Re:Cerebras Deploys Trillion-Parameter AI Models
by wmf on Sunday October 25, 2026 @01:26AM
(#50228597)
The EDA tools that are used to design chips do not support diagonal wires so that kind of rules out hexagonal grids. With only horizontal and vertical wires you end up with rectangular/square grids or rings.
[ Parent
| on HN ]
Re:Cerebras Deploys Trillion-Parameter AI Models
by xpct on Sunday October 25, 2026 @02:07AM
(#50228782)
If that is so, would it be entirely to decrease search space for layout algorithms? I believe there isn't anything in the fabrication process that couldn't model diagonals.
I could see that square packing is more simple, but by shifting elements per row I don't see why it couldn't propagate at odd angles.
Re:Cerebras Deploys Trillion-Parameter AI Models
by yvdriess on Sunday October 25, 2026 @04:40AM
(#50229480)
That's also my assumption. Place and route has to work out an NP hard problem on billions of wires.
Re:Cerebras Deploys Trillion-Parameter AI Models
by colordrops on Sunday October 25, 2026 @05:26AM
(#50229696)
Are the next generation of Cerebras chips designed by the current generation? Maybe it won't be recognizable as a particular layout but rather a chaotic but functional vibe layout.
Re:Cerebras Deploys Trillion-Parameter AI Models
by ithkuil on Sunday October 25, 2026 @03:02AM
(#50229019)
Do you need diagonal wires for a topological hexagonal tiling?
Wouldn't a rectangular brick layout be topologically a hexagonal tiling
Re:Cerebras Deploys Trillion-Parameter AI Models
by octoberfranklin on Sunday October 25, 2026 @11:14AM
(#50232443)
Oh the tools support it. The process doesn't.
Diagonal wires worked everywhere at 180nm and on a few fabs at 90nm if you rotated a whole metal layer (i.e. all metal-3 wires are diagonal to the metal-2 wires) and basically nowhere beyond 90nm.
OPC killed it. Too hard to OPC the diagonal stuff. And even if you rotate an entire metal layer, the contacts between a rotated and un-rotated layer would require enormous metal enclosures.