NVIDIA is reportedly rushing shipments of GeForce RTX 4090 GPUs to China in anticipation of expected export restrictions. We have already reported that NVIDIA might be canceling 5 billion US Dollars worth of orders. The US government will require an export license for shipping RTX 4090s to China, effectively restricting sales to the country. NVIDIA's add-in-board (AIB) partners are reportedly working at full capacity to produce as many RTX 4090 products for the Chinese market as possible before the potential restriction on November 17. While it remains unclear whether the export restrictions will ultimately be implemented, the anticipation of such measures has prompted NVIDIA and its partners to accelerate their production.

The Tweet that feeds this information is coming from Zed Wang, a well-known hardware leaker with historically accurate insights into NVIDIA's operations, who claims that "NVIDIA has been shipping tons of AD102 for AICs this week to manufacture as much RTX 4090 as possible before the original restriction date of RTX 4090 in China. It is still unclear whether the restriction will become true or not. But all AICs are at their full power in producing RTX 4090, regardless of that."

NVIDIA add-in card (AIC) partners are reported to be taking a nonchalant approach to producing new custom designs for NVIDIA's upcoming launch (July 18) of the GeForce RTX 4060 Ti 16 GB graphics card. The RTX 4060 Ti 8 GB variant arrived back in late May to yet another lukewarm reception for the Ada Lovelace generation—Team Green's board partners are likely anticipating that the 16 GB model's MSRP of $499 is not going to generate enough interest or buzz within the PC gaming hardware community.

MSI could be going against the grain with the introduction of a new custom design for the GeForce RTX 4060 Ti 16 GB GPU—in the form of its GAMING X Slim White model—as discovered by hongxing2020. This appears to be a white alternative to the company's GAMING TRIO X cooling solution—with a (slightly) slender redesign and RGB lighting strips placed in different positions, although the pale aesthetic does not extend to the PCB and heatsink fins. MSI's fancy GAMING X liveries usually add some extra expense to base prices (+$60 for the RTX 4060 Ti 8 GB Gaming X Trio), so this new white model could be sold for more than $559.

NVIDIA has confirmed that the GeForce RTX 4060 Ti 16 GB and the RTX 4060 8 GB non-Ti won't be getting the Founders Edition version as this will be reserved only for the RTX 4060 Ti 8 GB that comes on May 24th.

The NVIDIA GeForce RTX 4060 Ti 8 GB Founders Edition looks similar to the RTX 4070 version, except for a slight color change, where the RTX 4060 Ti will be getting the silver shroud. The Founders Edition were highly sought after as they offered both impressive cooling as well as better overclocking potential. Such a move also means that NVIDIA won't be competing directly with its add-in-card (AIC) partners with the RTX 4060 8 GB or the RTX 4060 Ti 16 GB which are both launching in July.

NVIDIA has traditionally refrained from lowering the PCIe lane counts on its mid-range GPUs, doing so only with its most entry-level SKUs, however, this is about to change with the GeForce RTX 40-series. A VideoCardz report says that the upcoming GeForce RTX 4060 Ti, based on the AD106 silicon, comes with a host interface of PCI-Express 4.0 x8.

While this is still plenty of interface bandwidth for a GPU of this market segment, with bandwidth comparable to that of PCI-Express 3.0 x16, using the RTX 4060 Ti on older platforms, such as 10th Gen Intel Core "Comet Lake," or even much newer processors such as the AMD Ryzen 5700G "Cezanne," would run the GPU at PCI-Express 3.0 x8, as the GPU physically lacks the remaining 8 lanes. The lower PCIe lane count should simplify board design for AIC partners, as it reduces the PCB traces and SMDs associated with each individual PCIe lane. Much like DRAM chip traces, PCIe traces are meticulously designed by EDA software (and later validated), to be of equal length across all lanes, for signal integrity.

NVIDIA's fresh faced GeForce RTX 4070 graphic card range has not been flying off shelves around the world, and Team Green could be pivoting their approach somewhat after receiving lower than expected sales figures via company reports. Their component suppliers have already mentioned that the entire GeForce RTX 40 family is on a comfortably steady production schedule - with no instructions received from HQ to up the ante. In the latest development this week, individuals with insider knowledge of factory schedules in China have claimed that NVIDIA has informed board partners (AICs) that output for the GeForce RTX 4070 line is getting paused for a month. The temporary cutoff in factory output will allow, they hope, for the currently sitting stock to get cleared out. A substantial surplus of GeForce RTX 4070 cards could disrupt distribution networks and overstock warehouses.

