or 2.11 GHz, with 10 GHz memory clocks, at a temperature of 67 degrees C. Available on May 27, it's priced at $599.More pictures after the break.

In all the 16 nm NVIDIA "Pascal" GPU fervor, it would be foolish to ignore AMD's first "Polaris" GPUs, built on the more advanced 14 nm process. Hot on the heels of reports that a fully-equipped "Ellesmere" GPU based Radeon R9 490 performs close to NVIDIA's GeForce GTX 980 Ti (and AMD's own R9 Fury X), with nearly half its power-draw, new numbers from an early GFXBench run suggests that its cut-down R9 480 (non-X) sibling performs close to the Radeon R9 390X. The R9 480 succeeds the currently-$200 R9 380, and its prospect of offering performance rivaling the $400 R9 390X at half its power-draw appears to meet AMD's "generational leap" claims for the "Polaris" architecture. Similarly, the R9 490, based on a better-endowed "Ellesmere" chip, offering performance rivaling current $600 GPUs at a $350-ish price-point (succeeding the R9 390), appears to meet expectations of a generation leap.

Taiwan's premier semiconductor foundry TSMC could begin 7 nanometer (nm) trial production in as early as the first half of 2017. Co-CEO Mark Liu, speaking at the company's investor-meet held earlier this month, stated that TSMC is currently engaging with over 20 companies on 7 nm development, with over 15 tape-outs within 2017, leading up to volume-production by early-2018. In the run-up to 7 nm, the company is also developing a 10 nm node for lower-powered devices (eg: mobile baseband). The company has already begun tape-outs of 10 nm chips in Q1-2016. TSMC is currently handling volume-production of 16 nm FinFET Plus chips.

NVIDIA is reportedly giving final touches to no less than three SKUs based on the 16 nm GP104 silicon, to launch some time this June. The ASIC markings for the chips that drive these SKUs are "GP104-400-A1," "GP104-200-A1" and "GP104-150-A1." If you recall, NVIDIA last reserved the "-400-A1" markings for the GeForce GTX 980 (GM204-400-A1), and the "-200-A1" for the GTX 970 (GM204-200-A1).

The GP104-150-A1 is a mystery ASIC. Either it will drive a more affordable third desktop SKU based on the GP104, or could signify a mobile SKU. The company plans to launch the products based on the GP104-400-A1 and GP104-200-A1, logical successors to the GeForce GTX 980 and GTX 970, in early June. The GP104-150-A1, on the other hand, could see the light of the day in mid-June.

NVIDIA unveiled the Tesla P100, the first product based on the company's "Pascal" GPU architecture. At its core is a swanky new multi-chip module, similar in its essential layout to the AMD "Fiji." A 15 billion-transistor GPU die sits on top of a silicon wafer, through which a 4096-bit wide HBM2 memory interface wires it to four 3D HBM2 stacks; and with the wafer sitting on the fiberglass substrate that's rooted into the PCB over a ball-grid array. With the GPU die, wafer, and memory dies put together, this package has a cumulative transistor count of 150 billion transistors. The GPU die is built on the 16 nm FinFET process, and is 600 mm² in area.

The P100 sits on top of a space-efficient PCB that looks less like a video card, and more like a compact module that can be tucked away into ultra-high density supercomputing cluster boxes, such as the new NVIDIA DGX-1. The P100 offers a double-precision (FP64) compute performance of 5.3 TFLOP/s, FP32 performance of 10.6 TFLOP/s, and FP16 performance of a whopping 21.2 TFLOP/s. The chip has registers as big as 14.2 MB, and an L2 cache of 4 MB. In addition to PCI-Express, each P100 chip will be equipped with NVLink, and in-house developed high-bandwidth interconnect by NVIDIA, with bandwidths as high as 80 GB/s per direction, 160 GB/s both directions. This allows extremely high-bandwidth paths between GPUs, so they could share memory and work more like single-GPUs. The P100 is already in volume production, with its target customers already having bought it all the way up to its OEM channel availability some time in Q1-2017.

With the GeForce GTX 900 series, NVIDIA has exhausted its GeForce GTX nomenclature, according to a sensational scoop from the rumor mill. Instead of going with the GTX 1000 series that has one digit too many, the company is turning the page on the GeForce GTX brand altogether. The company's next-generation high-end graphics card series will be the GeForce X80 series. Based on the performance-segment "GP104" and high-end "GP100" chips, the GeForce X80 series will consist of the performance-segment GeForce X80, the high-end GeForce X80 Ti, and the enthusiast-segment GeForce X80 TITAN.

