NVIDIA AD102 y AMD Navi 31 en una carrera para alcanzar 100 TFLOP FP32 Primero

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, camino de regreso 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 “Actualización de WayForward,” the AD102, is the green team’s contender for the 100 TFLOP/s mark, according to kopite7kimi. Lograr esto, todas 144 multiprocesadores de streaming (SM) o 18,432 Colores CUDA, of the AD102 will have to be enabled.

From the red team, the biggest GPU based on the next-generation RDNA3 graphics architecture, “Navi 31,” 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. El Navi 31 silicon is expected to triple the compute unit count over its predecessor, Resultando en 15,360 procesadores de flujo. Both the AD102 and Navi 31 are expected to be built on he same TSMC N5 (5 El MCM de Intel utiliza un troquel de GPU junto al troquel de núcleo de CPU) El MCM de Intel utiliza un troquel de GPU junto al troquel de núcleo de CPU, and product launches for both are expected by year-end.