Industry watchdogs have theorized that NVIDIA's board partners are having a difficult time offloading their premium tier RTX 4070 custom cards onto paying customers. The Founders Edition and closer-to-reference models have sold quite respectable numbers according to early analyses, but more expensive options are considered to be too expensive by the customer base. There is apparent crossover in pricing with the fancier GeForce RTX 4070 Ti range, and a savvy buyer will tend toward superior silicon rather than a shiny cooling solution combined with a factory-issued overclock. A computer hardware retailer in the UK, Novatech, has chosen to cut the price of a Palit RTX 4070 Dual model by £40/$50, as reported yesterday. The asking price has since returned closer to RRP - at the time of writing it stands at £579.98.

NVIDIA today announced the GeForce RTX 4070 "Ada" graphics card, with a starting price of USD $600, with availability slated for tomorrow, April 13. The GeForce RTX 4070 is a performance-segment graphics card based on the same "AD104" silicon as the RTX 4070 Ti, but heavily cut down—it features 5,888 CUDA cores, 46 RT cores, 184 Tensor cores, 64 ROPs, and 184 TMUs. The memory subsystem is unchanged from the RTX 4070 Ti, with 12 GB of 21 Gbps GDDR6X memory across a 192-bit memory interface.

The GeForce RTX 4070 targets maxed-out AAA gaming at 1440p, and high refresh-rate e-sports gaming. You get all of the features introduced with "Ada," including dual video encoding hardware accelerators, Optical Flow Accelerator, and DLSS 3 Frame Generation. The card has a typical board power of 200 W, and the company allowed board partners to use 8-pin PCIe power connectors instead of 16-pin 12VHPWR.Our launch day review coverage of the RTX 4070 (as on April 12) includes: NVIDIA GeForce RTX 4070 Founders Edition | PNY GeForce RTX 4070 | MSI GeForce RTX 4070 Ventus 3X | ASUS GeForce RTX 4070 DUAL | Gainward GeForce RTX 4070 Ghost

NVIDIA is reportedly flexible with its add-in card (AIC) partners with their choice of power connectors for the upcoming GeForce RTX 4070 graphics card. It stands to reason that this flexibility could extend even further down the lineup, to the RTX 4060 series and below. Igor's Lab reports that NVIDIA is allowing partners to choose between the newer 16-pin ATX 12VHPWR connector, or the older [and more reliable] 8-pin PCIe power connectors, in their custom-design products. Sources tell Igor's Lab that the RTX 4070 could have two TGP classes, a 225 W-rated one that is likely to feature 16-pin connectors, and a 200 W-class that will stick to PCIe power connectors.

With typical graphics power (TGP) values for the upcoming RTX 4070 expected to be well under 300 W, graphics cards can make do with two 8-pin PCIe connectors on the card, or a 16-pin connector with a dongle that converts two 8-pin connectors to a 300 W-rated 16-pin. A pair of 8-pin inputs on the card is the more cost-effective solution, as it spares AICs from having to include that NVIDIA-designed power adapter, besides the more exotic 16-pin input on the board. We have seen pictures of RTX 4070 and RTX 4060-series Founders Edition cards, which are sure to feature 16-pin connectors. For the RTX 4070, NVIDIA could take an unconventional product launch path, with custom-design graphics cards priced on NVIDIA MSRP launching a day sooner than the ones that are priced at a premium. It's possible that the MSRP cards could come with 8-pin PCIe connectors.

AIC today announced its EB202-CP is ready to support newly launched 4th Gen AMD EPYC Embedded 9004 processors. By leveraging the five-year product longevity supported by AMD EPYC Embedded processors, EB202-CP provides customers with stable and long-term support. AIC and AMD will join forces to showcase EB202-CP at Embedded World in AMD stand No. 2-411 from 14th to 16th March, 2023 in Nuremberg, Germany.

AIC EB202-CP, a 2U rackmount server designed for AI and edge appliances, is powered by the newly released 4th Gen AMD EPYC Embedded processors. Featuring the world's highest-performing x86 processor and PCIe 5.0 ready, the 4th Gen AMD EPYC Embedded processors enable low TCO and delivers leadership energy efficiency as well as state-of-the-art security, optimized for workloads across enterprise and edge. EB202-CP, with 22 inch in depth, supports eight front-serviceable and hot-swappable E1.S/ E3.S and four U.2 SSDs. By leveraging the features of the 4th Gen AMD Embedded EPYC processors, EB202-CP is well suited for broadcasting, edge and AI applications, which require greater processing performance and within the most efficient, space-saving format.

