TSMC has been the backbone of silicon designers for a long time. Whenever you question where you can use the latest technology and get some good supply capacity, TSMC got everyone covered. That case seems to be similar to Intel and its struggles. When Intel announced that its 7 nm semiconductor node is going to be delayed a full year, the company's customers and contractors surely became worried about the future releases of products and their delivery, like the case is with Aurora exascale supercomputer made for Argonne National Laboratory, which relies on Intel's 7 nm Ponte Vecchio graphics cards for most of the computation power.

To manage to deliver this, Intel is reportedly in talks with TSMC to prepare capacity for the GPUs and deliver them on time. However, according to industry sources of DigiTimes, TSMC is unlikely to build additional capacity for Intel, besides what it can deliver now. According to those sources, TSMC does not see Intel as a long-term customer and it is unknown what treatment will Intel get from TSMC. Surely, Intel will be able to make a deal with TSMC and secure enough of the present capacity for delivering next-generation processors.

MSI has found some ways to reduce pricing on their Radeon RX 5600 XT Gaming X series, and has materialized these savings on a new product. The RX 5600 XT Gaming M(X) sees itself as a lower-priced variant of the card, featuring 14 Gbps GDDR6 memory and making use of a cooler that is more alike the Armor series we know from the RX 580 models.

The new graphics card still features a dual-fan cooling solution, dual 8-pin power connectors, and I/O is assured by 3x DisplayPort and 1x HDMI. The Gaming M features slightly lower clocks than the Gaming or Gaming X series: 1130 MHz Base, 1375 MHz Game, and 1560 MHz Boost clocks is the quoted transistor ticking speed. The packaging still features the red stylized X employed on MSI's Gaming X series though, which may cause some confusion when it comes to shop around.

In a move that shocks no-one, considering the wealth of RTX features that Death Stranding will be supporting on PC, NVIDIA has announced it will be offering Kojima Productions' game with their RTX graphics cards. This offer is available for all RTX graphics cards, mind you, from the RTX 2060 all the way to the top of NVIDIA's RTX stack in the form of the RTX 2080 Ti.

The promotion includes both standalone RTX graphics cards and pre-built systems packing RTX graphics. The promotion starts from today and is valid for purchases through July 29th (you have until August 31st to redeem the digital game code), so if you're looking for a new graphics card ASAP and you're also looking for a beautiful walking simulator (though the game really does merit more than just that simplistic definition), you might want to jump on this opportunity.

NVIDIA is slowly preparing to launch its next-generation Ampere graphics cards for consumers after we got the A100 GPU for data-centric applications. The Ampere lineup is getting more and more leaks and speculations every day, so we can assume that the launch is near. In the most recent round of rumors, we have some new information about the GPU SKU and memory of the upcoming GeForce RTX 3070 and RTX 3070 Ti. Thanks to Twitter user kopite7kimi, who had multiple confirmed speculations in the past, we have information that GeForce RTX 3070 and RTX 3070 Ti use a GA104 GPU SKU, paired with GDDR6 memory. The cath is that the Ti version of GPU will feature a new GDDR6X memory, which has a higher speed and can reportedly go up to 21 Gbps.

The regular RTX 3070 is supposed to have 2944 CUDA cores on GA104-400 GPU die, while its bigger brother RTX 3070 Ti is designed with 3072 CUDA cores on GA104-300 die. Paired with new technologies that Ampere architecture brings, with a new GDDR6X memory, the GPUs are set to be very good performers. It is estimated that both of the cards would reach a memory bandwidth of 512 GB/s. So far that is all we have. NVIDIA is reportedly in Design Validation Test (DVT) phase with these cards and is preparing for mass production in August. Following those events is the official launch which should happen before the end of this year, with some speculations indicating that it is in September.

Embedded, GPU-accelerated computing is the use of a graphics processing unit (GPU) combined with a central processing unit (CPU) to facilitate advanced computing processes such as Artificial Intelligence of Things (AIoT), Deep Learning, Prototyping/Pre-concept design, CUDA development and medical Hi-Res imaging, to name a few.

