Ampere Discussion Thread

[SteelCrysis]

https://www.tomshardware.com/news/nvidia...ted-supply

If there was any doubt to the GeForce RTX 3090's performance, Nvidia just confirmed it via a blog post today. The GeForce RTX 3090, which Nvidia is dubbing as the big ferocious GPU or "BFGPU," is only 10% to 15% faster than the GeForce RTX 3080 at 4K gaming. The graphics card is sure to once again upset our list of best gaming graphics cards, hopefully in a good way.

The GeForce RTX 3090 officially goes on sale tomorrow. The Founders Edition will retail at $1,499, and custom models could cost between $1,499.99 to $1,799.99. Don't get your hope up just yet though since Nvidia itself has acknowledged that stock will be extremely limited.

In the post, Nvidia stated that "Since we built GeForce RTX 3090 for a unique group of users, like the TITAN RTX before it, we want to apologize upfront that this will be in limited supply on launch day. We know this is frustrating, and we’re working with our partners to increase the supply in the weeks to come."

https://www.techpowerup.com/272492/nvidi...d-pictured

Here is the first picture of an alleged next-generation Quadro RTX graphics card based on the "Ampere" architecture, courtesy YouTube channel "Moore's Law is Dead." The new Quadro RTX 6000-series shares many of its underpinnings with the recently launched GeForce RTX 3080 and RTX 3090, in being based on the 8 nm "GA102" silicon. The reference board design retains a lateral blower-type cooling solution, with the blower drawing in air from both sides of the card, through holes punched in the PCB, "Fermi" style. The card features the latest NVLink bridge connector, and unless we're mistaken, it features a single power input near its tail end, which is very likely a 12-pin Molex MicroFit 3.0 input.

As for specifications, "Moore's Law is Dead," shared a handful of alleged specifications that include maxing out of the "GA102" silicon, with all its 42 TPCs (84 SMs) enabled, working out to 10,752 CUDA cores. As detailed in an older story about the next-gen Quadro, NVIDIA is prioritizing memory size over bandwidth, which means this card will receive 48 GB of conventional 16 Gbps GDDR6 memory across the GPU's 384-bit wide memory interface. The 48 GB is achieved using twenty four 16 Gbit GDDR6 memory chips (two chips per 32-bit wide data-path). This configuration provides 768 GB/s of memory bandwidth, which is only 8 GB/s higher than that of the GeForce RTX 3080. The release date of the next-gen Quadro RTX will depend largely on the supply of 16 Gbit GDDR6 memory chips, with leading memory manufacturers expecting 2021 shipping, unless NVIDIA has secured an early production batch.

https://www.techpowerup.com/272508/galax...s-rtx-2080

An alleged event by GALAX targeted at distributors in China revealed up to three upcoming SKUs in NVIDIA's RTX 30-series. This comes as yet another confirmation from a major NVIDIA AIC partner about the 20 GB variant of the GeForce RTX 3080. The RTX 3080 originally launched with 10 GB memory earlier this month, and it is widely expected that NVIDIA fills the price-performance gap between this $700 SKU and its $1,500 sibling. The RTX 3080 uses twenty 8 Gbit GDDR6X memory chips (two chips per 32-bit data-path), much like how the RTX 3090 achieves its 24 GB memory amount.

Elsewhere we see GALAX mention the RTX 3060, a performance-segment SKU positioned under the RTX 3070. You'll notice that the product-stack graph by GALAX suggests performance comparisons to previous-generation SKUs. The RTX 3080 and RTX 3090 are faster than everything from the previous generation, while the RTX 3070, which is coming next month, is shown trading blows with both the RTX 2080 Ti and the RTX 2080 Super. In this same graph, the RTX 3060 is shown matching up to the RTX 2080 (non-Super), a card NVIDIA originally launched at $700.

There's an unnamed SKU slotted between the RTX 3070 and the RTX 3080 10 GB, which is codenamed "PG142 SKU 0." Some AICs/OEMs are referring to this as the "RTX 3070 Ti," and others the "RTX 3070 Super." Given that the Super brand extension has been used by NVIDIA to denote a mid-life refresh for an existing product stack, it's very likely that this SKU is simply the RTX 3070 16 GB (RTX 3070 with 16 GB of GDDR6 memory, and perhaps bolstering in other areas). This SKU is shown trading blows with the RTX 2080 Ti and the TITAN RTX.