AIC Inc., (from now on referred to as"AIC"), a leading provider in enterprise storage and server solutions, today unveiled its new server systems powered by 4th Gen Intel Xeon Scalable processors (formerly codenamed Sapphire Rapids). The new server platforms are designed to accelerate performance across the most in-demand workloads that businesses rely on including enterprise, storage, AI and HPC.

The newly launched AIC servers, SB102-HK, SB201-HK and HP202-KT, are designed to offer superior processing performance and energy efficiency by leveraging the innovative features of 4th Gen Intel Xeon Scalable processors. With built-in accelerators, the 4th Gen Intel Xeon Scalable processors optimize the utilization of CPU core resources and feature enhanced memory bandwidth with DDR5, advanced I/O with PCIe Gen 5 and Compute Express Link (CXL) 2.0/1.1, and the ability to accelerate PyTorch real-time inference performance by up to 10x using Intel Advanced Matrix Extensions (Intel AMX) compared to the previous generation. The new AIC servers are empowered by advanced security technologies from 4th Gen Intel Xeon Scalable processors, allowing them to protect data and unlock new opportunities for business collaborations.

A report by Moore's Law is Dead claims that NVIDIA is preparing to launch a new TITAN RTX halo product, based on a maxed-out 4 nm "AD102" silicon. Where does this put the RTX 4090 Ti? Somewhere in between the RTX 4090 and the TITAN RTX Ada, as NVIDIA gave itself plenty of segmentation headroom with the AD102 silicon, by using just 128 out of 144 SM physically present on the silicon, besides the same 21 Gbps GDDR6X memory as the previous-generation. NVIDIA's options with the new TITAN RTX include enabling all 144 SM (18,432 CUDA cores), and using faster 24 Gbps memory, giving the silicon (1152 GB/s memory bandwidth), a stock power-limit closer to the 600 W design limit of the 12VHPWR power connector (RTX 4090 stock typical board power is 450 W).

Moore's Law is Dead also posted what they claim to be the first real-world pictures of the upcoming TITAN RTX Ada. The card is an unabashed 4-slot enlargement of the dual-axial flow-through RTX 4090 Founders Edition, with the cooler capable of higher thermal loads. TITAN RTX cards are marketed as first-party Founders Edition cards only, and not through NVIDIA's AIC board partners as custom-designs. A maxed out AD102, with higher clock speeds, higher power-limit, and faster memory, should be unassailable for custom-design RTX 4090 cards, if NVIDIA wants to sell this card at the kind of prices its last TITAN RTX product sold at—USD $2,500.

AIC Inc., (from now on referred to as "AIC"), a leading provider in enterprise storage and server solutions, today revealed its new edge server appliance powered by 4th Gen AMD EPYC processors (codename Genoa). The new server, EB202-CP, is designed to deliver superior performance in a compact size while offering excellent cost efficiency. Combined with the 4th Gen AMD EPYC processors, EB202-CP is expected to drive the innovations in AI, training simulation, autonomous vehicles and edge applications. AIC will showcase EB202-CP at SC22 expo from November 14th to 17th, 2022.

AIC EB202-CP is a 2U rackmount server with 22 inches in depth. It supports eight E1.S/ E3.S or U.2 SSDs which are front-serviceable and hot-swappable. The E1.S/ E3.S drives are Enterprise and Datacenter SSD Form Factor (EDSFF) that enables EB202-CP to provide high-density all-flash NVMe for half petabyte storage capabilities and enhance IOPS and space utilization. EB202-CP has great expansion functionality and supports up to two double-stack GPU or accelerator cards, two FHHL/HHHL PCIe 5.0 cards and an OCP 3.0 card. Based on AIC server board Capella, EB202-CP supports single 4th Gen AMD EPYC processor and eight DDR5 DIMMs. The 4th Gen AMD EPYC processors, built on "Zen 4" architecture, are optimized for general-purpose workloads across enterprise, cloud and edge. This new generation of AMD EPYC features the world's highest-performing x86 processor, PCIe 5.0 ready, and enables low TCO. It also delivers leadership energy efficiency as well as state-of-the-art security features.

