Re:AMD Alveo V70 AI inference accelerator card
by typon on Tuesday January 10, 2023 @11:08AM
(#34326986)
It's not a traditional FPGA chip (lots of luts and flip flops). The "AI Engine" is basically hardened chiplets that are working alongside soft logic chiplets and I/O. This is how they're able to get their performance/power numbers
Re:AMD Alveo V70 AI inference accelerator card
by YakBizzarro on Tuesday January 10, 2023 @11:28AM
(#34327314)
I suspect that it still has some fpga fabric attacched to the ai engines. The two parts are separate, but according to Xilinx docs (talking about Versal Soc), they are supposed to work togheter
It's possible that AMD could have reworked an existing Xilinx design to incorporate RDNA chiplets in place of some of the FPGA-gate-grid chiplets, creating a heterogeneous mesh; but I find it just as likely that AMD just took their VLSI for an RDNA core and loaded it onto the existing FPGA.