Embedded, GPU-accelerated computing is gaining popularity as its potential becomes realized in many high-tech labs and R&D facilities around the world. GPU-accelerated computing plays a huge role in accelerating applications in platforms within these bleeding-edge industries. Whether it is designing self-driving cars, rendering ultra-HD scenes with millions of polygons (4K and above), or working with advanced CAD models for GIS mapping, a multi-GPU system will significantly increase the performance and capabilities advanced developers have available.
Through embedded GPU-accelerated technology, processing and computing times can be cut into a fraction of the time of what could be accomplished compared to traditional, less-sophisticated computing infrastructures. The combination of high-performance computing along with lower power consumption can result in a more significant and more extensive deep learning in neural networks.

The leading global motherboard, graphics card and mini PC manufacturer, ASRock, has launched new Radeon RX 5600 XT Challenger Pro 6G OC three-fan graphics card. The Radeon RX 5600 XT Challenger Pro 6G OC features ASRock's new styled shroud design with upgraded cooling fins, AMD's second-generation Radeon RX 5600 XT 7 nm GPU, plus 6 GB 192-bit GDDR6 memory and PCI Express 4.0 bus. The ASRock Radeon RX 5600 XT Challenger Pro 6G OC graphics card provides excellent overclocking settings, which enables users to enjoy a smooth 1080p gaming experience.

The ASRock Radeon RX 5600 XT Challenger Pro 6G OC adopts AMD's second-generation Radeon RX 5600 XT GPU. With factory default GPU base/game/boost clock settings, this new graphics card can reach 1420/1615/up to 1750 MHz respectively. The boost clock setting is 4% higher than the AMD's standard settings. Furthermore, the clock frequency of GDDR6 memory is set as 1750 MHz, which is 17% faster than AMD's memory default value - 1500 MHz. The ASRock Radeon RX 5600 XT Challenger Pro 6G OC is equipped with 3-fan cooler, 6 GB 192-bit GDDR6 memory and latest PCI Express 4.0 bus standard; ideally partnering with AMD Ryzen 3000 CPU systems and ASRock B550 and X570 motherboards. These premium specifications allow Radeon RX 5600 XT Challenger Pro 6G OC graphics card to have outstanding performance and bring users excellent 1080p gaming experience.

Matrox is pleased to announce that the Matrox QuadHead2Go Q155 multi-monitor controller card is now shipping. Powering up to four Full HD displays from a single HDMI video source—including HDCP devices—the QuadHead2Go Q155 card provides OEMs, system integrators, and AV installers with an innovative tool to quickly and easily add more displays to video walls of any type and size. Designed to integrate seamlessly into Matrox-based or third-party platforms, QuadHead2Go is ideal for a wide variety of video wall applications, including digital signage, control room, broadcast, and more.

QuadHead2Go Q155 controllers capture a single video signal—of up to 4Kp60 and 8Kx8K—for display across up to four screens, at resolutions up to 1920x1200 per output. The input content could be from any HDMI source—including digital signage players, media players, laptops, and more—while displays can be arranged in a variety of artistic configurations or classic rectangular 2x2, 2x1, 3x1, 4x1, 1x2, 1x3, or 1x4 setups. Pair multiple QuadHead2Go units to add more displays and/or combine with Matrox D-Series quad-4K graphics cards to power up to an astonishing 64 1920x1080p60 monitors from one system.

Raijintek today unveiled the MORPHEUS 8057, a large graphics card air-cooler. The cooler consists of a gargantuan aluminium fin-stack heatsink that's ventilated by a pair of 120 mm fans (not included). The heatsink features a large mirror-finish copper base, from which six 6 mm thick heat pipes emerge in either direction of the base (Raijintek for some reason counts this as 12 heat pipes), conveying heat to a large fin-stack with 112 aluminium fins that have ceramic coating.