As with the recent pre-launch listing of 13th Gen Core desktop processors, US retailer Newegg put out listings of various custom-design NVIDIA GeForce RTX 4090 "Ada" graphics cards, revealing their launch prices. These prices appear close enough to the $1,599 baseline price set by NVIDIA, to conclude that pricing sanity is slowly returning to the graphics card market. A lot will however depend on how the market behaves on October 12, when the RTX 4090 goes on sale; particularly whether scalpers vaporize inventory within minutes. Even if they did, scalpers would only see demand from the niche that actually wants to spend north of $1,600 on a graphics card, there are no crypto-currency miners lining up to buy graphics cards. Especially not after the Ethereum merge.

To illustrate that AIC prices are beginning to appear normal, one needs to look at the pricing of the MSI RTX 4090 SUPRIM Liquid, supposedly MSI's most premium RTX 4090 product, which is priced at $1,749, or just a $150 premium over the NVIDIA baseline. Several cards such as the ASUS TUF Gaming, GIGABYTE WindForce OC, and MSI Gaming (standard), are listed bang on the $1,599 baseline, while their OC siblings are at a small premium. The ASUS ROG Strix O24G is the most expensive card of the lot, priced at $1,999, or a $400 premium.

GIGABYTE TECHNOLOGY Co. Ltd, a leading manufacturer of motherboards, graphics cards, and hardware solutions announced the AORUS Gen5 AIC Adaptor with PCIe 5.0 support. It is a single-slot Add In Card, featuring four NVMe M.2 slots, supporting a maximum of four PCIe 5.0 SSDs with 16 TB storage. By configuring a RAID array, the bandwidth can boost up to 60 GB/s to allow massive data files to transfer in a snap. The eight integrated temperature sensors and active temperature-controlled double ball bearing fan should satisfy users with large-capacity, ultra-fast and ultra-cool data access.

"With the coming PCIe 5.0 platform, high-speed storage can reach access speed of more than 10 GB/s. For users who chase higher performance, GIGABYTE AORUS Gen5 AIC leads the way to extreme performance by building a disk array." said Jackson Hsu, Director of the GIGABYTE Channel Solutions Product Development Division. "Integrating four PCIe 5.0 slots, users can choose different NVMe M.2 SSDs with customized capacity and performance for the greatest flexibility. Meanwhile, the advanced thermal design prevents thermal throttling under high-speed operation which makes GIGABYTE AORUS Gen5 AIC the best choice when upgrading storage performance."

The NVIDIA GH100 silicon powering the next-generation NVIDIA H100 compute processor is a monstrosity on paper, with an NVIDIA whitepaper published over the weekend revealing its key specifications. NVIDIA is tapping into the most advanced silicon fabrication node currently available from TSMC to build the compute die, which is TSMC N4 (4 nm-class EUV). The H100 features a monolithic silicon surrounded by up to six on-package HBM3 stacks.

The GH100 compute die is built on the 4 nm EUV process, and has a monstrous transistor-count of 80 billion, a nearly 50% increase over the GA100. Interestingly though, at 814 mm², the die-area of the GH100 is less than that of the GA100, with its 826 mm² die built on the 7 nm DUV (TSMC N7) node, all thanks to the transistor-density gains of the 4 nm node over the 7 nm one.

Phison is on a mission to be the first to market with PCIe Gen 5 SSD controllers, having announced the E26-series controllers this CES. The company is ready with a branded drive under the MSI Spatium brand, the MSI Spatium E26. Built in the PCIe add-in-card (AIC) form-factor, the drive features a PCI-Express 5.0 x4 interface (128 Gbps per direction), and very likely sticks to the reference design that Phison demoed in its own booth.

This PCB is used in its client configuration, with just the controller, DRAM, and NAND flash chips; while the PCB allows an enterprise configuration with banks of capacitors offering explicit power-loss protection (the NAND flash chips offer implicit PLP). A simple copper-film heatspreader is used. Neither MSI nor Phison put out actual performance numbers, but mentioned sequential reads being "10 GB/s or beyond" (the interface is physically capable of 16 GB/s).Update Jan 17th: MSI clarified that this is not yet a shipping product, but a representation of what such a device could be. Thus, this should be considered a concept or at best proof of concept. Both MSI and Phison are actively working together on exploring what such a retail product could be.

Nostalgia is perhaps the most present feeling among many gamers across the globe, and someone is seemingly playing with ours as there is a Twitter account claiming the return of a company that has been dead for 20 years. 3dfx Interactive, once a giant in the graphics card industry, is allegedly returning after 20 years to give gamers a new choice of a graphics card. According to a Twitter account that claims that 3dfx Interactive is returning, we are seeing a massive amount of hype being built around the seemingly fake and bad attempt of playing with our nostalgia.