Based on the "Pascal" architecture, the GP104 silicon is expected to feature as many as 4,096 CUDA cores. It will also feature 256 TMUs, 128 ROPs, and a GDDR5X memory interface, with 384 GB/s memory bandwidth. 6 GB could be the standard memory amount. Its texture- and pixel-fillrates are rated to be 33% higher than those of the GM200-based GeForce GTX TITAN X. The GP104 chip will be built on the 16 nm FinFET process. The TDP of this chip is rated at 175W.

It looks like NVIDIA's next GPU architecture launch will play out much like its previous two generations - launching the second biggest chip first, as a well-priced "enthusiast" SKU that outperforms the previous-generation enthusiast product, and launching the biggest chip later, as the high-end enthusiast product. The second-biggest chip based on NVIDIA's upcoming "Pascal" architecture, the "GP104," which could let NVIDIA win crucial $550 and $350 price-points, will be a lean machine. NVIDIA will design the chip to keep manufacturing costs low enough to score big in price-performance, and a potential price-war with AMD.

As part of its efforts to keep GP104 as cost-effective as possible, NVIDIA could give exotic new tech such as HBM2 memory a skip, and go with GDDR5X. Implementing GDDR5X could be straightforward and cost-effective for NVIDIA, given that it's implemented the nearly-identical GDDR5 standard on three previous generations. The new standard will double densities, and one could expect NVIDIA to build its GP104-based products with 8 GB of standard memory amounts. GDDR5X breathed a new lease of life to GDDR5, which had seen its clock speeds plateau around 7 Gbps/pin. The new standard could come in speeds of up to 10 Gbps at first, and eventually 12 Gbps and 14 Gbps. NVIDIA could reserve HBM2 for its biggest "Pascal" chip, on which it could launch its next TITAN product.

NVIDIA is reportedly planning to unveil its next-generation GeForce GTX "Pascal" GPUs at the 2016 Computex show, in Taipei, scheduled for early-June. This unveiling doesn't necessarily mean market availability. SweClockers reports that problems, particularly related to NVIDIA supplier TSMC getting its 16 nm FinFET node up to speed, especially following the recent Taiwan earthquake, could delay market available to late- or even post-Summer. It remains to be seen if the "Pascal" architecture debuts as an all-mighty "GP100" chip, or a smaller, performance-segment "GP104" that will be peddled as enthusiast-segment over being faster than the current big-chip, the GM200. NVIDIA's next generation GeForce nomenclature will also be particularly interesting to look out for, given that the current lineup is already at the GTX 900 series.

Taiwan's premier semiconductor foundry, TSMC, announced that it is on track to begin production of chips on its 7 nanometer silicon fab process by the first half of 2018. The company also announced that production on an even newer 5 nanometer process should commence two years later, in 2020. The company has currently cleared all decks for mass-production of chips on its 16 nm FFC (FinFET compact) node, with the company hoping to grab over 70% of the worldwide 14/16 nm production market-share by the end of 2016.

NVIDIA's next-generation flagship graphics processor, codenamed "GP100," has reportedly graduated to testing phase. That is when a limited batch of completed chips are sent from the foundry partner to NVIDIA for testing and evaluation. The chips tripped speed-traps on changeover airports, on their way to NVIDIA. 3DCenter.org predicts that the GP100, based on the company's "Pascal" GPU architecture, will feature no less than 17 billion transistors, and will be built on the 16 nm FinFET+ node at TSMC. The GP100 will feature an HBM2 memory interface. HBM2 allows you to cram up to 32 GB of memory. The flagship product based on GP100 could feature about 16 GB of memory. NVIDIA's design goal could be to squeeze out anywhere between 60-90% higher performance than the current-generation flagship GTX TITAN-X.

NVIDIA's next-generation GPUs, based on the company's "Pascal" architecture, will be reportedly built on the 16 nanometer FinFET node at TSMC, and not the previously reported 14 nm FinFET node at Samsung. Talks of foundry partnership between NVIDIA and Samsung didn't succeed, and the GPU maker decided to revert to TSMC. The "Pascal" family of GPUs will see NVIDIA adopt HBM2 (high-bandwidth memory 2), with stacked DRAM chips sitting alongside the GPU die, on a multi-chip module, similar to AMD's pioneering "Fiji" GPU. Rival AMD, on the other hand, could build its next-generation GCNxt GPUs on 14 nm FinFET process being refined by GlobalFoundries.

