Topic: HashFast announces specs for new ASIC: 400GH/s - page 392. (Read 880816 times)

relax. its 11:49 am there.

The radiator and fans for just one water cooler takes a fair amount of space. You would need to mount one on top and maybe on on the backside. I'd expect a full size case to be able to fit 2.

"LIVE" mean ... hashing, then where are the results? screenshots?......

seems to me it's a full-tower case.

Btw, i guess that the transparent glass on the case is there to make you love it and not sue them.

About the right size to me. It needs to fit 2 water cooler/radiators.

wow, it's huge! thought it's a smaller box.

Hurry up, someone calculates the size and number of meters of copper needed to move 400W from under the table to the miner! The RPi has wifi so that aspect is covered!

Hyperinduction supercharging.  Resonant energy. Tesla would have approved.

Simpler question: Wouldn't it be plugged in in order to have network connectivity and power?

Wouldn't there be a laptop there, to show that the thing is hashing and not just bubbling water/spinning fans?

Get ready for a surprise!

https://www.youtube.com/watch?v=V17duGlHEYY

Two weeks ™.     

When it will be hashing, i will ask why it's not in the hands of DHL/whatever. We are losing what, 333$ per unit every day?

I'd be surprised if its not hashing.

Sweet, a case.

Can it blendhash?

So, you are gonna power it up, right?

Just a display case probably. I'd be surprised yet relieved to see it hashing.

Just posted on twitter

First Baby Jet - LIVE at Inside Bitcoins booth 21 in Vegas!!!!

Apparently the first babyjet is live at the bitcoin conference. Anyone there ?

https://twitter.com/HashFast

Yes it is 4 dies per "chip".  96 double nonce cores per die or 768 hashes per clock.

This is also clearly visible on the PCB photo.



The big brown square in the middle is the substrate which forms the base of the entire chip package.  The 4 squares on the substrate are the 4 dies.  Just about everything else on the green PCB is what is required to funnel that much power into that small chip.  I have to give them credit it is a pretty clean design.  There is a 6 pin PCIe power connector at each end of the board currently not populated in this photo.  Each half of the board essentially supplies power for two of the cores.  The heat sink mounting holes are standard (looks like Intel hole spacing) so any off the shelf cooling component could be used without any custom work needed.


As pointed out IF it is ~400 GH/s at 0.74V well that is incredibly low voltage.  0.85V would be 15% higher voltage, pushing it to 0.90V would be 22% higher.  Clock rate should scale at least linearly with voltage increase (probably super linearly) albeit at lower efficiency (J/GH).  I am not making a prediction on how much they can push it.  Remember power usage in semiconductors increases by the square of the voltage increase and the chip already uses a lot of power in a small package.  At some point you run into limits on how much power the PCB can deliver and how much power (heat) the cooling system can remove.

Still as tacotime pointed out the chip at 0.74V is a good sign.  If they were struggling to get 400 GH/s at 0.90V that would be a bad sign as they would already be pushing the limits of what the chip can handle.