The MORPHEUS 8057 heatsink measures 254 mm x 100 mm x 44 mm (WxDxH), weighing 515 g. Among the secondary heatsinks included are 12 heatsinks of various sizes for memory and VRM components; thermal pads, retention clips, and some thermal paste. Among the graphics cards supported are AMD "Navi 10" based graphics cards (RX 5700 series and RX 5600 series); and NVIDIA RTX 2080 Ti, RTX 2080/SUPER, RTX 2070/SUPER, and RTX 2060/SUPER. The company didn't reveal pricing.

ELSA has announced two new GeForce RTX 2070 Super graphics cards the Super ERAZOR X and Super S.A.C. The two new cards both feature a dual-fan design with backplates. The ELSA GeForce RTX 2070 Super ERAZOR X features a boost clock of 1815 MHz, four 8 mm diameter heat pipes cooled by dual 90 mm "SAC 3" fans. The card comes with an ESLA logo backplate and measures 267 mm (length) x 114 mm (height) x 50 mm (thickness), 2.5 slot size limiting SLI options. The card will be available in Japan from June 26th with a price of 81,200 yen (760 USD).

ELSA GeForce RTX 2070 Super S.A.C is a cheaper option with a boost clock of 1,770 MHz, four 6 mm diameter heat pipes cooled by dual 90 mm "SAC 2" fans. The card comes with a plain backplate and measures 271 mm (length) x 115 mm (height) x 42 mm (thickness). The card will be available in Japan from June 26th with a price of 71,400 yen (670 USD).

The Manli GeForce GTX 1650 DDR6 Low Profile is powered by NVIDIA's new GDDR6 memory, hence the "DDR6" moniker. The key upgrades include 12 Gbps memory speed and 192 GB/sec memory bandwidth, both improvements over the former DDR5. Clock speed is at 1410 MHz and can be boosted to 1590 MHz. This results in a performance boost of 6.31% over the DDR5. The performance benchmarks of the DDR6 slots it comfortably between the previous DDR5 and the
GeForce GTX 1650 Super. The sleeker design makes it more suitable for certain applications.

NVIDIA's next-generation GeForce "Ampere" RTX 3000 series graphics cards are heading for a September reveal, along with availability shortly after. Much of the news cycle over the past couple of weeks revolved around alleged leaks of the card's cooling solution that provides insights into what the finished product could look like, with some even doubting the veracity of the picture leaks given the September launch. Igor's Lab did some digging into the production timeline of these cards. The leaks seem to perfectly align with the timeline.

The chip design, prototyping, taping-out, and testing of "Ampere" IP completed before the mass-production timeline kicks off. This begins in April/May, with NVIDIA's OEM partners and other suppliers finalizing a bill of materials (BOM). June is also when the products go through the EVT (engineering validation test) and DVT (design validation test). It is at these stages that NVIDIA has the opportunity to approve or summarily reject/change the design of the product and finalize it. By July, there are working samples of the finished products for NVIDIA and its industry partners to validate. This is also when regulators such as the FCC and CE conduct EMI tests. Production validation tests (PVT), or proofing of the production line, occurs in late-July/early-August. The final BIOS is released to the OEM by NVIDIA around this time. Mass-production finally commences in August, and the onward march to distributors rolls on. The media event announcing the product and press reviews follow in September, and market availability shortly thereafter.

AMD has declared that the era of 4 GB graphics cards is over and that users should "Game Beyond 4 GB". AMD has conducted testing of its 4 GB RX 5500XT & 8 GB RX 5500XT to see how much of a difference VRAM can make on gaming performance. AMD tested the cards on a variety of games at 1080p high/ultra settings with a 3600X & 16 GB 3200 MHz ram, on average the 8 GB model performed ~19% better than its 4 GB counterpart. With next-gen consoles featuring 16 GB of combined memory and developers showing no sign of slowing down, it will be interesting to see what happens.

Matrox is pleased to announce that the Matrox D-Series D1480 multi-display graphics card is now shipping. Purpose-built to power next-generation video walls, this new single-slot graphics card supports up to four 4Kp60 DisplayPort monitors and can be combined to drive a high-density-output video wall of up 16 synchronized 4K displays. Along with a rich assortment of video wall software and developer tools, the D1480 card enables OEMs, system integrators, and AV installers to deploy high-performance display walls for a broad range of commercial and critical 24/7 applications, including control rooms, enterprises, industries, government, military, digital signage, broadcast, and more.