3dfx went bankrupt in 2000 and was acquired by NVIDIA, who took over the rights to trademarks and everything involved with the brand. In the latest tweet, the alleged resurrected company is claiming a return after 20 years. It says that Jansen Products, also an alleged investment firm, that we couldn't find in any database of registered firms, is now the owner of 3dfx Interactive brand and its trademarks. A simple Google search points towards a Belgian building firm, not an alleged San Francisco investment company.. Together, this is making the alleged return seem just like a joke, as someone must be playing with many gamers that used 3dfx's famous Voodoo lineup of graphics cards.

GIGABYTE Technology, one of the top global manufacturers of motherboards, graphics cards, and hardware solutions, today announced the AORUS XTREME Gen4 AIC SSD with 28 GB/s ultra-fast access speed. This high capacity and extreme performance SSD builds in eight 4 TB 2nd generation PCIe 4.0 NVMe M.2 SSDs with PHISON PS5018-E18 controller, AORUS XTREME Gen4 AIC SSD offers ultra-high transfer bandwidth and superior access performance through RAID configuration.

The AORUS Xtreme Gen4 AIC SSD features ultimate thermal design with large aluminium finned heatsink, M.2 baseplate for passive cooling, 10 temperature sensors and active dual-fan heat dissipation design, while the exclusive SSD Tool Box offers users real-time status and temperature monitoring of SSDs. GIGABYTE AORUS Storage Manager allows users to configure a RAID array with a single click and 3-phase fan speed adjustment, which enabling AORUS XTREME Gen4 AIC SSD to keep cool and performing at a high level. It promises a non-throttling experience for users who phase for high capacity and breakthrough performance.

NVIDIA is reported to be cutting down on production of its highly popular RTX 2060 graphics card, in a bid to increase production of the RTX 30-series graphics cards that still elude most consumers looking to get one on their gaming rig. The decision may be motivated by increased margins on RTX 30-series products, as well as by the continuing component shortage in the industry, with even GDDR6 becoming a limiting factor to production capability.

While one might consider this a strange move at face value (Turing is manufactured on TSMC's 12 nm node, whilst Ampere is manufactured on Samsung's 8 nm), the fact of the matter is that there are a multitude of components required for GPUs besides the graphics processing silicon proper; and NVIDIA essentially sells ready-to-produce kits to AICs (Add-in-Card Partners) which already include all the required components, circuitry, and GPU slice to put together. And since supply on most components and even simple logic is currently strained, every component in an RTX 2060-allocated kit could be eating into final production capacity for the RTX 30-series graphics cards - hence the decision to curb the attempt to satiate pent-up demand with a last-generation graphics card and instead focusing on current-gen hardware.

ASRock today unveiled the Thunderbolt 4 AIC, an add-on card that puts out two 40 Gbps Thunderbolt 4 ports in the USB-C form-factor, with DisplayPort 1.4 passthrough. The card works exclusively with ASRock's Intel 500-series chipset motherboards that have a special header needed by the card called "TBT_Header" (similar to the "TB_Header" on certain ASUS motherboards). In addition, the card needs a 9-pin USB 2.0 connection to one of the vacant headers on the motherboard.

The compact, yet full-height add-on card features a PCI-Express 3.0 x4 host interface, and is based on Intel JHL8540 "Maple Ridge" controller. It has two full-size DisplayPort 1.4 inputs, a pair of included DP cables lets you connect the card to your graphics card. The controller supports up to 5 devices in Thunderbolt daisy-chains. The DisplayPort passthrough supports resolutions of up to 5K @ 60 Hz. The card measures 8.4 cm in length, 10.41 cm in height, and is 1 slot thick. The company didn't reveal pricing.

ASUS was the first AIC partner to announce that due to increased costs in procuring supplies and components for PC component manufacture, it would be increasing prices on its motherboards and graphics cards. That announcement from ASUS seems to have opened the floodgates on other manufacturers, as now both EVGA and ZOTAC have increased pricing for their graphics cards - specifically for NVIDIA's RTX 30-series.

EVGA took a similar approach to ASUS, and announced via its website the changes in pricing and their effective date - January 11th. The company's announcement (which you can read in full after the break) sees pricing increase at around $70 across the board of already-launched NVIDIA RTX 30-series graphics cards. The company will still honor users in the queue system for a new graphics card with the previous pricing structure, should their orders complete through April 16th.