NVIDIA GeForce GTX 1080/1070 Cooler Shroud Dissected
By now you might already know that the new NVIDIA GeForce GTX 1080 and NVIDIA GeForce GTX 1070 are going to use a new cooler shroud that combined with the new design of the rest of it, makes it very Transformers-like.
This time, we have with us photos of the new shroud being taken apart piece by piece so as to give you a complete insight into it.
Nvidia is using die-sinking technology with the new shroud which uses electric sparks to shape a form. The whole thing is basically divided among four parts, one of whom has the GTX 10-0 cut into it. Number 7 or 8 would be cut in later depending on what model the shroud is to be used for.
Moving on, the fan shroud and the GTX logo you see on the side are both made of magnesium alloy. There also is an Nvidia logo on a small part behind the fan.
The first time that the NVIDIA GeForce GTX 1080/1070 Cooler Shroud made it to the news was when the new NVTTM design was leaked online. However, we now have a very in depth look at the sharp and angular design of the new NVTTM cooling solution.
With the first details on the Pascal shroud we had also listed down the known specifications of the Pascal architecture and the cards that are going to be based on it. Read up on that below.
Nvidia Pascal Specifications:
- Pascal graphics architecture
- 2x performance per watt estimated improvement over Maxwell
- To launch in 2016, purportedly the second half of the year
- DirectX 12 feature level 12_1 or higher
- Successor to the GM200 GPU found in the GTX Titan X and GTX 980 Ti
- Built on the 16nm FinFET manufacturing process from TSMC
- Allegedly has a total of 17 billion transistors, more than twice that of GM200
- Will feature four 4-Hi HBM2 stacks, for a total of 16GB of VRAM and 8-Hi stacks for up to 32GB for the professional compute SKUs
- Features a 4096-bit memory bus interface, same as AMD’s Fiji GPU power the Fury series
- Features NVLink (only compatible with next generation IBM PowerPC server processors)
- Supports half precision FP16 compute at twice the rate of full precision FP32