Backed by innovative technology and deep industry expertise, D1480 delivers exceptional video and graphics performance on up to four 4K DisplayPort monitors from a single-slot card. OEMs, system integrators, and AV professionals can easily add—and synchronize—displays by framelocking up to four D-Series cards via board-to-board framelock cables. In addition, D1480 offers HDCP support to display copy-protected content, as well as Microsoft DirectX 12, OpenGL 4.5, and OpenCL 1.2 support to run the latest professional applications.

NVIDIA investors have recently filed a suit against the company, claiming that NVIDIA wrongfully detailed its revenue indicators between departments. The main point of contention here is that investors claim NVIDIA knowingly obfuscated the total value of the crypto market boom (and subsequent bust) from investors, thus painting a picture of the company's outlook than was different from reality (making demand for the Gaming division look higher than it was in reality) and exposing them to a different state of affairs and revenue gains than they expected. The investors say that NVIDIA knew that a not insignificant number of its graphics cards sold between 2017 and 2018 was being bought-up solely for the purpose of crypto mining, and that the company knew this (and even marketed GPUs specifically for that purpose).

The crypto mining boom had miners gobbling up all NVIDIA and AMD graphics cards that they could, with both companies seemingly increasing production to meet the crypto mining bubble demand. However, due to the economics of crypto mining, it was clear that any profits derived from this bubble would ultimately open the door to an explosive logistics problem, as miners offloaded their graphics cards to the second-hand market, which could ultimately harm NVIDIA's financial book. Of course, one can look at NVIDIA's revenue categories at the time to see that crypto would hardly fit neatly into either the Gaming, Professional Visualization, Datacenter, Auto, or OEM & IP divisions.

AMD today announced its Radeon Pro VII professional graphics card targeting 3D artists, engineering professionals, broadcast media professionals, and HPC researchers. The card is based on AMD's "Vega 20" multi-chip module that incorporates a 7 nm (TSMC N7) GPU die, along with a 4096-bit wide HBM2 memory interface, and four memory stacks adding up to 16 GB of video memory. The GPU die is configured with 3,840 stream processors across 60 compute units, 240 TMUs, and 64 ROPs. The card is built in a workstation-optimized add-on card form-factor (rear-facing power connectors and lateral-blower cooling solution).

What separates the Radeon Pro VII from last year's Radeon VII is full double precision floating point support, which is 1:2 FP32 throughput compared to the Radeon VII, which is locked to 1:4 FP32. Specifically, the Radeon Pro VII offers 6.55 TFLOPs double-precision floating point performance (vs. 3.36 TFLOPs on the Radeon VII). Another major difference is the physical Infinity Fabric bridge interface, which lets you pair up to two of these cards in a multi-GPU setup to double the memory capacity, to 32 GB. Each GPU has two Infinity Fabric links, running at 1333 MHz, with a per-direction bandwidth of 42 GB/s. This brings the total bidirectional bandwidth to a whopping 168 GB/s—more than twice the PCIe 4.0 x16 limit of 64 GB/s.

TSMC is working hard to bring a new 5 nm (N5 and N5+) despite all the hiccups the company may have had due to the COVID-19 pandemic happening. However, it seems like nothing can stop TSMC, and plenty of companies have already reserved some capacity for their chips. With mass production supposed to start in Q3 of this year, 5 nm node should become one of the major nodes over time for TSMC, with predictions that it will account for 10% of all capacity for 2020. Thanks to the report of ChinaTimes, we have a list of new clients for the TSMC 5 nm node, with some very interesting names like Intel appearing on the list.