Plextor announced availability of its entry-level SATA 6 Gb/s SSD, the M6V series. The drives are offered in the 7 mm-thick 2.5-inch, M.2 (as M6GV series), and mSATA (as M6MV) form-factors; and in capacities of 128 GB, 256 GB, and 512 GB. It combines a Silicon Motion SMI-2246 controller with Toshiba 16 nm Toggle NAND flash memory. The 2.5-inch variant offers PlexTurbo technology, which speeds up sequential transfer-rates.

The 128 GB variant features 128 MB of DRAM cache, with sequential speeds of up to 535 MB/s reads, with up to 170 MB/s writes. The 256 GB variant, which comes with a larger 256 MB DRAM cache, offers up to 535 MB/s reads, with up to 335 MB/s writes. The 512 GB variant leads the pack, with a 512 MB DRAM cache, up to 535 MB/s reads, and up to 455 MB/s writes. 4K random-access performance for the three are in the range of 83,000 IOPS reads, with up to 80,000 IOPS writes. The 128 GB variant is priced at 69€, the 256 GB variant 115€, and the 512 GB variant 245€ (all prices include VAT).

Today, Micron Technology, Inc. announced a new addition to its expansive portfolio of flash storage products, providing a purpose-built solution for cost-sensitive consumer applications seeking high performance and reliability. The new TLC NAND is built on their 16-nanometer (nm) process and delivers a balanced set of features for applications like USB drives and consumer solid state drives. The market appetite for TLC is projected to be strong throughout 2015, constituting almost half of the total NAND gigabytes shipped.

Micron's 16 nm process-recognized by TechInsights as the Most Innovative Memory Device and 2014 Semiconductor of the Year-is a mature and proven storage technology, making it an excellent foundation for a reliable TLC design. TLC, or triple-level cell, is a technology that fits three bits in every flash data cell, creating greater cost and size efficiency. Customers of the technology will benefit from Micron's extensive design support team, who act as trusted advisors to ensure smooth qualification and optimal end-solution performance. Key flash customers and ecosystem partners worldwide have already begun working to integrate this new NAND with their latest designs, ensuring quick adoption in end applications.

SK Hynix Inc. announced it has developed UFS (Universal Flash Storage) 2.0 64 GB (Gigabytes) solution based on its own 16 nm NAND Flash and in-house firmware and controller. This UFS 2.0 represents a groundbreaking leap in performance by enabling High-Speed Gear 3 interface with dual data lanes.

UFS 2.0 is the next generation of embedded flash memory to eMMC for mobile IT gadgets which drives a remarkable boost in reading/writing speed at low power and supports high density. The Company's UFS 2.0 operates at 780 MB/s(Megabytes per second) and 160 MB/s of sequential read/write speed and runs random read/write speed at 32,000 IOPS and 17,000 IOPS. As a result, it works three times faster in read speed than eMMC 5.1.

In addition, this UFS 2.0 utilizes 'Command Queue' technology used in SSD solutions to handle read and write commands simultaneously to achieve data operation efficiency by preventing buffering load in multi-tasking and ordering priorities of data works. To maximize prioritized command processing feature of UFS standard, the device employs 'Multi-Thread' read processing internally to ensure that high priority command is serviced first irrespective of other outstanding tasks, delivering fast response to time-critical host requests for best user experience. In consequence, it realizes even better performance in speed and power consumption over eMMC.

Silicon Motion Technology Corporation, a global leader in designing and marketing NAND flash controllers for solid state storage devices, today announced that its SM2256 SATA (6 Gb/s) client SSD controller now supports Micron's new 16 nm 128 gigabit (Gb) TLC NAND flash, enabling high-performance and unprecedented reliability for a new class of cost-effective TLC-based SSDs.

SM2256, the world's first SSD controller supporting Micron's 16nm TLC NAND, offers the best performance and cost-optimized four channel SATA 6 Gb/s client SSD controller in the market. Using Micron's 128 Gb 16 nm TLC NAND, the SM2256 delivers up to 540 MB/s sequential read performance and 460 MB/s sequential write, as well as up to 90,000 random read IOPS and 80,000 random write IOPS. Leveraging Silicon Motion's proprietary NANDXtend error-correcting code (ECC) technology, the SM2256 enhances the endurance and retention of TLC NAND, delivering more than three times better reliability for TLC SSD as compared to the existing BCH ECC schemes.

