There are now only weeks left until Nvidia releases the architecture Pascal for consumers. First out is the GP104 graphics circuit, which in various versions replaces the Geforce GTX 970, GTX 980 and GTX 980 Ti. Now find two variants of the circuit on the web and block the information about Nvidia’s range to be segmented with different memory technologies.
The pictures show two variants of the graphics circuit GP104, GP104-400 and GP104-200, which are expected to be Geforce GTX 1080 and GTX 1070. In addition to marking on the two graphics circuits, there is a small but at the same time significant difference in memory, where GP104-400 has smaller memory circuits.
While GDDR5X is a further development of GDDR5, their physical size differs. The GDDR5X memory type is housed in 14 x 10 mm BGA capsules, while long-used GDDR5 measures 14 x 12 mm. In other words, it looks like the GP104-400 is paired with the newer and faster memory technology.
Furthermore, both graphics circuits have eight memory capsules, which suggests that the GP104 comes with a 256-bit memory bus. For GP104-200, 8 GB GDDR5 in 8 Gbps is expected for a bandwidth of 256 GB / s, up from 224 GB / s for Geforce GTX 970 and GTX 980 which come with 4 GB GDDR5 in 7 Gbps.
The GP104-400 sibling has the Micron memory capsules 6GA77 Z9TXT, which are not yet officially listed. Depending on whether the speed is 10 or 12 Gbps, this gives a bandwidth of 320 or 384 GB / s, which is just below a bit above the Geforce GTX 980 Ti and GTX Titan X of 336 GB / s, respectively.
Another detail that emerges is approximate dimensions of the GP104, which is estimated to measure around 315-330 mm2. This can be compared to 398 mm2 for GM204 and solid 601 mm2 for the GM200 which the circuit is intended to replace. Despite a significantly smaller circuit, the number of transistors and performance are expected to be in line with the GM200, which is attributed to the transition to a more advanced 16-nanometer technology from TSMC.
The launch of Nvidia’s graphics architecture Pascal for consumers is expected to take place later in May, in connection with the component fair Computex 2016.
Source: Videocardz, Wccftech, Chiphell.
Mining on RTX 3070. Overclocking, tuning, profitability, consumption: If you are interested in finding more…
Mining with GTX 1660, 1660 Ti, 1660 Super. Overclocking, settings, consumption, profitability, comparisons - If…
Mining with RTX 2070 and 2070 Super. Overclocking, profitability, consumption, comparison What the RTX 2070…
Mining with RTX 3060, 3060 Ti. Limitations, overclocking, settings, consumption, profitability, comparison Let's look at…
Alphacool Eisblock Aurora Acryl GPX-A (2022) with Sapphire Radeon RX 6950 XT Nitro+ Pure in…
In the ever-evolving landscape of business strategy, Bitcoin has emerged as a pivotal asset. With…
This website uses cookies.