Apple and Huawei/HiSilicon will be the biggest customers for the node this year with A14 and Kirin 1000 chips being made for N5 node, with Apple ordering the A15 chips and Huawei readying the Kirin 1100 5G chip for the next generation N5+. From there, AMD will join the 5 nm party for Zen 4 processors and RDNA 3 graphics cards. NVIDIA has also reserved some capacity for its Hopper architecture, which is expected to be a consumer-oriented option, unlike Ampere. And perhaps the most interesting entry to the list is Intel Xe graphics cards. The list shows that Intel might use the N5 process form TSMC so it can ensure the best possible performance for its future cards, in case it has some issues manufacturing its own nodes, just like it did with 10 nm.

Bitspower today introduced its 1S full-coverage graphics card water-block for a wide range of NVIDIA GeForce RTX 20-series custom-design graphics cards, bearing the model number BP-VG2080RD1S. The uses nickel-plated copper as its primary material, coupled with a clear-acrylic top. The block supports a wide range of RTX 2080 Ti, RTX 2080/2080S, RTX 2070/2070S, and RTX 2060/2060S graphics cards. With a thickness of 15.8 mm, 244.5 mm length, and 125 mm height, the block is capable of single-slot applications. Available now, it is priced around USD $130.

As the world's most popular GAMING graphics card vendor, MSI is proud to unleash the most powerful Turing-based gaming graphics card onto the market. The famous GAMING TRIO series has reached its ultimate form in custom GeForce graphics cards to push the limits of performance once more. Making sure gamers will bask in glorious amounts of frames, MSI has fitted the GeForce RTX 2080 Ti with extremely fast 16 Gbps memory. Outperforming the MSI GeForce RTX 2080 Ti GAMING X TRIO by over 5% out of the box, the industry-leading MSI GeForce RTX 2080 Ti GAMING Z TRIO sets a new bar for extreme gaming.

Rocking the mighty TRI-FROZR design with supreme cooling power allows the MSI GeForce RTX 2080 Ti GAMING Z TRIO to deliver top notch in-game and thermal performance. Featuring MSI's patented TORX 3.0 fans, the unique fan design combines the advantages of two differently shaped fan blades to generate huge amounts of concentrated airflow while remaining virtually silent. The Wave-Curved 2 fin design helps to dissipate heat from the heatsink quicker than ever to keep you cool in the heat of battle.

Micron Technologies, in the latest earnings report, announced that they will start shipping High-Bandwidth Memory 2 (HBM2) DRAM. Used for high-performance graphics cards, server processors and all kinds of processors, HBM2 memory is wanted and relatively expensive solution, however, when Micron enters the market of its manufacturing, prices, and the market should adjust for the new player. Previously, only SK-Hynix and Samsung were manufacturing the HBM2 DRAM, however, Micron will join them and they will again form a "big-three" pact that dominates the memory market.

Up until now, Micron used to lay all hopes on its proprietary Hybrid Memory Cube (HMC) DRAM type, which didn't gain much traction from customers and it never really took off. Only a few rare products used it, as Fujitsu SPARC64 XIfx CPU used in Fujitsu PRIMEHPC FX100 supercomputer introduced in 2015. Micron announced to suspend works on HMC in 2018 and decided to devote their efforts to GDDR6 and HBM development. So, as a result, we are seeing that they will launch HBM2 DRAM products sometime this year.

With the global crisis of COVID-19, we understand that these are critical times for everyone. This has impacted all aspects of our lives, and we understand that during these times, priorities are placed on more health-concerned matters. Many in the process of RMAs may find difficulty in shipping out cards for repair or service at this time, so we will be adding a 3-month extension to customers with warranties expiring between March through June 2020. PowerColor remains committed to delivery great products and services to our customers, and want to assure that we will continue to do so during these trying times.

AMD today announced in the form of a blog post that its upcoming graphics cards based on RDNA 2 architecture will feature support for Microsoft's latest DirectX 12 Ultimate API. "With this architecture powering both the next generation of AMD Radeon graphics cards and the forthcoming Xbox Series X gaming console, we've been working very closely with Microsoft to help move gaming graphics to a new level of photorealism and smoothness thanks to the four key DirectX 12 Ultimate graphics features -- DirectX Raytracing (DXR), Variable Rate Shading (VRS), Mesh Shaders, and Sampler Feedback." - said AMD in the blog.