Faced with continuous development roadblocks with TSMC, AMD is reportedly planning to switch to the 28 nm SHP process of GlobalFoundries, to build GPUs in 2015. The 28 nm SHP (super high-performance) node will allow the company to lower voltages, giving it greater room to increase clock speeds of its upcoming GPUs. AMD's GPUs in 2015 could be based on its latest Graphics CoreNext 1.2 architecture, and AMD needs every means to minimize voltages, and crank up clock speeds.

The company hasn't abandoned TSMC completely just yet, with reports speaking of AMD using the Taiwanese fab's 16 nm FinFet node to manufacture its next-generation "Zen" CPUs. Zen is the successor to AMD's "Bulldozer" architecture and its derivatives ("Piledriver" and "Steamroller.") It could feature a radically different core design.

An OEM for notable SSD brands such as Plextor, LiteOn kicked off its own consumer SSD line, with ZETA. Built in the 7 mm thick, 2.5-inch form-factor, with SATA 6 Gb/s interface, these drives come in three capacities, 128 GB (LCH-128V2S), 256 GB (LCH-256V2S), and 512 GB (LCH-512V2S), featuring LPDDR3 controller cache of 128 MB, 256 MB, and 512 MB, respectively. The drive is based on Silicon Motion SM2246EN controller, with 16 nm MLC NAND flash, made by SK Hynix.

All three capacities offer sequential read speeds of up to 520 MB/s, differing with sequential write speeds. The 128 GB variant offers up to 150 MB/s writes, the 256 GB variant offers up to 260 MB/s, and the 512 GB variant up to 430 MB/s. Their 4K random-access read speeds are up to 67,500 IOPS, up to 82,500 IOPS, and up to 83,500 IOPS, respectively; and random-access write speeds are up to 37,500 IOPS, up to 72,500 IOPS, and up to 80,000 IOPS, respectively. Most common client SSD features, such as TRIM, NCQ, and 256-bit AES native encryption, are part of the package. LiteOn didn't announce pricing information for markets outside the Greater China region, where the drives will make their debut.

Patriot's upcoming line of performance 2.5-inch SSDs, the Patriot Torch, got listings on Amazon, ahead of its launch. These 7 mm-thick, 2.5-inch drives, with SATA 6 Gb/s interfaces, come in two capacities (for now), 120 GB and 240 GB. Under the hood, they feature 16 nm synchronous MLC NAND flash, and Phison PS3110 controllers. The 240 GB variant offers sequential transfer rates of up to 555 MB/s reads, with 535 MB/s writes; while the 120 GB variant offers 545 MB/s reads, with 430 MB/s writes. The 240 GB variant is priced at US $106.11, while the 120 GB variant goes for $66.63.

Micron Technology, Inc., today announced a next-generation, client-class solid state drive (SSD) that sets a new bar for low-power, high-performance storage for personal computers. The M600 SATA SSD - specifically designed to take advantage of Micron's leading-edge NAND Flash technology - addresses the storage demands of modern mobile computing applications, including Ultrabook platforms and tablets, as well as performance-oriented PC desktops and video capture systems.

"Storage is an important enabler for ultrathin designs in personal portable computing devices," said Greg Wong, founder and principal analyst at Forward Insights. "Micron's M600 delivers the power efficiency and performance that helps to enable instant-on performance and responsiveness as well as the all-day battery life demanded by next-generation computing systems."

TSMC may lose out on orders to competing fabs on the 16 nanometer (nm) and 14 nm nodes, in terms of market share, in 2015, according to company chairman Morris Chang. Chips built on the 16 nm node will amount to single-digit percentages of the company's output in the year. Samsung Electronics is expected to take the lead on these processes, as it just netted orders from Qualcomm, a major mobile baseband chip and SoC designer.

Chang stressed that 20 nm and 16 nm will drive revenue for the next three years for major fabs. 20 nm products will account for 10 percent of TSMC's revenues in Q3 2014, will expand to 20 percent in Q4, and contribute over 20 percent of TSMC's revenues in 2015. TSMC's 16 nm node will be competitive for products such as mobile baseband chips, ICs, GPUs, NICs, and server chips. Despite these setbacks in the company's competitive outlook, it expects its revenues to grow by 12.6 to 14.2 percent sequentially in Q3 2014, year over year.