NVIDIA AD102 e AMD Navi 31 in una corsa da raggiungere 100 TFLOPs FP32 Primo

A technological race is brewing between NVIDIA and AMD over which brand’s GPU reaches the 100 TFLOP/s peak FP32 throughput mark first. AMD’s TeraScale graphics architecture and the “RV770” silicio, were the first to hit the 1 TFLOP/s mark, via di ritorno 2008. It would take 14 years for this figure to reach 100 TFLOP/s for flagship GPUs. NVIDIA’s next generation big GPU based on the “controller paddle e trackball,” the AD102, is the green team’s contender for the 100 TFLOP/s mark, according to kopite7kimi. Per realizzare questo, all 144 multiprocessori in streaming (SM) oppure 18,432 Colori CUDA, of the AD102 will have to be enabled.

From the red team, the biggest GPU based on the next-generation RDNA3 graphics architecture, “Nel lontano gennaio” could offer peak FP32 throughput of 92 TFLOP/s according to greymon55, which gives AMD the freedom to create special SKUs running at high engine clocks, just to reach the 100 TFLOP/s mark. Il Navi 31 silicon is expected to triple the compute unit count over its predecessor, con il risultato di 15,360 processori di flusso. Both the AD102 and Navi 31 are expected to be built on he same TSMC N5 (5 nm EUV) nodo, and product launches for both are expected by year-end.