Reportedly, Microsoft and AMD have worked closely to enable this feature set and provide the best possible support for RDNA 2 based hardware, meaning that future GPUs and consoles are getting the best possible integration of the new API standard.

Microsoft Thursday released the DirectX 12 Ultimate logo. This is not a new API with any new features, but rather a differentiator for graphics cards and game consoles that support four key modern features of DirectX 12. This helps consumers recognize the newer and upcoming GPUs, and tell them apart from some older DirectX 12 capable GPUs that were released in the mid-2010s. For a GPU to be eligible for the DirectX 12 Ultimate logo, it must feature hardware acceleration for ray-tracing with the DXR API; must support Mesh Shaders, Variable Rate Shading (VRS), and Sampler Feedback (all of the four). The upcoming Xbox Series X console features this logo by default. Microsoft made it absolutely clear that the DirectX 12 Ultimate logo isn't meant as a compatibility barrier, and that these games will work on older hardware, too.

As it stands, the "Navi"-based Radeon RX 5000 series are "obsolete", just like some Turing cards from the GeForce GTX 16-series. At this time, the only shipping product which features the logo is NVIDIA's GeForce RTX 20-series and the TITAN RTX, as they support all the above features.

NVIDIA graphics cards, starting from the current generation GeForce RTX "Turing" lineup, will support the upcoming DirectX 12 Ultimate API. Thanks to a slide obtained by our friends over at VideoCardz, we have some information about the upcoming iteration of the DirectX 12 API made by Microsoft. In the new API revision, called "DirectX 12 Ultimate", it looks like there are some enhancements made to the standard DirectX 12 API. From the leaked slide we can see the improvements coming in the form of a few additions.

The GeForce RTX lineup will support the updated version of API with features such as ray tracing, variable-rate shading, mesh shader, and sampler feedback. While we do not know why Microsoft decided to call this the "Ultimate" version, it is possibly used to convey clearer information about which features are supported by the hardware. In the leaked slide there is a mention of consoles as well, so it is coming to that platform as well.

Expreview has caught the sighting of an apparently upcoming AMD graphics card based around the RX 590 SKU. The new revision, being named the RX 590 GME, apparently features lower clocks than the base Polaris 30 RX 590 ~around 1,385 MHz boost compared to the vanilla RX590's 1545 MHz. That clockspeed puts the RX 590 GME slightly above the RX 580 in terms of specs, but way below the RX 590, which should lead to a distinct performance variation between the two.

It's unclear as to what GPU die this new Polaris-based graphics card will be using. If I were a betting man, I'd say these are being harvested from 12 nm Polaris 30 dies that haven't been able to sustain the 1545 MHz clockspeeds rated for RX 590 chips - but still being put to use and very likely with a better power/performance ratio than the RX 590. For now, the model is only available for pre-order through a Chinese e-tailer, which could mean this is a China-only release.

Jon Peddie Research have released their report on the overall market outlook for GPU shipments for Q4'2019, and the news are great for AMD. Due to the launch of more affordable Navi-based 7 nm graphics cards, the company managed to achieve a growth of 22.6% in shipment volume for the last quarter of 2019, compared to Q3 of the same year. This 22.6% volume increase is pretty significant (and is miles ahead of competitors NVIDIA (whose shipments decreased by -1.9%) and Intel (a 0.2% increase), having increased AMD's overall market share by 3%. This means that AMD now commands 19% of the overall GPU market share, surpassing NVIDIA (which counts with 18%) but both being dwarfed by Intel (with a commanding 63% share). It's important to note here that the numbers include integrated- and discrete-GPUs, and AMD's numbers could be assisted by its mobile processor and APU sales, just as iGPUs make up all of Intel's numbers.

Those numbers are skewed, of course, when we look solely at the discrete GPU market share, with NVIDIA commanding a huge, 73% chunk of the market against AMD's paltry (by comparison) 27%. All in all, Jon Peddie Research reports that the overall PC market increased by 1.99% quarter-to-quarter and increased by 3.54% year-to-year, thus resulting a good performance for these "little" chips.